Florent Delgrange won the Best Blue Sky Paper Award at AAMAS 2026 for his work Foundation World Models for Agents that Learn, Verify, and Adapt Reliably Beyond Static Environments. We caught up with him to find out more about his vision for agent learning.

What is the topic of your Blue Sky Ideas paper and why is it an interesting area for study?

My Blue Sky Ideas paper asks a simple but difficult question: how can an autonomous agent keep learning as its world changes without quietly losing the guarantees that made its behavior trustworthy?

Reinforcement learning and formal methods address complementary parts of this problem. Reinforcement learning allows an agent to learn by trial and error and can scale to environments for which we could never write down every rule. However, the agent is usually asked to maximize a reward. A poorly specified reward can be exploited, and a high reward does not by itself tell us that a safety or coordination requirement has been satisfied. Reactive synthesis starts from the other end: given a model of the environment and a logical description of the intended behavior, it can construct a policy that is correct by design. The difficulty is that it normally needs an explicit, fixed model, which is precisely what an agent lacks in an open and changing world.

The paper proposes a research agenda that brings these traditions into one loop. A foundation world model would be learned from experience, but structured so that a verifier can reason about it. As the agent learns a policy, it would update its model, measure the reliability of its abstraction, and check whether the policy still satisfies its specification. The verifier’s feedback could reject an unsafe update, request data from an uncertain region, or trigger a revision of the model.

This matters because real environments do not politely remain as they were during training. Goals evolve, conditions change, and, in a multi-agent system, every adapting agent changes the environment perceived by the others. Reliability therefore cannot be a certificate obtained once at deployment. It has to be maintained as the agent continues to learn.

What is your vision for foundation world models?

To me, foundation refers first to reuse, not simply to size. I do not envision a larger video predictor trained on more trajectories. I envision a persistent and structured model that an agent can carry across tasks, policies, and changing populations of agents.

One way to think about it is as a map that records more than roads. It should also tell the agent which areas have been surveyed, which conclusions depend on those areas, and when a change in the world has made an old route unreliable. A useful foundation world model should do the same for decision-making: predict what may happen, expose the structure needed for reasoning, and quantify when those predictions are trustworthy enough to support a guarantee.

I’d want such a model to have three key properties. First, it should be calibrated: every learned abstraction should come with a measure of its error or coverage, so that the agent knows where formal conclusions remain valid. Second, it should be compositional: verified local dynamics, behaviors, and certificates should be reusable when a new task is assembled. Third, it should be semantically queryable: a formal requirement or high-level instruction should help the agent derive a suitable reward model, task-specific abstraction, or policy prior with little additional experience.

The durable idea is that the world model becomes a common substrate for learning, planning, and verification. It should help an agent act, but also identify the limits of its competence, gather evidence where those limits matter, and explain why a particular behavior can or cannot currently be certified.

How does this vision differ from current models?

Most current model-based approaches focus on learning for a particular task, environment, policy, or training distribution. Their main model learning objective is predictive accuracy: reconstruct an observation, forecast the next (latent) state, or generate imagined trajectories for planning. Those are important capabilities, but average predictive metric is not the same as fitness for a particular guarantee.

Consider a model for a scenario involving an agent interacting in a warehouse, where the world model predicts almost every transition correctly but misses a rare, dangerous interaction with a forklift. Its average error may be excellent while that transition is exactly the one that determines whether a collision-avoidance claim is valid. The reverse is also possible: a compact model may ignore colors and textures yet preserve everything needed to reason about routes and collisions. For verification, the relevant question is therefore not only “How accurate is the model?” but “Which conclusions does this accuracy justify, for this policy and this requirement?”

Foundation world models would make that connection an explicit design objective. Their abstractions would carry reliability information tied to the behavior being analyzed, and this information would be revised online as the data distribution changes. Previously verified components could be reused and composed, while specifications expressed in logic or language could guide which representation and policy the agent needs for a new task.

The main difference is therefore a change in role. Current models are primarily prediction tools. The model I envisage is a persistent, analyzable basis for learning, adaptation, and formal reasoning, with language models providing a complementary semantic interface. They could translate high-level instructions into candidate specifications or propose structured model updates, while the world model grounds these proposals in experience and the verifier checks their validity. Foundation world models may benefit from scale through broader task and environment coverage, but scale alone does not provide the structure or certificates required for reliability.

Could you give an example of how such a model might work?

Consider a delivery robot in a busy warehouse. Its task could be stated as: “eventually deliver the package while always avoiding collisions.” Instead of manually combining many bonuses and penalties, the system would translate that requirement into a reward model. Learning and verification would then start from the same description of the intended behavior.

As the robot receives observations, it would learn a compact representation of the warehouse and a policy that acts on that representation. A verifier would ask two related questions. Does the policy satisfy the delivery and collision-avoidance requirement in the learned world model? And is the learned abstraction accurate enough, along the routes that matter, for that conclusion to be trusted? A certificate is meaningful only when both answers are supported.

Now suppose a new forklift begins using a shortcut that was rarely visited during training, cluttering the way. Rather than treating an old prediction as a guarantee, the model should lower its confidence in that region. The verifier would detect this, withdraw the affected certificate, reject a risky policy update, direct exploration toward the shortcut, and reinstate a guarantee only after the world model has been recalibrated.

The paper also considers a more ambitious test-time loop. A language model could propose one or more small formal program describing the new dynamics. A model checker would test them, learn to compose with them, and return a counterexample or structural inconsistency when they are wrong. The language model could revise its hypothesis, the robot could collect targeted experience, and the cycle would repeat. In this division of labor, the language model proposes and the formal verifier checks.

We already have pieces of the loop, including formal reward translations, verifiable abstractions, safe policy-improvement methods, and program generation. Building an efficient end-to-end agent that keeps all of these pieces calibrated while it learns remains the research challenge.

What do you think the impact of such a framework on multi-agent systems could be?

Multi-agent systems make the problem both more urgent and more difficult. Each learning agent is a moving part of every other agent’s environment. Even when the physical world is unchanged, the effective dynamics evolve as agents update their policies, join or leave the system, share information, or pursue new objectives.

A foundation world model could retain reusable descriptions of these interaction patterns, while formal specifications state what must hold for the group. A fleet of warehouse robots, for example, may need to avoid collisions and complete deliveries while respecting shared capacity constraints. The model could connect each local policy to the assumptions on which its certificate depends. If one robot changes its route, the system could identify which assumptions and guarantees are affected, collect new data where needed, and revise only the relevant components rather than relearning and re-verifying the entire fleet.

Composition is the main source of potential leverage. Verified local dynamics or coordination behaviors could serve as building blocks for new teams and tasks, and previous agents could provide useful priors for new participants. This could support faster adaptation while making failures easier to diagnose: the system should report which interaction invalidated a certificate and provide a counterexample, rather than only revealing that the joint reward has fallen.

The central obstacle for multi-agent systems is scalability. The joint state space grows very quickly with the number of agents, and local guarantees do not automatically compose into a global one. We will need principled ways to expose dependencies, preserve soundness under composition, and run verification quickly enough to influence learning online. If we can solve those problems, the field could move from learning coordination strategies and checking them afterwards to learning new strategies while continuously tracking which global properties remain guaranteed.

About Florent

Florent Delgrange is a postdoctoral researcher in computer science at the Artificial Intelligence Lab of Vrije Universiteit Brussel (VUB). His research lies at the intersection of reinforcement learning, world models, and formal verification. He develops methods for agents that can learn and adapt while justifying and certifying the behavior they adopt. He completed a joint PhD at VUB and the University of Antwerp in 2024 on the formal verification of deep reinforcement learning policies. His paper Foundation World Models for Agents that Learn, Verify, and Adapt Reliably Beyond Static Environments received the Best Blue Sky Paper Award at AAMAS 2026.

In an article published today in Nature, Sony AI introduce Ace, the first robot to beat elite human players in competitive physical sport.

Although AI systems have shown advanced performance in digital domains and board games (such as complex video games, chess and Go), translating this to physical performance has remained a significant challenge. Such a feat requires perception, planning, and control to work in a high-speed domain on the scale of milliseconds. Table tennis is a demanding and complex real-world test for robotics, requiring rapid decision-making, precise physical execution, and continuous adaptation to an unpredictable opponent. The ball’s high speed, spin, and complex trajectories are central to competitive play.

Director of Sony AI in Zürich, and project lead for Ace, Peter Dürr said “this research has shown that an autonomous robot can, in fact, win at a competitive sport, matching or exceeding the reaction time and decision making of humans in a physical space. Table tennis is a game of enormous complexity that requires split-second decisions as well as speed and power. This research breakthrough highlights the potential of physical AI agents to perform real-time interactive tasks, and represents a significant step toward creating robots with broader applications in fast, precise, and real-time human interactions.”

A complete view of table tennis robot, Ace, including arm and track. Credit: Sony AI.

What new components does Ace incorporate?

Ace combines event-based vision sensors and a control system based on model-free reinforcement learning, as well as state-of-the-art high-speed robot hardware. Ace was designed with three novel components:

• A high speed perception system composed of nine active pixel sensor cameras to determine the ball’s precise 3D position, combined with three gaze control systems that use event-based vision sensor cameras, pan/tilt mirrors, and telephoto tunable lens to measure the ball’s angular velocity and spin in real time.
• A novel control system based on model-free reinforcement learning to enable rapid adaptation and decision-making without reliance on pre-programmed models.
• High-speed robotic hardware capable of executing precise, high-speed control for agile physical interaction.

Members of the Ace research team and table tennis officials pose with the robot and its human opponent, Mayuka Taira, following an official match in December 2025.

Testing Ace against elite players

For the results reported in the Nature publication, Ace was evaluated in matches against five elite players and two professional table tennis players, under International Table Tennis Federation (ITTF) regulations. Ace achieved three victories in five matches against the elite players, along with competitive performances in the remaining matches.

There were some interesting results from the evaluations, including the fact that Ace was able to return a wide range of spins, consistently achieving over 75% return rate up to spins of 450 rad/s. The control systems behind Ace also allowed for quick reaction to unusual shots, such as balls bouncing off the net. This behavior illustrates the ability of the approach to generalize to situations that are both rare and hard to model in simulation.

Following submission of the Nature manuscript, the team conducted additional competitive matches in December 2025 and March 2026, beating professional players in the process. Compared with earlier evaluations, Ace demonstrated higher shot speeds, more aggressive placement closer to the table edge, and faster-paced rallies, reflecting continued performance gains under competitive conditions.

Find out more about the project in this video from Sony AI.

AIhub is excited to launch a new series, speaking with leading researchers to explore the breakthroughs driving AI and the reality of the future promises – to give you an inside perspective on the headlines. The first interviewee is Ross King, who created the first robot scientist back in 2009. He spoke to us about the nature of scientific discovery, the role AI has to play, and his recent work in DNA computing.

Automated science is a really exciting area, and it feels like everyone’s talking about it at the moment – e.g. AlphaFold sharing the 2024 Nobel Prize. But you’ve been working in this field for many years now. In 2009 you developed Adam, the first robot scientist to generate novel scientific knowledge. Could you tell me some more about that?

So the history goes back to before Adam. Back in the late 1990s, I moved from a postdoc at what was then the Imperial Cancer Research Fund – now Cancer Research UK – and got my first academic job at the University of Wales, Aberystwyth. That’s where I had the original idea of trying to automate scientific research.

Our first publication on this was in 2004. It was a paper about robot scientists, published in Nature. That was the start. We showed that the different steps in the scientific method – forming hypotheses, determining experiments to test them, analysis of the results – could all be individually automated. But the whole cycle wasn’t fully automated, and the AI system didn’t do any novel science at that point.

In 2009, we built the Adam system. Adam was a (physically) large laboratory automation system, combined with AI that could perform full cycles of scientific research, and had knowledge about yeast functional genomics. Adam hypothesised and experimentally confirmed novel scientific knowledge about yeast metabolism, which we manually verified in the lab. 

How has the field evolved since then?

For many years, not much happened. Funding was difficult due to the financial crisis, which made the British Research Councils much more conservative. Before that period, panels would choose the most exciting science. Afterwards, they focused more on what would help Britain financially in the near term.

We couldn’t get funding for many years, and few others were interested. There was some work in symbolic regression – finding interpretable mathematical models to fit phenomena – but not much automation of science. What changed was the general rise of AI. As AI became more prominent, interest picked up, especially after 2017.

What are the potential upsides and downsides of AI scientists? 

I’ll start with the big picture: I think that science is positive for humanity. I think our lives in the 21st century are better than those of kings and queens in the 17th century, when modern science started. We have better food from around the world, beautiful fruits for breakfast, and much better healthcare – a 17th-century dentist was not pleasant. My mobile phone can communicate with billions of people at the touch of a button, and I can fly around the world. These are unbelievably good standards of living for billions of people, not just elites. The application of science to technology has provided this.  Of course there are downsides – pollution, environmental damage – but generally, for humans, I think life is better than in the 17th century. 

However, we still have huge problems. We can’t stop global warming or many diseases, and a billion people still live with food insecurity. I think we have sufficient technology to solve these problems if the nations of the world collaborated and shared resources. But I see no prospect of that happening in the current world situation, and I see no examples from history where these things have happened. So my only hope is that science becomes more efficient. If AI can help achieve that, then perhaps we can overcome these challenges. If we have better technology and we treat people badly after that, then it’s not down to constraints in the world, it’s down to human beings. 

As for having AI scientists as colleagues: AI systems don’t understand the big picture. They can’t do really clever things, like Einstein seeing space and time as a four-dimensional continuum as opposed to quite separate things. If you read the 1905 paper by Einstein, it starts off with this philosophical problem about electricity and magnets – AI systems are nowhere near as clever as being able to do anything like that. They can’t see deep analogies or connections, but they are brilliant at other parts of science. They can literally read everything – they have read every paper in the world 1000 times. If you have a small amount of data, machine learning systems can analyze it better than humans would. In this sense, they have superhuman powers. 

One interesting thing now is that if you’re a working scientist and you’re not using AI, in almost all fields you’re not going to be competitive anymore. AI on its own is not better than humans – yet. But a human plus AI is better than a human alone. Human scientists need to embrace AI and use it to do better science.

Do you think we’ll reach a point where autonomous AI will be able to generate the research questions and direct the movement of research?

Yes, I think so, although we’re not close to that at the moment. They can generate new ideas in constrained spaces, often better than humans, but they don’t really have the big picture yet. 

I think that will come sooner or later. I’m involved in a project called the Nobel Turing Challenge. The goal of that is to build an AI robotic system able to do autonomous science at the level of a Nobel Prize winner, by the year 2050. And if you can do that, we can build two machines, a hundred machines, a million machines – and we’d transform society.

Do you think that’s feasible by 2050? 

Just before the pandemic and during the pandemic, I thought the probability of hitting that target was dropping. But then there was the breakthrough of large language models, which are amazing in many ways – often remarkably stupid too, but generally very clever. I think that they alone will not be enough to beat the Nobel Turing Challenge, but I think they’ve made the probability of hitting that target much more likely.

What is interesting – and I don’t know the answer to this – is whether you need to solve AI in general to solve science, or whether it’s more like chess, where you can build a special machine which is genius at chess but not anything else. Imagine some machine which is a genius at physics but doesn’t know anything about poetry or history. Would that be enough? 

My instinct would be to say that it’s not, because everything’s so interlinked – poetry has rhythm, music contains mathematical structures. I think an AI scientist would need a broader understanding of reality than just its specific domain. 

People used to think that we needed those things to solve chess, so our human intuition is not very good at these things. For example, I didn’t expect LLMs to work so well, just by building a bigger network and putting in more data. I assumed they’d need some deep internal model of the world, or even that they would need a body to really understand how things move around in the world.

LLMs raise some interesting questions – are they just mimicking intelligence, as they lack internal models? 

I think AI must have, in some sense, some internal model inside. It’s just we don’t really understand why they work. It’s purely empirical, which is very unusual. I don’t remember a case where we have such an important technology, but we have so little understanding of it.

It is quite mysterious. Especially because science is always asking “what’s the mechanism?”  With AI, it’s the opposite. The question is “does it work?” We don’t know what the mechanism is. 

It’s not even clear what the theory to explain it is. Coming from machine learning, I assumed it would be some sort of Bayesian inference or something. But the mathematicians say no, it’s all to do with function mapping in some high dimensional space. These don’t seem to be the same, so it’s not even clear what framework we should use to explain it. 

And, mapping in a high dimensional space is something that’s fundamentally not intuitively understandable to humans. 

Yes, so it’s a mystery. So why do they do so well, and why do they not overfit over so many parameters. How do they manage to come to a reasonable answer? Generally, it’s easy to understand why they make mistakes, but it’s not so easy to understand why they actually work so well. 

Can you speak about your work in DNA computing, and how it relates to automated science?

With automated science, we’re using computer science to understand, for instance, biology or chemistry. With DNA computing we’re using technology from biology and chemistry to improve computer science. With DNA, you have the potential to have many, many orders of magnitude greater computing density than with electronics. This is because the bases in DNA are roughly the same size as the smallest transistors, but you can pack DNA in three dimensions, whereas transistors can only be in two dimensions. In our design for DNA, every DNA strand is a tiny computer. 

And the beautiful thing with DNA is that it can replicate itself – nature has made ways of copying DNA which are very effective. That’s how we as humans and all animals and plants and bacteria replicate, whereas electronic computers don’t replicate themselves – they’re built in factories costing billions. We can piggyback on top of this wonderful technology which nature has given us.

How does a DNA computer work? 

One of the greatest discoveries ever made was by Alan Turing, who discovered, or invented, the concept of the universal Turing machine. So this is an abstract mathematical object which can essentially compute anything which any other computer can compute. You can’t make a more powerful computer, in the sense that it can compute a function which that universal Turing machine can’t compute.

And there’s many different ways of physically implementing a universal Turing machine. The most common one is to build an electronic computer. But you could, in principle, build a Turing machine out of tin cans, for instance – the only difference is how fast they go and how much memory they have. The reason that your computer can do multiple tasks is because it can be programmed to do.

The beautiful thing which you can do with DNA is you can make a non deterministic universal Turing machine. These compute the same functions as normal universal Turing machines, but they do so exponentially faster – every time there is a decision point in the program, rather than having to explore only one path, it can go both ways simultaneously. So you can make a computer which, like an organism (think rabbits), can replicate and replicate and replicate until we solve the problem, or you run out of space. So space becomes the limiting factor rather than time. 

You can imagine that if you wanted to search through a tree to find something, you could put down all the branches in parallel, whereas a normal computer would go down one branch at a time. If you do the sums for DNA computing, you could have more memory and more compute on a desktop than all the electronic computers on the planet, which seems incredible. That’s just because of the density of compute. 

That would be an incredible scale-up – like how a modern smartphone is so  much more powerful than NASA’s supercomputers in the 60s. But computing isn’t improving at the same rate as it used to. 

Yes. Computers are not improving like they used to for many decades (Moore’s law). That’s why these big tech companies are building big compute farms the size of Manhattan or soon maybe Texas. So the world does need more efficient ways of doing compute.

If we had a lot of compute, what kinds of scientific problems or areas do you think AI-enabled science could best be applied to? Are there any low-hanging fruits?

What’s very important is to integrate AI systems with actual experiments and laboratories. You can’t just think about science and get the right answer. We need to actually go into the labs and test things, but a lot of AI people and AI companies don’t really appreciate that. They’ve been so successful in science with AI plus simulation that they don’t realize simulation is only so good as something that’s testable.

Areas with low-hanging fruit include materials science, as we need better battery materials, better solar panels, and lots more. There’s something of a gold rush happening there right now, with many startup companies getting huge valuations.

The other area of automation, which is in some sense easier, is drug design, because it’s much easier to move liquids around than solid phase materials. Closed-loop automation has sort of transformed early-stage drug design, and there are lots of companies in that space now.

The big picture is that the economic cost of science is dropping. A lot of the actual thinking involved in science can now be done by AI systems, and the experimental work can be done very well by lab automation. You don’t need to employ people to move things around, and people aren’t as accurate and don’t record things as well as automation does. So that’s the big picture: what can we do if we can make science much cheaper?

Where do you think AI science is headed next?

I think there’s an analogy with computer games like chess and Go. In my lifetime, computers went from playing chess pretty poorly to being able to beat the world champion. I think it’s the same in science. There’s a continuum of ability from what current technology can do, from the average human, to grandmasters of science like Newton, Einstein, Darwin and others. If you agree there is no sharp cutoff on that path, then I think that with faster computers, better algorithms, and better data, there’s nothing stopping them getting better and better at science. Whereas there’s evidence that humans are getting worse at science – the average economic benefit per scientist is decreasing. I think they’ll get better and better and sooner or later overtake humans in science. We shall see, but I’m optimistic. If we get through this period, better science can improve the standard of living and happiness of humanity,  and save the planet at the same time.

And now we have so much data, we need that raw power and intelligence to look at it all.

Yes, we need factories doing a lot of automation to scale things up. There’s no point in AI having brilliant ideas if we can’t test them in the lab. In my mind, science is still at the pre-industrial level. A PI with some post-docs and a few students is like a cottage industry, as opposed to a factory of science. I think humans will still be doing science, but we won’t be actually pipetting things in the future. It’s one reason we chose the name Adam (Adam Smith), we want to change the economics of science. 

And Eve?

Eve was a system we developed some years ago to look at early-stage drug design. Eve optimises a process, rather than doing pure science. Most systems don’t actually do hypothesis-driven science, they optimise something, e.g. find a better material for batteries, which is useful, but not necessarily science. 

Our new system is called Genesis. There we’re trying to scale up the experiments we can do and build up a lot of data. We’re using a continuous flow bioreactor, which enables you to control the growth rate of microorganisms. This is important if you want to understand their internal workings.

And you’re beginning with microorganisms because they’re a fundamental unit of life? 

Yes, we want to understand the eukaryotic cells. There are three branches of life, and the other two are bacteria. Eukaryotes evolved more than 1 billion years ago. We are eukaryotes. Biology is conservative, so the design of yeast and human cells is pretty much the same, but yeast cells are much simpler than human ones. To understand how we work, first we need to understand yeast, then human cells. Once we understand how human cells work, we can understand how organs work, then how humans work, and then we can solve medicine. It’s a reductionist approach to science – we understand something simple first, and then build from there. 

I like the progression, that approach makes sense. 

Unfortunately, it doesn’t make sense to our funders. They generally want to fund practical work on human cells now. They don’t easily fund research on fundamental questions. 

That’s the problem with the funding system. Most great discoveries in science over the last few centuries would not have been funded – they happened because people were doing the most impractical things for the most impractical reasons. And maybe a century later they were found to have a practical purpose. 

Exactly. Some years ago in the UK you had to write a 2-pages for every Research Council grant on how your research was going to make Britain richer or healthier. What would Alan Turing have written on his grant application for the Entscheidungsproblem? 

Thank you. This has been a very interesting conversation.

Thank you, happy to discuss this. It’s a very interesting topic. 

About Ross King

Ross King is a Professor with joint positions at the University of Cambridge, and Chalmers Institute of Technology, Sweden. He originated the idea of a ‘Robot Scientist’: integrating AI and laboratory robotics to physically implement scientific discovery. His research has been published in top scientific journals – Science, Nature, etc. – and received wide publicity. His other core research interest is DNA computing. He developed the first nondeterministic universal Turing machine, and is now working on a DNA computer that can solve larger NP complete problems than conventional or quantum computers.

In the latest in our series of interviews meeting the AAAI/SIGAI Doctoral Consortium participants, we caught up with Aniket Roy to find out more about his research on generative models for computer vision tasks.

Tell us a bit about your PhD – where did you study, and what was the topic of your research?

I recently completed my PhD in Computer Science at Johns Hopkins University, where I worked under the supervision of Bloomberg Distinguished Professor Rama Chellappa. My research primarily focused on developing methods for resource-constrained image generation and visual understanding. In particular, I explored how modern generative models can be adapted to operate efficiently while maintaining strong performance.

During my PhD, I worked broadly at the intersection of generative AI, multimodal learning, and few-shot learning. Much of my work involved designing techniques that enable models to learn new concepts or perform complex visual tasks with limited data or computational resources. This included research on diffusion models, personalized image generation, and multimodal representation learning. Overall, my work aims to make advanced vision and generative AI systems more adaptable, efficient, and practical for real-world applications.

Could you give us an overview of the research you carried out during your PhD?

During my PhD, my research broadly focused on improving the adaptability, efficiency, and quality of modern generative models for computer vision tasks. The rapid progress in generative AI–particularly diffusion models and vision–language models–has created new opportunities to address long-standing challenges such as data scarcity, controllable generation, and personalized image synthesis. My work aimed to develop methods that allow these large models to adapt effectively with limited data and computational resources while maintaining high visual fidelity.

One line of my research addressed learning in data-constrained settings. For example, I proposed FeLMi, a few-shot learning framework that leverages uncertainty-guided hard mixup strategies to improve robustness and generalization when only a small number of labeled samples are available. Building on this idea of improving training data quality, I also developed Cap2Aug, which introduces caption-guided multimodal augmentation. This approach uses textual descriptions to guide synthetic image generation, improving visual diversity while reducing the domain gap between real and generated data.

Overview of Cap2Aug.

Another aspect of my research focused on improving the perceptual quality of images generated by diffusion models. In this direction, I proposed DiffNat, a plug-and-play regularization method based on the kurtosis-concentration property observed in natural images. By incorporating this principle into diffusion models through a KC loss, the generated images exhibit more natural texture statistics and improved perceptual realism, which also benefits downstream vision tasks.

A major part of my work explored personalization and efficient adaptation of large generative models. I introduced DuoLoRA, a parameter-efficient framework for composing low-rank adapters that enables fine-grained control over content and style without requiring full retraining of the base model. I further extended personalization to zero-shot settings using a training-free textual inversion approach that allows arbitrary objects to be customized directly during generation. Finally, I proposed MultiLFG, a frequency-guided multi-LoRA composition framework that uses wavelet-domain representations and timestep-aware weighting to enable accurate and training-free fusion of multiple concepts in diffusion models.

Overview of DuoLoRA.

Overall, my research contributes toward building generative systems that are more efficient, adaptable, and controllable, enabling high-quality image generation and understanding even in data-limited or resource-constrained scenarios.

Was there a specific project or an aspect of your research that was particularly interesting?

One project that I found particularly interesting during my PhD is DiffNat, which was published in TMLR 2025. Diffusion models have become the backbone of many modern generative AI systems and have achieved impressive results in generating and editing realistic images. However, improving the perceptual quality and naturalness of generated images remains an important challenge.

Overview of DiffNat.

In this work, we introduced a simple but effective regularization technique called the kurtosis concentration (KC) loss, which can be integrated into standard diffusion model pipelines as a plug-and-play component. The idea was inspired by a statistical property of natural images: when an image is decomposed into different band-pass filtered versions–for example using the Discrete Wavelet Transform–the kurtosis values across these frequency bands tend to be relatively consistent. In contrast, generated images often show large discrepancies across these bands. Our method reduces the gap between the highest and lowest kurtosis values across the frequency components, encouraging the generated images to follow more natural image statistics.

In addition, we introduced a condition-agnostic perceptual guidance strategy during inference that further improves image fidelity without requiring additional training signals. We evaluated the approach across several diverse tasks, including personalized few-shot finetuning with text guidance, unconditional image generation, image super-resolution, and blind face restoration. Across these tasks, incorporating the KC loss and perceptual guidance consistently improved perceptual quality, measured through metrics such as FID and MUSIQ, as well as through human evaluation.

What I particularly liked about this project is that it connects classical image statistics with modern diffusion models. It shows that relatively simple statistical insights about natural images can still play a powerful role in improving large generative models.

What are your plans for building on the PhD – where are you working now and what will you be investigating next?

During my PhD, I discovered that I genuinely enjoy the process of research–especially the moment when an intuition or idea turns out to work in practice. That process of exploring new ideas and pushing the boundaries of what we know is something I find very motivating.

To continue pursuing this, I will be joining NEC Laboratories America as a Research Scientist. In this role, I hope to build on my PhD work by developing new methods for generative models and exploring how these models can interact with broader multimodal systems. In particular, I am interested in advancing research at the intersection of generative models, vision–language–action models, and embodied AI. More broadly, my goal is to contribute to the development of intelligent systems that can understand, generate, and interact with the visual world more effectively, while also continuing to push forward the scientific understanding of these models.

I’m interested in how you got into the field. What inspired you to study computer vision and machine learning?

My interest in computer vision and machine learning started during my undergraduate studies, when I took courses in signal processing and image processing. I found those subjects particularly fascinating because they allowed you to experiment with algorithms and immediately see their effects on images. That visual and intuitive aspect made the field very engaging, and it helped me appreciate how mathematical concepts can directly translate into meaningful visual results.

At the same time, I was also curious about how the human brain processes visual information—how we are able to recognize objects, understand scenes, and interpret complex visual signals so effortlessly. That curiosity led me to wonder whether we could design computational models that mimic aspects of human perception and enable machines to understand visual data in a similar way.

A major influence during this time was my professor, Dr. Kuntal Ghosh, who encouraged me to think more deeply about these problems and approach them with a scientific mindset. His mentorship played an important role in shaping my interest in research. Since then, that curiosity about visual perception and intelligent systems has continued to drive my work in computer vision and machine learning.

What was your experience of the Doctoral Consortium at AAAI?

Unfortunately, I was not able to attend the AAAI Doctoral Consortium in person due to visa-related issues. However, a colleague kindly helped present my poster on my behalf during the event. Even though I could not be there physically, I was very encouraged by the response my work received. Several researchers reached out to me after seeing the poster, and we had some very insightful discussions about the ideas and potential future directions of the research. In that sense, I still found the experience quite rewarding. The Doctoral Consortium is a great platform for sharing early-stage ideas, receiving feedback from the community, and connecting with other researchers working on related problems. I appreciated the opportunity to engage with people who were interested in the work, and those interactions helped spark new perspectives and collaborations.

Could you tell us an interesting (non-AI related) fact about you?

Outside of research, I’m a big fan of music and stand-up comedy, and I really enjoy traveling whenever I get the chance. Exploring new places, cultures, and perspectives is something I find refreshing—it’s a great way to recharge and stay curious about the world beyond work. I also enjoy writing poetic satire from time to time, and I occasionally perform it. It’s a fun creative outlet that allows me to mix humor and storytelling, which is quite different from the analytical nature of the research work I usually do.

About Aniket Roy

Aniket is currently a Research Scientist at NEC Labs America. He obtained his PhD from the Computer Science dept at Johns Hopkins University under the guidance of Bloomberg Distinguished Professor Prof. Rama Chellappa. Prior to that, he did a Master’s from Indian Institute of Technology Kharagpur. He was recognized with the Best Paper Award at IWDW 2016 and the Markose Thomas Memorial Award for the best research paper at the Master’s level. During PhD, he explored domains of few-shot learning, multimodal learning, diffusion models, LLMs, LoRA merging with publications in leading venues such as NeurIPS, ICCV, TMLR, WACV, CVPR and also 3 US patents filed. During his PhD, he also gained industrial experience through multiple internships in Amazon, Qualcomm, MERL, and SRI International. He was awarded as an Amazon Fellow (2023-24) at JHU and selected to participate in ICCV’25 and AAAI’26 doctoral consortium.

RoboCup is an international competition that promotes and advances robotics and AI through the challenges presented by its various leagues. We got the chance to sit down with Professor Manuela Veloso, one of RoboCup’s founders, to find out more about how it all started, how the community has grown over the years, and the vision for the future.

I think it would be very interesting to go right back to the beginning and hear how RoboCup got started. What was the initial idea, and how did it get set up?

So we are talking about the mid-90s. In terms of the research in those days, it was the beginning of the internet and many AI and computer science researchers were focused on the internet, first on sophisticated search algorithms, on natural language understanding, on information retrieval, and then on software agents and machine learning applied to digital information. From what I recall, there was a smaller group of researchers who were interested in actual, physical robots, and in particular in AI and robotics. I myself was specifically interested in the problem of creating autonomous robots with perception (get information from the world), cognition (select action to achieve goals), and then act (execute the planned actions). This combination of perception, cognition, and action is a very good framework for autonomous robots, because they have to get their information from their sensors, they have to reason about actions to achieve their goals, and then execute them. So, during the 90s, I was at Carnegie Mellon with this AI research goal of integrating perception, cognition, and action in autonomous robots.

Over in Canada there was Alan Mackworth, who jointly with his wonderful student, Michael Sahota, built a one-on-one little autonomous robot soccer set-up. Two robots ran on a small field that had a camera overhead, and aimed at scoring each in one of the two little goals. This work showed that this task of kicking a ball and defending and aiming at a goal could be done autonomously. So it was a tremendous demonstration that a robot soccer world could exist. Mostly at the same time, in Japan, Minoru Asada was showing that a big robot could learn with reinforcement learning how to push a ball into a goal. So you have these one-on-one, fully autonomous little robot cars that were pushing balls around in Canada, and then there was this effort of learning to score with a larger robot in Japan. The learning robot didn’t have a team, it was not a real game, but it was showing that reinforcement learning could learn the skill of aiming into a goal. And then there was also Hiroaki Kitano at Sony who was very interested in little humanoids.

So this is very beautiful because all these things came into play – all of us had different interests.

Alan Mackworth did not get involved with RoboCup, but he gave a demonstration of these one-on-one robots at AAAI in 1994. And in those days, I had a PhD student who had just joined – Peter Stone. And Peter was a serious and passionate soccer player. He saw this little game and he came to me and said, “this is what I want to do for my thesis research, robot soccer!” And for me, I was trying to find a research environment where autonomy was needed in the robot world. I had already a student, Karen Haigh, who was working with autonomous office robots, and learning to plan and execute. But with these soccer robots and Peter Stone’s interest everything came to play, and we started robot soccer research in my lab.

In 1996, there was also a robot soccer effort in South Korea, called MIROSOT, and that’s the first competition we participated in. So Peter Stone, myself, and the team we built at Carnegie Mellon – Sorin Achim and Kwun Han – went to South Korea to participate. From South Korea, we flew to a robot soccer workshop in Japan organized by Minoru Asada and Hiroaki Kitano. Also in attendance were Dominique Duhaut, Itsuki Noda, Silvia Coradeschi, and Enrico Pagello. And that’s where RoboCup really started – we decided to do a competition. And the good thing was that Kitano was the chair of IJCAI, which was going to happen in Osaka in the summer of 1997. So we are there in Osaka and literally we came up with this idea of having a robot soccer competition, RoboCup. It was a big moment for us as researchers. We had to come up with the rules of this competition so that people would be able to participate seven months later. We came up with the three leagues that we were interested in and had expertise in.

The small size league, building upon our Carnegie Mellon interests, would have a field with a camera overhead connected to a computer and then the computer would remotely control the robots through radio.

Then Minoru Asada had these bigger robots with wheels, and we created a league that we call the middle-size league to include the robotics research of Minoru Asada and others. And then Itsuki Noda was interested in creating a simulation environment. We thought that this would help get more people participating in this task of robot soccer.

So that’s how the three leagues started: the small size, the middle size, and the simulation. Hiroaki Kitano, Dominique Duhaut and I were in charge of the small-size league, Minoru Asada was in charge of the middle-size league, and Itsuki Noda ran the simulation league.

One of the challenges was to come up with the rules and define the robots and playing fields. I remember my own pragmatism in suggesting that we play on a ping-pong table for the small-size, as a ping-pong table is something that exists in the whole world. That meant that we would have a playing surface, with defined size and texture, anywhere in the world. We decided one ping-pong table for the small-size league, and nine ping-pong tables for the middle-size league.

In the summer of 1997, at IJCAI, when we all went to the actual first RoboCup competition, the space was gorgeous. Hiroaki Kitano had made these beautiful fields and white bleachers around the fields. It was a very beautiful space with an area with computers for the simulation league. There were 80 teams that had joined the simulation online. We were, I believe, five teams for the small size league and about eight to ten for the middle size league.

That’s how it all started. And 1997 it was in Osaka, in 1998 Dominique Duhaut organized RoboCup in Paris, at a modern Science Center, La Villette. And then in 1999, RoboCup was organized by Silvia Coradeschi, in Stockholm, again co-located with the IJCAI conference. In these three years 1997, ’98, and ’99, there were only these three leagues, small size, middle size, and simulation. It was the foundation of everything. RoboCup grew consistently every year in terms of the number of teams, the number of participants, and the number of participating countries.

Some of the pitches in the main soccer arena at RoboCup 2024, held in Eindhoven, The Netherlands.

So how did RoboCup expand and could you talk about the decisions to add extra leagues?

Well, nothing was necessarily planned, it was more related to the research interests that people had. So when we were in Melbourne in 2000, there were two things that were added. One was RoboCupJunior. There was a professor, Elizabeth Sklar, who had a tremendous interest in robotics education for children. She proposed the RoboCupJunior competitions for children K-12. The goal of RoboCupJunior was to train all these young people to do research in robotics. It was and it still is extremely successful. In Melbourne there were probably the same number of children as there were people competing in what we now call the major leagues. As well as the soccer leagues, Elizabeth also ran a dance competition. This was very impressive – the children would dance on stage with their designed, built, and programmed mobile robots.

I believe that the rescue league was also introduced in 2000. The reason why we came up with rescue was because in those days, there was a lot of research on robots in disaster environments. So many people in our groups had an interest in developing robots that were able to handle disaster environments. So, we included that interest. And later on, @home was also introduced because people had an interest in service robots.

The logistics league came later to cover robots inside factories. The reason for introducing new leagues was always to include the community. And we didn’t want anyone to feel they could not come to RoboCup because they did different research with their robots. And so it was a very intellectually inclusive environment for AI and robotics researchers that could perform tasks autonomously – with perception, cognition, and action mostly in teams for particular tasks.

Rescue league arena at RoboCup 2024.

Could you talk about the changes that were announced last year, and the decision behind those?

Back in 1997, Hiroaki Kitano came up with this goal of a robot soccer team being able to beat the human World Cup winners by 2025. (I later tried, in the early 2000s, to rephrase that goal so that it was not about the robots beating the humans, but instead having robots playing alongside human players by 2050.) However, for this to happen, we have started the humanoid league so that the robots would have legs, not wheels. Our roadmap hence moves towards humanoid robots. It also happens that currently there are several robot companies who are producing humanoid robots that are easy to acquire, so researchers do not have the design and build their own humanoid robots, which was a difficult task that was pursued only by a limited group of researchers. In parallel, events started aiming at including humanoid robot soccer. We believed that RoboCup should be visible and a reference for humanoid robot soccer. We then proposed and changed that, in the international RoboCup competitions, robot soccer will focus solely on humanoid robots. That doesn’t mean that the other RoboCup leagues aren’t valuable. But if they continue at a regional level, there will still be venues to foster these other types of interests. The RoboCup international competitions would be solely focused on humanoid robot soccer.

Action from the humanoid soccer league at RoboCup 2025. Image courtesy of Alessandra Rossi.

RoboCup was tremendously successful in terms of including a variety of different autonomous robot research interests from the community. But I also believe that now we should move into just humanoid soccer at the international level. This will help with visibility of the competition and also for consolidation. We can now buy humanoid robots that we didn’t have before. Previously, you had to build them in your universities, and that was not a research direction for many people. But there is not that excuse anymore. You can buy humanoid robots, and increasingly, you can talk with these humanoid robots using GenAI. So it became a different challenge, a much more accessible challenge than before. The challenge will be: can these platforms play soccer in the presence of another team? I think it’s a fascinating new direction to try to focus on this challenge of the game of soccer – multiple players, two teams in a large space, eventually coordinating, collaborating, or playing with and against humans. So that’s the rationale.

When people don’t know the story, they tend to wonder why we have all these other leagues, such as rescue and logistics. It was always driven by the interests of the community and a big heart for a research approach. And we always thought that because we were organizing an event with a venue, that we could include these people that have interests outside of soccer. That has always been our drive. However, it’s true that it diluted a little bit the goal of 2050 – the humanoid soccer robots. Now I think it’s time to go back to soccer as a main focus, and still keep supporting the other interests that we have fostered, more at a regional level.

There are still a lot of details to be sorted out. And, of course, people may be upset by leagues terminating at the international level. I have always participated in the small-size league myself, 20 years of participating, and I am very attached to it. I was always the trustee representing the small-size league, and I am not sure I am happy with the small-size not being in the international event. But I need to think beyond what my personal interests are and try to understand what would have a bigger impact for AI, robotics, and RoboCup. I think that that’s demonstrating a group of humanoids playing soccer. And if we don’t do it at RoboCup, maybe someone else will.

The way I think about it is that we have made this decision and we can reevaluate it in five or ten years. But not making a change and never having the courage to deviate from what we have been pursuing is less exciting. Things have stalled a bit, with the same number of teams, the same people, the same rules, the same type of intellectual and research accomplishments. We need to excite people about something major again. So I think that the community will greatly embrace this new RoboCup international. And we are so well organized locally, that we can support other leagues at the local events.

I do think that, from a scientific and research point of view, it’s the right moment to target the soccer humanoid robots, because of their availability and our RoboCup ultimate goal. I think it would be amazing if people knew RoboCup international as the humanoid robot soccer competition. Can you imagine in 2027 having 100 teams all playing soccer with humanoids? We’ll see.

About Manuela Veloso

Herbert A. Simon University Professor Emerita, School of Computer Science, Carnegie Mellon University 2018-2026 Founder and Head, JPMorganChase AI Research, Managing Director

For the last eight years, Manuela Veloso has been the founder and Head of JPMorganChase AI Research and Herbert A. Simon University Professor Emerita at Carnegie Mellon University, where she was faculty in the Computer Science Department and then Head of the Machine Learning Department.

At JPMorganChase, she built a team of 100 top talented members with graduate education (PhD and Masters) in AI and related disciplines. The team focused on pillar areas of AI in finance, including data-driven optimization, planning and search, document analysis, trustworthy AI, AI and mathematical reasoning, continual learning, and multiagent systems. The team published their research in academic venues and addressed and contributed to business needs and vision.

Veloso has a licenciatura degree in Electrical Engineering and an M.Sc. in Electrical and Computer Engineering from Instituto Superior Técnico, Lisbon, an M.A. in Computer Science from Boston University, and a Ph.D. in Computer Science from Carnegie Mellon University. Veloso has Doctorate Honoris Causa degrees from the Örebro University, Sweden, the Instituto Universitário de Lisboa (ISCTE), Portugal, the Université de Bordeaux, France, and the Universidade Católica of Portugal.

She served as president of the Association for the Advancement of Artificial Intelligence (AAAI), and she is co-founder and a Past President of the RoboCup Federation. She is a fellow of main professional organizations in her area, namely AAAI, IEEE, AAAS, and ACM. She is the recipient of the ACM/SIGART Autonomous Agents Research Award, the Einstein Chair of the Chinese Academy of Sciences, an NSF Career Award, and the Allen Newell Medal for Excellence in Research. Veloso is a member of the National Academy of Engineering with a citation “for contributions to artificial intelligence and its applications in robotics and the financial services industry.” She is also a member of the Academy of Sciences of Portugal.

Her research interests are in AI, including Multiagent Systems, Autonomous Robots, Continual Learning Agents, and AI in Finance. For further details, see Manuela’s webpage.

One of the key challenges in building robots for household or industrial settings is the need to master the control of high-degree-of-freedom systems such as mobile manipulators. Reinforcement learning has been a promising avenue for acquiring robot control policies, however, scaling to complex systems has proved tricky. In their work SLAC: Simulation-Pretrained Latent Action Space for Whole-Body Real-World RL, Jiaheng Hu, Peter Stone and Roberto Martín-Martín introduce a method that renders real-world reinforcement learning feasible for complex embodiments. We caught up with Jiaheng to find out more.

What is the topic of the research in your paper and why is it an interesting area for study?

This paper is about how robots (in particular, household robots like mobile manipulators) can autonomously acquire skills via interacting with the physical world (i.e. real-world reinforcement learning). Reinforcement learning (RL) is a general learning framework for learning from trial-and-error interaction with an environment, and has huge potential in allowing robots to learn tasks without humans hand-engineering the solution. RL for robotics is a very exciting field, as it can open possibilities for robots to self-improve in a scalable way, towards the creation of general-purpose household robots that can assist people in our everyday lives.

What were some of the issues with previous methods that your paper was trying to address?

Previously, most of the successful applications of RL to robotics were done by training entirely in simulation, then deploying the policy in the real-world directly (i.e. zero-shot sim2real). However, such a method has big limitations: on one hand, it is not very scalable, as you need to create task-specific, high-fidelity simulation environments that highly match the real-world environment that you want to deploy the robot in, and this can often take days or months for each and every task. On the other hand, some tasks are actually very hard to simulate, as they involve deformable objects and contact-rich interactions (for example, pouring water, folding clothes, wiping whiteboard). For these tasks, the simulation is often quite different from the real world. This is where real-world RL comes into play: if we can allow a robot to learn by directly interacting with the physical world, we don’t need a simulator anymore. However, while several attempts have been made towards realizing real-world RL, it is actually a very hard problem since: 1. Sample-inefficiency: RL requires a lot of samples (i.e. interaction with the environment) to learn good behavior, which is often impossible to collect in large quantities in the real-world. 2. Safety Issues: RL requires exploration, and random exploration in the real-world is often very very dangerous. The robot can break itself and will never be able to recover from that.

Could you tell us about the method (SLAC) that you’ve introduced?

So, creating high-fidelity simulations is very hard, and directly learning in the real-world is also really hard. What should we do? The key idea of SLAC is that we can use a low-fidelity simulation environment to assist subsequent real-world RL. Specifically, SLAC implements this idea in a two-step process: in the first step, SLAC learns a latent action space in simulation via unsupervised reinforcement learning. Unsupervised RL is a technique that allows the robot to explore a given environment and learn task-agnostic behaviors. In SLAC, we design a special unsupervised RL objective that encourages these behaviors to be safe and structured.

In the second step, we treat these learned behaviors as the new action space of the robot, where the robot does real-world RL for downstream tasks such as wiping whiteboards by making decisions in this new action space. Importantly, this method allow us to circumvent the two biggest problem of real-world RL: we don’t have to worry about safety issues since the new action space is pretrained to be always safe; and we can learn in a sample-efficient way because our new action space is trained to be very structured.

The robot carrying out the task of wiping a whiteboard.

How did you go about testing and evaluating your method, and what were some of the key results?

We test our methods on a real Tiago robot – a high degrees-of-freedom, bi-manual mobile manipulation, on a series of very challenging real-world tasks, including wiping a large whiteboard, cleaning a table, and sweeping trash into a bag. These tasks are challenging from three aspects: 1. They are visuo-motor tasks that require processing of high-dimensional image information. 2. They require the whole-body motion of the robot (i.e. controlling many degrees-of-freedom at the same time), and 3. They are contact-rich, which makes it hard to simulate accurately. On all of these tasks, our method allows us to learn high-performance policies (>80% success rate) within an hour of real-world interactions. By comparison, previous methods simply cannot solve the task, and often risk breaking the robot. So to summarize, previously it was simply not possible to solve these tasks via real-world RL, and our method has made it possible.

What are your plans for future work?

I think there is still a lot more to do at the intersection of RL and robotics. My eventual goal is to create truly self-improving robots that can learn entirely by themselves without any human involvement. More recently, I’ve been interested in how we can leverage foundation models such as vision-language models (VLMs) and vision-language-action models (VLAs) to further automate the self-improvement loop.

About Jiaheng

Jiaheng Hu is a 4th-year PhD student at UT-Austin, co-advised by Prof. Peter Stone and Prof. Roberto Martín-Martín. His research interest is in Robot Learning and Reinforcement Learning, with the long-term goal of developing self-improving robots that can learn and adapt autonomously in unstructured environments. Jiaheng’s work has been published at top-tier Robotics and ML venues, including CoRL, NeurIPS, RSS, and ICRA, and has earned multiple best paper nominations and awards. During his PhD, he interned at Google DeepMind and Ai2, and is a recipient of the Two Sigma PhD Fellowship.

Read the work in full

SLAC: Simulation-Pretrained Latent Action Space for Whole-Body Real-World RL, Jiaheng Hu, Peter Stone, Roberto Martín-Martín.

Congratulations to Sven Koenig on winning the 2026 ACM/SIGAI Autonomous Agents Research Award. This prestigious award is made for excellence in research in the area of autonomous agents. It is intended to recognize researchers in autonomous agents whose current work is an important influence on the field.

Professor Sven Koenig was recognised “for his work on AI planning and search, which has shaped how intelligent agents reason and act in complex, dynamic environments. His contributions seamlessly bridge theory and practice, with a profound impact not only on AI and multi-agent systems, but also on robotics, where his algorithms have enabled robust, scalable autonomy in real-world robotic platforms”.

Sven Koenig is Chancellor’s Professor and Bren Chair at the Computer Science Department of UC Irvine. A Fellow of AAAI, AAAS, and ACM, Professor Koenig has received several best paper awards from AAAI, ICALP and SoCS, and contributed to the community in numerous service roles, most recently having served as the conference chair of AAAI 2026.

A core objective of RoboCup is to promote and advance robotics and AI research through the challenges offered by its various leagues. The ultimate goal of the soccer competition is that, by 2050, a team of fully autonomous humanoid robots will defeat the most recent winner of the FIFA World Cup. To bring this vision closer to reality, the RoboCup Federation has announced several changes to the leagues. We spoke with Alessandra Rossi, a trustee who has been involved in the humanoid soccer league for many years, to learn more.

Could you start by introducing yourself and tell us how you’ve been involved in RoboCup throughout the years, because you’ve been involved in so many aspects of the competition!

I am Alessandra Rossi from the University of Naples “Federico II”, where I am an Assistant Professor of Computer Science. I began working with and collaborating in RoboCup in 2016, when I started my PhD at the University of Hertfordshire in the UK. I am still affiliated with the University of Hertfordshire, as I remain a member of the humanoid KidSize team Bold Hearts, the longest continuously active team in the UK. After a few years, I became the team leader of Bold Hearts.

In 2019, I became a member of both the Technical Committee and the Organizing Committee of the Humanoid League. After serving on the Technical Committee for two years, I was elected to the Executive Committee of the Humanoid League. In 2025, I was elected to the Board of Trustees for the first time.

Over the years, I have steadily increased my involvement and commitment to RoboCup. I have always sought to actively engage the RoboCup community, both during competitions and outside of competition periods. I also work to encourage engagement between the major and junior leagues and to participate in regional RoboCup events.

While working at the University of Hertfordshire as a Visiting Lecturer, we launched an online module that uses RoboCup as a benchmark for teaching robotics to undergraduate students. The module is still running. I initially served as the module leader, and this role has since been taken over by our Bold Hearts teammate, Bente Riegler.

Last year, Maike Paetzel-Prüsmann, Merel Keijsers, and I (as lead authors), in collaboration with several trustees and many members from different leagues, published a paper on the current and future challenges in humanoid robotics. The paper was published in Autonomous Robots and is, to the best of my knowledge, the first to involve such a large and diverse group of contributors from across the RoboCup leagues. It discusses research within RoboCup and the collaboration and synergies between the leagues.

Group photo of the humanoid league teams at RoboCup 2025.

I understand that there are some changes planned for the leagues. Could say something about that, and specifically the changes that affect the soccer and the humanoid side.

The 2050 goal of the RoboCup Federation, as many people are probably aware, is for a team of humanoid robots to play against the winners of the FIFA World Cup. To achieve this, it is necessary to push further in that direction. One of the key changes, therefore, will be a stronger focus on humanoid robots.

Another major change will be the merger of the Standard Platform League (SPL) and the KidSize Humanoid League. This merged league will have the freedom to define its exact format and to develop a new roadmap that aligns the entire league toward a shared objective. While the 2050 goal itself remains unchanged, the path toward achieving it will need to be adjusted.

It is crucial to continue fostering the engagement of teams in the leagues that will be affected by these changes. At the same time, we must recognize that technology is advancing rapidly. Over the past year, in particular, we have seen significant progress in both hardware platforms and large language models. As RoboCup serves as a global benchmark for robotics research, we should continuously strive to advance technology and research—while still having fun.

Soccer is the complex task and behavior we are studying, and it is complex in many dimensions: from physical control and robot motion, to communication and strategy, and even human-like interactions. These include responding to the referee’s whistle, verbal and non-verbal communication among team members, interactions with the coach, and communication with the referee. All of these aspects will ultimately need to be incorporated into the humanoid league.

The RoboCup Federation has agreed some new partnerships with Unitree, Fourier and Booster. What impact will this have on the humanoid league? Will there be a standard platform element with teams using a specific humanoid robot?

I believe we will see a mix of different robots. With the three companies currently sponsoring RoboCup, we have already seen that their robots can achieve a wide range of behaviors, and there have been significant improvements in robot control. Some of these robots can walk very quickly—almost to the point of running.

Initially, there may be the possibility of multiple teams using the same platform. However, we must keep in mind that both hardware and software can become obsolete very quickly, so we need to remain open to multiple options. A robot that is state of the art today may no longer be so in a year or two. As a result, committing to a single standard platform could limit future progress.

For this reason, the current idea is to remain open to multiple platforms. Many teams already have excellent custom-built robots, and further improvements to these platforms should be encouraged. That said, the exact structure has not yet been decided, and these decisions will be made in consultation with the teams. It is important to give the RoboCup community the time it needs to adapt and move forward.

There have been some big advances in the humanoid adult-size league in the past couple of years. What improvements stood out to you at RoboCup2025 in Brazil?

One major change is that we have added extra robots to each team. Previously, teams played with just two robots per side, but matches are now played three versus three.

Another important improvement is the reduced presence of humans on the field. There is no longer a handler assigned to each robot. In the past, a team member had to walk behind the robots in case they fell and risked being damaged.

I have actually played in a match against the winning humanoid team. Naturally, the human team won, but it was an enjoyable and very interesting game, as the robots were surprisingly fast.

What has been the general reaction from the RoboCup community to the changes? I guess it depends on which league you’re in as to how much it affects you.

Yes, it depends on which league you are part of. The reactions have been a mix of excitement and passion. Of course, everyone is keen to see improvements, and participants have always been prepared for changes to the rules and the league structures. However, there are still some open questions, and teams are waiting to see how things will evolve. Tomorrow, there will be a meeting with the President and several trustees to address questions raised by the leagues.

The overall direction of RoboCup, guided by the 2050 goal has not changed. Each league has been extremely valuable and has contributed in different ways toward achieving that goal. RoboCup has also been immensely valuable for robotics research more broadly. Beyond being fun, the challenges involved in making robots play soccer are extraordinarily complex. The research and solutions developed within RoboCup can be applied to many other fields and applications.

About Alessandra Rossi

Alessandra is Assistant Professor at the University of Naples Federico II, Italy. Her PhD thesis was part of the Marie Sklodowska-Curie Research ETN SECURE project at the University of Hertfordshire (UK). Her research interests include Human–(Multi) Robot Interaction, social robotics, trust, XAI, multi-agent systems and user profiling. She is Project Manager and co-supervisor of the MSCA PERSEO (955778), TRAIL (101072488) and SWEET (101168792). She is also co-PI of the project ERROR (FA8655-23-1-7060), and part of several national and international projects. Alessandra is also trustee member of RoboCup Federation, and member of the Humanoid League team called Bold Hearts. She is Chair of the IEEE P3108 “Study Design”, and a member of the “Appendix” groups, she is Program Chair of IEEE RO-MAN 2027, she has been Robotic Challenge Chair at ICSR 2025, Special Session Chair of IEEE RO-MAN 2024, Publicity Chair of IEEE RO-MAN 2022 and 2023, Organising Chair of the 26th RoboCup International Symposium 2023, and she is on the program committee of several international conferences on human–robot interaction and artificial intelligence.

Tell us a bit about your PhD – where are you studying, and what is the topic of your research?

I am pursuing my PhD at Purdue University, where my dissertation focuses on developing scalable and adaptive deep learning frameworks for human activity recognition (HAR) using wearable sensors. I was drawn to this topic because wearables have the potential to transform fields like healthcare, elderly care, and long-term activity tracking. Unlike video-based recognition, which can raise privacy concerns and requires fixed camera setups, wearables are portable, non-intrusive, and capable of continuous monitoring, making them ideal for capturing activity data in natural, real-world settings.

The central challenge my dissertation addresses is that wearable data is often noisy, inconsistent, and uncertain, depending on sensor placement, movement artifacts, and device limitations. My goal is to design deep learning models that are not only computationally efficient and interpretable but also robust to the variability of real-world data. In doing so, I aim to ensure that wearable HAR systems are both practical and trustworthy for deployment outside controlled lab environments.

This research has been supported by the Polytechnic Summer Research Grant at Purdue. Beyond my dissertation work, I contribute to the research community as a reviewer for conferences such as CoDIT, CTDIAC, and IRC, and I have been invited to review for AAAI 2026. I was also involved in community building, serving as Local Organizer and Safety Chair for the 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2025), and continuing as Safety Chair for AAMAS 2026.

Could you give us an overview of the research you’ve carried out so far during your PhD?

So far, my research has focused on developing a hierarchical fuzzy deep neural network that can adapt to diverse human activity recognition datasets. In my initial work, I explored a hierarchical recognition approach, where simpler activities are detected at earlier levels of the model and more complex activities are recognized at higher levels. To enhance both robustness and interpretability, I integrated fuzzy logic principles into deep learning, allowing the model to better handle uncertainty in real-world sensor data.

A key strength of this model is its simplicity and low computational cost, which makes it particularly well suited for real-time activity recognition on wearable devices. I have rigorously evaluated the framework on multiple benchmark datasets of multivariate time series and systematically compared its performance against state-of-the-art methods, where it has demonstrated both competitive accuracy and improved interpretability.

Is there an aspect of your research that has been particularly interesting?

Yes, what excites me most is discovering how different approaches can make human activity recognition both smarter and more practical. For instance, integrating fuzzy logic has been fascinating, because it allows the model to capture the natural uncertainty and variability of human movement. Instead of forcing rigid classifications, the system can reason in terms of degrees of confidence, making it more interpretable and closer to how humans actually think.

I also find the hierarchical design of my model particularly interesting. Recognizing simple activities first, and then building toward more complex behaviors, mirrors the way humans often understand actions in layers. This structure not only makes the model efficient but also provides insights into how different activities relate to one another.

Beyond methodology, what motivates me is the real-world potential. The fact that these models can run efficiently on wearables means they could eventually support personalized healthcare, elderly care, and long term activity monitoring in people’s everyday lives. And since the techniques I’m developing apply broadly to time series data, their impact could extend well beyond HAR, into areas like medical diagnostics, IoT monitoring, or even audio recognition. That sense of both depth and versatility is what makes the research especially rewarding for me.

What are your plans for building on your research so far during the PhD – what aspects will you be investigating next?

Moving forward, I plan to further enhance the scalability and adaptability of my framework so that it can effectively handle large scale datasets and support real-time applications. A major focus will be on improving both the computational efficiency and interpretability of the model, ensuring it is not only powerful but also practical for deployment in real-world scenarios.

While my current research has focused on human activity recognition, I am excited to broaden the scope to the wider domain of time series classification. I see great potential in applying my framework to areas such as sound classification, physiological signal analysis, and other time-dependent domains. This will allow me to demonstrate the generalizability and robustness of my approach across diverse applications where time-based data is critical.

In the longer term, my goal is to develop a unified, scalable model for time series analysis that balances adaptability, interpretability, and efficiency. I hope such a framework can serve as a foundation for advancing not only HAR but also a broad range of healthcare, environmental, and AI-driven applications that require real-time, data-driven decision-making.

What made you want to study AI, and in particular the area of wearables?

My interest in wearables began during my time in Paris, where I was first introduced to the potential of sensor-based monitoring in healthcare. I was immediately drawn to how discreet and non-invasive wearables are compared to video-based methods, especially for applications like elderly care and patient monitoring.

More broadly, I have always been fascinated by AI’s ability to interpret complex data and uncover meaningful patterns that can enhance human well-being. Wearables offered the perfect intersection of my interests, combining cutting-edge AI techniques with practical, real-world impact, which naturally led me to focus my research on this area.

What advice would you give to someone thinking of doing a PhD in the field?

A PhD in AI demands both technical expertise and resilience. My advice would be:

• Stay curious and adaptable, because research directions evolve quickly, and the ability to pivot or explore new ideas is invaluable.
• Investigate combining disciplines. AI benefits greatly from insights in fields like psychology, healthcare, and human-computer interaction.
• Most importantly, choose a problem you are truly passionate about. That passion will sustain you through the inevitable challenges and setbacks of the PhD journey.

Approaching your research with curiosity, openness, and genuine interest can make the PhD not just a challenge, but a deeply rewarding experience.

Could you tell us an interesting (non-AI related) fact about you?

Outside of research, I’m passionate about leadership and community building. As president of the Purdue Tango Club, I grew the group from just 2 students to over 40 active members, organized weekly classes, and hosted large events with internationally recognized instructors. More importantly, I focused on creating a welcoming community where students feel connected and supported. For me, tango is more than dance, it’s a way to bring people together, bridge cultures, and balance the intensity of research with creativity and joy.

I also apply these skills in academic leadership. For example, I serve as Local Organizer and Safety Chair for the AAMAS 2025 and 2026 conferences, which has given me hands-on experience managing events, coordinating teams, and creating inclusive spaces for researchers worldwide.

About Zahra

Zahra Ghorrati is a PhD candidate and teaching assistant at Purdue University, specializing in artificial intelligence and time series classification with applications in human activity recognition. She earned her undergraduate degree in Computer Software Engineering and her master’s degree in Artificial Intelligence. Her research focuses on developing scalable and interpretable fuzzy deep learning models for wearable sensor data. She has presented her work at leading international conferences and journals, including AAMAS, PAAMS, FUZZ-IEEE, IEEE Access, System and Applied Soft Computing. She has served as a reviewer for CoDIT, CTDIAC, and IRC, and has been invited to review for AAAI 2026. Zahra also contributes to community building as Local Organizer and Safety Chair for AAMAS 2025 and 2026.

RoboCup is an international scientific initiative with the goal of advancing the state of the art of intelligent robots, AI and automation. The annual RoboCup event took place from 15-21 July in Salvador, Brazil. The Logistics League forms part of the Industrial League and is an application-driven league inspired by the industrial scenario of a smart factory. Ahead of the Brazil meeting, we spoke with three key members of the league to find out more. Alexander Ferrein is a RoboCup Trustee overseeing the Industrial League, and Till Hofmann and Wataru Uemura are Logistics League Executive Committee members.

Could you start by giving us an introduction to the Logistics League?

Alexander Ferrein: The idea of the Logistics League is to have robots helping in intra-production logistics. The playing field is set up with different machines and the robots need to bring raw materials and products to the machines and pick products up from them. There are orders coming in for different products of different complexities. The idea is that the robots deliver these products after they have been machined, at a certain handover point, and then the team will be awarded points. The setup is that we have six machines per team, and three robots operating in the smart factory.

There are two teams competing at the same time on different sides of the field. Most of the machines are on the home side of the field, but some machines are also on the opponent’s side of the field. The teams need to show basic robotics skills like navigation skills and collision avoidance. For the production of products we have little discs that have different colours and can be stacked on top of each other, and they have different caps. We have around 550 different items that can be produced. We don’t focus so much on the handling of the parts, therefore the manipulating mechanisms are quite simple and are usually custom built by the teams. They just need to grab these discs and drive them around and put them on conveyor belts on the machines.

The main focus is on the production logistics and the planning phase. The complex products need to be produced or machined by a team of robots – without this planning and team work it wouldn’t be possible to deliver the products within the allotted time in the competition.

Until now, we had been supported by Festo didactics, who supplied the machines. However, they pulled out in February and told us that they won’t support us in bringing the machines to Brazil. Our team in Aachen has a complete field set up, so we are in the (not so easy) process of packing the machines up in pallets and shipping them to Brazil.

Till Hofmann: One important detail is that all the products that need to be manufactured, the orders for those come online, and the number of possible products is very high. Therefore, you can’t do any planning in advance – you can’t just create a big database that contains one sequence that you execute for every possible product, that doesn’t really work. So the robots need to do online planning. Due to the fact that we have multiple robots in the team and then also the opponents teams’ robots on the field, many things go differently than planned, so a very big aspect of the competition is execution monitoring and online replanning. Basically you create an initial plan, but you need to constantly adapt that plan to what actually happens during execution. I just want to stress that in contrast to other RoboCup competitions, it’s really a long-horizon planning task in the sense that we usually need to do actions on a time horizon of five to ten minutes to actually get to an intermediate goal of producing one of those products.

Wataru Uemura: The focus of our league is on how to handle the production line. The three mobile robots are a very important part. At first these were autonomous guided robots, but now they are completely autonomous mobile robots. The robots need to decide on their path to make the product.

Could you talk about some of the challenges the teams face in the league, and is there a challenge or aspect of the competition that the teams have found particularly difficult?

Alexander: First of all, one needs to say that it is a really tough problem that we are facing here. So the teams that are starting new, they have to deal with all of the robotic aspects, so mobile robots, autonomous intelligence systems, they need to drive around, map, interact with the machines. As these items that we are pushing around are non-standard things, they also need to build their own manipulating devices. And then there is this massive planning aspect of the league, which is also not so easy. When we started this in 2011, 2012, we were thinking that this must be a solved problem, that one could use scheduling systems, that production is digital, and that everything would be easy. However, we found out it’s not actually easy, and there are no off-the-shelf solutions for a fleet of robots doing planning and production.

Looking at our team (which has become particularly successful over the years) and from observing the other teams as a trustee, I think that the integration aspect of all the different tasks is really a hard thing. Having a software system that is capable of so many things, communicating with the centralized referee box, and making it run within the time limit of a match, is the major challenge. Today, navigation of a robot is not the big issue, basically, but getting it integrated into your software system and building all the rest around the planning components and so on, this is, from my point of view, the major challenge.

Till: As I mentioned, I think the combination of long-horizon planning and execution monitoring is particularly difficult. We do have a lot of failures during one production run, because of hardware limitations and problems with the robots. Sometimes the machines themselves fail and they need to deal with this, without being able to solve the problem itself, because it’s not in their control. So they need to do a lot of reasoning that considers all the different cases that may happen. For example, suddenly you have a product appearing in a machine and you no longer know the configuration because this information was lost on the way. How do you deal with this? Another example is that the robot drops a piece while it is driving around and then tries to feed it into the machine. Then the machine reports a failure and the team needs to keep its world model up-to-date to know that this product is no longer where they thought it was. How do we deal with this?

Will there be any new challenges introduced for RoboCup 2025?

Alexander: Because the problem we are trying to solve is so hard, we don’t have many teams in the league. We had a new team at RoboCup2023, in Bordeaux, and they are now consistently coming to the RoboCups, which is nice. Apart from this, we have a core of three to five teams that participate in the league. As the challenge itself is hard to get into, the skills only develop slowly, so new challenges are not really introduced. There are slight changes here and there. One of the major changes in recent years was during Coronavirus times where we had to abandon the whole match aspect because we couldn’t play with two teams at the same time. We introduced aspects of the game as challenges. Now we have a challenge track as well, where teams can just focus on certain aspects of the league and do not need to play the full game.

The skills of the teams are not developing in such a way that we really need to add new challenges because it is still unsolved and hard for all the teams to get the robots running, because we have so many different aspects.

I understand that you are thinking about some changes to the league. Could you say more about this?

Alexander: Yes, we have some ideas for a new Industrial League. As Festo are pulling out we don’t see the need to stick with this particular machine type. We had a workshop earlier this year with all the teams and organising committees and we’re proposing a future challenge, or league. We will discuss this at RoboCup2025.

Till: We actually already had discussions with @work, and agreed that the long-term goal is to merge the two competitions into one big Industrial League. Next year, we will start converging by doing some kind of collaboration challenge or crossover challenge where teams from @work will collaborate with what’s now the Logistics League, but will be the Smart Manufacturing League by that time. Then hopefully, in two or three years, this will be one big league rather than separate industrial competitions. And the idea of the league that we’re currently planning to migrate to is really a broader smart manufacturing scenario where we have different aspects of smart manufacturing. So currently it’s really only the production logistics part. But in the future, we also want to include the assembly itself as part of the competition and also extend this to humanoid robots and also focus on human-robot collaboration in this manufacturing setting.

So this will be very different to the Logistics League as it is right now. How we will do the migration from what we have to that new league without losing all the teams is something that’s still in the making.

Alexander: I also don’t think we shouldn’t restrict ourselves to just one type of robot. As we see, there is something going on with respect to humanoid robots, and the Rescue League is proposing a quadruped robot. In the @Home League there are ideas to introduce the staircases where you need more agility in these settings. So for me, I wouldn’t restrict the type of robots that we’re using. We are just thinking about proposing challenges that are looking towards the future. So far we have been doing things that we thought might be relevant to industry, but industry is not very interested in what we are doing here. At least, they are not knocking at our doors and asking what our solutions are. That’s also another aspect that we will possibly discuss at Robocup 2025 – how we could increase our impact as a league for the outside world.

So that’s one of the aims, I guess, to evolve in a way such that industry will be more interested?

Alexander: Yes, be relevant, right? I mean, you see so much going on, in particular in China with the robot manufacturing OEMs [original equipment manufacturers] that build these robots in a few years that have quite impressive capabilities. And well, we stand aside and just watch. So maybe we should use those robots, and integrate them into our process. It’s very important that we are opening our minds to envision a future that’s different from today.

About the interviewees

	Alexander Ferrein received his MSc in Computer Science (Dipl.-Inform.) and his PhD (Dr. rer. nat) from Aachen University in 2001 and 2007, respectively. Between 2009-2011 he joined the Robotics and Agents Research Lab, University of Cape Town, as a postdoctoral research fellow with Feodor-Lynen scholarship granted by the Alexander-von-Humboldt Foundation. He then re-joined the Knowledge-Based Systems Group at Aachen University before he became a professor for Robotics and Computer Science at FH Aachen University of Applied Sciences. He is a heading the Mobile Autonomous Systems & Cognitive Robotics Institute at Aachen Applied Science University. His research focusses on the field of Artificial Intelligence and Cognitive Robotics. Since 2015 he is member of the Advisory Committee of the African-German Network of Excellence in Science whose Vice-president he was between 2019-2023. His research concentrates on the field of cognitive robotics. In particular, he is interested in high-level control and decision making of robots and agents acting under real-time constraints.
	Till Hofmann is a Postdoc at RWTH Aachen University. His research focuses on planning, plan execution, generalized planning as well as reactive synthesis, with a particular focus on planning for robotics. He was a participant in the RoboCup Logistics League from 2016 until 2019 and member of the technical committee from 2017 until 2020. Since 2024, he is on the executive committee of the RCLL.
	Wataru Uemura was born in 1977, and received B.E, M.E. and D.E. degrees from Osaka City University, in 2000, 2002, and 2005. He is an associate professor in Electronics, Information and Communication Engineering Course, Faculty of Advanced Science and Technology, Ryukoku University in Shiga, Japan. He is a member of IEEE, RoboCup and others. He is a chairperson of the RoboCup Japanese National Committee. He is an executive committee member of RoboCup Logistics League. He was a member of the Industrial Robotics Competition Committee, the World Robot Summit. He was TPC Vice Chairs of GCCE 2012, Conference Chair of GCCE 2016, and Publication Chairs of GCCE (Global Conference on Consumer Electronics). He is a member of the World Skills in Japan organizing committee of Autonomous Mobile Robots.

The video could highlight your own research, that of another researcher or group, introduce viewers to an AI topic, or include interviews with AI researchers. Any theme is welcome, but videos covering the following are particularly encouraged: large language models, AI and ethics, societal impact of AI, and risks of deployed AI.

The videos will be assessed in terms of their content, understandability, relevance to AI, entertainment value, and presentation quality.

To give you a flavour of what these videos could look like, click here to see the winners of the previous iteration of the competition.

The deadline for submissions is 30 November 2025. To submit, you must upload your video to a publicly accessible website, and fill in the submission form.

You can find out more here.

At this year’s International Conference on Machine Learning (ICML2025), Jaeho Kim, Yunseok Lee and Seulki Lee won an outstanding position paper award for their work Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards. We hear from Jaeho about the problems they were trying to address, and their proposed author feedback mechanism and reviewer reward system.

Could you say something about the problem that you address in your position paper?

Our position paper addresses the problems plaguing current AI conference peer review systems, while also raising questions about the future direction of peer review.

The imminent problem with the current peer review system in AI conferences is the exponential growth in paper submissions driven by increasing interest in AI. To put this with numbers, NeurIPS received over 30,000 submissions this year, while ICLR saw a 59.8% increase in submissions in just one year. This huge increase in submissions has created a fundamental mismatch: while paper submissions grow exponentially, the pool of qualified reviewers has not kept pace.

Submissions to some of the major AI conferences over the past few years.

This imbalance has severe consequences. The majority of papers are no longer receiving adequate review quality, undermining peer review’s essential function as a gatekeeper of scientific knowledge. When the review process fails, inappropriate papers and flawed research can slip through, potentially polluting the scientific record.

Considering AI’s profound societal impact, this breakdown in quality control poses risks that extend far beyond academia. Poor research that enters the scientific discourse can mislead future work, influence policy decisions, and ultimately hinder genuine knowledge advancement. Our position paper focuses on this critical question and proposes methods on how we can enhance the quality of review, thus leading to better dissemination of knowledge.

What do you argue for in the position paper?

Our position paper proposes two major changes to tackle the current peer review crisis: an author feedback mechanism and a reviewer reward system.

First, the author feedback system enables authors to formally evaluate the quality of reviews they receive. This system allows authors to assess reviewers’ comprehension of their work, identify potential signs of LLM-generated content, and establish basic safeguards against unfair, biased, or superficial reviews. Importantly, this isn’t about penalizing reviewers, but rather creating minimal accountability to protect authors from the small minority of reviewers who may not meet professional standards.

Second, our reviewer incentive system provides both immediate and long-term professional value for quality reviewing. For short-term motivation, author evaluation scores determine eligibility for digital badges (such as “Top 10% Reviewer” recognition) that can be displayed on academic profiles like OpenReview and Google Scholar. For long-term career impact, we propose novel metrics like a “reviewer impact score” – essentially an h-index calculated from the subsequent citations of papers a reviewer has evaluated. This treats reviewers as contributors to the papers they help improve and validates their role in advancing scientific knowledge.

Could you tell us more about your proposal for this new two-way peer review method?

Our proposed two-way peer review system makes one key change to the current process: we split review release into two phases.

The authors’ proposed modification to the peer-review system.

Currently, authors submit papers, reviewers write complete reviews, and all reviews are released at once. In our system, authors first receive only the neutral sections – the summary, strengths, and questions about their paper. Authors then provide feedback on whether reviewers properly understood their work. Only after this feedback do we release the second part containing weaknesses and ratings.

This approach offers three main benefits. First, it’s practical – we don’t need to change existing timelines or review templates. The second phase can be released immediately after the authors give feedback. Second, it protects authors from irresponsible reviews since reviewers know their work will be evaluated. Third, since reviewers typically review multiple papers, we can track their feedback scores to help area chairs identify (ir)responsible reviewers.

The key insight is that authors know their own work best and can quickly spot when a reviewer hasn’t properly engaged with their paper.

Could you talk about the concrete reward system that you suggest in the paper?

We propose both short-term and long-term rewards to address reviewer motivation, which naturally declines over time despite starting enthusiastically.

Short-term: Digital badges displayed on reviewers’ academic profiles, awarded based on author feedback scores. The goal is making reviewer contributions more visible. While some conferences list top reviewers on their websites, these lists are hard to find. Our badges would be prominently displayed on profiles and could even be printed on conference name tags.
Example of a badge that could appear on profiles.

Long-term: Numerical metrics to quantify reviewer impact at AI conferences. We suggest tracking measures like an h-index for reviewed papers. These metrics could be included in academic portfolios, similar to how we currently track publication impact.

The core idea is creating tangible career benefits for reviewers while establishing peer review as a professional academic service that rewards both authors and reviewers.

What do you think could be some of the pros and cons of implementing this system?

The benefits of our system are threefold. First, it is a very practical solution. Our approach doesn’t change current review schedules or review burdens, making it easy to incorporate into existing systems. Second, it encourages reviewers to act more responsibly, knowing their work will be evaluated. We emphasize that most reviewers already act professionally – however, even a small number of irresponsible reviewers can seriously damage the peer review system. Third, with sufficient scale, author feedback scores will make conferences more sustainable. Area chairs will have better information about reviewer quality, enabling them to make more informed decisions about paper acceptance.

However, there is strong potential for gaming by reviewers. Reviewers might optimize for rewards by giving overly positive reviews. Measures to counteract these problems are definitely needed. We are currently exploring solutions to address this issue.

Are there any concluding thoughts you’d like to add about the potential future
of conferences and peer-review?

One emerging trend we’ve observed is the increasing discussion of LLMs in peer review. While we believe current LLMs have several weaknesses (e.g., prompt injection, shallow reviews), we also think they will eventually surpass humans. When that happens, we will face a fundamental dilemma: if LLMs provide better reviews, why should humans be reviewing? Just as the rapid rise of LLMs caught us unprepared and created chaos, we cannot afford a repeat. We should start preparing for this question as soon as possible.

About Jaeho

Jaeho Kim is a Postdoctoral Researcher at Korea University with Professor Changhee Lee. He received his Ph.D. from UNIST under the supervision of Professor Seulki Lee. His main research focuses on time series learning, particularly developing foundation models that generate synthetic and human-guided time series data to reduce computational and data costs. He also contributes to improving the peer review process at major AI conferences, with his work recognized by the ICML 2025 Outstanding Position Paper Award.

Read the work in full

Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards, Jaeho Kim, Yunseok Lee, Seulki Lee.

RoboCup is an international scientific initiative with the goal of advancing the state of the art of intelligent robots, AI and automation. The annual RoboCup event, where teams gather from across the globe to take part in competitions across a number of leagues, this year took place in Salvador, Brazil from 15-21 July. In a series of interviews, we’ve been meeting some of the RoboCup trustees, committee members, and participants, to find out more about their respective leagues. Christoph Steup is an Executive Committee member and oversees the @Work League. Ahead of the event in Brazil, we spoke to Christoph to find out more about the @Work League, the tasks that teams need to complete, and future plans for the League.

Could you start by giving us an introduction to the @Work league?

The @Work League, along with the Logistics League, forms the Industrial League. Our goal is to mimic some of the aspects of industrial production systems. An important aspect of this is factory automization and trying to mimic the factory of the future, where you have autonomous robots building products according to customer design. In these factories of the future, a single piece would be produced individually for each customer. Factories nowadays have big conveyor belts and a lot of automization, with the tasks mostly done in the same way, and you can only build stuff efficiently if you build millions of items. We are working on building individual pieces, where automization is still possible, and even a single piece can be built effectively. But obviously, in our RoboCup competitions, we are not interested in building on a factory scale – we are doing it on a very small scale. That means our robots are typically 80 centimeters long, the largest are around 70 centimeters wide, and some of them are also 80 centimeters high. So let’s say they fit in a one metre cubed box. Also, all our operations are done on the ground. This is just for simplification because building big tables to make it more realistic would also increase the cost for RoboCup and wouldn’t give much additional value.

What our robots need to do is transport objects from different workstations. So we have a default configuration where the arena starts, and there are workstations with objects lying on them, and some of these objects need to be transported to other workstations. The robot needs to do that completely autonomously. So this is one of the special things about the @Work League, that it’s completely autonomous and there is only a single restart allowed per team. So that means the robot really needs to be reliable. One of the big differences between medium teams and very good teams is that the very good teams perform well all the time whereas the medium teams have some good runs and some bad runs.

As well as the object transportation that you mentioned, and there other tasks that the teams need to carry out?

There are some special tasks in our league, like the precision placement task where the robot needs to fit an object into a cavity that is essentially the same shape and size as the object. It’s a little bit like the game that babies do to train their dexterity.

We also have a task that is inspired by a conveyor belt, but we are using a table that is constantly turning. The robots need to grasp stuff while the table is turning. This looks a little bit silly because no one would actually put a rotating table in a factory, however this is our way of actually mimicking a conveyor belt. The conveyor belt itself would be really, really difficult to integrate into the competition, so we just abstracted that and use this rotating table to actually have the same challenge but in a more manageable way. And it’s still a very, very hard challenge.

Then there are some special challenges that we integrate. For example, that robots need to report their state back so that we can observe what the robot is doing. We also have a challenge where humans are in the loop. For example, the robot brings pieces to a certain workstation where a human is present, the human assembles the pieces, and then the human needs to give a sign to the robot, and then the robot will take the piece away and put it somewhere else. This is designed to really mimic the automated factory flow.

In the past we also had a challenge where the robots needed to open a drawer, take something out and then close the drawer again. We’ve also had tasks where the robot has to handle fragile objects, like sweets, where the robot really needed to be careful in manipulating them. So in general, what differentiates us most from the Logistics League is that we are focusing a lot on manipulation and all the difficulties that come with manipulation and unknown objects, whereas Logistics is more tailored towards large-scale logistics processes with all their optimization and planning.

I was lucky enough to attend RoboCup last year in Eindhoven and what the teams were doing was really impressive. It was also interesting to see how varied the robots were, and how teams were approaching the tasks in distinct ways, with different grabbers and so on.

Yes, this difference in approaches is related to the history of our League, which is a little bit similar to the Logistics League. The Logistics League was originally a sponsored demonstration by Festo, which is a large company from Germany that creates tools, but they also have a didactics area where they provide tools to help people understand factory optimization. The @Work League was sponsored by Kuka, the robotics company, and, in the beginning, they required every team to compete with the Kuka youBot. So this was pretty much the default platform for our league, but at some point Kuka dropped from a sponsor to just an advisor to the league, and nowadays they are not part of the league at all. So when the Kuka youBot was going out of commission, the teams searched for alternatives and now we are presented with a wide variety of robots that are competing in the league, which I personally find really cool. Now we have all these different robots, all these different approaches, and some work better in some scenarios and worse in others. So we really have a scientific approach to the problem and we are really getting some insights into how you can tackle this problem on multiple levels.

Have you noticed that some of the challenges specifically are more difficult in general for all the teams?

In 2018 we introduced a challenge of so-called arbitrary surfaces which are surfaces unknown to the teams that are put on top of the workstations. The teams need to be able to deal with these surfaces. There are two surfaces that are really, really awful for the teams – one is grass that we pretty much stole from the soccer competitions! We just thought it would be funny to try it, and it was a really interesting problem, especially for some of the grippers of the different teams. For example, the current world champion, they have a rigid gripper so they can have force feedback when they grasp. However, the grass is really difficult for them – because of their rigidity, they always grasp the grass itself and then they pull up the grass with the object. And this led to some interesting problems, like they are transporting the actual surface around and not only the object. This isn’t a problem for teams using a flexible gripper. However, on the other hand, the flexible gripper makes it really difficult to assess if you have grasped the object because you have very bad force feedback. So there are two different approaches that have their pros and cons in different scenarios.

Three robots from the @Work competition in Brazil.

Are you introducing any new tasks for this year?

Yes and no. So actually we are introducing a completely new challenge which is different from what we’ve done before. The new challenge is the so-called smart farming challenge, which is opening our league to a whole new field of applications, because we are now looking at agriculture. We are working on this with Studica, a robotics company from Canada, whose hardware we are using. We’ve already given it a try at the German Open. This challenge comes with some new specifics and one these is that the teams only get the robot shortly before the competition. So they don’t really know the robot largely in advance, and they need to assemble, program and design the robot in a very short time. To compensate for this, we reduce the amount of optimization and robustness that is necessary. Because it’s an agriculture setting, we have different objects, like fruits, that the teams need to handle. This makes it a little bit more complicated because fruits have a more arbitrary shape and different levels of ripeness that need to be detected. We also have some grapes that are hanging on a wall, which is a completely different kind of manipulation task than before, because before the teams just needed to grasp things from surfaces, but now they really need to pluck stuff from a wall in a reliable way. So this is the new challenge. It also comes with a lot of software challenges because the computational power of this robot is very limited because it only has a Raspberry Pi. For example, there is not a lot of image processing possible, especially compared to the current robots, some of which even have GPUs embedded.

Is there a particular part of the hardware or software that you’ve seen some of the biggest developments in over the last year or so?

Yeah, I think one big change I observed over the years was a switch from custom neural networks for object detection to off-the-shelf components. So pretty much all teams nowadays use YOLO networks, which you can get pre-trained and they just deploy them on GPUs that they embedded into their robots. This is also one of the reasons why the robots really grew in size over the last few years because they needed space for the larger computational power. This actually made it possible for a lot of teams to reliably detect the objects. Object detection was a big problem in the beginning of the league and nowadays it’s not really a big issue – most teams are really good at that. Sometimes they are a little bit startled with decoy objects – these are objects in the arena that are not really part of the task, and they are unknown to the teams beforehand. Sometimes they are, let’s say, evil decoys that look like an object and there’s some mismatches that the teams do, but this is becoming very rare.

I think the second big change is a switch to larger manipulators with more degrees of freedom. So in the beginning, everyone had a very small manipulator with only five degrees of freedom, which limited the operating range, and nowadays pretty much all teams have a six degree of freedom manipulator with a large range. This means that they don’t need to move their robot when they are in front of a workstation, which makes them much faster and also much more precise.

Could you talk about the future plans for the League?

There are a few things we are thinking about.

With regards to the competition itself, we had a discussion with the teams about what they are interested in doing in the future. Two things came up that they really want to have. One is mobile obstacles, so they want other objects to move autonomously through the arena. We’re in the process of creating that, in cooperation with EduArt, which is a company from Germany that also provides small educational robots. And the second thing we want to introduce is a kind of humanoid robot that the teams can use to actually handle special manipulation tasks that cannot be done simply with a robot manipulator.

In terms of creating an entry-level League, we have been working on this and one potential idea is to use the smart-farming challenge as the entry point. Through the collaboration with Studica, we can provide teams with the robot and they get to keep it after the competition. At the German Open I spoke to the Rapidly-Manufactured Rescue League about this crossover between the Rescue and the Junior Leagues, and they are very keen to collaborate.

We’re also talking with the Logistics League. Their sponsor, Festo, has dropped out of their league and now they need to reorganize. We are wondering if it would be worthwhile to bring our leagues closer together, or even fuse them together to a single RoboCup Industrial league. The Logistics League wants to do more manipulation, and the @Work League wants to do more planning, so we are closing the gap naturally between the two. However, this is just a thought at the moment – we need to see how the teams react to that.

About Christoph

Christoph Steup is an active researcher specializing in various fields of robotics, including swarm robotics, precision farming, and weather-resilient autonomous driving. He currently works at the Fraunhofer Institute for Transportation and Infrastructure Systems (IVI), where he leads the Swarm Technology Group. Prior to this role, he headed the Computational Intelligence in Robotics group at the Otto von Guericke University Magdeburg. Christoph’s involvement with RoboCup began in 2015 when he joined the robOTTO team of Otto von Guericke University as team leader. His contributions to the RoboCup community expanded as he became a member of the Technical Committee for the @Work League in 2017. In 2019, he further advanced his participation by joining the Executive Committee of the league.

In this interview series, we’re meeting some of the AAAI/SIGAI Doctoral Consortium participants to find out more about their research. In this latest interview, Haimin Hu tells us about his research on the algorithmic foundations of human-centered autonomy and his plans for future projects, and gives some advice for PhD students looking to take the next step in their career.

Could you give us an overview of the research you carried out during your PhD?

My PhD research, conducted under the supervision of Professor Jaime Fernández Fisac in the Princeton Safe Robotics Lab, focuses on the algorithmic foundations of human-centered autonomy. By integrating dynamic game theory with machine learning and safety-critical control, my work aims to ensure autonomous systems, from self-driving vehicles to drones and quadrupedal robots, are performant, verifiable, and trustworthy when deployed in human-populated space. The core principle of my PhD research is to plan robots’ motion in the joint space of both physical and information states, actively ensuring safety as they navigate uncertain, changing environments and interact with humans. Its key contribution is a unified algorithmic framework—backed by game theory—that allows robots to safely interact with their human peers, adapt to human preferences and goals, and even help humans refine their skills. Specifically, my PhD work contributes to the following areas in human-centered autonomy and multi-agent systems:

• Trustworthy human–robot interaction: Planning safe and efficient robot trajectories by closing the computation loop between physical human-robot interaction and runtime learning that reduces the robot’s uncertainty about the human.
• Verifiable neural safety analysis for complex robotic systems: Learning robust neural controllers for robots with high-dimensional dynamics; guaranteeing their training-time convergence and deployment-time safety.
• Scalable interactive planning under uncertainty: Synthesizing game-theoretic control policies for complex and uncertain human–robot systems at scale.

Was there a project (or aspect of your research) that was particularly interesting?

Safety in human-robot interaction is especially difficult to define, because it hinges on an, I’d say, almost unanswerable question: How safe is safe enough when humans might behave in arbitrary ways? To give a concrete example: Is it sufficient if an autonomous vehicle can avoid hitting a fallen cyclist 99.9% of the time? What if this rate can only be achieved by the vehicle always stopping and waiting for the human to move out of the way?

I would argue that, for trustworthy deployment of robots in human-populated space, we need to complement standard statistical methods with clear-cut robust safety assurances under a vetted set of operation conditions as well established as those of bridges, power plants, and elevators. We need runtime learning to minimize the robot’s performance loss caused by safety-enforcing maneuvers; this calls for algorithms that can reduce the robot’s inherent uncertainty induced by its human peers, for example, their intent (does a human driver want to merge, cut behind, or stay in the lane?) or response (if the robot comes closer, how will the human react?). We need to close the loop between the robot’s learning and decision-making so that it can optimize efficiency by anticipating how its ongoing interaction with the human may affect the evolving uncertainty, and ultimately, its long-term performance.

What made you want to study AI, and the area of human-centered robotic systems in particular?

I’ve been fascinated by robotics and intelligent systems since childhood, when I’d spend entire days watching sci-fi anime like Mobile Suit Gundam, Neon Genesis Evangelion, or Future GPX Cyber Formula. What captivated me wasn’t just the futuristic technology, but the vision of AI as a true partner—augmenting human abilities rather than replacing them. Cyber Formula in particular planted the idea of human-AI co-evolution in my mind: an AI co-pilot that not only helps a human driver navigate high-speed, high-stakes environments, but also adapts to the driver’s style over time, ultimately making the human a better racer and deepening mutual trust along the way. Today, during my collaboration with Toyota Research Institute (TRI), I work on human-centered robotics systems that embody this principle: designing AI systems that collaborate with people in dynamic, safety-critical settings by rapidly aligning with human intent through multimodal inputs, from physical assistance to visual cues and language feedback, bringing to life the very ideas that once lived in my childhood imagination.

You’ve landed a faculty position at Johns Hopkins University (JHU) – congratulations! Could you talk a bit about the process of job searching, and perhaps share some advice and insights for PhD students who may be at a similar stage in their career?

The job search was definitely intense but also deeply rewarding. My advice to PhD students: start thinking early about the kind of long-term impact you want to make, and act early on your application package and job talk. Also, make sure you talk to people, especially your senior colleagues and peers on the job market. I personally benefited a lot from the following resources:

• The Professor Is In
• Faculty Application Advice by Professor Sylvia Herbert
• Tips for Computer Science Faculty Applications by Professor Yisong Yue
• Research Statement by Professor Tom Silver
• Autonomy Talks (examples of great talks in broad areas of autonomy and AI)

Do you have an idea of the research projects you’ll be working on at JHU?

I wish to help create a future where humans can unquestionably embrace the presence of robots around them. Towards this vision, my lab at JHU will investigate the following topics:

• Uncertainty-aware interactive motion planning: How can robots plan safe and efficient motion by accounting for their evolving uncertainty, as well as their ability to reduce it through future interaction, sensing, communication, and learning?
• Human–AI co-evolution and co-adaptation: How can embodied AI systems learn from human teammates while helping them refine existing skills and acquire new ones in a safe, personalized manner?
• Safe human-compatible autonomy: How can autonomous systems ensure prescribed safety while remaining aligned with human values and attuned to human cognitive limitations?
• Scalable and generalizable strategic decision-making: How can multi-robot systems make safe, coordinated decisions in dynamic, human-populated environments?

How was the experience attending the AAAI Doctoral Consortium?

I had the privilege of attending the 2025 AAAI Doctoral Consortium, and it was an incredibly valuable experience. I’m especially grateful to the organizers for curating such a thoughtful and supportive environment for early-career researchers. The highlight for me was the mentoring session with Dr Ming Yin (postdoc at Princeton, now faculty at Georgia Tech CSE), whose insights on navigating the uncertain and competitive job market were both encouraging and eye-opening.

Could you tell us an interesting (non-AI related) fact about you?

I am passionate about skiing. I learned to ski primarily by vision-based imitation learning from a chairlift, though I’m definitely paying the price now for poor generalization! One day, I hope to build an exoskeleton that teaches me to ski better while keeping me safe on the double black diamonds.

About Haimin

Haimin Hu is an incoming Assistant Professor of Computer Science at Johns Hopkins University, where he is also a member of the Data Science and AI Institute, the Institute for Assured Autonomy, and the Laboratory for Computational Sensing and Robotics. His research focuses on the algorithmic foundations of human-centered autonomy. He has received several awards and recognitions, including a 2025 Robotics: Science and Systems Pioneer, a 2025 Cyber-Physical Systems Rising Star, and a 2024 Human-Robot Interaction Pioneer. Additionally, he has served as an Associate Editor for IEEE Robotics and Automation Letters since his fourth year as a PhD student. He obtained a PhD in Electrical and Computer Engineering from Princeton University in 2025, an MSE in Electrical Engineering from the University of Pennsylvania in 2020, and a BE in Electronic and Information Engineering from ShanghaiTech University in 2018.

The AIhub coffee corner captures the musings of AI experts over a short conversation. This month we tackle the topic of agentic AI. Joining the conversation this time are: Sanmay Das (Virginia Tech), Tom Dietterich (Oregon State University), Sabine Hauert (University of Bristol), Sarit Kraus (Bar-Ilan University), and Michael Littman (Brown University).

Sabine Hauert: Today’s topic is agentic AI. What is it? Why is it taking off? Sanmay, perhaps you could kick off with what you noticed at AAMAS [the Autonomous Agents and Multiagent Systems conference]?

Sanmay Das: It was very interesting because obviously there’s suddenly been an enormous interest in what an agent is and in the development of agentic AI. People in the AAMAS community have been thinking about what an agent is for at least three decades. Well, longer actually, but the community itself dates back about three decades in the form of these conferences. One of the very interesting questions was about why everybody is rediscovering the wheel and rewriting these papers about what it means to be an agent, and how we should think about these agents. The way in which AI has progressed, in the sense that large language models (LLMs) are now the dominant paradigm, is almost entirely different from the way in which people have thought about agents in the AAMAS community. Obviously, there’s been a lot of machine learning and reinforcement learning work, but there’s this historical tradition of thinking about reasoning and logic where you can actually have explicit world models. Even when you’re doing game theory, or MDPs, or their variants, you have an explicit world model that allows you to specify the notion of how to encode agency. Whereas I think that’s part of the disconnect now – everything is a little bit black boxy and statistical. How do you then think about what it means to be an agent? I think in terms of the underlying notion of what it means to be an agent, there’s a lot that can be learnt from what’s been done in the agents community and in philosophy.

I also think that there are some interesting ties to thinking about emergent behaviors, and multi-agent simulation. But it’s a little bit of a Wild West out there and there are all of these papers saying we need to first define what an agent is, which is definitely rediscovering the wheel. So, at AAMAS, there was a lot of discussion of stuff like that, but also questions about what this means in this particular era, because now we suddenly have these really powerful creatures that I think nobody in the AAMAS community saw coming. Fundamentally we need to adapt what we’ve been doing in the community to take into account that these are different from how we thought intelligent agents would emerge into this more general space where they can play. We need to work out how we adapt the kinds of things that we’ve learned about negotiation, agent interaction, and agent intention, to this world. Rada Mihalcea gave a really interesting keynote talk thinking about the natural language processing (NLP) side of things and the questions there.

Sabine: Do you feel like it was a new community joining the AAMAS community, or the AAMAS community that was converting?

Sanmay: Well, there were people who were coming to AAMAS and seeing that the community has been working on this for a long time. So learning something from that was definitely the vibe that I got. But my guess is, if you go to ICML or NeurIPS, that’s very much not the vibe.

Sarit Kraus: I think they’re wasting some time. I mean, forget the “what is an agent?”, but there have been many works from the agent community for many years about coordination, collaboration, etc. I heard about one recent paper where they reinvented Contract Nets. Contract Nets were introduced in 1980, and now there is a paper about it. OK, it’s LLMs that are transferring tasks from one another and signing contracts, but if they just read the past papers, it would save their time and then they could move to more interesting research questions. Currently, they say with LLM agents that you need to divide the task into sub agents. My PhD was about building a Diplomacy player, and in my design of the player there were agents that each played a different part of a Diplomacy play – one was a strategic agent, one was a Foreign Minister, etc. And now they are talking about it again.

Michael Littman: I totally agree with Sanmay and Sarit. The way I think about it is this: this notion of “let’s build agents now that we have LLMs” to me feels a little bit like we have a new programming language like Rust++, or whatever, and we can use it to write programs that we were struggling with before. It’s true that new programming languages can make some things easier, which is great, and LLMs give us a new, powerful way to create AI systems, and that’s also great. But it’s not clear that they solve the challenges that the agents community have been grappling with for so long. So, here’s a concrete example from an article that I read yesterday. Claudius is a version of Claude and it was agentified to run a small online shop. They gave it the ability to communicate with people, post slack messages, order products, set prices on things, and people were actually doing economic exchanges with the system. At the end of the day, it was terrible. Somebody talked it into buying tungsten cubes and selling them in the store. It was just nonsense. The Anthropic people viewed the experiment as a win. They said “ohh yeah, there were definitely problems, but they’re totally fixable”. And the fixes, to me, sounded like all they’d have to do is solve the problems that the agents community has been trying to solve for the last couple of decades. That’s all, and then we’ve got it perfect. And it’s not clear to me at all that just making LLMs generically better, or smarter, or better reasoners suddenly makes all these kinds of agents questions trivial because I don’t think they are. I think they’re hard for a reason and I think you have to grapple with the hard questions to actually solve these problems. But it’s true that LLMs give us a new ability to create a system that can have a conversation. But then the system’s decision-making is just really, really bad. And so I thought that was super interesting. But we agents researchers still have jobs, that’s the good news from all this.

Sabine: My bread and butter is to design agents, in our case robots, that work together to arrive at desired emergent properties and collective behaviors. From this swarm perspective, I feel that over the past 20 years we have learned a lot of the mechanisms by which you reach consensus, the mechanisms by which you automatically design agent behaviours using machine learning to enable groups to achieve a desired collective task. We know how to make agent behaviours understandable, all that good stuff you want in an engineered system. But up until now, we’ve been profoundly lacking the individual agents’ ability to interact with the world in a way that gives you richness. So in my mind, there’s a really nice interface where the agents are more capable, so they can now do those local interactions that make them useful. But we have this whole overarching way to systematically engineer collectives that I think might make the best of both worlds. I don’t know at what point that interface happens. I guess it comes partly from every community going a little bit towards the other side. So from the swarm side, we’re trying visual language models (VLMs), we’re trying to have our robots understand using LLMs their local world to communicate with humans and with each other and get a collective awareness at a very local level of what’s happening. And then we use our swarm paradigms to be able to engineer what they do as a collective using our past research expertise. I imagine for those who are just entering this discipline they need to start from the LLMs and go up. I think it’s part of the process.

Tom Dietterich: I think a lot of it just doesn’t have anything to do with agents at all, you’re writing computer programs. People found that if you try to use a single LLM to do the whole thing, the context gets all messed up and the LLM starts having trouble interpreting it. In fact, these LLMs have a relatively small short-term memory that they can effectively use before they start getting interference among the different things in the buffer. So the engineers break the system into multiple LLM calls and chain them together, and it’s not an agent, it’s just a computer program. I don’t know how many of you have seen this system called DSPy (written by Omar Khattab)? It takes an explicit sort of software engineering perspective on things. Basically, you write a type signature for each LLM module that says “here’s what it’s going to take as input, here’s what it’s going to produce as output”, you build your system, and then DSPy automatically tunes all the prompts as a sort of compiler phase to get the system to do the right thing. I want to question whether building systems with LLMs as a software engineering exercise will branch off from the building of multi-agent systems. Because virtually all the “agentic systems” are not agents in the sense that we would call them that. They don’t have autonomy any more than a regular computer program does.

Sabine: I wonder about the anthropomorphization of this, because now that you have different agents, they’re all doing a task or a job, and all of a sudden you get articles talking about how you can replace a whole team by a set of agents. So we’re no longer replacing individual jobs, we’re now replacing teams and I wonder if this terminology also doesn’t help.

Sanmay: To be clear, this idea has existed at least since the early 90s, when there were these “soft bots” that were basically running Unix commands and they were figuring out what to do themselves. It’s really no different. What people mean when they’re talking about agents is giving a piece of code the opportunity to run its own stuff and to be able to do that in service of some kind of a goal.

I think about this in terms of economic agents, because that’s what I grew up (AKA, did my PhD) thinking about. And, do I want an agent? I could think about writing an agent that manages my (non-existent) stock portfolio. If I had enough money to have a stock portfolio, I might think about writing an agent that manages that portfolio, and that’s a reasonable notion of having autonomy, right? It has some goal, which I set, and then it goes about making decisions. If you think about the sensor-actuator framework, its actuator is that it can make trades and it can take money from my bank account in order to do so. So I think that there’s something in getting back to the basic question of “how does this agent act in the world?” and then what are the percepts that it is receiving?

I completely agree with what you were saying earlier about this question of whether the LLMs enable interactions to happen in different ways. If you look at pre-LLMs, with these agents that were doing pricing, there’s this hilarious story of how some old biology textbook ended up costing $17 million on Amazon because there were these two bots that were doing the pricing of those books at two different used book stores. One of them was a slightly higher-rated store than the other, so it would take whatever price that the lower-rated store had and push it up by 10%. Then the lower-rated store was an undercutter and it would take the current highest price and go to 99% of that price. But this just led to this spiral where suddenly that book cost $17 million. This is exactly the kind of thing that’s going to happen in this world. But the thing that I’m actually somewhat worried about, and anthropomorphising, is how these agents are going to decide on their goals.There’s an opportunity for really bad errors to come out of programming that wouldn’t be as harmful in a more constrained situation.

Tom: In the reinforcement learning literature, of course, there’s all this discussion about reward hacking and so on, but now we imagine two agents interacting with each other and hacking each other’s rewards effectively, so the whole dynamics blows up – people are just not prepared.

Sabine: The breakdown of the problem that Tom mentioned, I think there’s perhaps a real benefit to having these agents that are narrower and that as a result are perhaps more verifiable at the individual level, they maybe have clearer goals, they might be more green because we might be able to constrain what area they operate with. And then in the robotics world, we’ve been looking at collaborative awareness where narrow agents that are task-specific are aware of other agents and collectively they have some awareness of what they’re meant to be doing overall. And it’s quite anti-AGI in the sense that you have lots of narrow agents again. So part of me is wondering, are we going back to heterogeneous task-specific agents and the AGI is collective, perhaps? And so this new wave, maybe it’s anti-AGI – that would be interesting!

Tom: Well, it’s almost the only way we can hope to prove the correctness of the system, to have each component narrow enough that we can actually reason about it. That’s an interesting paradox that I was missing from Stuart Russell’s “What if we succeed?” chapter in his book, which is what if we succeed in building a broad-spectrum agent, how are we going to test it?

It does seem like it would be great to have some people from the agents community speak at the machine learning conferences and try to do some diplomatic outreach. Or maybe run some workshops at those conferences.

Sarit: I was always interested in human-agent interaction and the fact that LLMs have solved the language issue for me, I’m very excited. But the other problem that has been mentioned is still here – you need to integrate strategies and decision-making. So my model is you have LLM agents that have tools that are all sorts of algorithms that we developed and implemented and there should be several of them. But the fact that somebody solved our natural language interaction, I think this is really, really great and good for the agents community as well for the computer science community generally.

Sabine: And good for the humans. It’s a good point, the humans are agents as well in those systems.

In this interview series, we’re meeting some of the AAAI/SIGAI Doctoral Consortium participants to find out more about their research. Kate Candon is a PhD student at Yale University interested in understanding how we can create interactive agents that are more effectively able to help people. We spoke to Kate to find out more about how she is leveraging explicit and implicit feedback in human-robot interactions.

Could you start by giving us a quick introduction to the topic of your research?

I study human-robot interaction. Specifically I’m interested in how we can get robots to better learn from humans in the way that they naturally teach. Typically, a lot of work in robot learning is with a human teacher who is only tasked with giving explicit feedback to the robot, but they’re not necessarily engaged in the task. So, for example, you might have a button for “good job” and “bad job”. But we know that humans give a lot of other signals, things like facial expressions and reactions to what the robot’s doing, maybe gestures like scratching their head. It could even be something like moving an object to the side that a robot hands them – that’s implicitly saying that that was the wrong thing to hand them at that time, because they’re not using it right now. Those implicit cues are trickier, they need interpretation. However, they are a way to get additional information without adding any burden to the human user. In the past, I’ve looked at these two streams (implicit and explicit feedback) separately, but my current and future research is about combining them together. Right now, we have a framework, which we are working on improving, where we can combine the implicit and explicit feedback.

In terms of picking up on the implicit feedback, how are you doing that, what’s the mechanism? Because it sounds incredibly difficult.

It can be really hard to interpret implicit cues. People will respond differently, from person to person, culture to culture, etc. And so it’s hard to know exactly which facial reaction means good versus which facial reaction means bad.

So right now, the first version of our framework is just using human actions. Seeing what the human is doing in the task can give clues about what the robot should do. They have different action spaces, but we can find an abstraction so that we can know that if a human does an action, what the similar actions would be that the robot can do. That’s the implicit feedback right now. And then, this summer, we want to extend that to using visual cues and looking at facial reactions and gestures.

So what kind of scenarios have you been kind of testing it on?

For our current project, we use a pizza making setup. Personally I really like cooking as an example because it’s a setting where it’s easy to imagine why these things would matter. I also like that cooking has this element of recipes and there is a formula, but there’s also room for personal preferences. For example, somebody likes to put their cheese on top of the pizza, so it gets really crispy, whereas other people like to put it under the meat and veggies, so that maybe it is more melty instead of crispy. Or even, some people clean up as they go versus others who wait until the end to deal with all the dishes. Another thing that I’m really excited about is that cooking can be social. Right now, we’re just working in dyadic human-robot interactions where it’s one person and one robot, but another extension that we want to work on in the coming year is extending this to group interactions. So if we have multiple people, maybe the robot can learn not only from the person reacting to the robot, but also learn from a person reacting to another person and extrapolating what that might mean for them in the collaboration.

Could you say a bit about how the work that you did earlier in your PhD has led you to this point?

When I first started my PhD, I was really interested in implicit feedback. And I thought that I wanted to focus on learning only from implicit feedback. One of my current lab mates was focused on the EMPATHIC framework, and was looking into learning from implicit human feedback, and I really liked that work and thought it was the direction that I wanted to go into.

However, that first summer of my PhD it was during COVID and so we couldn’t really have people come into the lab to interact with robots. And so instead I did an online study where I had people play a game with a robot. We recorded their face while they were playing the game, and then we tried to see if we could predict based on just facial reactions, gaze, and head orientation if we could predict what behaviors they preferred for the agent that they were playing with in the game. We actually found that we could decently well predict which of the behaviors they preferred.

The thing that was really cool was we found how much context matters. And I think this is something that is really important for going from just a solely teacher-learner paradigm to a collaboration – context really matters. What we found is that sometimes people would have really big reactions but it wasn’t necessarily to what the agent was doing, it was to something that they had done in the game. For example, there’s this clip that I always use in talks about this. This person’s playing and she has this really noticeably confused, upset look. And so at first you might think that’s negative feedback, whatever the robot did, the robot shouldn’t have done that. But if you actually look at the context, we see that it was the first time that she lost a life in this game. For the game we made a multiplayer version of Space Invaders, and she got hit by one of the aliens and her spaceship disappeared. And so based on the context, when a human looks at that, we actually say she was just confused about what happened to her. We want to filter that out and not actually consider that when reasoning about the human’s behavior. I think that was really exciting. After that, we realized that using implicit feedback only was just so hard. That’s why I’ve taken this pivot, and now I’m more interested in combining the implicit and explicit feedback together.

You mentioned the explicit element would be more binary, like good feedback, bad feedback. Would the person-in-the-loop press a button or would the feedback be given through speech?

Right now we just have a button for good job, bad job. In an HRI paper we looked at explicit feedback only. We had the same space invaders game, but we had people come into the lab and we had a little Nao robot, a little humanoid robot, sitting on the table next to them playing the game. We made it so that the person could give positive or negative feedback during the game to the robot so that it would hopefully learn better helping behavior in the collaboration. But we found that people wouldn’t actually give that much feedback because they were focused on just trying to play the game.

And so in this work we looked at whether there are different ways we can remind the person to give feedback. You don’t want to be doing it all the time because it’ll annoy the person and maybe make them worse at the game if you’re distracting them. And also you don’t necessarily always want feedback, you just want it at useful points. The two conditions we looked at were: 1) should the robot remind someone to give feedback before or after they try a new behavior? 2) should they use an “I” versus “we” framing? For example, “remember to give feedback so I can be a better teammate” versus “remember to give feedback so we can be a better team”, things like that. And we found that the “we” framing didn’t actually make people give more feedback, but it made them feel better about the feedback they gave. They felt like it was more helpful, kind of a camaraderie building. And that was only explicit feedback, but we want to see now if we combine that with a reaction from someone, maybe that point would be a good time to ask for that explicit feedback.

You’ve already touched on this but could you tell us about the future steps you have planned for the project?

The big thing motivating a lot of my work is that I want to make it easier for robots to adapt to humans with these subjective preferences. I think in terms of objective things, like being able to pick something up and move it from here to here, we’ll get to a point where robots are pretty good. But it’s these subjective preferences that are exciting. For example, I love to cook, and so I want the robot to not do too much, just to maybe do my dishes whilst I’m cooking. But someone who hates to cook might want the robot to do all of the cooking. Those are things that, even if you have the perfect robot, it can’t necessarily know those things. And so it has to be able to adapt. And a lot of the current preference learning work is so data hungry that you have to interact with it tons and tons of times for it to be able to learn. And I just don’t think that that’s realistic for people to actually have a robot in the home. If after three days you’re still telling it “no, when you help me clean up the living room, the blankets go on the couch not the chair” or something, you’re going to stop using the robot. I’m hoping that this combination of explicit and implicit feedback will help it be more naturalistic. You don’t have to necessarily know exactly the right way to give explicit feedback to get the robot to do what you want it to do. Hopefully through all of these different signals, the robot will be able to hone in a little bit faster.

I think a big future step (that is not necessarily in the near future) is incorporating language. It’s very exciting with how large language models have gotten so much better, but also there’s a lot of interesting questions. Up until now, I haven’t really included natural language. Part of it is because I’m not fully sure where it fits in the implicit versus explicit delineation. On the one hand, you can say “good job robot”, but the way you say it can mean different things – the tone is very important. For example, if you say it with a sarcastic tone, it doesn’t necessarily mean that the robot actually did a good job. So, language doesn’t fit neatly into one of the buckets, and I’m interested in future work to think more about that. I think it’s a super rich space, and it’s a way for humans to be much more granular and specific in their feedback in a natural way.

What was it that inspired you to go into this area then?

Honestly, it was a little accidental. I studied math and computer science in undergrad. After that, I worked in consulting for a couple of years and then in the public healthcare sector, for the Massachusetts Medicaid office. I decided I wanted to go back to academia and to get into AI. At the time, I wanted to combine AI with healthcare, so I was initially thinking about clinical machine learning. I’m at Yale, and there was only one person at the time doing that, so I was looking at the rest of the department and then I found Scaz (Brian Scassellati) who does a lot of work with robots for people with autism and is now moving more into robots for people with behavioral health challenges, things like dementia or anxiety. I thought his work was super interesting. I didn’t even realize that that kind of work was an option. He was working with Marynel Vázquez, a professor at Yale who was also doing human-robot interaction. She didn’t have any healthcare projects, but I interviewed with her and the questions that she was thinking about were exactly what I wanted to work on. I also really wanted to work with her. So, I accidentally stumbled into it, but I feel very grateful because I think it’s a way better fit for me than the clinical machine learning would have necessarily been. It combines a lot of what I’m interested in, and I also feel it allows me to flex back and forth between the mathy, more technical work, but then there’s also the human element, which is also super interesting and exciting to me.

Have you got any advice you’d give to someone thinking of doing a PhD in the field? Your perspective will be particularly interesting because you’ve worked outside of academia and then come back to start your PhD.

One thing is that, I mean it’s kind of cliche, but it’s not too late to start. I was hesitant because I’d been out of the field for a while, but I think if you can find the right mentor, it can be a really good experience. I think the biggest thing is finding a good advisor who you think is working on interesting questions, but also someone that you want to learn from. I feel very lucky with Marynel, she’s been a fabulous advisor. I’ve worked pretty closely with Scaz as well and they both foster this excitement about the work, but also care about me as a person. I’m not just a cog in the research machine.

The other thing I’d say is to find a lab where you have flexibility if your interests change, because it is a long time to be working on a set of projects.

For our final question, have you got an interesting non-AI related fact about you?

My main summertime hobby is playing golf. My whole family is into it – for my grandma’s 100th birthday party we had a family golf outing where we had about 40 of us golfing. And actually, that summer, when my grandma was 99, she had a par on one of the par threes – she’s my golfing role model!

About Kate

Kate Candon is a PhD candidate at Yale University in the Computer Science Department, advised by Professor Marynel Vázquez. She studies human-robot interaction, and is particularly interested in enabling robots to better learn from natural human feedback so that they can become better collaborators. She was selected for the AAMAS Doctoral Consortium in 2023 and HRI Pioneers in 2024. Before starting in human-robot interaction, she received her B.S. in Mathematics with Computer Science from MIT and then worked in consulting and in government healthcare.

RoboCup2025 took place from 15-21 July in Salvador, Brazil. The event saw around 3000 participants competing in the various leagues. In our first social media round-up post we saw what the teams got up to during the first couple of days of the event. In this second post, we take a look at the action from the final days when the competitions reached their climax.

View this post on Instagram

A post shared by RoboCup 2025 – Salvador, Brazil (@robocup2025)

In the #RoboCup2025 @Home OPL Final, our robot performed very well. It opened two doors, removed trash, and closed a cabinet door. Overall, NimbRo came in second, next to team Tidyboy (Korea).
www.ais.uni-bonn.de/nimbro/@Home

[image or embed]

— Sven Behnke (@sven-behnke.bsky.social) 20 July 2025 at 18:04

View this post on Instagram

A post shared by RoboCupJunior Panamá (@robocupjrpa)

#RoboCup 2025 Competitions Day 3

Today was a tense day! The best robots in each category advanced to the final round that will take place tomorrow! Good luck to all the finalists #robocup2025 #robotics #ai pic.twitter.com/cC5PihLAge

— Asad Norouzi (@asadnorouzi) July 19, 2025

View this post on Instagram

A post shared by Nix-Lab (@nixlabmx)

View this post on Instagram

A post shared by RoboCup 2025 – Salvador, Brazil (@robocup2025)

ロボカップシンポジウム
Panel: The Future of RoboCup

大盛況です#Kyutech #KitaQ #HMA #RoboCup2025 #Salvador pic.twitter.com/eYCaFkiprb

— Hibikino-Musashi@Home (@HMA_wakamatsu) July 21, 2025

View this post on Instagram

A post shared by Juliana Vellanes (@julianavellanes)

We are in the finals!

We started with our own robot damaged during the transportation but now our super-team, including RoboCanes (U. of Miami), PUMAS (UNAM), @_erasers, and TIDbots (@jikei_tid), has got into the final at the #RoboCup at Home (DSPL) league!#RoboCup2025 pic.twitter.com/yFbCK7GEU6

— Luis Contreras (@TenshiTeacher) July 20, 2025

View this post on Instagram

A post shared by Fagner Ribeiro (@fagnerbribeiro)

View this post on Instagram

A post shared by Equipe de Robótica da UMI Tânia Leite Santos (@umibots)

View this post on Instagram

A post shared by RoboCup 2025 – Salvador, Brazil (@robocup2025)

View this post on Instagram

A post shared by autonOhm (@autonohm_official)

View this post on Instagram

A post shared by RoboCup 2025 – Salvador, Brazil (@robocup2025)

RoboCup2025 took place in Salvador, Brazil. The event saw around 3000 participants competing in the various leagues. Find out what the teams got up to during the first couple of days:

View this post on Instagram

A post shared by OBR (Olimpíada Brasileira de Robótica) (@olimpiadabrasileiraderobotica)

View this post on Instagram

A post shared by RoboCup 2025 – Salvador, Brazil (@robocup2025)

View this post on Instagram

A post shared by Matheus Moldes | MD – Design de interiores (@m3d_int)

View this post on Instagram

A post shared by TIGERs Mannheim (@tigersmannheim)

View this post on Instagram

A post shared by Reinaldo Bianchi (@bianchireinaldo)

View this post on Instagram

A post shared by Nix-Lab (@nixlabmx)

View this post on Instagram

A post shared by UP Robotics (@up_robotics_ags)

View this post on Instagram

A post shared by RoboCup 2025 – Salvador, Brazil (@robocup2025)

View this post on Instagram

A post shared by RoboCup 2025 – Salvador, Brazil (@robocup2025)

View this post on Instagram

A post shared by ER-Force Erlangen (@roboticserlangen)

View this post on Instagram

A post shared by RobôCIn (@robocinufpe)

View this post on Instagram

A post shared by @escherciliamoreira

View this post on Instagram

A post shared by UCIMU-SISTEMIPERPRODURRE (@ucimu.sistemiperprodurre)

View this post on Instagram

A post shared by Höhere Fachschule Technik Mittelland (@hftmag)

View this post on Instagram

A post shared by Brisbane Boys’ College Co-curricular (@bbccocurricular)

View this post on Instagram

A post shared by Flavio Dusse (@flaviodusse)

RoboCup2025 is currently taking place in Salvador, Brazil. With day one of the main competition complete, things are hotting up across the many different leagues. From soccer to rescue, from industrial to home scenarios, teams are putting their robots through their paces across a variety of tasks and matches.

If you would like to catch up on the action from the first day, you can watch the recording of the livestream below. This includes coverage of the teams competing, interviews with participants and organisers, and insights into RoboCup and the various leagues.

The livestreams for days two and three, which will feature the knockout stages of the competitions, can be found below:

The livestream for the award ceremony, will be here:

You can also find the livestream on the RoboCup Twitch channel

Read our series of interviews with RoboCup organisers, trustees, and committee members:

• Preparing for kick-off at RoboCup2025: an interview with General Chair Marco Simões
• Gearing up for RoboCupJunior: Interview with Ana Patrícia Magalhães
• RoboCupRescue: an interview with Adam Jacoff
• An interview with Nicolai Ommer: the RoboCupSoccer Small Size League
• Tackling the 3D Simulation League: an interview with Klaus Dorer and Stefan Glaser

The annual RoboCup event, where teams gather from across the globe to take part in competitions across a number of leagues, will this year take place in Brazil, from 15-21 July. In advance of kick-off, we spoke to two members of the RoboCup Soccer 3D Simulation League: Executive Committee Member Klaus Dorer, and Stefan Glaser, who is on the Maintenance Committee and who has been recently developing a new simulator for the League.

Could start by just giving us a quick introduction to the Simulation League?
Klaus Dorer: There are two Simulation Leagues in Soccer: the 2D Simulation League and the 3D Simulation League. The 2D Simulation League, as the name suggests, is a flat league where the players and ball are simulated with simplified physics and the main focus is on team strategy. The 3D Simulation League is much closer to real robots; it simulates 11 versus 11 Nao robots. The level of control is like with real robots, where you move each motor of the legs and the arms and so on to achieve movement.

I understand that you have been working on a new simulator for the 3D League. What was the idea behind this new simulator?
Klaus: The aim is to bring us closer to the hardware leagues so that the simulator can be more useful. The current simulator that we use in the 3D Simulation League is called SimSpark. It was created in the early 2000s with the aim of making it possible to play 11 vs 11 players. With the hardware constraints of that time, there had to be some compromises on the physics to be able to simulate 22 players at the same time. So the simulation is physically somewhat realistic, but not in the sense that it’s easy to transpose it to a real Nao robot.

Stefan Glaser: The idea for developing a new simulator has been around for a few years. SimSpark is a very powerful simulation framework. The base framework is domain independent (not soccer specific) and specific simulations are realized via plugins. It supports multiple physics engines in the backend and provides a flexible scripting interface for configuration and adaptations of the simulation. However, all this flexibility comes with the price of complexity. In addition to that, SimSpark uses custom robot model specifications and communication protocols, limiting the amount of available robot models and requiring teams to develop custom communication layers only for communicating with SimSpark. As a result of this, SimSpark has not been widely adopted in the RoboCup community.

With the new simulator, I would like to address these two major issues: complexity and standardization. In the ML community, the MuJoCo physics engine has become a very popular choice for learning environments after Google DeepMind acquired it and released it open source. Its standards for world and robot model specifications are widely adopted in the community and there exist a lot of ready-to-use robot model specifications for a wide variety of virtual as well as real-world robots. In the middle of last year, they (MuJoCo) added a feature which allows you to manipulate the world representation during simulation (adding and removing objects to / from the simulation while preserving the simulation state). This is one essential requirement we have in the simulation league, where we start with an empty field and then the agents connect on demand and form the teams. When this feature has been added, I decided to make a step forward and try to implement a new simulator for the 3D Simulation League based on MuJoCo. Initially, I wanted to start development in C/C++ to achieve maximum performance, but then decided to start in Python to reduce complexity and make it more accessible for other developers. I started development on Easter Monday so it’s not even three months old!

I think it might be useful to explain a little bit more about the setup of our league and the requirements of the simulator. If we take the FIFA game (on your favorite gaming device) as an example, there is one simulation happening which simulates 22 players and the decision making is part of the simulation having full access to the state of the world. In the 3D Simulation League we have two teams with 11 robots on the field, but we also have 22 individual agent softwares which are connected to the simulation server, each controlling one single robot. Each connected agent only receives sensor information related to their robot in the simulation. They are also only allowed to communicate via the server – there is no direct communication between the agents allowed in Simulation League. So we have a general setup where the simulation server has to be able to accept up to 22 connections and manage the situation there. This functionality has been the major focus for me for the last couple of months and this part is already working well. Teams can connect their agents, which will receive sensor information and can actuate joints of the robot in the simulation and so on. They are also able to select different robot models if they like.

An illustration of the simulator set-up.

Presumably the new simulator has a better representation of the physics of a real robot.
Klaus: Exactly. For example, how the motors are controlled is now a bit different and much closer to real robots. So when I did my first experiments, I saw the robot collapse and I thought it was exactly how a real robot would collapse! In SimSpark we also had falling robots but the motor control in the new simulator is different. Now you can control the motors by speed, by force, by position, which is much more flexible – it’s closer to what we know from real robots.

I think that, at least initially, it will be more difficult for the Simulation League teams to get the robots to do what they want them to do, because it’s more realistic. For example, in SimSpark the ground contact was much more forgiving. So if you step hard on the ground, you don’t fall immediately with a SimSpark robot but with a MuJoCo robot this will be much more realistic. Indeed, in real robots ground contact is somewhat less forgiving.

I had a question about the vision aspect – how do the individual agents “see” the position of the other agents on the field?
Stefan: We simulate a virtual vision pipeline on the server side. You have a restricted field of view of ±60° horizontally and vertically. Within that field of view you will detect the head, the arms, the feet of other players, or the ball, for example, or different features of the field. Similar to common real-world vision pipelines, each detection consists of a label, a direction vector and the distance information. The information has some noise on it like real robots have, too, but teams don’t need to process camera images. They get the detections directly from the simulation server.

We’ve previously had a discussion about moving towards getting camera images of the simulation to integrate into the vision pipeline on the agent side. This was never really realistic in SimSpark with the implementation we had there. However, it should be possible with MuJoCo. However, for the first version, I used the same way the traditional simulator treated the vision. This means that teams don’t need to train a vision model, and don’t need to handle camera images to get started. This reduces the load significantly and also shifts the focus of the problem towards motion and decision making.

Will the simulator be used at RoboCup 2025?
Stefan: We plan to have a challenge with a new simulator and I will try to provide some demo games. At the moment it’s not really in a state where you can play a whole competition.

Klaus: That’s usually how we proceed with new simulators. We would not move from one to the other without any intermediate step. We will have a challenge this year at RoboCup 2025 with the new MuJoCo simulator where each participating team will try to teach the robot to kick as far as possible. So, we will not be playing a whole game, we won’t have multiple robots, just a single robot stepping in front of the ball and kicking the ball. That’s the technical challenge for this year. Teams will get an idea of how the simulator works, and we’ll get an idea of what has to be changed in the simulator to proceed.

This new challenge will be voluntary, so we are not sure how many teams will participate. Our team (MagmaOffenburg) will certainly take part. It will be interesting to see how well the teams perform because no one knows how far a good kick is in this simulator. It’s a bit like in Formula One when the rules change and no one knows which team will be the leading team.

Do you have an idea of how much adaptation teams will have to make if and when you move to the new simulator for the full matches?
Stefan: As a long-term member of 3D Simulation League, I know the old simulator SimSpark pretty well, and know the protocols involved and how the processes work. So the first version of the new simulator is designed to use the same basic protocol, the same sensor information, and so on. The idea is that the teams can use the new simulator with minimal effort in adapting their current agent software. So they should be able to get started pretty fast.

Although, when designing a new platform, I would like to take the opportunity to make a step forward in terms of protocols, because I also want to integrate other Leagues in the long-term. They usually have other control mechanisms, and they don’t use the same protocol that is prominent in 3D Simulation. Therefore there has to be some flexibility in the future. But for the first version, the idea was to get the Simulation League ready with minimal effort.

Klaus: The big idea is that this is not just used in the 3D Simulation league, but also as a useful simulator for the Humanoid League and also for the Standard Platform League (SPL). So if that turns out to be true, then it will be completely successful. For the Kick Challenge this year, for example, we use a T1 robot that is a Humanoid League robot.

Could you say something about this simulation to real world (Sim2Real) aspect?
Stefan: We’d like it to be possible for the motions and behaviors in the simulator to be ported to real robots. From my point of view, it would be useful the other way round too.

We, as a Simulation League, usually develop for the Simulation League and therefore would like to get the behaviors running on a real robot. But the hardware teams usually have a similar issue when they want to test high-level decision making. They might have two to five robots on the field, and if they want to play a high-level decision-making match and train in that regard, they always have to deploy a lot of robots. If they also want to have an opponent, they have to double the amount of robots in order to play a game to see how the strategy would turn out. The Sim2Real aspect is also interesting for these teams, because they should be able to take what they deployed on the real robot and it should also work in the simulation. They can then use the simulation to train high-level skills like team play, player positioning and so on, which is a challenging aspect for the real robot leagues like SPL or the Humanoid Leagues.

Klaus: And the reason we know this is because we have a team in the Simulation League and we have a team in the Humanoid League. So that’s another reason why we are keen to bring these things closer together.

How does the refereeing work in the Simulation League?
Klaus: A nice thing about Simulation Leagues is that there is a program which knows the real state of the world so we can build in the referee inside the simulator and it will not fail. For things like offside, whether the ball passed the goal line, that’s fail safe. All the referee decisions are taken by the system itself. We have a human referee but they never need to intervene. However, there are situations where we would like artificial intelligence to play a role. This is not currently the case in SimSpark because the rules are all hard coded. We have a lot of fouls that are debatable. For example, there are many fouls that teams agree should not have been a foul, and other fouls that are not called that should have been. It would be a nice AI learning task to get some situations judged by human referees and then train an AI model to better determine the rules for what is a foul and what isn’t a foul. But this is currently not the case.

Stefan: On the new simulator I am not that far into the development that I have implemented the automatic referee yet. I have some basic set of rules which progress the game as such, but judging fouls and deciding on special situations is not yet implemented in the new simulator.

What are the next steps for developing the simulator?
Stefan: One of the next major steps will be to refine the physics simulation. For instance, even though there exists a ball in the simulation, it is not yet really well refined. There are a lot of physics parameters which we have to decide on to reflect the real world as good as possible. This will likely require a series of experiments in order to get to the correct values for various aspects. In this aspect I’m hoping for some engagement of the community, as it is a great research opportunity and I personally would prefer the community to decide on a commonly accepted parameter set based on a level of evidence that I can’t easily provide all by myself. So in case someone is interested in refining the physics of the simulation such that it best reflects the real world, you are welcome to join!

Another major next step will be the development of the automatic referee of the soccer simulation, deciding on fouls, handling misbehaving agents and so on. In the first version, foul conditions will likely be judged by an expert system specifically designed for this purpose. The simulation league has developed a set of foul condition specifications which I plan to adapt. In a second step, I would like to integrate and support the development of AI based foul detection models. But yeah, one step after the other.

What are you particularly looking forward to at RoboCup2025?
Klaus: Well, with our team we have been vice world champion seven times in a row. This year we are really hoping to make it to world champion. We are very experienced in getting losses in finals and this year we are looking forward to changing that, from a team perspective.

Stefan: I’m going to Brazil in order to promote the simulator, not just for the Simulation League, but also across the boundaries for the Humanoid Leagues and the SPL Leagues. I think that this simulator is a great chance to bring people from all the leagues together. I’m particularly interested in the specific requirements of all the teams of the different leagues. This understanding will help me tailor the new simulator towards their needs. This is one of my major highlights for this year, I would say.

You can find out more about the new simulator at the project webpage, and from the documentation.

Klaus Dorer is professor for artificial intelligence, autonomous systems and software engineering at Offenburg University, Germany. He is also a member of the Institute for Machine Learning and Analytics IMLA. He has been team leader of the RoboCup simulation league teams magmaFreiburg (since 1999), living systems, magmaFurtwangen and is now team leader of magmaOffenburg since 2009. Since 2014, he has also been part of the humanoid adult size league team Sweaty.

Stefan Glaser is teaching assistant for artificial intelligence and intelligent autonomous systems at the Offenburg University, Germany. He has been part of the RoboCup simulation league team magmaOffenburg since 2009 and the RoboCup humanoid adult size league team Sweaty since 2014.

RoboCup is an international scientific initiative with the goal of advancing the state of the art of intelligent robots, AI and automation. The annual RoboCup event is due to take place from 15-21 July in Salvador, Brazil. The Soccer component of RoboCup comprises a number of Leagues, with one of these being the Small Size League (SSL). We caught up with Executive Committee member Nicolai Ommer to find out more about the SSL, how the auto referees work, and how teams use AI.

Could start by giving us a quick introduction to the Small Size League?

In the Small Size League (SSL) we have 11 robots per team – the only physical RoboCup soccer league to have the full number of players. The robots are small, cylindrical robots on wheels and they can move in any direction. They are self-built by the teams, so teams have to do both the hardware and the programming, and a lot of things have to work together to make a team work. The AI is central. We don’t have agents, so teams have a central computer at the field where they can do all the computation and then they send the commands to the robots in different abstractions. Some teams will just send velocity commands, other teams send a target.

We have a central vision system – this is maintained by the League, and has been since 2010. There are cameras above the field to track all the robots and the ball, so everyone knows where the robots are.

The robots can move up to 4 meters per second (m/s), after this point it gets quite unstable for the robots. They can change direction very quickly, and the ball can be kicked at 6.5 m/s. It’s quite fast and we’ve already had to limit the kick speed. Previously we had a limit of 8 m/s and before that 10m/s. However, no robot can catch a ball with this speed, so we decided to reduce it and put more focus on passing. This gives the keeper and the defenders a chance to actually intercept a kick.

It’s so fast that for humans it’s quite difficult to understand all the things that are going on. And that’s why, some years ago, we introduced auto refs, which help a lot in tracking, especially things like collisions and so on, where the human referee can’t watch everything at the same time.

How do the auto refs work then, and is there more than one operating at the same time?

When we developed the current system, to keep things fair, we decided to have multiple implementations of an auto ref system. These independent systems implement the same rules and then we do a majority vote on the decisions.

To do this we needed a middle component, so some years ago I started this project to have a new game controller. This is the user interface (UI) for the human referee who sits at a computer. In the UI you see the current game state, you can manipulate the game state, and this component coordinates the auto refs. The auto refs can connect and report fouls. If only one auto ref detects the foul, it won’t count it. But, if both auto refs report the foul within the time window, then it is counted. Part of the challenge was to make this all visual for the operator to understand. The human referee has the last word and makes the final decision.

We managed to establish two implementations. The aim was to have three implementations, which makes it easier to form a majority. However, it still works with just two implementations and we’ve had this for multiple years now. The implementations are from two different teams who are still active.

How do the auto refs deal with collisions?

We can detect collisions from the data. However, even for human referees it’s quite hard to determine who was at fault when two robots collide. So we had to just define a rule, and all the implementations of the auto ref implement the same rule. We wrote in the rulebook really specifically how you calculate if a collision happened and who was at fault. The first consideration is based on the velocity – below 1.5m/s it’s not a collision, above 1.5m/s it is. There is also another factor, relating to the angle calculation, that we also take into account to determine which robot was at fault.

What else do the auto refs detect?

Other fouls include the kick speed, and then there’s fouls relating to the adherence to normal game procedure. For example, when the other team has a free kick, then the opposing robots should maintain a certain distance from the ball.

The auto refs also observe non-fouls, in other words game events. For example, when the ball leaves the field. That’s the most common event. This one is actually not so easy to detect, particularly if there is a chip kick (where the ball leaves the playing surface). With the camera lens, the parabola of the ball can make it look like it’s outside the field of play when it isn’t. You need a robust filter to deal with this.

Also, when the auto refs detect a goal, we don’t trust them completely. When a goal is detected, we call it a “possible goal”. The match is halted immediately, all the robots stop, and the human referee can check all the available data before awarding the goal.

You’ve been involved in the League for a number of years. How has the League and the performance of the robots evolved over that time?

My first RoboCup was in 2012. The introduction of the auto refs has made the play a lot more fluent. Before this, we also introduced the concept of ball placement, so the robots would place the ball themselves for a free kick, or kick off, for example.

From the hardware side, the main improvement in recent years has been dribbling the ball in one-on-one situations. There has also been an improvement in the specialized skills performed by robots with a ball. For example, some years ago, one team (ZJUNlict) developed robots that could pull the ball backwards with them, move around defenders and then shoot at the goal. This was an unexpected movement, which we hadn’t seen before. Before this you had to do a pass to trick the defenders. Our team, TIGERs Mannheim, has also improved in this area now. But it’s really difficult to do this and requires a lot of tuning. It really depends on the field, the carpet, which is not standardized. So there’s a little bit of luck that your specifically built hardware is actually performing well on the competition carpet.

The Small Size League Grand Final at RoboCup 2024 in Eindhoven, Netherlands. TIGERs Mannheim vs. ZJUNlict. Video credit: TIGERs Mannheim. You can find the TIGERs’ YouTube channel here.

What are some of the challenges in the League?

One big challenge, and also maybe it’s a good thing for the League, is that we have a lot of undergraduate students in the teams. These students tend to leave the teams after their Bachelor’s or Master’s degree, the team members all change quite regularly, and that means that it’s difficult to retain knowledge in the teams. It’s a challenge to keep the performance of the team; it’s even hard to reproduce what previous members achieved. That’s why we don’t have large steps forward, because teams have to repeat the same things when new members join. However, it’s good for the students because they really learn a lot from the experience.

We are continuously working on identifying things which we can make available for everyone. In 2010 the vision system was established. It was a huge factor, meaning that teams didn’t have to do computer vision. And we are currently looking at establishing standards for wireless communication – this is currently done by everyone on their own. We want to advance the League, but at the same time, we also want to have this nature of being able to learn, being able to do all the things themselves if they want to.

You really need to have a team of people from different areas – mechanical engineering, electronics, project management. You also have to get sponsors, and you have to promote your project, get interested students in your team.

Could you talk about some of the AI elements to the League?

Most of our software is script-based, but we apply machine learning for small, subtle problems.

In my team, for example, we do model calibration with quite simple algorithms. We have a specific model for the chip kick, and another for the robot. The wheel friction is quite complicated, so we come up with a model and then we collect the data and use machine learning to detect the parameters.

For the actual match strategy, one nice example is from the team CMDragons. One year you could really observe that they had trained their model so that, once they scored goal, they upvoted the strategy that they applied before that. You could really see that the opponent reacted the same way all the time. They were able to score multiple goals, using the same strategy again and again, because they learned that if one strategy worked, they could use it again.

For our team, the TIGERs, our software is very much based on calculating scores for how good a pass is, how well can a pass be intercepted, and how we can improve the situation with a particular pass. This is hard-coded sometimes, with some geometry-based calculations, but there is also some fine-tuning. If we score a goal then we track back and see where the pass came from and we give bonuses on some of the score calculations. It’s more complicated than this, of course, but in general it’s what we try to do by learning during the game.

People often ask why we don’t do more with AI, and I think the main challenge is that, compared to other use cases, we don’t have that much data. It’s hard to get the data. In our case we have real hardware and we cannot just do matches all day long for days on end – the robots would break, and they need to be supervised. During a competition, we only have about five to seven matches in total. In 2016, we started to record all the games with a machine-readable format. All the positions are encoded, along with the referee decisions, and everything is in a log file which we publish centrally. I hope that with this growing amount of data we can actually apply some machine learning algorithms to see what previous matches and previous strategies did, and maybe get some insights.

What plans do you have for your team, the TIGERs?

We have actually won the competition for the last four years. We hope that there will be some other teams who can challenge us. Our defence has not really been challenged so we have a hard time finding weaknesses. We actually play against ourselves in simulation.

One thing that we want to improve on is precision because there is still some manual work to get everything calibrated and working as precisely as we want it. If some small detail is not working, for example the dribbling, then it risks the whole tournament. So we are working on making all these calibration processes easier, and to do more automatic data processing to determine the best parameters. In recent years we’ve worked a lot on dribbling in the 1 vs 1 situations. This has been a really big improvement for us and we are still working on that.

About Nicolai

Nicolai Ommer is a Software Engineer and Architect at QAware in Munich, specializing in designing and building robust software systems. He holds a B.Sc. in Applied Computer Science and an M.Sc. in Autonomous Systems. Nicolai began his journey in robotics with Team TIGERs Mannheim, participating in his first RoboCup in 2012. His dedication led him to join the RoboCup Small Size League Technical Committee and, in 2023, the Executive Committee. Passionate about innovation and collaboration, Nicolai combines academic insight with practical experience to push the boundaries of intelligent systems and contribute to the global robotics and software engineering communities.

RoboCup is an international scientific initiative with the goal of advancing the state of the science of intelligent robots, AI and automation. The annual RoboCup event will take place from 15-21 July in Salvador, Brazil. The RoboCupRescue League is an important element of the competition and focuses on the challenges involved in search and rescue applications. We caught up with Adam Jacoff, co-founder of the RoboCupRescue league, former RoboCup Trustee, and chair of the organising committee, to find out more.

Could you start by giving us an overview of the Rescue League?

The RoboCupRescue League is now in its 25th year hosting competitions and workshops all around the world. We’re focused on developing autonomous robots that can enable emergency responders to perform extremely hazardous tasks from safer stand-off distances. That includes search and rescue scenarios in compromised or collapsed structures, for example, but there are many tasks that firefighters and other public safety organizations do every day that would be safer with robots doing the dangerous part. We are really the only League at RoboCup that’s focused on emergency responders, so our arenas appear a little more chaotic than the other leagues, but in a controlled sort of way. We have twenty standard test methods that we use as challenge tasks that emergency responders and our league of teams around the world have helped develop and validate over many years. These competitions do three things at once.

First, they guide the research with tangible terrains, obstacles, and tasks that are representative of emergency response operations. The researchers likely do not know any emergency responders, but we do, and we have distilled their requirements into twenty or so standard test methods. So the teams know that if they can solve the challenges presented to them in the test lanes, maybe not all twenty, but ten of them, or five of them, that combination of capabilities are applicable to some public safety mission. And the more autonomy the researchers can implement into their robots, the more likely the robots will be effective and easy to use in the field. The main objective of our league is to quicken the development of effective and reliable autonomous behaviors for these complex environments.

RoboCup is an excellent incubator for developing and evaluating cutting edge research and at the same time for developing, validating, and disseminating new standard test methods. Our standard test methods are reproducible and approach the reality of very complex and hazardous environments in an incremental way. We have increasingly difficult settings for each test. So we start easy in the Preliminaries with all the terrain lanes flat so teams can optimize their approaches for each particular challenge. By Semi-Finals the terrain lanes are inclined into crossover 15° slopes with a complex terrain obstacle in the middle. The teams start performing sequences of multiple lanes, so they need to intelligently switch between different behaviors to succeed. Then for the Finals we inject more complexity with slippery features for the robots to lose traction, pinch points to force more steering, and higher step-over obstacles to make the sequences even harder. This is how we guide and challenge both autonomous and remotely operated robots beyond their comfort zone.

Second, the intensity of the experience and education for engineers and computer scientists leads to recruiting opportunities and careers. Everybody understands that teams who do well at RoboCupRescue have done something special. They can go on to more intense research or can help implement that technology in the commercial market. Our League has inspired and validated new robotic approaches to very complex environments and helped make the jump from research to commercial implementation.

The third piece of the puzzle is our connection to various communities of emergency responders. Our sequence of test lanes is exactly what emergency responders use to support their procurement and training. They use trial data captured with the robot manufacturers to help decide what robot to buy. They also use the test lanes to train remote operators and measure their proficiency. So RoboCupRescue helps emergency responders understand what the next wave of emerging technologies can do. For example, the nuclear waste cleanup industry wants to credential their remote robot operators to ensure robots don’t get stranded within extremely harsh radiation-filled environments. The robots need to keep working for 1,000 hours or more to be cost effective. They also want to ensure remote operators are proficient enough to safely perform the intended tasks without crashing the robot on the stairs and blocking the way for all other robots. Or worse yet, force humans in protective suits to go in and clear the way. Different organizations come to RoboCupRescue competitions and see various aspects of the league in action that are useful to them. In this case, as an obstacle course to get a robot driver’s license.

At Eindhoven last year (for RoboCup2024) we had the local bomb squads provide what we call a “reverse demonstration.” All these researchers give demonstrations of their robots at their schools to sponsors, family, friends, and maybe even to emergency responders. But they never get to see what the emergency responders do for a living – how dangerous their jobs are. So the RoboCupRescue league typically pauses for a while during the competition and comes together to watch a bomb technician get into their padded suit and go through the sequence of test lanes doing all the tasks that we’re asking the robots to perform. The researchers see how much of a burden it is just to wear the padded suits, which are very heavy and require forced air into the helmet. It’s not only physically difficult, they’re walking to and interacting with known explosives to render them safe – which is unconscionable given the capabilities of robots these days. They need to be working remotely from a safe stand-off distance. These “reverse demonstrations” are likely the first time the researchers ever get to meet people in bomb suits, and understand that it is these emergency responders we are working to help. Whether it’s firefighters or police, a natural or manmade disaster, we’re trying to help emergency responders stay out of harm’s way. They need capable, reliable, and easy to use robots to deal with extreme hazards more safely and effectively.

The RoboCupRescue arena at ICRA2025 (one of the qualifying events for RoboCup2025). Credit: Adam Jacoff.

So you mentioned trying to promote autonomy over teleoperation. How do you go about trying to encourage people to use more autonomy in the league?

Competitions need to have simple and clear rules. They need to challenge robots, lead them toward practical solutions, and highlight teams that are successful in a variety of challenges. So RoboCupRescue has developed scoring tasks for mobility, dexterity, and mapping within complex terrains. To score mobility points, for example, the robot needs to drive from one end of a terrain lane to the other end, or ascend and descend obstacles like stairs. They earn 1 point for each successful traverse up to 10 total repetitions to add some statistical significance. The operator is always out of sight of the robot, so working only through their interface as if the robot is inside a building. The terrain lanes and obstacles start easy and get harder, but all teams are being evaluated in the same difficulty setting as the competition progresses, so the points stay the same.

If the robot can successfully traverse the lane or perform the dexterity tasks without the operator touching the interface, we call that autonomy. At the beginning of each traverse the operator can manually set a goal point at the other end of the lane. Then they hit “go” and we all watch and learn together. If the robot gets to the other end without the operator touching the controls, the team gets 4 points instead of 1 point for that autonomous traverse. That 4:1 one ratio appears to be enough incentive to make sure teams develop autonomous behaviors and try them at each start point. However, they can always repair back to remote operation anytime the robot stalls to score at the lesser rate, so the rules encourage trying autonomy first. Also, we give Best-In-Class Autonomy awards to recognize teams that earned the most points autonomously throughout the competition.

Why do we need autonomy in emergency response operations? First, because the onboard autonomy typically makes the robot easier to use for a remote operator, which can also mean it is more likely to succeed down range or maybe be more reliable. Also, inside buildings there are often radio communications drop-out zones. Think about your cell phone reception inside concrete buildings or in basements under buildings, these places still need to be searched even when radio communication from a remote stand-off location outside the structure doesn’t support real-time video or control. So each RoboCupRescue lane, and the entire Labyrinth or Maze used for mapping, is considered a “radio drop-out zone” with tasks that score 4 to 1 if you can perform them autonomously. That applies to mobility, dexterity, and mapping tasks.

An example of one of the lanes (challenges) that teams tackle during competition. Credit: Adam Jacoff.

Will there be any new innovations to look out for this year?

What you’re going to see new this year are four-legged robots, called quadrupeds, that now have wheels as feet. There was a commercial robot that came to RoboCup2024 in Eindhoven. I invited them to demonstrate in the test lanes while the teams were at lunch, and this new robot design literally dominated our Semi-Finals sequence. Now that was a demonstration, conducted with the operator in direct line-of-sight of the robot, so much easier than remotely controlling the robot in the same terrains. But it didn’t have a remote interface. That’s exactly what our league of teams do best by adding interfaces, sensors, mapping, manipulators, and the autonomy to make it all effective and easier to use remotely.

These legged robots with wheels are a literal step function improvement in mobility, the likes of which I’ve only seen twice in thirty plus years. They have a level of mobility relative to their size that is astonishing. So we’re turning that new robot into our league’s first “standard platform.”

One of the four-legged robots with wheels as feet. Image from video taken at ICRA 2025, of the robot tackling one of the test lanes. Credit: Adam Jacoff.

Yes, I wanted to ask about the League’s plans for introducing a standard platform. Could you talk more about that?

This robot will provide a common development platform across teams with inherently good mobility within our terrains and obstacles. The league is negotiating with the manufacturer so that teams can purchase it at a relatively low price, which will bring down the cost of entry for new teams into the league. That level of mobility within our complex terrains and obstacles makes the autonomy a lot easier to develop – teams can focus on higher-level planning because the lower-level autonomous gaits and behaviors are already relatively effective. Similarly equipped teams can collaborate more closely, compare performance more directly, and share software solutions.

As a league, we can also start introducing teaming tasks for multiple robots. What kind of teaming might we explore? Maybe a certain object of interest is too heavy to drag for one robot, but could three of them work together to get it done like a team of dogs pulling a sled? Or maybe to carry payloads and supplies down-range, or even a non-ambulatory victim in a so-called litter back up-range to the base of operations. There will be lots of possibilities.

This new class of robots will operate in all the same test lanes along with all the other wheeled, tracked, and other robots developed by teams. We score every robot similarly of course, but then can separately compare the quantitative trial results for different classes of robots. It might turn out that it’s unfair to compare a new legged robot with wheels with a slower but stronger tracked robot that’s been winning RoboCupRescue for years. It’s not like tracked robots don’t have their use cases in emergency response operations. As soon as you get to tasks that involve exerting forces on the environment, like turning valves, the robots benefit from being heavier and stronger, which typically means tracks with independent front and rear flippers to negotiate the complex terrains and climb stairs. Everyone doesn’t need to adopt the new robot to compete, teams should work on implementations that push the state of the science in whatever direction they can. Then our Best-In-Class Awards can recognize the most effective robots in a variety of like-kind implementations, wheeled, tracked, legged, and maybe now legged with wheels.

When humanoids come into the league, and they will at some point, they’ll be welcomed and will be compared directly against other humanoids at least initially. We can also aggregate performance across a class of robots to identify advantages and apparent weaknesses. Emergency responders can then look at all the trial results to see which systems might work in their environments.

Do you know how many teams will be using this new robot?

I think we have almost twenty teams involved this year, but I’m not sure how many will be using the new legged robot with wheels. I expect maybe three or four initially, which would make a reasonable bracket of teams that can collaborate and compare more closely than others. There is a team from Austria that was in the German Open that is planning to come to Brazil. I’m sure when more people see the robot in action they’ll want one. Especially any new team coming into the league starting from scratch. Meanwhile, the RoboCupRescue league is poised to evaluate that robot design fully, add essential operational capabilities, and push the state of the science a bit further.

Will there be any different challenges this year?

Yes, this year we’re adding a new version of our original Stepfield terrain. They were our first rather complex terrain that inspired drastic changes in robot designs twenty years ago. The Stepfield terrain ensures the robots are always in contact with multiple different terrain elevations, and there is no respite throughout, even for legged robots with wheels. For the past couple of years, we got away from the Stepfield terrain because it was the hardest terrain to replicate at a temporary venue. But the year off for COVID was a growth time for us in terms of making the test methods as inexpensive and stowable as possible, so that small research organizations can replicate the tests to practice, refine approaches, and evaluate themselves during their development process. We first found a way to fabricate new Stepfields terrains from purchased, stackable crates. Now we have a fabricated version that accomplishes the same objectives less expensively. So RoboCupRescue teams will validate that the test apparatus as fabricated can stand up to the constant rigor of a very wide variety of robots across hundreds of trials in less than a week. That’s why RoboCupRescue is an excellent incubator for standard test methods too.

Is there anything else you’d like to highlight about the League?

One of the key features of RoboCupRescue is that the test lanes fabricated for the competition typically become a robot test facility for a local organization, like a nearby emergency responder facility or university. It can be set up perpetually, or it can move periodically to support regional competitions within the country. We usually try to connect the local organizers with their nearest emergency responders who already have robots or are seeking to purchase robots. The Olympic Village is the best analogy because it stays behind after the competition is over to be useful to the local region. So as we host our 25th year of RoboCupRescue in Brazil, we add to our world map of standard test facilities and new friends that we can continue to collaborate with professionally, and hopefully help their regional emergency responders use robots to stay out of harm’s way.

About Adam

Adam Jacoff is a robotics research engineer at the National Institute of Standards and Technology (NIST) which is part of the U.S. Department of Commerce. Over the past thirty years he has developed a variety of innovative robots and directed evaluations of more than a hundred others in a range of sizes, including the first technology readiness level assessment of autonomous mobility for the U.S. Army’s Experimental Unmanned Vehicle (XUV) (2002-2003).   His current efforts are focused toward developing 50 standard test methods to objectively evaluate ground robots, aerial drones, and aquatic vehicles for public safety operations. He has conducted 50 international robot competitions using the test methods as challenge tasks to guide innovation and measure progress (2000-present), and more than a hundred robot exercises to refine and validate the test methods with emergency responders and robot manufacturers (2005-present). These include dozens of comprehensive robot evaluations using the test methods to quantify key capabilities guiding more than $200M of purchasing decisions for civilian and military organizations (2010-present). He is now validating use of the test methods as repeatable practice tasks to focus remote operator/pilot training and measure proficiency for credentialing (2015-present).  He received a B.S. degree in Mechanical Engineering from the University of Maryland and a M.S. degree in Computer Science from Johns Hopkins University.

The annual RoboCup event, where teams gather from across the globe to take part in competitions across a number of leagues, will this year take place in Brazil, from 15-21 July. An important part of the week is RoboCupJunior, which is designed to introduce RoboCup to school children, and sees hundreds of kids taking part in a variety of challenges across different leagues. This year, the lead organizer for RoboCupJunior is Ana Patrícia Magalhães. We caught up with her to find out how the preparations are going, what to expect at this year’s competition, and how RoboCup inspires communities.

Could you tell us about RoboCupJunior and the plans you have for the competition this year?

RoboCup will take place from 15-21 July, in Salvador, Brazil. We expect to receive people from more than 40 countries, across the Junior and Major Leagues. We are preparing everything to accommodate all the students taking part in RoboCupJunior, who will participate in the Junior Leagues of Soccer, Rescue and OnStage. They are children and teenagers, so we have organized shuttles to take them from the hotels to the convention center. We’ve also prepared a handbook with recommendations about security, places they can visit, places to eat. The idea is to provide all the necessary support for them, because they are so young. We’re also organizing a welcome party for the Juniors so that they can experience a little bit of our culture. It will hopefully be a good experience for them.

The Juniors will be located on the first level of the mezzanine at the convention center. They will be separate from the Major Leagues, who will be on the ground floor. Of course, they’ll be able to visit the Major Leagues, and talk to the students and other competitors there, but it will be nice for them to have their own space. There will also be some parents and teachers with them, so we decided to use this special, dedicated space.

RoboCupJunior On Stage at RoboCup 2024. Photo: RoboCup/Bart van Overbeeke.

Do you have any idea of roughly how many teams will be taking part?

Yes, so we’ll have about 48 teams in the Soccer Leagues, 86 teams in the Rescue Leagues, and 27 in OnStage. That’s a lot of teams. Each team has about three or four students, and many of the parents, teachers and professors travel with them too. In total, we expect about 600 people to be associated with RoboCupJunior.

RoboCupJunior Soccer at RoboCup 2024. Photo: RoboCup/Bart van Overbeeke.

Have you got more RoboCupJunior participants from Brazil this year due to the location?

Yes, we have many teams from Brazil competing. I don’t know the exact number, but there are definitely more Brazilian teams this year, because it’s a lot cheaper and easier for them to travel here. When we have competitions in other countries, it’s expensive for them. For example, I have a team here in Salvador that qualified for the super regional event in the US and our team couldn’t go. They had qualified, but they couldn’t go because they didn’t have money to pay for the ticket. Now, it will be possible for all the Brazilian teams qualified to participate because it’s cheaper for them to come here. So it’s a big opportunity for development and to live the RoboCup experience. It’s very important for children and teenagers to share their research, meet people from other countries, and see what they are doing, and what research path they are following. They are very grateful for the opportunity to have their work tested against others. In a competition, it is possible to compare your research with others. So it’s different from conferences where you present a paper and show your work, but it’s not possible to compare and evaluate the results with other similar work. In a competition you have this opportunity. It’s a good way to get insights and improve your research.

RoboCupJunior Rescue at RoboCup 2024. Photo: RoboCup/Bart van Overbeeke.

Your role at this RoboCup will be organizing RoboCupJunior. Are you also involved in the Major Leagues?

Yes, so my main role is organizing RoboCupJunior and I am also one of the chairs of the RoboCup Symposium. Besides, some teams from my laboratory are competing in the Major leagues. My team participates in the @Home league, but I haven’t had much time to help them recently, with all the preparations for RoboCup2025. Our laboratory also has teams from the 3d Simulation Soccer League, and the Flying Robots Demo. This will be the first time we’ll see a flying robot demo league at a RoboCup.

We’ll also have two junior teams from the Rescue Simulation League. They are very excited about taking part.

RoboCupJunior Rescue at RoboCup 2024. Photo: RoboCup/Bart van Overbeeke.

RoboCup was last held in Brazil in 2014, and I understand that there were quite a lot of new people that were inspired to join a team after that. Do you think the 2025 RoboCup will have the same effect and will inspire more people in Brazil to take part?

Yes, I hope so. The last one inspired many, many students. We could perceive the difference before and after RoboCup at that time, related to projects in schools. In 2014, RoboCup was held in João Pessoa, a city in the north east that is not as developed or populated as many other states in Brazil. It really improved the research in that place and the interest in robotics especially. After the 2014 RoboCup, we’ve had many projects submitted to the Brazilian RoboCup competition from that state every year. We believe that it was because of RoboCup being held there.

We hope that RoboCup2025 next month will have the same effect. We think it might have an even bigger impact, because there is more social media now and the news can spread a lot further. We are expecting many visitors. We will have a form where schools that want to visit can enroll on a guided visit of RoboCup. This will go live on the website next week, but we are already receiving many messages from schools asking how they can participate with their group. They are interested in the events, so we have high expectations.

We have been working on organizing RoboCup2025 for over a year, and there is still much to do. We are excited to receive everybody here, both for the competition and to see the city. We have a beautiful city on the coast, and some beautiful places to visit, so I recommend that people come and stay for some days after the competition to get to know our city.

About Ana Patrícia

Ana Patrícia F. Magalhães Mascarenhas received her PhD in Computer Science from the Federal University of Bahia (2016) and Master in Mechatronics from the Federal University of Bahia (2007). She is currently an adjunct professor at the State University of Bahia (UNEB) at the Information Systems course. She is a researcher and vice coordinator of the Center for Research in Computer Architecture, Intelligent Systems and Robotics (ACSO). Her current research focuses on service robotics and software engineering, especially related to the use of Artificial Intelligence (AI) in the software development process and in Model-Driven Development (DDM).

RoboCup is an international scientific initiative with the goal of advancing the state of the art of intelligent robots, AI and automation. The annual RoboCup event, where teams gather from across the globe to take part in competitions across a number of leagues, will this year take place in Brazil, from 15-21 July. We spoke to Marco Simões, one of the General Chairs of RoboCup 2025 and President of RoboCup Brazil, to find out what plans they have for the event, some new initiatives, and how RoboCup has grown in Brazil over the past ten years.

Marco Simões

Could you give us a quick introduction to RoboCup 2025?

RoboCup will be held in Salvador, Brazil. When RoboCup was held in Brazil 11 years ago, in 2014, we had a total of 100,000 visitors, so that was a great success. This year, we expect even more, around 150,000, during all the events. Nowadays, AI and robotics are attracting more attention. We are also in a town, Salvador, with a bigger population than the previous location (João Pessoa). For these reasons, we estimate the attendance to be about 150,000 people.

Regarding the number of teams, registration has not closed yet, so we’re unsure about the final numbers. However, we expect to have about 300-400 teams and around 3000 competitors. We have been helping with visas, so we hope to see higher participation from teams who couldn’t attend in the previous two years due to visa issues. We are doing our best to ensure people can come and have fun at RoboCup!

This is also a great year for the RoboCup community: We have just agreed on new global league partners, including the Chinese companies Unitree, Fourier, and Booster Robotics. They will bring their humanoids and four-legged robots to RoboCup. These will not only be exhibited to the public but also used by some teams. They are amazing robots with very good skills. So, I think this will be an amazing edition of RoboCup this year.

Did the 2014 event in Brazil inspire more teams to participate in RoboCup?

Yes, we have seen a significant increase in our RoboCup community. In the last two years, Brazil has had the fourth-largest number of teams and participants at RoboCup in Bordeaux (2023) and Eindhoven (2024). This was a very big increase because ten years ago, we were not even in the top eight or nine.

We’ve made a significant effort with RoboCupJunior in the last ten years. Most people who’ve taken part in RoboCupJunior have carried on and joined the RoboCup Major League. So, the number of teams in Brazil has been increasing year by year over the last ten years. This year, we have a great number of participants because of the lower travel costs. We are expecting to be in the top three this year in terms of the highest number of participants.

Photo of participants at RoboCup 2024, which took place in Eindhoven. Photo credit: RoboCup/Bart van Overbeeke

It’s impressive that so many RoboCupJunior participants go on to join a Major League team.

Yes, we have an initiative here in Brazil called the Brazilian Robotics Olympiad. In this event, we chose two Junior Leagues – OnStage and the Rescue Line League – and we organized a competition based on these two Leagues. We run it in regional competitions all over Brazil – so 27 states. We organize at least one competition in each state during the year, and the best teams from each state come to the national competition together with the Major Leagues. We organize the Brazilian Olympiad to get RoboCupJunior to more students. This is how we’ve managed to increase participation in RoboCupJunior. Then, when students go to university, many of them continue to participate, but in the Major Leagues. So that’s a very successful strategy we’ve used in Brazil in the last 10 years.

Could you tell us about some more of the highlights from the Brazilian RoboCup community in recent years?

Two or three years ago, one of the Brazilian teams was the champion of RoboCup @Home. We have seen a big increase in the number of teams in the @Home League. In the national competition in Brazil, we have more than 12 teams participating. Back in 2014, we only had one team participating. So we’ve had a great increase—this League is one of the highlights in Brazil.

More teams are also participating in the Small Size League (part of the soccer League). Two years ago, one of the Brazilian teams was the champion of the division B of the Small Size League. So, over the last five years, we’ve seen some Brazilian teams in the top three positions in Major Leagues in the RoboCup world competition. This is a result of the increase in the number of teams and the quality of what the teams are developing. So at this time, we have an increased number of publications and teams participating in the competition with good results, so that’s very important.

Another excellent contribution for this year is a league we created five years ago – a flying robot league, where autonomous drones perform some missions and tasks. We’ve proposed this League as a demo for RoboCup2025, and we will have a Flying Robot Demo at the competition this year. This will be the first time we’ll have autonomous drones at the RoboCup competition, and the Brazilian community proposed it.

RoboCup @Home with Toyota HSR robots in the Domestic Standard Platform League, RoboCup 2024. Photo: RoboCup/Bart van Overbeeke.

Will you be taking part in the competition this year, or will you be focusing entirely on your role as General Chair?

This year, my laboratory (ACSO/Uneb) has qualified for the 3d Simulation League (soccer), the Flying Robot Demo, and RoboCup @Home, so we are participating in three Leagues. We also supervise RoboCupJunior Teams in the Rescue Simulation League. This year, my students have had only a little supervision from me because I’ve been very engaged with the organization.

In our 3D simulation team, we have lots of developments with deep reinforcement learning and some new novel strategies that allow our teams to gain new skills, and we are combining the new skills with our former multi-agent coordination strategy. For this reason, I think we will have a robust team in the competition because we are not only working on skills, we are also working on multi-agency strategies. When both aspects are joined, you can have a really good soccer team that plays very well. We have a good team and expect to achieve a greater position this year. In the latter years, we were in the top four or five, but we hope to get into the top three this year.

In 3D, you not only work on multi-agent aspects but also need to work on skills such as walking, kicking, and running. Teams are now trying to develop new skills. For example, in recent years, our team has developed the sprint running movement, which was a result of deep reinforcement learning. It is not a natural running motion but a running movement that works according to the League’s rules. It makes the robots go very fast from one point to another, making the team very competitive.

Most teams are learning skills but don’t know how to exploit them strategically in the game. Our focus is not only on creating new skills but also on using them strategically. We are currently working on a very innovative approach.

This year, the simulation league will run a challenge using a new simulator based on MuJoCo. If the challenge goes well, we may move to this new simulator in the following years, which can more realistically simulate real humanoid robots.

Action from the semi-finals of RoboCup Soccer Humanoid League at RoboCup 2024. Photo: RoboCup/Bart van Overbeeke.

Finally, is there anything else you’d like to highlight about RoboCup2025?

We are working on partnerships with local companies. For example, we have sponsorship from Petrobras, one of the biggest oil companies in the world. They will discuss how they are using robotics and AI in their industry. They were also one of the first sponsors of the Flying Robots League. It’s important to have these links between industry and the RoboCup community.

We also have excellent support from local companies and the government. They will be showing the community their latest developments. In the Rescue League, for example, we’ll have a demonstration from the local force showing what they do to support people in disaster situations.

This event is also an excellent opportunity for RoboCuppers, especially those who have never been to Brazil, to spend some days after the event in Salvador, visiting some tourist spots. Salvador was the first Brazilian capital, so we have a rich history. There are a lot of historical sites to see and some great entertainment options, such as beaches or parties. People can have fun and enjoy the country!

About Marco

Marco Simões is an Associate Professor at Bahia State University, Salvador, Brazil. He is the General Chair of RoboCup2025, and President of RoboCup Brazil.

In this interview series, we’re meeting some of the AAAI/SIGAI Doctoral Consortium participants to find out more about their research. The Doctoral Consortium provides an opportunity for a group of PhD students to discuss and explore their research interests and career objectives in an interdisciplinary workshop together with a panel of established researchers. In this latest interview, we hear from Amar Halilovic, a PhD student at Ulm University.

Tell us a bit about your PhD – where are you studying, and what is the topic of your research?

I’m currently a PhD student at Ulm University in Germany, where I focus on explainable AI for robotics. My research investigates how robots can generate explanations of their actions in a way that aligns with human preferences and expectations, particularly in navigation tasks.

Could you give us an overview of the research you’ve carried out so far during your PhD?

So far, I’ve developed a framework for environmental explanations of robot actions and decisions, especially when things go wrong. I have explored black-box and generative approaches for the generation of textual and visual explanations. Furthermore, I have been working on planning of different explanation attributes, such as timing, representation, duration, etc. Lately, I’ve been working on methods for dynamically selecting the best explanation strategy depending on the context and user preferences.

Is there an aspect of your research that has been particularly interesting?

Yes, I find it fascinating how people interpret robot behavior differently depending on the urgency or failure context. It’s been especially rewarding to study how explanation expectations shift in different situations and how we can tailor explanation timing and content accordingly.

What are your plans for building on your research so far during the PhD – what aspects will you be investigating next?

Next, I’ll be extending the framework to incorporate real-time adaptation, enabling robots to learn from user feedback and adjust their explanations on the fly. I’m also planning more user studies to validate the effectiveness of these explanations in real-world human-robot interaction settings.

Amar with his poster at the AAAI/SIGAI Doctoral Consortium at AAAI 2025.

What made you want to study AI, and, in particular, explainable robot navigation?

I’ve always been interested in the intersection of humans and machines. During my studies, I realized that making AI systems understandable isn’t just a technical challenge—it’s key to trust and usability. Robot navigation struck me as a particularly compelling area because decisions are spatial and visual, making explanations both challenging and impactful.

What advice would you give to someone thinking of doing a PhD in the field?

Pick a topic that genuinely excites you—you’ll be living with it for several years! Also, build a support network of mentors and peers. It’s easy to get lost in the technical work, but collaboration and feedback are vital.

Could you tell us an interesting (non-AI related) fact about you?

I have lived and studied in four different countries.

About Amar

Amar is a PhD student at the Institute of Artificial Intelligence of Ulm University in Germany. His research focuses on Explainable Artificial Intelligence (XAI) in Human-Robot Interaction (HRI), particularly how robots can generate context-sensitive explanations for navigation decisions. He combines symbolic planning and machine learning to build explainable robot systems that adapt to human preferences and different contexts. Before starting his PhD, he studied Electrical Engineering at the University of Sarajevo in Sarajevo, Bosnia and Herzegovina, and Computer Science at Mälardalen University in Västerås, Sweden. Outside academia, Amar enjoys travelling, photography, and exploring connections between technology and society.

The AAMAS 2025 best paper and demo awards were presented at the 24th International Conference on Autonomous Agents and Multiagent Systems, which took place from 19-23 May 2025 in Detroit. The Distinguished Dissertation Award was also recently announced. The winners in the various categories are as follows:

Best Paper Award

Winner

• Soft Condorcet Optimization for Ranking of General Agents, Marc Lanctot, Kate Larson, Michael Kaisers, Quentin Berthet, Ian Gemp, Manfred Diaz, Roberto-Rafael Maura-Rivero, Yoram Bachrach, Anna Koop, Doina Precup

Finalists

• Azorus: Commitments over Protocols for BDI Agents, Amit K. Chopra, Matteo Baldoni, Samuel H. Christie V, Munindar P. Singh
• Curiosity-Driven Partner Selection Accelerates Convention Emergence in Language Games, Chin-Wing Leung, Paolo Turrini, Ann Nowe
• Reinforcement Learning-based Approach for Vehicle-to-Building Charging with Heterogeneous Agents and Long Term Rewards, Fangqi Liu, Rishav Sen, Jose Paolo Talusan, Ava Pettet, Aaron Kandel, Yoshinori Suzue, Ayan Mukhopadhyay, Abhishek Dubey
• Ready, Bid, Go! On-Demand Delivery Using Fleets of Drones with Unknown, Heterogeneous Energy Storage Constraints, Mohamed S. Talamali, Genki Miyauchi, Thomas Watteyne, Micael Santos Couceiro, Roderich Gross

Pragnesh Jay Modi Best Student Paper Award

Winners

• Decentralized Planning Using Probabilistic Hyperproperties, Francesco Pontiggia, Filip Macák, Roman Andriushchenko, Michele Chiari, Milan Ceska
• Large Language Models for Virtual Human Gesture Selection, Parisa Ghanad Torshizi, Laura B. Hensel, Ari Shapiro, Stacy Marsella

Runner-up

• ReSCOM: Reward-Shaped Curriculum for Efficient Multi-Agent Communication Learning, Xinghai Wei, Tingting Yuan, Jie Yuan, Dongxiao Liu, Xiaoming Fu

Finalists

• Explaining Facial Expression Recognition, Sanjeev Nahulanthran, Leimin Tian, Dana Kulic, Mor Vered
• Agent-Based Analysis of Green Disclosure Policies and Their Market-Wide Impact on Firm Behavior, Lingxiao Zhao, Maria Polukarov, Carmine Ventre

Blue Sky Ideas Track Best Paper Award

Winner

• Grounding Agent Reasoning in Image Schemas: A Neurosymbolic Approach to Embodied Cognition, François Olivier, Zied Bouraoui

Finalist

• Towards Foundation-model-based multiagent system to Accelerate AI for social impact, Yunfan Zhao, Niclas Boehmer, Aparna Taneja, Milind Tambe

Best Demo Award

Winner

• Serious Games for Ethical Preference Elicitation, Jayati Deshmukh, Zijie Liang, Vahid Yazdanpanah, Sebastian Stein, Sarvapali Ramchurn

Victor Lesser Distinguished Dissertation Award

The Victor Lesser Distinguished Dissertation Award is given for dissertations in the field of autonomous agents and multiagent systems that show originality, depth, impact, as well as quality of writing, supported by high-quality publications.

Winner

• Jannik Peters. Thesis title: Facets of Proportionality: Selecting Committees, Budgets, and Clusters

Runner-up

• Lily Xu. Thesis title: High-stakes decisions from low-quality data: AI decision-making for planetary health

The 2025 IEEE International Conference on Robotics and Automation (ICRA) best paper winners and finalists in the various different categories have been announced. The recipients were revealed during an award ceremony at the conference, which took place from 19-23 May in Atlanta, USA.

IEEE ICRA Best Paper Award on Robot Learning

Winner

• *Robo-DM: Data Management for Large Robot Datasets, Kaiyuan Chen, Letian Fu, David Huang, Yanxiang Zhang, Yunliang Lawrence Chen, Huang Huang, Kush Hari, Ashwin Balakrishna, Ted Xiao, Pannag Sanketi, John Kubiatowicz, Ken Goldberg

Finalists

• Achieving Human Level Competitive Robot Table Tennis, David D’Ambrosio, Saminda Wishwajith Abeyruwan, Laura Graesser, Atil Iscen, Heni Ben Amor, Alex Bewley, Barney J. Reed, Krista Reymann, Leila Takayama, Yuval Tassa, Krysztof Choromanski, Erwin Coumans, Deepali Jain, Navdeep Jaitly, Natasha Jaques, Satoshi Kataoka, Yuheng Kuang, Nevena Lazic, Reza, Mahjourian, Sherry Moore, Kenneth Oslund, Anish Shankar, Vikas Sindhwani, Vincent Vanhoucke, Grace Vesom, Peng Xu, Pannag Sanketi
• *No Plan but Everything under Control: Robustly Solving Sequential Tasks with Dynamically Composed Gradient Descent, Vito Mengers, Oliver Brock

IEEE ICRA Best Paper Award in Field and Service Robotics

Winner

• *PolyTouch: A Robust Multi-Modal Tactile Sensor for Contact-Rich Manipulation Using Tactile-Diffusion Policies, Jialiang Zhao, Naveen Kuppuswamy, Siyuan Feng, Benjamin Burchfiel, Edward Adelson

Finalists

• A New Stereo Fisheye Event Camera for Fast Drone Detection and Tracking, Daniel Rodrigues Da Costa, Maxime Robic, Pascal Vasseur, Fabio Morbidi
• *Learning-Based Adaptive Navigation for Scalar Field Mapping and Feature Tracking, Jose Fuentes, Paulo Padrao, Abdullah Al Redwan Newaz, Leonardo Bobadilla

IEEE ICRA Best Paper Award on Human-Robot Interaction

Winner

• *Human-Agent Joint Learning for Efficient Robot Manipulation Skill Acquisition, Shengchent Luo, Quanuan Peng, Jun Lv, Kaiwen Hong, Katherin Driggs-Campbell, Cewu Lu, Yong-Lu Li

Finalists

• *To Ask or Not to Ask: Human-In-The-Loop Contextual Bandits with Applications in Robot-Assisted Feeding, Rohan Banerjee, Rajat Kumar Jenamani, Sidharth Vasudev, Amal Nanavati, Katherine Dimitropoulou, Sarah Dean, Tapomayukh Bhattacharjee
• *Point and Go: Intuitive Reference Frame Reallocation in Mode Switching for Assistive Robotics, Allie Wang, Chen Jiang, Michael Przystupa, Justin Valentine, Martin Jagersand

IEEE ICRA Best Paper Award on Mechanisms and Design

Winner

• Individual and Collective Behaviors in Soft Robot Worms Inspired by Living Worm Blobs, Carina Kaeser, Junghan Kwon, Elio Challita, Harry Tuazon, Robert Wood, Saad Bhamla, Justin Werfel

Finalists

• *Informed Repurposing of Quadruped Legs for New Tasks, Fuchen Chen, Daniel Aukes
• *Intelligent Self-Healing Artificial Muscle: Mechanisms for Damage Detection and Autonomous, Ethan Krings, Patrick Mcmanigal, Eric Markvicka

IEEE ICRA Best Paper Award on Planning and Control

Winner

• *No Plan but Everything under Control: Robustly Solving Sequential Tasks with Dynamically Composed Gradient Descent, Vito Mengers, Oliver Brock

Finalists

• *SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models, Yi Wu, Zikang Xiong, Yiran Hu, Shreyash Sridhar Iyengar, Nan Jiang, Aniket Bera, Lin Tan, Suresh Jagannathan
• *Marginalizing and Conditioning Gaussians Onto Linear Approximations of Smooth Manifolds with Applications in Robotics, Zi Cong Guo, James Richard Forbes, Timothy Barfoot

IEEE ICRA Best Paper Award in Robot Perception

Winner

• *MAC-VO: Metrics-Aware Covariance for Learning-Based Stereo Visual Odometry, Yuheng Qju, Yutian Chen, Zihao Zhang, Wenshan Wang, Sebastian Scherer

Finalists

• *Ground-Optimized 4D Radar-Inertial Odometry Via Continuous Velocity Integration Using Gaussian Process, Wooseong Yang, Hyesu Jang, Ayoung Kim
• *UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation, Yihe Tang, Wenlong Huang, Yingke Wang, Chengshu Li, Roy Yuan, Ruohan Zhang, Jiajun Wu, Li Fei-Fei

IEEE ICRA Best Paper Award in Robot Manipulation and Locomotion

Winner

• *D(R, O) Grasp: A Unified Representation of Robot and Object Interaction for Cross-Embodiment Dexterous Grasping, Zhenyu Wei, Zhixuan Xu, Jingxiang Guo, Yiwen Hou, Chongkai Gao, Zhehao Cai, Jiayu Luo, Lin Shao

Finalists

• *Full-Order Sampling-Based MPC for Torque-Level Locomotion Control Via Diffusion-Style Annealing, Haoru Xue, Chaoyi Pan, Zeji Yi, Guannan Qu, Guanya Shi
• *TrofyBot: A Transformable Rolling and Flying Robot with High Energy Efficiency, Mingwei Lai, Yugian Ye, Hanyu Wu, Chice Xuan, Ruibin Zhang, Qiuyu Ren, Chao Xu, Fei Gao, Yanjun Cao

IEEE ICRA Best Paper Award in Automation

Winner

• *Physics-Aware Robotic Palletization with Online Masking Inference, Tiangi Zhang, Zheng Wu, Yuxin Chen, Yixiao Wang, Boyuan Liang, Scott Moura, Masayoshi Tomizuka, Mingyu Ding, Wei Zhan

Finalists

• *In-Plane Manipulation of Soft Micro-Fiber with Ultrasonic Transducer Array and Microscope, Jieyun Zou, Siyuan An, Mingyue Wang, Jiaqi Li, Yalin Shi, You-Fu Li, Song Liu
• *A Complete and Bounded-Suboptimal Algorithm for a Moving Target Traveling Salesman Problem with Obstacles in 3D, Anoop Bhat, Geordan Gutow, Bhaskhar Vundurthy, Zhonggiang, Sivakumar Rathinam, Howie Choset

IEEE ICRA Best Paper Award in Medical Robotics

Winner

• *In-Vivo Tendon-Driven Rodent Ankle Exoskeleton System for Sensorimotor Rehabilitation, Juwan Han, Seunghyeon Park, Keehon Kim

Finalists

• *Image-Based Compliance Control for Robotic Steering of a Ferromagnetic Guidewire, An Hu, Chen Sun, Adam Dmytriw, Nan Xiao, Yu Sun
• *AutoPeel: Adhesion-Aware Safe Peeling Trajectory Optimization for Robotic Wound Care, Xiao Liang, Youcheng Zhang, Fei Liu, Florian Richter, Michael C. Yip

IEEE ICRA Best Paper Award on Multi-Robot Systems

Winner

• *Deploying Ten Thousand Robots: Scalable Imitation Learning for Lifelong Multi-Agent Path Finding, He Jiang, Yutong Wang, Rishi Veerapaneni, Tanishq Harish Duhan, Guillaume Adrien Sartoretti, Jiaoyang Li

Finalists

• Distributed Multi-Robot Source Seeking in Unknown Environments with Unknown Number of Sources, Lingpeng Chen, Siva Kailas, Srujan Deolasee, Wenhao Luo, Katia Sycara, Woojun Kim
• *Multi-Nonholonomic Robot Object Transportation with Obstacle Crossing Using a Deformable Sheet, Weijian Zhang, Charlie Street, Masoumeh Mansouri

IEEE ICRA Best Conference Paper Award

Winners

• *Marginalizing and Conditioning Gaussians Onto Linear Approximations of Smooth Manifolds with Applications in Robotics, Zi Cong Guo, James Richard Forbes, Timothy Barfoot
• *MAC-VO: Metrics-Aware Covariance for Learning-Based Stereo Visual Odometry, Yuheng Qju, Yutian Chen, Zihao Zhang, Wenshan Wang, Sebastian Scherer

In addition to the papers listed above, these paper were also finalists for the IEEE ICRA Best Conference Paper Award.

Finalists

• *MiniVLN: Efficient Vision-And-Language Navigation by Progressive Knowledge Distillation, Junyou Zhu, Yanyuan Qiao, Siqi Zhang, Xingjian He, Qi Wu, Jing Liu
• *RoboCrowd: Scaling Robot Data Collection through Crowdsourcing, Suvir Mirchandani, David D. Yuan, Kaylee Burns, Md Sazzad Islam, Zihao Zhao, Chelsea Finn, Dorsa Sadigh
• How Sound-Based Robot Communication Impacts Perceptions of Robotic Failure, Jai’La Lee Crider, Rhian Preston, Naomi T. Fitter
• *Obstacle-Avoidant Leader Following with a Quadruped Robot, Carmen Scheidemann, Lennart Werner, Victor Reijgwart, Andrei Cramariuc, Joris Chomarat, Jia-Ruei Chiu, Roland Siegwart, Marco Hutter
• *Dynamic Tube MPC: Learning Error Dynamics with Massively Parallel Simulation for Robust Safety in Practice, William Compton, Noel Csomay-Shanklin, Cole Johnson, Aaron Ames
• *Bat-VUFN: Bat-Inspired Visual-And-Ultrasound Fusion Network for Robust Perception in Adverse Conditions, Gyeongrok Lim, Jeong-ui Hong, Min Hyeon Bae
• *TinySense: A Lighter Weight and More Power-Efficient Avionics System for Flying Insect-Scale Robots, Zhitao Yu, Josh Tran, Claire Li, Aaron Weber, Yash P. Talwekar, Sawyer Fuller
• *TSCLIP: Robust CLIP Fine-Tuning for Worldwide Cross-Regional Traffic Sign Recognition, Guoyang Zhao, Fulong Ma, Weiging Qi, Chenguang Zhang, Yuxuan Liu, Ming Liu, Jun Ma
• *Geometric Design and Gait Co-Optimization for Soft Continuum Robots Swimming at Low and High Reynolds Numbers, Yanhao Yang, Ross Hatton
• *ShadowTac: Dense Measurement of Shear and Normal Deformation of a Tactile Membrane from Colored Shadows, Giuseppe Vitrani, Basile Pasquale, Michael Wiertlewski
• *Occlusion-aware 6D Pose Estimation with Depth-guided Graph Encoding and Cross-semantic Fusion for Robotic Grasping, Jingyang Liu, Zhenyu Lu, Lu Chen, Jing Yang, Chenguang Yang
• *Stable Tracking of Eye Gaze Direction During Ophthalmic Surgery, Tinghe Hong, Shenlin Cai, Boyang Li, Kai Huang
• *Configuration-Adaptive Visual Relative Localization for Spherical Modular Self-Reconfigurable Robots, Yuming Liu, Qiu Zheng, Yuxiao Tu, Yuan Gao, Guanqi Liang, Tin Lun Lam
• *Realm: Real-Time Line-Of-Sight Maintenance in Multi-Robot Navigation with Unknown Obstacles, Ruofei Bai, Shenghai Yuan, Kun Li, Hongliang Guo, Wei-Yun Yau, Lihua Xie

IEEE ICRA Best Student Paper Award

Winners

• *Deploying Ten Thousand Robots: Scalable Imitation Learning for Lifelong Multi-Agent Path Finding, He Jiang, Yutong Wang, Rishi Veerapaneni, Tanishq Harish Duhan, Guillaume Adrien Sartoretti, Jiaoyang Li
• *ShadowTac: Dense Measurement of Shear and Normal Deformation of a Tactile Membrane from Colored Shadows, Giuseppe Vitrani, Basile Pasquale, Michael Wiertlewski
• *Point and Go: Intuitive Reference Frame Reallocation in Mode Switching for Assistive Robotics, Allie Wang, Chen Jiang, Michael Przystupa, Justin Valentine, Martin Jagersand
• *TinySense: A Lighter Weight and More Power-Efficient Avionics System for Flying Insect-Scale Robots, Zhitao Yu, Josh Tran, Claire Li, Aaron Weber, Yash P. Talwekar, Sawyer Fuller

Note: papers with an * were eligible for the IEEE ICRA Best Student Paper Award.

The 2025 IEEE International Conference on Robotics & Automation (ICRA) took place from 19–23 May, in Atlanta, USA. The event featured plenary and keynote sessions, tutorial and workshops, forums, and a community day. Find out what the participants got up during the conference.

Check out what’s happening at the #ICRA2025 Welcome Reception! pic.twitter.com/w66IQDFsku

— IEEE ICRA (@ieee_ras_icra) May 19, 2025

The excitement is real — #ICRA2025 is already buzzing! pic.twitter.com/DtVgLwiaTB

— IEEE ICRA (@ieee_ras_icra) May 19, 2025

#ICRA #ICRA2025 #RoboticsInAfrica

[image or embed]

— Black in Robotics (@blackinrobotics.bsky.social) 18 May 2025 at 23:22

At #ICRA2025? Check out my student Yi Wu’s talk (TuCT1.4) at 3:30PM Tuesday in Room 302 at the Award Finalists 3 Session about how SELP Generates Safe and Efficient Plans for #Robot #Agents with #LLMs! #ConstrainedDecoding #LLMPlanner
@purduecs.bsky.social
@cerias.bsky.social

[image or embed]

— Lin Tan (@lin-tan.bsky.social) 19 May 2025 at 13:25

My MS student, Robel Mamo, is presenting his poster at #ICRA2025 #Field_Robotics workshop. His work is on "Crop-Aligned Cutout," a novel data augmentation method for under-canopy navigation @ieee_ras_icra @kennesawstate @KSUresearch pic.twitter.com/CBewagkpaQ

— Taeyeong Choi (최태영) (@ssuty) May 19, 2025

#ICRA2025 pic.twitter.com/FRfqgmSqNd

— Masato Kobayashi @るっと (@MeRTcooking) May 21, 2025

Malte Mosbach will present today 16:45 at #ICRA2025 in room 404 our paper:
"Prompt-responsive Object Retrieval with Memory-augmented Student-Teacher Learning"
www.ais.uni-bonn.de/videos/ICRA_…

[image or embed]

— Sven Behnke (@sven-behnke.bsky.social) 20 May 2025 at 15:57

#ICRA2025 pic.twitter.com/ANKoq3ry5K

— Masato Kobayashi @るっと (@MeRTcooking) May 21, 2025

Tomorrow morning at #ICRA2025, I will be presenting our findings on whether robots can learn dual-arm tasks from just a single demonstration. (Spoiler: they can!)

Come along!

This was led by my excellent PhD student Yilong Wang.

Paper & videos here: https://t.co/F2PtNJEJZT. pic.twitter.com/ycSAzuAgPn

— Edward Johns @ ICRA 2025 (@Ed__Johns) May 20, 2025

I will present our work on air-ground collaboration with SPOMP in 407A in a few minutes! We deployed 1 UAV and 3 UGVs in a fully autonomous mapping mission in large-scale environments. Come check it out! #ICRA2025 @grasplab.bsky.social

[image or embed]

— Fernando Cladera (@fcladera.bsky.social) 21 May 2025 at 20:13

Snapshots from #ICRA2025 @ieee_ras_icra : fans keep balloon walkers in constrained area @DennisHongRobot ; Artly coffee robot https://t.co/NCAMEo4fr5 ; mural ; and robo-friends #robots #artly #innovators pic.twitter.com/YAZdUWr9CD

— Heather Knight (@heatherknight) May 21, 2025

Cool things happening at #ICRA2025
RoboRacers gearing up for their qualifiers

[image or embed]

— Ameya Salvi (@ameyasalvi.bsky.social) 21 May 2025 at 13:56

Wednesday #ICRA2025 highlights included:

Plenary talk by Tessa Lau, CEO & Co-Founder, Dusty Robotics
Keynote & Technical Sessions
Community Day
ICRA Expo
Competitions
And more!

Check out tomorrow's events here: https://t.co/kS4WmAlZwJ pic.twitter.com/IboRH05KEI

— IEEE ICRA (@ieee_ras_icra) May 22, 2025

Our Community Building Day has been a success. LatinX in Robotics, Queer in Robotics, and Black in Robotics are just some of the incredible groups building community here at #ICRA2025! pic.twitter.com/EWNi0xY2NI

— IEEE ICRA (@ieee_ras_icra) May 21, 2025

New work at #ICRA2025!
Robust Robot Walker
We enable quadruped robots to pass tiny traps (bars, pits, poles) using only proprioception – no cameras, no depth!

Catch us at Thursday 16:55pm in Room 305!
https://t.co/571p4xTJ5c pic.twitter.com/03F2Gqf40D

— shaoting zhu (@ShaotingZ38103) May 22, 2025

Robot parade at @ieee_ras_icra #ICRA2025 pic.twitter.com/q2wHcQQN3R

— Sriram (@SriRam2528) May 22, 2025

Prof. Concha Monje presenting our BSc degree in Robotics Engineering at #ICRA2025 Forum on Undergraduate Robotics in Atlanta @uc3m @EPS_UC3M @ofic_eps_uc3m @ieeeras @ieee_ras_icra @mecanohumano https://t.co/R8fjbvJ6V3 pic.twitter.com/kDiWqSgx8M

— uc3mRoboticsLab (@uc3mRoboticsLab) May 22, 2025

We received the #ICRA2025 #HRI #Award for Arts & Robotics on our co-painting robot

This project shows how arts and robotics can be used as a testbed to create better robots and to discover new knowledge about humans.@ieee_ras_icra @UMRobotics @DARPA pic.twitter.com/T4VKxH2dKP

— patrícia alves-oliveira (@p_alvesoliveira) May 23, 2025

Fun times at the #ICRA2025 farewell reception! Celebrating Atlanta style with a block party. pic.twitter.com/rg71RPWWKc

— IEEE ICRA (@ieee_ras_icra) May 22, 2025

Plenary speakers

There are three plenary sessions this year. The speakers are as follows:

• Allison Okamura (Stanford University) – Rewired: The Interplay of Robots and Society
• Tessa Lau (Dusty Robotics) – So you want to build a robot company?
• Raffaello (Raff) D’Andrea (ETH Zurich) – Models are dead, long live models!

Keynote sessions

Tuesday 20, Wednesday 21 and Thursday 22 will see a total of 12 keynote sessions. The featured topics and speakers are:

• Rehabilitation & Physically Assistive Systems
• Brenna Argall
• Robert Gregg
• Keehoon Kim
• Christina Piazza
• Optimization & Control
• Todd Murphey
• Angela Schoellig
• Jana Tumova
• Ram Vasudevan
• Human Robot Interaction
• Sonia Chernova
• Dongheui Lee
• Harold Soh
• Holly Yanco
• Soft Robotics
• Robert Katzschmann
• Hugo Rodrigue
• Cynthia Sung
• Wenzhen Yuan
• Field Robotics
• Margarita Chli
• Tobias Fischer
• Joshua Mangelson
• Inna Sharf
• Bio-inspired Robotics
• Kyujin Cho
• Dario Floreano
• Talia Moore
• Yasemin Ozkan-Aydin
• Haptics
• Jeremy Brown
• Matej Hoffman
• Tania Morimoto
• Jee-Hwan Ryu
• Planning
• Hanna Kurniawati
• Jen Jen Chung
• Dan Halperin
• Jing Xiao
• Manipulation
• Tamim Asfour
• Yasuhisa Hasegawa
• Alberto Rodriguez
• Shuran Song
• Locomotion
• Sarah Bergbreiter
• Cosimo Della Santina
• Hae-Won Park
• Ludovic Righetti
• Safety & Formal Methods
• Chuchu Fan
• Meng Guo
• Changliu Liu
• Pian Yu
• Multi-robot Systems
• Sabine Hauert
• Dimitra Panagou
• Alyssa Pierson
• Fumin Zhang

Science communication training

Join Sabine Hauert, Evan Ackerman and Laura Bridgeman for a crash course on science communication. In this concise tutorial, you will learn how to share your work with a broader audience. This session will take place on 22 May, 11:00 – 12:15.

Workshops and tutorials

The programme of workshops and tutorials will take place on Monday 19 May and Friday 23 May. There are 59 events to choose from, and you can see the full list here.

Forums

There will be three forums as part of the programme, one each on Tuesday 20, Wednesday 21 and Thursday 22.

• Robot Ethics Forum
• Harnessing Learning, Data, Foundation Models and Open Source: How African Scientists are Advancing Robotics Research
• Undergraduate Robotics Education Programs: Structures, Platforms, and Approaches

Community building day

Wednesday 21 May is community building day, with six events planned:

• Queer in Robotics: Building a Community and Generating Inclusive Guidelines
• Harnessing Learning, Data, Foundation Models and Open Source: How African Scientists are Advancing Robotics Research
• RAS-WiE Voices — Women shaping the future of robotics and automation
• Black in Robotics and Blacks in Technology Social
• LatinX in AI & Robotics
• Community Building Day Dinner

Other events

You can find out more about the other sessions and event at the links below:

• Arts in robotics
• Career fair
• Competitions
• Stage presentations
• Technical tours

By Kristýna Janovská and Pavel Surynek

Imagine if all of our cars could drive themselves – autonomous driving is becoming possible, but to what extent? To get a vehicle somewhere by itself may not seem so tricky if the route is clear and well defined, but what if there are more cars, each trying to get to a different place? And what if we add pedestrians, animals and other unaccounted for elements? This problem has recently been increasingly studied, and already used in scenarios such as warehouse logistics, where a group of robots move boxes in a warehouse, each with its own goal, but all moving while making sure not to collide and making their routes – paths – as short as possible. But how to formalize such a problem? The answer is MAPF – multi-agent path finding [Silver, 2005].

Multi-agent path finding describes a problem where we have a group of agents – robots, vehicles or even people – who are each trying to get from their starting positions to their goal positions all at once without ever colliding (being in the same position at the same time).

Typically, this problem has been solved on graphs. Graphs are structures that are able to simplify an environment using its focal points and interconnections between them. These points are called vertices and can represent, for example, coordinates. They are connected by edges, which connect neighbouring vertices and represent distances between them.

If however we are trying to solve a real-life scenario, we strive to get as close to simulating reality as possible. Therefore, discrete representation (using a finite number of vertices) may not suffice. But how to search an environment that is continuous, that is, one where there is basically an infinite amount of vertices connected by edges of infinitely small sizes?

This is where something called sampling-based algorithms comes into play. Algorithms such as RRT* [Karaman and Frazzoli, 2011], which we used in our work, randomly select (sample) coordinates in our coordinate space and use them as vertices. The more points that are sampled, the more accurate the representation of the environment is. These vertices are connected to that of their nearest neighbours which minimizes the length of the path from the starting point to the newly sampled point. The path is a sequence of vertices, measured as a sum of the lengths of edges between them.

Figure 1: Two examples of paths connecting starting positions (blue) and goal positions (green) of three agents. Once an obstacle is present, agents plan smooth curved paths around it, successfully avoiding both the obstacle and each other.

We can get a close to optimal path this way, though there is still one problem. Paths created this way are still somewhat bumpy, as the transition between different segments of a path is sharp. If a vehicle was to take this path, it would probably have to turn itself at once when it reaches the end of a segment, as some robotic vacuum cleaners do when moving around. This slows the vehicle or a robot down significantly. A way we can solve this is to take these paths and smooth them, so that the transitions are no longer sharp, but smooth curves. This way, robots or vehicles moving on them can smoothly travel without ever stopping or slowing down significantly when in need of a turn.

Our paper [Janovská and Surynek, 2024] proposed a method for multi-agent path finding in continuous environments, where agents move on sets of smooth paths without colliding. Our algorithm is inspired by the Conflict Based Search (CBS) [Sharon et al., 2014]. Our extension into a continuous space called Continuous-Environment Conflict-Based Search (CE-CBS) works on two levels:

Figure 2: Comparison of paths found with discrete CBS algorithm on a 2D grid (left) and CE-CBS paths in a continuous version of the same environment. Three agents move from blue starting points to green goal points. These experiments are performed in the Robotic Agents Laboratory at Faculty of Information Technology of the Czech Technical University in Prague.

Firstly, each agent searches for a path individually. This is done with the RRT* algorithm as mentioned above. The resulting path is then smoothed using B-spline curves, polynomial piecewise curves applied to vertices of the path. This removes sharp turns and makes the path easier to traverse for a physical agent.

Individual paths are then sent to the higher level of the algorithm, in which paths are compared and conflicts are found. Conflict arises if two agents (which are represented as rigid circular bodies) overlap at any given time. If so, constraints are created to forbid one of the agents from passing through the conflicting space at a time interval during which it was previously present in that space. Both options which constrain one of the agents are tried – a tree of possible constraint settings and their solutions is constructed and expanded upon with each conflict found. When a new constraint is added, this information passes to all agents it concerns and their paths are re-planned so that they avoid the constrained time and space. Then the paths are checked again for validity, and this repeats until a conflict-free solution, which aims to be as short as possible is found.

This way, agents can effectively move without losing speed while turning and without colliding with each other. Although there are environments such as narrow hallways where slowing down or even stopping may be necessary for agents to safely pass, CE-CBS finds solutions in most environments.

This research is supported by the Czech Science Foundation, 22-31346S.

You can read our paper here.

References

• Janovská, K. and Surynek, P. (2024). Multi-agent Path Finding in Continuous Environment, CoRR.
• Sharon, G., Stern, R., Felner, A., and Sturtevant, N. R. (2014). Conflict-based search for optimal multi-agent pathfinding, Artificial Intelligence.
• Karaman, S. and Frazzoli, E. (2011). Sampling-based algorithms for optimal motion planning, CoRR.
• Piegl, L. and Tiller, W. (1996). The NURBS Book, Springer-Verlag, New York, USA, second edition.
• Silver, D. (2005). Cooperative pathfinding, Proceedings of the First Artificial Intelligence and Interactive Digital Entertainment Conference, Marina del Rey, California, USA.

There are two pieces of research we’d like to ask you about today. Could we start with the GenWarp paper? Could you outline the problem that you were focused on in this work?

The problem we aimed to solve is called single-shot novel view synthesis, which is where you have one image and want to create another image of the same scene from a different camera angle. There has been a lot of work in this space, but a major challenge remains: when an image angle changes substantially, the image quality degrades significantly. We wanted to be able to generate a new image based on a single given image, as well as improve the quality, even in very challenging angle change settings.

How did you go about solving this problem – what was your methodology?

The existing works in this space tend to take advantage of monocular depth estimation, which means only a single image is used to estimate depth. This depth information enables us to change the angle and change the image according to that angle – we call it “warp.” Of course, there will be some occluded parts in the image, and there will be information missing from the original image on how to create the image from a new angle. Therefore, there is always a second phase where another module can interpolate the occluded region. Because of these two phases, in the existing work in this area, geometrical errors introduced in warping cannot be compensated for in the interpolation phase.

We solve this problem by fusing everything together. We don’t go for a two-phase approach, but do it all at once in a single diffusion model. To preserve the semantic meaning of the image, we created another neural network that can extract the semantic information from a given image as well as monocular depth information. We inject it using a cross-attention mechanism, into the main base diffusion model. Since the warping and interpolation were done in one model, and the occluded part can be reconstructed very well together with the semantic information injected from outside, we saw the overall quality improved. We saw improvements in image quality both subjectively and objectively, using metrics such as FID and PSNR.

Can people see some of the images created using GenWarp?

Yes, we actually have a demo, which consists of two parts. One shows the original image and the other shows the warped images from different angles.

Moving on to the PaGoDA paper, here you were addressing the high computational cost of diffusion models? How did you go about addressing that problem?

Diffusion models are very popular, but it’s well-known that they are very costly for training and inference. We address this issue by proposing PaGoDA, our model which addresses both training efficiency and inference efficiency.

It’s easy to talk about inference efficiency, which directly connects to the speed of generation. Diffusion usually takes a lot of iterative steps towards the final generated output – our goal was to skip these steps so that we could quickly generate an image in just one step. People call it “one-step generation” or “one-step diffusion.” It doesn’t always have to be one step; it could be two or three steps, for example, “few-step diffusion”. Basically, the target is to solve the bottleneck of diffusion, which is a time-consuming, multi-step iterative generation method.

In diffusion models, generating an output is typically a slow process, requiring many iterative steps to produce the final result. A key trend in advancing these models is training a “student model” that distills knowledge from a pre-trained diffusion model. This allows for faster generation—sometimes producing an image in just one step. These are often referred to as distilled diffusion models. Distillation means that, given a teacher (a diffusion model), we use this information to train another one-step efficient model. We call it distillation because we can distill the information from the original model, which has vast knowledge about generating good images.

However, both classic diffusion models and their distilled counterparts are usually tied to a fixed image resolution. This means that if we want a higher-resolution distilled diffusion model capable of one-step generation, we would need to retrain the diffusion model and then distill it again at the desired resolution.

This makes the entire pipeline of training and generation quite tedious. Each time a higher resolution is needed, we have to retrain the diffusion model from scratch and go through the distillation process again, adding significant complexity and time to the workflow.

The uniqueness of PaGoDA is that we train across different resolution models in one system, which allows it to achieve one-step generation, making the workflow much more efficient.

For example, if we want to distill a model for images of 128×128, we can do that. But if we want to do it for another scale, 256×256 let’s say, then we should have the teacher train on 256×256. If we want to extend it even more for higher resolutions, then we need to do this multiple times. This can be very costly, so to avoid this, we use the idea of progressive growing training, which has already been studied in the area of generative adversarial networks (GANs), but not so much in the diffusion space. The idea is, given the teacher diffusion model trained on 64×64, we can distill information and train a one-step model for any resolution. For many resolution cases we can get a state-of-the-art performance using PaGoDA.

Could you give a rough idea of the difference in computational cost between your method and standard diffusion models. What kind of saving do you make?

The idea is very simple – we just skip the iterative steps. It is highly dependent on the diffusion model you use, but a typical standard diffusion model in the past historically used about 1000 steps. And now, modern, well-optimized diffusion models require 79 steps. With our model that goes down to one step, we are looking at it about 80 times faster, in theory. Of course, it all depends on how you implement the system, and if there’s a parallelization mechanism on chips, people can exploit it.

Is there anything else you would like to add about either of the projects?

Ultimately, we want to achieve real-time generation, and not just have this generation be limited to images. Real-time sound generation is an area that we are looking at.

Also, as you can see in the animation demo of GenWarp, the images change rapidly, making it look like an animation. However, the demo was created with many images generated with costly diffusion models offline. If we could achieve high-speed generation, let’s say with PaGoDA, then theoretically, we could create images from any angle on the fly.

Find out more:

• GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping, Junyoung Seo, Kazumi Fukuda, Takashi Shibuya, Takuya Narihira, Naoki Murata, Shoukang Hu, Chieh-Hsin Lai, Seungryong Kim, Yuki Mitsufuji.
• GenWarp demo
• PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher, Dongjun Kim, Chieh-Hsin Lai, Wei-Hsiang Liao, Yuhta Takida, Naoki Murata, Toshimitsu Uesaka, Yuki Mitsufuji, Stefano Ermon.

About Yuki Mitsufuji

Yuki Mitsufuji is a Lead Research Scientist at Sony AI. In addition to his role at Sony AI, he is a Distinguished Engineer for Sony Group Corporation and the Head of Creative AI Lab for Sony R&D. Yuki holds a PhD in Information Science & Technology from the University of Tokyo. His groundbreaking work has made him a pioneer in foundational music and sound work, such as sound separation and other generative models that can be applied to music, sound, and other modalities.

In a series of interviews, we’re meeting some of the AAAI/SIGAI Doctoral Consortium participants to find out more about their research. In this latest interview, we hear from Amina Mević who is applying machine learning to semiconductor manufacturing. Find out more about her PhD research so far, what makes this field so interesting, and how she found the AAAI Doctoral Consortium experience.

Tell us a bit about your PhD – where are you studying, and what is the topic of your research?

I am currently pursuing my PhD at the University of Sarajevo, Faculty of Electrical Engineering, Department of Computer Science and Informatics. My research is being carried out in collaboration with Infineon Technologies Austria as part of the Important Project of Common European Interest (IPCEI) in Microelectronics. The topic of my research focuses on developing an explainable multi-output virtual metrology system based on machine learning to predict the physical properties of metal layers in semiconductor manufacturing.

Could you give us an overview of the research you’ve carried out so far during your PhD?

In the first year of my PhD, I worked on preprocessing complex manufacturing data and preparing a robust multi-output prediction setup for virtual metrology. I collaborated with industry experts to understand the process intricacies and validate the prediction models. I applied a projection-based selection algorithm (ProjSe), which aligned well with both domain knowledge and process physics.

In the second year, I developed an explanatory method, designed to identify the most relevant input features for multi-output predictions.

Is there an aspect of your research that has been particularly interesting?

For me, the most interesting aspect is the synergy between physics, mathematics, cutting-edge technology, psychology, and ethics. I’m working with data collected during a physical process—physical vapor deposition—using concepts from geometry and algebra, particularly projection operators and their algebra, which have roots in quantum mechanics, to enhance both the performance and interpretability of machine learning models. Collaborating closely with engineers in the semiconductor industry has also been eye-opening, especially seeing how explanations can directly support human decision-making in high-stakes environments. I feel truly honored to deepen my knowledge across these fields and to conduct this multidisciplinary research.

What are your plans for building on your research so far during the PhD – what aspects will you be investigating next?

I plan to focus more on time series data and develop explanatory methods for multivariate time series models. Additionally, I intend to investigate aspects of responsible AI within the semiconductor industry and ensure that the solutions proposed during my PhD align with the principles outlined in the EU AI Act.

How was the AAAI Doctoral Consortium, and the AAAI conference experience in general?

Attending the AAAI Doctoral Consortium was an amazing experience! It gave me the opportunity to present my research and receive valuable feedback from leading AI researchers. The networking aspect was equally rewarding—I had inspiring conversations with fellow PhD students and mentors from around the world. The main conference itself was energizing and diverse, with cutting-edge research presented across so many AI subfields. It definitely strengthened my motivation and gave me new ideas for the final phase of my PhD.

Amina presenting two posters at AAAI 2025.

What made you want to study AI?

After graduating in theoretical physics, I found that job opportunities—especially in physics research—were quite limited in my country. I began looking for roles where I could apply the mathematical knowledge and problem-solving skills I had developed during my studies. At the time, data science appeared to be an ideal and promising field. However, I soon realized that I missed the depth and purpose of fundamental research, which was often lacking in industry roles. That motivated me to pursue a PhD in AI, aiming to gain a deep, foundational understanding of the technology—one that can be applied meaningfully and used in service of humanity.

What advice would you give to someone thinking of doing a PhD in the field?

Stay curious and open to learning from different disciplines—especially mathematics, statistics, and domain knowledge. Make sure your research has a purpose that resonates with you personally, as that passion will help carry you through challenges. There will be moments when you’ll feel like giving up, but before making any decision, ask yourself: am I just tired? Sometimes, rest is the solution to many of our problems. Finally, find mentors and communities to share ideas with and stay inspired.

Could you tell us an interesting (non-AI related) fact about you?

I’m a huge science outreach enthusiast! I regularly volunteer with the Association for the Advancement of Science and Technology in Bosnia, where we run workshops and events to inspire kids and high school students to explore STEM—especially in underserved communities.

About Amina

Amina Mević is a PhD candidate and teaching assistant at the University of Sarajevo, Faculty of Electrical Engineering, Bosnia and Herzegovina. Her research is conducted in collaboration with Infineon Technologies Austria as part of the IPCEI in Microelectronics. She earned a master’s degree in theoretical physics and was awarded two Golden Badges of the University of Sarajevo for achieving a GPA higher than 9.5/10 during both her bachelor’s and master’s studies. Amina actively volunteers to promote STEM education among youth in Bosnia and Herzegovina and is dedicated to improving the research environment in her country.

Congratulations to Shlomo Zilberstein on winning the 2025 ACM/SIGAI Autonomous Agents Research Award. This prestigious award is made for excellence in research in the area of autonomous agents. It is intended to recognize researchers in autonomous agents whose current work is an important influence on the field.

Professor Shlomo Zilberstein was recognised for his work establishing the field of decentralized Markov Decision Processes (DEC-MDPs), laying the groundwork for decision-theoretic planning in multi-agent systems and multi-agent reinforcement learning (MARL). The selection committee noted that these contributions have become a cornerstone of multi-agent decision-making, influencing researchers and practitioners alike.

Shlomo Zilberstein is Professor of Computer Science and former Associate Dean of Research at the University of Massachusetts Amherst. He is a Fellow of AAAI and the ACM, and has received numerous awards, including the UMass Chancellor’s Medal, the IFAAMAS Influential Paper Award, and the AAAI Distinguished Service Award.

The Association for the Advancement of Artificial Intelligence (AAAI), has published a report on the Future of AI Research. The report, which was announced by outgoing AAAI President Francesca Rossi during the AAAI 2025 conference, covers 17 different AI topics and aims to clearly identify the trajectory of AI research in a structured way.

The report is the result of a Presidential Panel, chaired by Francesca Rossi, and comprising of 24 experienced AI researchers, who worked on the project between summer 2024 and spring 2025. As well as the views of the panel members, the report also draws on community feedback, which was received from 475 AI researchers via a survey.

The 17 topics, each with a dedicated chapter, are as follows.

• AI Reasoning
• AI Factuality & Trustworthiness
• AI Agents
• AI Evaluation
• AI Ethics & Safety
• Embodied AI
• AI & Cognitive Science
• Hardware & AI
• AI for Social Good
• AI & Sustainability
• AI for Scientific Discovery
• Artificial General Intelligence (AGI)
• AI Perception vs. Reality
• Diversity of AI Research Approaches
• Research Beyond the AI Research Community
• Role of Academia
• Geopolitical Aspects & Implications of AI

Each chapter includes a list of main takeaways, context and history, current state and trends, research challenges, and community opinion. You can read the report in full here.

The Association for Computing Machinery, has named Andrew Barto and Richard Sutton as the recipients of the 2024 ACM A.M. Turing Award. The pair have received the honour for “developing the conceptual and algorithmic foundations of reinforcement learning”. In a series of papers beginning in the 1980s, Barto and Sutton introduced the main ideas, constructed the mathematical foundations, and developed important algorithms for reinforcement learning.

The Turing Award comes with a $1 million prize, to be split between the recipients. Since its inception in 1966, the award has honoured computer scientists and engineers on a yearly basis. The prize was last given for AI research in 2018, when Yoshua Bengio, Yann LeCun and Geoffrey Hinton were recognised for their contribution to the field of deep neural networks.

Andrew Barto is Professor Emeritus, Department of Information and Computer Sciences, University of Massachusetts, Amherst. He began his career at UMass Amherst as a postdoctoral Research Associate in 1977, and has subsequently held various positions including Associate Professor, Professor, and Department Chair. Barto received a BS degree in Mathematics (with distinction) from the University of Michigan, where he also earned his MS and PhD degrees in Computer and Communication Sciences.

Richard Sutton is a Professor in Computing Science at the University of Alberta, a Research Scientist at Keen Technologies (an artificial general intelligence company based in Dallas, Texas) and Chief Scientific Advisor of the Alberta Machine Intelligence Institute (Amii). Sutton was a Distinguished Research Scientist at Deep Mind from 2017 to 2023. Prior to joining the University of Alberta, he served as a Principal Technical Staff Member in the Artificial Intelligence Department at the AT&T Shannon Laboratory in Florham Park, New Jersey, from 1998 to 2002. Sutton received his BA in Psychology from Stanford University and earned his MS and PhD degrees in Computer and Information Science from the University of Massachusetts at Amherst.

The two researchers began collaborating in 1978, at the University of Massachusetts at Amherst, where Barto was Sutton’s PhD and postdoctoral advisor.

Find out more

• ACM announcement
• Richard Sutton in conversation with Stephen Hanson

The AAAI Award for Artificial Intelligence for the Benefit of Humanity recognizes positive impacts of artificial intelligence to protect, enhance, and improve human life in meaningful ways with long-lived effects. The award is given annually at the conference for the Association for the Advancement of Artificial Intelligence (AAAI).

This year, the AAAI Awards Committee has announced that the 2025 recipient of the award and $25,000 prize is Stuart J. Russell, “for his work on the conceptual and theoretical foundations of provably beneficial AI and his leadership in creating the field of AI safety”.

Stuart will give an invited talk at AAAI 2025 entitled “Can AI Benefit Humanity?”

About Stuart

Stuart J. Russell is a Distinguished Professor of Computer Science at the University of California, Berkeley, and holds the Michael H. Smith and Lotfi A. Zadeh Chair in Engineering. He is also a Distinguished Professor of Computational Precision Health at UCSF. His research covers a wide range of topics in artificial intelligence including machine learning, probabilistic reasoning, knowledge representation, planning, real-time decision making, multitarget tracking, computer vision, computational physiology, and philosophical foundations. He has also worked with the United Nations to create a new global seismic monitoring system for the Comprehensive Nuclear-Test-Ban Treaty. His current concerns include the threat of autonomous weapons and the long-term future of artificial intelligence and its relation to humanity.

Read our content featuring previous winners of the award

• 2024 award #AAAI2024 invited talk: Milind Tambe – using ML for social good
• 2023 award: #AAAI2023 invited talk: Tuomas Sandholm on organ exchanges
• 2022 award: Cynthia Rudin wins AAAI Squirrel AI Award
• 2022 award: #AAAI2022 invited talk – Cynthia Rudin on interpretable machine learning
• 2021 award: Regina Barzilay wins $1M Association for the Advancement of Artificial Intelligence Squirrel AI award
• 2021 award: #AAAI2021 invited talk – Regina Barzilay on deploying machine learning methods in cancer diagnosis and drug design

On Friday 22 November, IEEE Robotics and Automation Society will be hosting an online science communication training session for robotics and AI researchers. The tutorial will introduce you to science communication and help you create your own story through hands-on activities.

Date: 22 November 2024
Time: 10:00 – 13:00 EST (07:00 – 10:00 PST, 15:00 – 18:00 GMT, 16:00 – 19:00 CET)
Location: Online – worldwide
Registration
Website

Science communication is essential. It helps demystify robotics and AI for a broad range of people including policy makers, business leaders, and the public. As a researcher, mastering this skill can not only enhance your communication abilities but also expand your network and increase the visibility and impact of your work.

In this three-hour session, leading science communicators in robotics and AI will teach you how to clearly and concisely explain your research to non-specialists. You’ll learn how to avoid hype, how to find suitable images and videos to illustrate your work, and where to start with social media. We’ll hear from a leading robotics journalist on how to deal with media and how to get your story out to a wider audience.

This is a hands-on session with exercises for you to take part in throughout the course. Therefore, please come prepared with an idea about a piece of research you’d like to communicate about.

Agenda

Part 1: How to communicate your work to a broader audience

• The importance of science communication
• How to produce a short summary of your research for communication via social media channels
• How to expand your outline to write a complete blog post
• How to find and use suitable images
• How to avoid hype when communicating your research
• Unconventional ways of doing science communication

Part 2: How to make videos about your robots

• The value of video
• Tips on making a video

Part 3: Working with media

• Why bother talking to media anyway?
• How media works and what it’s good and bad at
• How to pitch media a story
• How to work with your press office

Speakers:
Sabine Hauert, Professor of Swarm Engineering, Executive Trustee AIhub / Robohub
Lucy Smith, Senior Managing Editor AIhub / Robohub
Laura Bridgeman, Audience Development Manager IEEE Spectrum
Evan Ackerman, Senior Editor IEEE Spectrum

Sign up here.

The 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024) was held from 14-18 October in Abu Dhabi, UAE. We take a look at what the participants got up to.

Join us today for the Brain over Brawn (BoB) Workshop on Label Efficient Learning Paradigms for Autonomy at Scale #IROS2024
The program is exciting:
– speakers: @ftm_guney @lucacarlone1 @peymanm @mpopovic514
– panelists: @_ayoungk @stachnis @maththrills https://t.co/t9RMqKFT2U pic.twitter.com/NGUyjgqX8Q

— Andrei Bursuc (@abursuc) October 14, 2024

#IROS2024 attendees, come and see our presentation on wednesday morning!

WePI2T09.07 | Wed 16 Oct 2024 | Room 9
[1] Teaser Session (Navigation I):
09:00 – 10:00
[2] Interactive session: 10:00 – 12:00 in the poster area near the Room 9. https://t.co/Bs3M5gDzaU pic.twitter.com/HaZBmuUqK1

— MIZUHO AOKI (@mizuhoaoki1998) October 14, 2024

In #IROS2024 Workshop, "Collecting, Managing and Utilizing Data through Embodied Robots" (https://t.co/d81DRq1JGk) was successfully held!
Thank you so much for all of speakers,
presenters, audiences!@namikosaito_ @tetsuyaogata1 @hshige_86 @rsk_tmr @funabashihand @RMalsada3 https://t.co/ZA9T8qehDH pic.twitter.com/sdXBWhe79Q

— Tamon Miyake (@T_Miyake3) October 14, 2024

What about 12 talks in parallel in the same room?
Personal headphones for everyone make it possible.
@IEEEorg #IROS2024 Abu Dhabi is trying this quite a peculiar setup which is working well and keep everyone in a single open space. pic.twitter.com/PDXCdyKrsT

— Giovanni Reina (@joefresna) October 14, 2024

Thanks @BotJunkie from @IEEESpectrum and Lucy from @AIhuborg / @Robohub for the #IROS2024 scicomm training! Great content from 'why to communicate', to 'how to write a story, find images, and avoid hype', and finally 'engaging with media'. Great it was available online @ieeeras! pic.twitter.com/aFPbO5WTzH

— Sabine Hauert (@sabinehauert) October 15, 2024

Live demo from plenary! Remote operation from Abu Dhabi to Stanford. #IROS2024 pic.twitter.com/4YsGicbZ4M

— Ayoung (@_ayoungk) October 15, 2024

Early morning talk in Abu Dhabi = 1am talk in Boston

Sad to miss @IEEEorg #IROS2024 in person but glad I still had a chance to share the latest updates on biohybrid robotics from our lab @MITMechE!

Now for some caffeine pic.twitter.com/Ph8RWOdZa9

— Ritu Raman (@DrRituRaman) October 15, 2024

Not all heroes wear capes, sometimes they carry external GPU for robot #IROS2024 pic.twitter.com/rZ2CUHGgpG

— Michael Cho – Rbt/Acc (@micoolcho) October 16, 2024

OMRON SINIC X at #IROS2024! (4/7)
Title: Robot Swarm Control Based on Smoothed Particle Hydrodynamics for Obstacle-Unaware Navigation
Date: Thu, Oct 17, 11:30-11:45 | Room14
Oral Presentations: Paper ThBT14.3
Learn more: https://t.co/lFdkNv6F6H
YouTube: https://t.co/3wLKbvqCAg

— OMRON SINIC X (OSX) (@omron_sinicx) October 17, 2024

Some exciting work is being showcased at the IEEE/RSJ International Conference on Intelligent Robots and Systems. In his research, Javier proposes methods for reconfigurable robots to navigate safely. #IROS2024 #ReconfigurableRobots #AbuDhabi #UAE pic.twitter.com/Yls06W0No7

— IEEE RAS (@ieeeras) October 17, 2024

Day 3 at #IROS2024 is off to a great start!
Yesterday was action-packed with interactive demos and insightful discussions. If you haven't visited yet, be sure to stop by booth 49—we're excited to meet you!
Check out some highlights from yesterday!#HatsuMuv #HatsuHand pic.twitter.com/jpV8bUvDNv

— HatsuMuv Official (@HatsuMuv) October 17, 2024

We had a wonderful time at the Workshop on Interactive Robots and AI for Healthcare at #IROS2024 at ADNEC Centre Abu Dhabi. We enjoyed engaging in discussions with friends and new collaborators.https://t.co/vH2xIsiDXQ@BristolRobotLab @ieeeras @UWEBristol pic.twitter.com/eOB3ONfYL1

— Carlos Cifuentes (@cacifuentesg) October 17, 2024

Plenary talks

There are four plenary talks on the programme this year:

• Oussama Khatib – Mission in Dubai, collaboration with UAE
• Najwa Aaraj – Building Trust in Autonomous Systems: Security Strategies for the Next Generation of Robotics
• Yoshihiko Nakamura – Embodiment of AI and Biomechanics/Neuroscience
• Magnus Egerstedt – Mutualistic Interactions in Heterogeneous Multi-Robot Systems: From Environmental Monitoring to the Robotarium

Keynote talks

The keynotes this year fall under the umbrella topics of: flying machines, biorobotics, AI and robotics, and robotics competitions.

• Flying machines
• Davide Scaramuzza – Drone Racing
• Guido De Croon – DelFly Explorer
• Giuseppe Loianno – Agile Robotics and Perception Lab
• Mirko Kovac – Drones for Environmental Health
• Biorobotics
• Auke Ijspeert – Bio Robotics, Computational neuroscience
• Barbara Mazzolai – Bioinspired Soft Robotics
• Kaspar Althoefer – Graphene and 2D materials, sensor applications
• AI and robotics
• Barbara Caputo – Applied Artificial Intelligence
• Merouane Debbah – TelecomGPT
• Concepción Alicia Monje – (soft) robot control
• Jianwei Zhang – Crossmodal Learning
• Robotics competitions
• Pedro Lima – Europe: European Robotics League, euROBIN Coopetitions
• Timothy Chung – Americas: DARPA Challenges
• Ubbo Visser – RoboCup Federation
• Thomas McCarthy – Grand Challenges as a Mechanism to Hasten Translation from Lab to Market

Forums

The forums are three-hour events that focus on a particular topic. Each forum will have keynote speakers, with some including a poster session and other talks.

• Robots for Sustainability and Sustainable Robots
• Europe Regulates Artificial Intelligence: the Challenge for Robotics
• Government Forum: Funding for Robotics Research
• Robotics in Africa Forum
• Robotics & AI in the UAE: Research Innovation and Entrepreneurship
• Human-Avatars Symbiosis: Can you imagine a future society where you can remotely control multiple avatars?
• Empowering Diverse Voices in Robotics
• Sustainable Medical and Surgical Robotics
• Moonshot R&D Program Goal 3 Forum. Envisioning a Future of Human-Robot Co-living: Potential for Robotics to Transform Human Lives
• Marine Robotics in Ocean Decade Initiative for Sustainable Development
• The Future of Work: AI-Enhanced Robotics and Human Interaction Research in M3S
• Industrial Opportunities and Socio-Economic Impact of Medical Robotics
• Robots for a Better Tomorrow: Wellbeing Through Advanced Technology

Science communication for roboticists

This session is a collaboration between AIhub.org/Robohub.org and IEEE Spectrum. We will cover different ways to communicate about your work to a more general audience, and how to work with media. You can find out more here.

Workshops

The 46 workshops take place on 14 and 15 October.

• AI Meets Autonomy: Vision, Language, and Autonomous Systems
• Interactive Robots and AI for Healthcare
• Brain Over Brawn: Workshop on Label Efficient Learning Paradigms for Autonomy at Scale
• XR-ROB 2024 – Horizons of an Extended Robotics Reality – a Converging Future of XR and Robotics
• Maritime Heterogeneous Unmanned Robotic Systems
• The Evolving Landscape of Haptic Technologies: Research Challenges and Industry needs
• Agricultural Robotics for a Sustainable Future
• 3rd Workshop on Mobile Manipulation and Embodied Intelligence: Generalization Challenges for Real-World Deployment
• Collecting, Managing and Utilizing Data through Embodied Robots
• The Grand Challenge of Cybernetic Avatars: Dreams and Facts
• Nonverbal cues for human-robot cooperative intelligence
• Real-World Challenges in Multi-Robot Cooperation
• 3D/4D Printing and Smart Materials for Sustainable Soft Robotics
• Advanced Robotics and Visualization for micrO Surgery
• Equivariant Robotics: The Role of Symmetry Across Perception, Estimation, and Control
• Environment Dynamics Matters: Embodied Navigation to Movable Objects
• R-, r-, reply- Articles, what are they? Case Studies of Reproducibility and Benchmarking in Robotic Research
• Standing the Test of Time: Retrospective and Future of World Representations for Lifelong Robotics
• The Workshop and Competition on Multi-Robot Perception and Navigation Challenges in Logistics and Inspection Tasks
• The Grand Challenge of Cybernetic Avatars: Ethical and Social Sustainability
• Unlocking the Potential: Innovations in Drone-Assisted Infrastructure Inspection and Maintenance
• AI and Robotics for Future Farming
• Self-healing and Damage Resilient Soft Robots
• Autonomous Robotic Systems in Aquaculture: Research Challenges and Industry Needs
• 2nd Workshop on Machine Learning in Medical Robotics: Bridging ML Theory and Clinical Frontiers
• ROMADO: 4th workshop on RObotic MAnipulation of Deformable Objects: beyond traditional approaches
• Trustworthy Human-swarm Interaction
• Multisensory Transparency-Augmented Teleoperation in Extreme Environments
• Long-Term Perception for Autonomy in Dynamic Human-centric Environments: What Do Robots Need?
• Embodied Neuromorphic AI for Robotic Perception and Control
• Integrating Physical and Cognitive Perspectives in Assistive Robotics Design
• 3rd Workshop Toward Robot Avatars
• From Learning-based to Foundation models for mapping: challenges and opportunities (LFM)
• Robot Safety in Times of AI: Data, Decision, and Multimodal Interaction
• Bio-inspired, Biomimetics, and Biohybrid (Cyborg) Systems
• Benchmarking Autonomous Service Robotics in Real Life
• The 2nd Workshop on Formal methods techniques in robotics systems: Design and control
• Workshop on 14th Planning, Perception and Navigation for Intelligent Vehicles
• Workshop on Interaction-aware Autonomous Systems
• The SOFT frontier: adaptive technologies in soft robotics
• Variable Impedance Learning and Control: Navigating Challenges, Exploring Opportunities, and Shaping the Future
• Workshop on Ethical, Legal and User Perspectives on Assisting Robots and Systems (WELUPARS)
• Safety of Intelligent and Autonomous Vehicles: Formal Methods vs. Machine Learning approaches for reliable navigation (SIAV-FM2L)
• Building and Evaluating Ethical Robotic Systems
• From Geometry to General Autonomy of Robotic Systems
• Benchmarking via Competitions in Robotic Grasping and Manipulation

Tutorials

The tutorials take place on 14 and 15 October. There are 10 to choose from this year.

• Multi-Robot Path Planning: Heuristic Search Meets Reinforcement Learning
• ML in Autonomous Systems and Mobile Robots: Security and Privacy Issues for ML
• Edge AI for Aerial Robots: Enhancing Drone Operations with AI
• From Hover to Horizon: Mastering Drone Control in MATLAB
• KOMPASS: An event-driven advanced navigation stack for autonomous mobile robots
• Low-code design and simulation of robotics capabilities
• State-of-the-art Simulation in Autonomous Robotic Systems
• Foundations of interaction control for contact robots (part I): Interaction control in humans and with robots
• Foundations of interaction control for contact robots (part II): Energy-based methods and interactive learning
• Humanoid Hybrid sprint

You can view the programme overview here.

Today, 21 July, saw the competitions draw to a close in a thrilling finale. In the third and final of our round-up articles, we provide a flavour of the action from this last day. If you missed them, you can find our first two digests here: 19 July | 20 July.

My first port of call this morning was the Standard Platform League, where Dr Timothy Wiley and Tom Ellis from Team RedbackBots, RMIT University, Melbourne, Australia, demonstrated an exciting advancement that is unique to their team. They have developed an augmented reality (AR) system with the aim of enhancing the understanding and explainability of the on-field action.

The RedbackBots travelling team for 2024 (L-to-R: Murray Owens, Sam Griffiths, Tom Ellis, Dr Timothy Wiley, Mark Field, Jasper Avice Demay). Photo credit: Dr Timothy Wiley.

Timothy, the academic leader of the team explained: “What our students proposed at the end of last year’s competition, to make a contribution to the league, was to develop an augmented reality (AR) visualization of what the league calls the team communication monitor. This is a piece of software that gets displayed on the TV screens to the audience and the referee, and it shows you where the robots think they are, information about the game, and where the ball is. We set out to make an AR system of this because we think it’s so much better to view it overlaid on the field. What the AR lets us do is project all of this information live on the field as the robots are moving.”

The team has been demonstrating the system to the league at the event, with very positive feedback. In fact, one of the teams found an error in their software during a game whilst trying out the AR system. Tom said that they’ve received a lot of ideas and suggestions from the other teams for further developments. This is one of the first (if not, the first) AR system to be trialled across the competition, and first time it has been used in the Standard Platform League. I was lucky enough to get a demo from Tom and it definitely added a new level to the viewing experience. It will be very interesting to see how the system evolves.

Mark Field setting up the MetaQuest3 to use the augmented reality system. Photo credit: Dr Timothy Wiley.

From the main soccer area I headed to the RoboCupJunior zone, where Rui Baptista, an Executive Committee member, gave me a tour of the arenas and introduced me to some of the teams that have been using machine learning models to assist their robots. RoboCupJunior is a competition for school children, and is split into three leagues: Soccer, Rescue and OnStage.

I first caught up with four teams from the Rescue league. Robots identify “victims” within re-created disaster scenarios, varying in complexity from line-following on a flat surface to negotiating paths through obstacles on uneven terrain. There are three different strands to the league: 1) Rescue Line, where robots follow a black line which leads them to a victim, 2) Rescue Maze, where robots need to investigate a maze and identify victims, 3) Rescue Simulation, which is a simulated version of the maze competition.

Team Skollska Knijgia, taking part in the Rescue Line, used a YOLO v8 neural network to detect victims in the evacuation zone. They trained the network themselves with about 5000 images. Also competing in the Rescue Line event were Team Overengeniering2. They also used YOLO v8 neural networks, in this case for two elements of their system. They used the first model to detect victims in the evacuation zone and to detect the walls. Their second model is utilized during line following, and allows the robot to detect when the black line (used for the majority of the task) changes to a silver line, which indicates the entrance of the evacuation zone.

Left: Team Skollska Knijgia. Right: Team Overengeniering2.

Team Tanorobo! were taking part in the maze competition. They also used a machine learning model for victim detection, training on 3000 photos for each type of victim (these are denoted by different letters in the maze). They also took photos of walls and obstacles, to avoid mis-classification. Team New Aje were taking part in the simulation contest. They used a graphical user interface to train their machine learning model, and to debug their navigation algorithms. They have three different algorithms for navigation, with varying computational cost, which they can switch between depending on the place (and complexity) in the maze in which they are located.

Left: Team Tanorobo! Right: Team New Aje.

I met two of the teams who had recently presented in the OnStage event. Team Medic’s performance was based on a medical scenario, with the team including two machine learning elements. The first being voice recognition, for communication with the “patient” robots, and the second being image recognition to classify x-rays. Team Jam Session’s robot reads in American sign language symbols and uses them to play a piano. They used the MediaPipe detection algorithm to find different points on the hand, and random forest classifiers to determine which symbol was being displayed.

Left: Team Medic Bot Right: Team Jam Session.

Next stop was the humanoid league where the final match was in progress. The arena was packed to the rafters with crowds eager to see the action.
Standing room only to see the Adult Size Humanoids.

The finals continued with the Middle Size League, with the home team Tech United Eindhoven beating BigHeroX by a convincing 6-1 scoreline. You can watch the livestream of the final day’s action here.

The grand finale featured the winners of the Middle Size League (Tech United Eindhoven) against five RoboCup trustees. The humans ran out 5-2 winners, their superior passing and movement too much for Tech United.

This is the second of our daily digests from RoboCup2024 in Eindhoven, The Netherlands. If you missed the first digest, which gives some background to RoboCup, you can find it here.

Competitions continued across all the leagues today, with participants vying for a place in Sunday’s finals.

The RoboCup@Work league focusses on robots in work-related scenarios, utilizing ideas and concepts from other RoboCup competitions to tackle open research challenges in industrial and service robotics.

I arrived at the arena in time to catch the advanced navigation test. Robots have to autonomously navigate, picking up and placing objects at different work stations. In this advanced test, caution tape is added to the arena floor, which the robots should avoid travelling over. There is also a complex placing element where teams have to put an object that they’ve collected into a slot – get the orientation or placement of the object slightly wrong and the it won’t fall into the slot.

The RoboCup@Work arena just before competition start.

Eight teams are taking part in the league this year. Executive Committee member Asad Norouzi said that there are plans to introduce a sub-league which would provide an entry point for new teams or juniors to get into the league proper.

I caught up with Harrison Burns, Mitchell Torok and Jasper Arnold from Team MiRobot. They are based at the University of New South Wales and are attending RoboCup for the first time.

Team MiRobot from UNSW.

The team actually only started six months ago, so final preparations have been a bit stressful. However, the experience has been great fun, and the competition has gone well so far. Like most teams, they’ve had to make many refinements as the competition has progressed, leading to some late nights.

One notable feature of the team’s robot is the bespoke, in-house-designed grasping mechanism on the end of the arm. The team note that “it has good flexible jaws, so when it grabs round objects it actually pulls the object directly into it. Because it uses a linear motion, compared to a lot of other rotating jaws, it has a lot better reliability for picking up objects”.

Here is some footage from the task, featuring Team bi-t-bots and Team Singapore.

Team b-it-bots take on the RoboCup@Work advanced navigation test, picking up a drill bit #RoboCup2024 pic.twitter.com/QfijZpxaOK

— AIhub (@aihuborg) July 20, 2024

Team Singapore placing an object in the RoboCup@Work advanced navigation test pic.twitter.com/SvgLBOaVo7

— AIhub (@aihuborg) July 20, 2024

In the Middle Size Soccer league (MSL), teams of five fully autonomous robots play with a regular size FIFA ball. Teams are free to design their own hardware but all sensors have to be on-board and there is a maximum size and weight limit of 40kg for the robots. The research focus is on mechatronics design, control and multi-agent cooperation at plan and perception levels. Nine teams are competing this year.

Action from the Middle Size League at #RoboCup2024.

Falcons vs Robot Club Toulon pic.twitter.com/GHcNLOx2nV

— AIhub (@aihuborg) July 20, 2024

I spoke to António Ribeiro, who is a member of the technical committee and part of Team LAR@MSL from the University of Minho, Portugal. The team started in 1998, but António and most of his colleagues on the current team have only been involved in the MSL since September 2022. The robots have evolved as the competition has progressed, and further improvements are in progress. Refinements so far have included communication, the detection system, and the control system. They are pleased with the improvements from the previous RoboCup. “Last year we had a lot of hardware issues, but this year the hardware seems pretty stable. We also changed our coding architecture and it is now much easier and faster for us to develop code because we can all work on the code at the same time on different modules”.

António cited versatility and cost-effective solutions as strengths of the team. “Our robot is actually very cheap compared to other teams. We use a lot of old chassis, and our solutions always go to the lowest cost possible. Some teams have multiple thousand dollar robots, but, for example, our vision system is around $70-80. It works pretty well – we need to improve the way we handle it, but it seems stable”.

Team LAR@MSL

The RoboCup@Home league aims to develop service and assistive robot technology with high relevance for future personal domestic applications. A set of benchmark tests is used to evaluate the robots’ abilities and performance in a realistic non-standardized home environment setting. These tests include helping to prepare breakfast, clearing the table, and storing groceries.

I arrived in time to watch the “stickler for the rules” challenge, where robots have to navigate different rooms and make sure that the people inside (“guests” at a party) are sticking to four rules: 1) there is one forbidden room – if a guest is in there the robot must alert them and ask them to follow it into another room), 2) everyone must have a drink in their hand – if not, the robot directs them to a shelf with drinks, 3) no shoes to be worn in the house, 4) there should be no rubbish left on the floor.

After watching an attempt from the LAR@Home robot, Tiago from the team told me a bit about the robot. “The goal is to develop a robot capable of multi general-purpose tasks in home and healthcare environments.” With the exception of the robotic arm, all of the hardware was built by the team. The robot has two RGBD cameras, two LIDARs, a tray (where the robot can store items that it needs to carry), and two emergency stop buttons that deactivate all moving parts. Four omnidirectional wheels allow the robot to move in any direction at any time. The wheels have independent suspension systems which guarantees that they can all be on the ground at all times, even if there are bumps and cables on the venue floor. There is a tablet that acts as a visual interface, and a microphone and speakers to enable communication between humans and the robot, which is all done via speaking and listening.

Tiago told me that the team have talked to a lot healthcare practitioners to find out the main problems faced by elderly people, and this inspired one of their robot features. “They said that the two main injury sources are from when people are trying to sit down or stand up, and when they are trying to pick something up from the floor. We developed a torso that can pick objects from the floor one metre away from the robot”.

The LAR@Home team.

You can keep up with the latest news direct from RoboCup here.

Click here to see all of our content pertaining to RoboCup.

RoboCup is an international scientific initiative with the goal to advance the state of the art of intelligent robots. As part of this initiative, a series of competitions and events are held throughout the year. The main showcase event is an international affair with teams travelling from far and wide to put their machines through their paces.

This year, RoboCup is being held in three arenas in the Genneper Parken, Eindhoven, The Netherlands. The organisers are expecting over 2,000 participants, from 45 different countries, with around 300 teams signed up to take part in the various competitions.

Although RoboCup started out as a football (or soccer) playing competition, other leagues have since been introduced, focussing on robots in industrial, rescue, and home settings. There is even a dedicated league for young roboticists – RoboCupJunior – where participants can take part in either football, rescue, or artistic events.

I am lucky enough to be able to attend this year, and, for the next three days, I’ll be bringing you a daily digest of some of the exciting happenings from Eindhoven.

Today, 19 July, sees the competition in full swing. The main soccer arena, boasting multiple pitches, hosts a number of the different leagues which form RoboCupSoccer.

Some of the pitches in the main soccer arena.

My first port of call was the Standard Platform League, where the round 5 champions cup match between SPQR Team vs rUNSWift was taking place. SPQR ran out winners and advance to round 6. In this league, all teams compete with identical robots (currently the humanoid NAO by Aldebaran). The robots operate fully autonomously, meaning that there is no external control from neither humans nor computers.

Standard platform league. Round 5 champions cup match between SPQR Team vs rUNSWift.

Goal! pic.twitter.com/dMfNDUKNZc

— AIhub (@aihuborg) July 19, 2024

The Humanoid AdultSize league is arguably the most challenging of the leagues, with many constraints placed on the robots to make them as human-like as possible. For example, they must have roughly human-like body proportions, they need to walk on two legs, and they are only allowed to use human-like sensors (up to two cameras to sense the environment). In this AdultSize competition, two robots from each team compete, and the team members walk behind the robots to catch them in case of a fall. Such a mishap could prove costly in terms of potential hardware damage.

Action from the Humanoid AdultSize League.

The RoboCup Rescue Robot League sees teams developing robotic systems with the goal of enabling emergency responders to perform extremely hazardous tasks from safer stand-off distances. During the competition, teams compete in a round-robin, putting their robots through their paces on a number of different challenges. The leading teams following this initial phase progress to the finals on Sunday. The tasks include navigating in complex environments, opening doors, and sensing. Teams may run the machines completely autonomously, or with some assistive control. More points are awarded for completely autonomous operation.

RoboCup Rescue arena from above.

Some action from the @robocup_org #RoboCup2024 Rescue league, where teams compete in a variety of challenges.

Team Hector Darmstadt in the "Obstacles: pallets with pipes" challenge pic.twitter.com/4Ll75uENjM

— AIhub (@aihuborg) July 19, 2024

KMUTNB navigate rough terrain, including gravel and sand pic.twitter.com/rsI7NliEwd

— AIhub (@aihuborg) July 19, 2024

You can keep up with more RoboCup2024 news here.

The 2024 IEEE International Conference on Robotics and Automation (ICRA) best paper winners and finalists in the various different categories have been announced. The recipients were revealed during an award luncheon at the conference, which took place from 13-17 May in Yokohama, Japan.

IEEE ICRA Best Paper Award in Automation

Winner

TinyMPC: Model-Predictive Control on Resource-Constrained Microcontrollers, Anoushka Alavilli, Khai Nguyen, Samuel Schoedel, Brian Plancher, and Zachary Manchester

Finalists

• A Movable Microfluidic Chip with Gap Effect for Manipulation of Oocytes, Shuzhang Liang, Satoshi Amaya, Hirotaka Sugiura, Hao Mo, Yuguo Dai, and Fumihito Arai
• Under Pressure: Learning-Based Analog Gauge Reading in the Wild, Maurits Reitsma, Julian Keller, Kenneth Blomqvist, and Roland Siegwart
• Efficient Composite Learning Robot Control Under Partial Interval Excitation, Tian Shi, Weibing Li, Haoyong Yu, and Yongping Pan
• MORALS: Analysis of High-Dimensional Robot Controllers via Topological Tools in a Latent Space, Ewerton Vieira, Aravind Sivaramakrishnan, Sumanth Tangirala, Edgar Granados, Konstantin Mischaikow, and Kostas E. Bekris

IEEE ICRA Best Paper Award in Cognitive Robotics

Winner

VLFM: Vision-Language Frontier Maps for Semantic Navigation, Naoki Yokoyama, Sehoon Ha, Dhruv Batra, Jiuguang Wang, and Bernadette Bucher

Finalists

• NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration, Ajay Sridhar, Dhruv Shah, Catherine Glossop, and Sergey Levine
• Resilient Legged Local Navigation: Learning to Traverse with Compromised Perception End-to-End, Chong Zhang, Jin Jin, Jonas Frey, Nikita Rudin, Matias Mattamala, Cesar Cadena Lerma, and Marco Hutter
• Learning Continuous Control with Geometric Regularity from Robot Intrinsic Symmetry, Shengchao Yan, Baohe Zhang, Yuan Zhang, Joschka Boedecker, and Wolfram Burgard
• Learning Vision-Based Bipedal Locomotion for Challenging Terrain, Helei Duan, Bikram Pandit, Mohitvishnu S. Gadde, Bart Jaap Van Marum, Jeremy Dao, Chanho Kim, and Alan Fern

IEEE ICRA Best Paper Award in Robot Manipulation

Winner

SARA-RT: Scaling up Robotics Transformers with Self-Adaptive Robust Attention, Isabel Leal, Krzysztof Choromanski, Deepali Jain, Avinava Dubey, Jacob Varley, Michael S. Ryoo, Yao Lu, Frederick Liu, Vikas Sindhwani, Tamas Sarlos, Kenneth Oslund, Karol Hausman, Quan Vuong, and Kanishka Rao

Finalists

• Open X-Embodiment: Robotic Learning Datasets and RT-X Models, Sergey Levine, Chelsea Finn, Ken Goldberg, Lawrence Yunliang Chen, Gaurav Sukhatme, Shivin Dass, Lerrel Pinto, Yuke Zhu, Yifeng Zhu, Shuran Song, Oier Mees, Deepak Pathak, Hao-Shu Fang, Henrik Iskov Christensen, Mingyu Ding, Youngwoon Lee, Dorsa Sadigh, Ilija Radosavovic, Jeannette Bohg, Xiaolong Wang, Xuanlin Li, Krishan Rana, Kento Kawaharazuka, Tatsuya Matsushima, Jihoon Oh, Takayuki Osa, Oliver Kroemer, Beomjoon Kim, Edward Johns, Freek Stulp, Jan Schneider, Jiajun Wu, Yunzhu Li, Heni Ben Amor, Lionel Ott, Roberto Martin-Marin, Karol Hausman, Quan Vuong, Pannag Sanketi, Nicolas Heess, Vincent Vanhoucke, Karl Pertsch, Stefan Schaal, Cheng Chi, Chuer Pan, and Alex Bewley
• Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Plans, Homanga Bharadhwaj, Abhinav Gupta, Vikash Kumar, and Shubham Tulsiani
• Hearing Touch: Audio-Visual Pretraining for Contact-Rich Manipulation, Jared Mejia, Victoria Dean, Tess Hellebrekers, and Abhinav Gupta
• DenseTact-Mini: An Optical Tactile Sensor for Grasping Multi-Scale Objects From Flat Surfaces, Won Kyung Do, Ankush Ankush Dhawan, Mathilda Kitzmann, and Monroe Kennedy
• Constrained Bimanual Planning with Analytic Inverse Kinematics, Thomas Cohn, Seiji Shaw, Max Simchowitz, and Russ Tedrake

IEEE ICRA Best Paper Award on Human-Robot Interaction

Winner

CoFRIDA: Self-Supervised Fine-Tuning for Human-Robot Co-Painting, Peter Schaldenbrand, Gaurav Parmar, Jun-Yan Zhu, James Mccann, and Jean Oh

Finalists

• POLITE: Preferences Combined with Highlights in Reinforcement Learning, Simon Holk, Daniel Marta, and Iolanda Leite
• MateRobot: Material Recognition in Wearable Robotics for People with Visual Impairments, Junwei Zheng, Jiaming Zhang, Kailun Yang, Kunyu Peng, and Rainer Stiefelhagen
• Robot-Assisted Navigation for Visually Impaired through Adaptive Impedance and Path Planning, Pietro Balatti, Idil Ozdamar, Doganay Sirintuna, Luca Fortini, Mattia Leonori, Juan M. Gandarias, and Arash Ajoudani
• Incremental Learning of Full-Pose Via-Point Movement Primitives on Riemannian Manifolds, Tilman Daab, Noémie Jaquier, Christian R. G. Dreher, Andre Meixner, Franziska Krebs, and Tamim Asfour
• Supernumerary Robotic Limbs to Support Post-Fall Recoveries for Astronauts, Erik Ballesteros, Sang-Yoep Lee, Kalind Carpenter, and Harry Asada

IEEE ICRA Best Paper Award in Medical Robotics

Winner

Exoskeleton-Mediated Physical Human-Human Interaction for a Sit-to-Stand Rehabilitation Task, Lorenzo Vianello, Emek Baris Kucuktabak, Matthew Short, Clément Lhoste, Lorenzo Amato, Kevin Lynch, and Jose L. Pons

Finalists

• Intraoperatively Iterative Hough Transform Based In-plane Hybrid Control of Arterial Robotic Ultrasound for Magnetic Catheterization, Zhengyang Li, Magejiang Yeerbulati, and Qingsong Xu
• Efficient Model Learning and Adaptive Tracking Control of Magnetic Micro-Robots for Non-Contact Manipulation, Yongyi Jia, Shu Miao, Junjian Zhou, Niandong Jiao, Lianqing Liu, and Xiang Li
• Colibri5: Real-Time Monocular 5-DoF Trocar Pose Tracking for Robot-Assisted Vitreoretinal Surgery, Shervin Dehghani, Michael Sommersperger, Mahdi Saleh, Alireza Alikhani, Benjamin Busam, Peter Gehlbach, Ioan Iulian Iordachita, Nassir Navab, and M. Ali Nasseri
• Hybrid Volitional Control of a Robotic Transtibial Prosthesis using a Phase Variable Impedance Controller, Ryan Posh, Jonathan Allen Tittle, David Kelly, James Schmiedeler, and Patrick M. Wensing
• Design and Implementation of a Robotized Hand-held Dissector for Endoscopic Pulmonary Endarterectomy, Runfeng Zhu, Xilong Hou, Wei Huang, Lei Du, Zhong Wu, Hongbin Liu, Henry Chu, and Qing Xiang Zhao

IEEE ICRA Best Paper Award on Mechanisms and Design

Winner

Design and Modeling of a Nested Bi-cavity-based Soft Growing Robot for Grasping in Constrained Environments, Haochen Yong, Fukang Xu, Chenfei Li, Han Ding, and Zhigang Wu

Finalists

• Optimized Design and Fabrication of Skeletal Muscle Actuators for Bio-syncretic Robots, Lianchao Yang, Chuang Zhang, Ruiqian Wang, Yiwei Zhang, and Lianqing Liu
• Lissajous Curve-Based Vibrational Orbit Control of a Flexible Vibrational Actuator with a Structural Anisotropy, Yuto Miyazaki and Mitsuru Higashimori
• Dynamic Modeling of Wing-Assisted Inclined Running with a Morphing Multi-Modal Robot, Eric Sihite, Alireza Ramezani, and Gharib Morteza

IEEE ICRA Best Paper Award on Multi-Robot Systems

Winner

Do We Run Large-Scale Multi-Robot Systems on the Edge? More Evidence for Two-Phase Performance in System Size Scaling, Jonas Kuckling, Robin Luckey, Viktor Avrutin, Andrew Vardy, Andreagiovanni Reina, and Heiko Hamann

Finalists

• Observer-based Distributed MPC for Collaborative Quadrotor-Quadruped Manipulation of a Cable-Towed Load, Shaohang Xu, Yi’An Wang, Wentao Zhang, Chin Pang Ho, and Lijun Zhu
• Learning for Dynamic Subteaming and Voluntary Waiting in Heterogeneous Multi-Robot Collaborative Scheduling, Williard Joshua Jose and Hao Zhang
• Asynchronous Distributed Smoothing and Mapping via On-Manifold Consensus ADMM, Daniel Mcgann, Kyle Lassak, and Michael Kaess
• Uncertainty-Bounded Active Monitoring of Unknown Dynamic Targets in Road-Networks with Minimum Fleet, Shuaikang Wang, Yiannis Kantaros, and Meng Guo

IEEE ICRA Best Paper Award in Service Robotics

Winner

Learning to Walk in Confined Spaces Using 3D Representation, Takahiro Miki, Joonho Lee, Lorenz Wellhausen, and Marco Hutter

Finalists

• Censible: A Robust and Practical Global Localization Framework for Planetary Surface Missions, Jeremy Nash, Quintin Dwight, Lucas Saldyt, Haoda Wang, Steven Myint, Adnan Ansar, and Vandi Verma
• Efficient and Accurate Transformer-Based 3D Shape Completion and Reconstruction of Fruits for Agricultural Robots, Federico Magistri, Rodrigo Marcuzzi, Elias Ariel Marks, Matteo Sodano, Jens Behley, and Cyrill Stachniss
• CoPAL: Corrective Planning of Robot Actions with Large Language Models, Frank Joublin, Antonello Ceravola, Pavel Smirnov, Felix Ocker, Joerg Deigmoeller, Anna Belardinelli, Chao Wang, Stephan Hasler, Daniel Tanneberg, and Michael Gienger
• CalliRewrite: Recovering Handwriting Behaviors from Calligraphy Images without Supervision, Yuxuan Luo, Zekun Wu, and Zhouhui Lian

IEEE ICRA Best Paper Award in Robot Vision

Winner

NGEL-SLAM: Neural Implicit Representation-based Global Consistent Low-Latency SLAM System, Yunxuan Mao, Xuan Yu, Kai Wang, Yue Wang, Rong Xiong, and Yiyi Liao

Finalists

• HEGN: Hierarchical Equivariant Graph Neural Network for 9DoF Point Cloud Registration, Adam Misik, Driton Salihu, Xin Su, Heike Brock, and Eckehard Steinbach
• Deep Evidential Uncertainty Estimation for Semantic Segmentation under Out-Of-Distribution Obstacles, Siddharth Ancha, Philip Osteen, and Nicholas Roy
• SeqTrack3D: Exploring Sequence Information for Robust 3D Point Cloud Tracking, Yu Lin, Zhiheng Li, Yubo Cui, and Zheng Fang
• Ultrafast Square-Root Filter-based VINS, Yuxiang Peng, Chuchu Chen, and Guoquan Huang
• Universal Visual Decomposer: Long-Horizon Manipulation Made Easy, Zichen Zhang, Yunshuang Li, Osbert Bastani, Abhishek Gupta, Dinesh Jayaraman, Yecheng Jason Ma, and Luca Weihs

IEEE ICRA Best Paper Award on Unmanned Aerial Vehicles

Winner

Time-Optimal Gate-Traversing Planner for Autonomous Drone Racing, Chao Qin, Maxime Simon Joseph Michet, Jingxiang Chen, and Hugh H.-T. Liu

Finalists

• A Trajectory-based Flight Assistive System for Novice Pilots in Drone Racing Scenario, Yuhang Zhong, Guangyu Zhao, Qianhao Wang, Guangtong Xu, Chao Xu, and Fei Gao
• Co-Design Optimisation of Morphing Topology and Control of Winged Drones, Fabio Bergonti, Gabriele Nava, Valentin Wüest, Antonello Paolino, Giuseppe L’Erario, Daniele Pucci, and Dario Floreano
• FC-Planner: A Skeleton-guided Planning Framework for Fast Aerial Coverage of Complex 3D Scenes, Chen Feng, Haojia Li, Mingjie Zhang, Xinyi Chen, Boyu Zhou, and Shaojie Shen
• Sequential Trajectory Optimization for Externally-Actuated Modular Manipulators with Joint Locking, Jaeu Choe, Jeongseob Lee, Hyunsoo Yang, Hai-Nguyen (Hann) Nguyen, and Dongjun Lee
• Spatial Assisted Human-Drone Collaborative Navigation and Interaction through Immersive Mixed Reality, Luca Morando and Giuseppe Loianno

IEEE ICRA Best Student Paper Award

Winner

Optimized Design and Fabrication of Skeletal Muscle Actuators for Bio-syncretic Robots, Lianchao Yang, Chuang Zhang, Ruiqian Wang, Yiwei Zhang, and Lianqing Liu

Finalists

• TinyMPC: Model-Predictive Control on Resource-Constrained Microcontrollers, Anoushka Alavilli, Khai Nguyen, Samuel Schoedel, Brian Plancher, and Zachary Manchester
• Goal Masked Diffusion Policies for Unified Navigation and Exploration, Ajay Sridhar, Dhruv Shah, Catherine Glossop, and Sergey Levine
• Open X-Embodiment: Robotic Learning Datasets and RT-X Models, Sergey Levine, Chelsea Finn, Ken Goldberg, Lawrence Yunliang Chen, Gaurav Sukhatme, Shivin Dass, Lerrel Pinto, Yuke Zhu, Yifeng Zhu, Shuran Song, Oier Mees, Deepak Pathak, Hao-Shu Fang, Henrik Iskov Christensen, Mingyu Ding, Youngwoon Lee, Dorsa Sadigh, Ilija Radosavovic, Jeannette Bohg, Xiaolong Wang, Xuanlin Li, Krishan Rana, Kento Kawaharazuka, Tatsuya Matsushima, Jihoon Oh, Takayuki Osa, Oliver Kroemer, Beomjoon Kim, Edward Johns, Freek Stulp, Jan Schneider, Jiajun Wu, Yunzhu Li, Heni Ben Amor, Lionel Ott, Roberto Martin-Martin, Karol Hausman, Quan Vuong, Pannag Sanketi, Nicolas Heess, Vincent Vanhoucke, Karl Pertsch, Stefan Schaal, Cheng Chi, Chuer Pan, and Alex Bewley
• POLITE: Preferences Combined with Highlights in Reinforcement Learning, Simon Holk, Daniel Marta, and Iolanda Leite
• Exoskeleton-Mediated Physical Human-Human Interaction for a Sit-to-Stand Rehabilitation Task, Lorenzo Vianello, Emek Baris Kucuktabak, Matthew Short, Clément Lhoste, Lorenzo Amato, Kevin Lynch, and Jose L. Pons
• Design and Modeling of a Nested Bi-cavity- based Soft Growing Robot for Grasping in Constrained Environments, Haochen Yong, Fukang Xu, Chenfei Li, Han Ding, and Zhigang Wu
• Observer-based Distributed MPC for Collaborative Quadrotor-Quadruped Manipulation of a Cable-Towed Load, Shaohang Xu, Yi’An Wang, Wentao Zhang, Chin Pang Ho, and Lijun Zhu
• Censible: A Robust and Practical Global Localization Framework for Planetary Surface Missions, Jeremy Nash, Quintin Dwight, Lucas Saldyt, Haoda Wang, Steven Myint, Adnan Ansar, and Vandi Verma
• HEGN: Hierarchical Equivariant Graph Neural Network for 9DoF Point Cloud Registration, Adam Misik, Driton Salihu, Xin Su, Heike Brock, and Eckehard Steinbach
• A Trajectory-based Flight Assistive System for Novice Pilots in Drone Racing Scenario, Yuhang Zhong, Guangyu Zhao, Qianhao Wang, Guangtong Xu, Chao Xu, and Fei Gao

IEEE ICRA Best Conference Paper Award

Winners

• Goal Masked Diffusion Policies for Unified Navigation and Exploration, Ajay Sridhar, Dhruv Shah, Catherine Glossop, and Sergey Levine
• Open X-Embodiment: Robotic Learning Datasets and RT-X, Sergey Levine, Chelsea Finn, Ken Goldberg, Lawrence Yunliang Chen, Gaurav Sukhatme, Shivin Dass, Lerrel Pinto, Yuke Zhu, Yifeng Zhu, Shuran Song, Oier Mees, Deepak Pathak, Hao-Shu Fang, Henrik Iskov Christensen, Mingyu Ding, Youngwoon Lee, Dorsa Sadigh, Ilija Radosavovic, Jeannette Bohg, Xiaolong Wang, Xuanlin Li, Krishan Rana, Kento Kawaharazuka, Tatsuya Matsushima, Jihoon Oh, Takayuki Osa, Oliver Kroemer, Beomjoon Kim, Edward Johns, Freek Stulp, Jan Schneider, Jiajun Wu, Yunzhu Li, Heni Ben Amor, Lionel Ott, Roberto Martin-Martin, Karol Hausman, Quan Vuong, Pannag Sanketi, Nicolas Heess, Vincent Vanhoucke, Karl Pertsch, Stefan Schaal, Cheng Chi, Chuer Pan, and Alex Bewley

Finalists

• TinyMPC: Model-Predictive Control on Resource-Constrained Microcontrollers, Anoushka Alavilli, Khai Nguyen, Samuel Schoedel, Brian Plancher, and Zachary Manchester
• POLITE: Preferences Combined with Highlights in Reinforcement Learning, Simon Holk, Daniel Marta, and Iolanda Leite
• Exoskeleton-Mediated Physical Human-Human Interaction for a Sit-to-Stand Rehabilitation Task, Lorenzo Vianello, Emek Baris Kucuktabak, Matthew Short, Clément Lhoste, Lorenzo Amato, Kevin Lynch, and Jose L. Pons
• Optimized Design and Fabrication of Skeletal Muscle Actuators for Bio-syncretic Robots, Lianchao Yang, Chuang Zhang, Ruiqian Wang, Yiwei Zhang, and Lianqing Liu
• Design and Modeling of a Nested Bi-cavity- based Soft Growing Robot for Grasping in Constrained Environments, Haochen Yong, Fukang Xu, Chenfei Li, Han Ding, and Zhigang Wu
• Observer-based Distributed MPC for Collaborative Quadrotor-Quadruped Manipulation of a Cable-Towed Load, Shaohang Xu, Yi’An Wang, Wentao Zhang, Chin Pang Ho, and Lijun Zhu
• Censible: A Robust and Practical Global Localization Framework for Planetary Surface Missions, Jeremy Nash, Quintin Dwight, Lucas Saldyt, Haoda Wang, Steven Myint, Adnan Ansar, and Vandi Verma
• HEGN: Hierarchical Equivariant Graph Neural Network for 9DoF Point Cloud Registration, Adam Misik, Driton Salihu, Xin Su, Heike Brock, and Eckehard Steinbach
• A Trajectory-based Flight Assistive System for Novice Pilots in Drone Racing Scenario, Yuhang Zhong, Guangyu Zhao, Qianhao Wang, Guangtong Xu, Chao Xu, and Fei Gao

The 2024 IEEE International Conference on Robotics and Automation (ICRA) will take place from 13-17 May, in Yokohama, Japan. The event will feature plenary and keynote talks, technical sessions, posters, workshops and tutorials.

Plenary speakers

There are three plenary talks at the conference this year:

• Yoky Matsuoka – How to Turn a Roboticist into a Corporate Explorer
• Sami Haddadin – The Great Robot Accelerator: Collective Learning of Optimal Embodied AI
• Sunil K Agrawal – Rehabilitation Robotics: How to Improve Daily Functions in People with Impairments?

Keynote talks

There will be 15 keynote talks, given by:

• Lianqing Liu – Biosyncretic sensing, actuation and intelligence for robotics
• Dawn M. Tilbury – Digital Twins for Manufacturing Automation
• Claudio Pacchierotti – Beyond Force Feedback: Cutaneous Haptics in Human-centered Robotics
• Yu Sun – Medical Robotics for Cell Surgery – Science and Applications
• Yasuhisa Hirata – Adaptable AI-enabled Robots to Create a Vibrant Society – Moonshot R&D Projects in Japan
• Calin Belta – Formal Methods for Safety-Critical Control
• Manuel Catalano – Robots in the Wild: From Research Labs to the Real World
• Harold Soh – Building Guidance Bridges with Generative Models for Robot Learning and Control
• Lorenzo Sabattini – Unleashing the power of many: decentralized control of multi-robot systems
• Myunghee Kim – Human-wearable robot co-adaptation
• Yoko Yamanishi – Emergent Functions of Electrically-induced Bubbles and Intra-cellular-Cybernetic Avatar
• Kensuke Harada – Robotic manipulation aiming for industrial applications
• Iolanda Leite – The Quest for Social Robot Autonomy
• Rong Xiong – Integration of Robotics and AI: Changes and Challenges
• Mariana Medina-Sánchez – Tiny Robots, Big Impact: Transforming Gynecological Care

Tutorials

The tutorials will be held on Monday 13 May and Friday 17 May.

• Tutorial on Ergodic Control
• Connected Robotics Platform for ROS Deployment in Real-world Network Settings
• How to manage fleets of robots with open source software
• Riemann and Gauss meet Asimov: 2nd Tutorial on Geometric Methods in Robot Learning, Optimization and Control
• Cloud and Fog Robotics: A Hands-on Tutorial with ROS2 and FogROS2
• Choreographic swarms: From scripting to emergent expressive behaviors to CONNECT humans and robots

Workshops

The workshops will also be held on Monday 13 May and Friday 17 May. There are 73 to choose from this year.

• Debates on the Future of Robotics Research
• Workshop on Field Robotics
• Continuum and Soft robotics for medical applications with rising stars on the stage
• Agile Robotics: From Perception to Dynamic Action
• 6th Workshop on Long-Term Human Motion Prediction
• 2nd HERMES Workshop: Multi-Robot Sensing & Perception in Extreme Environments
• Towards Collaborative Partners: Design, Shared Control, and Robot Learning for Physical Human-Robot Interaction
• Society of Avatar-Symbiosis through Social Field Experiments
• 3rd Workshop on Future of Construction: Lifelong Learning Robots in Changing Construction Sites
• What does Responsible Robotics mean?: Stretching roboticists’ horizons from an academic, government and philosophical perspective
• Workshop on Ontologies and Standards for Robotics and Automation
• Exploring Role Allocation in Human-Robot Co-Manipulation
• C4SR+: Continuum, Compliant, Cooperative, Cognitive Surgical Robotic Systems in the Embodied AI Era
• Dynamic Duos: Human-Robot Co-Worker Adaptation in Manufacturing
• Autonomy in Robotics Surgery: State of the art, technical and regulatory challenges for clinical application
• 2nd Robot-Assisted Medical Imaging ICRA-RAMI
• Back to the Future: Robot Learning Going Probabilistic
• Bioinspired, soft and other novel design paradigms for aerial robotics
• Impulsive motion in soft robotic and microrobotic systems
• Agile Movements II: Animal Behavior, Biomechanics, and Robot Devices
• Bimanual manipulation: On kitchen challenges
• The robotics, psychology and neuroscience of body augmentation
• Sustainable Soft Robots: Working with the Environment
• Robotics and Sustainability: A Bidirectional Relationship
• 2nd Workshop on Mobile Manipulation and Embodied Intelligence (MOMA) Integrating Perception, Learning and Control for Full Autonomy
• (Re)designing the tree of robotic life: a game of alternative timelines
• Advancing Sustainable Food Systems through Agri-Robotics Innovations
• Co-design in Robotics: Theory, Practice, and Challenges
• Robot Trust for Symbiotic Societies
• Soft Continuum Manipulators: Bottlenecks and Applications
• Advanced human-robot interfaces based on physiological signals and sensory stimulations
• Assistive Systems: Lab to Patient Care
• MAD-Games: Workshop on Multi-Agent Dynamic Games
• Workshop on Robot Ethics – Ethical, Legal and User Perspectives in Robotics and Automation (WOROBET)
• Applications and Future Directions of Affective Technologies
• ProxyTouch: Whole-body Proxy-Tactile Architectures for Industrial and Service Applications
• Bio-inspired robotics and robotics for biology
• A Future Roadmap for Sensorimotor Skill Learning for Robot Manipulation
• Robotics and Automation in Nuclear Environments
• 3D Visual Representations for Robot Manipulation
• Advancements in Trajectory Optimization and Model Predictive Control for Legged Systems – 2nd Edition
• Robots for Understanding Natural Ecosystems
• Cooking Robotics: Perception and motion planning
• Robot Software Architectures (RSA24)
• Multi-Object Grasping: Progress and Prospects
• First Workshop on Vision-Language Models for Navigation and Manipulation
• Radar in Robotics: Resilience from Signal to Navigation
• Anthropomorphic and zoomorphic end-effectors: asset or useless bias?
• Workshop on Resilient Off-road Autonomy
• Breaking Swarm Stereotypes
• Translational research in medical robotics: From Lab Bench to Clinical Use – How to?
• 4th Workshop on Representing and Manipulating Deformable Objects
• Loco-Manipulation: Algorithms, Challenges & Applications
• Cognition across species: from nature to robotic application
• Unconventional Robots: Universal Lessons for Designing Unique Systems
• Accelerating Discovery in Natural Science Laboratories with AI and Robotics
• Human-Robot Companionship for Healthcare and Wellness: Which Form of Companionship for What Type of Care?
• Humanoid Whole-body Control: From human motion understanding to humanoid locomotion
• RoboNerF: Neural Fields in Robotics
• ViTac 2024: Robot Embodiment through Visuo-Tactile Perception
• Supervised autonomy: how to shape human-robot interaction from the body to the brain
• Robots and roboticists in the age of climate change
• Human-Centric Multilateral Teleoperation: Perception, Telecommunication, and Coordination
• Innovations and Applications of Human Modeling in Physical Human-Robot Interaction
• How to Ensure Correct Robot Behaviors? Software Challenges in Formal Methods for Robotics
• Advancing Wearable Devices and Applications through Novel Design, Sensing, Actuation, and AI
• Wearable Intelligence for Healthcare Robotics (WIHR): from Brain Activity to Body Movements
• Emerging Technologies in Smart Exoskeleton Systems
• Expanding Frontiers of Sim2Real: Robotics, biomechanics, plasma physics, chip design, and beyond
• Nursing Robotics: a new field emerging from the integration between robotics and nursing science
• Speed-dating to long-term relationships: Art-robot Residencies Enabled by Common Language
• Workshop on Human-aligned Reinforcement Learning for Autonomous Agents and Robots
• 2nd Workshop on NeuroDesign in Human-Robot Interaction: The making of engaging HRI technology your brain can’t resist

You can see the programme overview here, with a detailed programme available here.

Thanks to those that sent and suggested AI and robotics-themed holiday videos, images, and stories. Here’s a sample to get you into the spirit this season.

Josh Miller used ChatGPT to create the 12 days of Christmas. Prompt: “I want to make 12 images in an early 1980s era to depict the twelve days of Christmas”.

See the pictures in higher definition here.

“Santa’s Secret: Robots Saved Christmas! | CPS XMAS video 2023” from Chair of Cyber-Physical Systems.

“AI rewriting classic Christmas stories” from GingerPale.

Using PaLM2 to generate haikus.

Prompt: “Write me a haiku about an alternative xmas”.
No gifts, no grand feast,
Just laughter and joy, warmth spread,
Kindness fills the air.

Prompt: “Write a haiku about the winter holiday season”.
Snow blankets the land,
Hearts aglow with love’s warmth,
Joyous cheer surrounds.

“Put a Bow on It | Happy Holidays” from Boston Dynamics.

“Christmas Magic: Animated Backgrounds for an Enchanting Atmosphere” from AI-ArtificialIntelligence.

“XMAS – Episode 3: AI – Christmas music for the HAKOM Christmas party” from HAKOM Time Series.

“Christmas tree in python notebook with Turtle” from Learn Upwards.

“FZI Living Lab Christmas Robotics 2023 – Robotic Reindeer Rescue” from FZI channel.

A letter to Santa generated by PaLM2. Prompt: “Write me a letter to Santa Claus. I don’t want any presents, just inspiration in my machine learning research for 2024.”

Dear Santa Claus,

As the year comes to a close, I find myself reflecting on the remarkable advancements in machine learning that have transformed our world. From self-driving cars to personalized medicine, these innovations have opened up new possibilities and enriched our lives in ways we could have only imagined a few decades ago.

I am writing to you today not to ask for material gifts, but rather for something more precious: inspiration to continue exploring the frontiers of machine learning in the year to come. As a researcher in this field, I am eager to contribute to the development of algorithms and techniques that can further enhance our understanding of the world around us and create solutions to pressing global challenges.

I am particularly fascinated by the potential of machine learning to address the climate crisis. By harnessing the power of data and computation, we can develop more efficient renewable energy sources, optimize transportation systems, and mitigate the impact of extreme weather events. Additionally, I believe that machine learning can play a crucial role in improving education, healthcare, and environmental sustainability.

I know that you have a special ability to see the world in a unique and insightful way. I hope that you can share some of your wisdom with me and guide me towards promising research directions. I am eager to embark on new challenges and make a positive impact on the world through machine learning.

Thank you for considering my request, Santa Claus. I look forward to your guidance and inspiration as I pursue my research endeavors in the year ahead.

With warmest regards,

[Your Name]

The AAAI Fall Symposium Series took place in Arlington, USA, and comprised seven different symposia. One of these, the tenth Artificial Intelligence for Human-Robot Interaction (AI-HRI) symposium was run as a hybrid in-person/online event, and we tuned in to the opening keynote, which was given by Patrícia Alves-Oliveira.

As a psychology student, Patrícia’s dream was to become a therapist. However, an internship, where she encountered a robot for the first time, inspired her to change her plans, and she decided to go into the field of human-robot interaction. Following a PhD in the field, she worked as a postdoc, before heading to industry as a designer in the Amazon Astro robot team.

Patrícia has worked on a number of interesting projects during her time in academia and in industry. Thinking about how to design robots for specific user needs, and keeping the user at the forefront during the design process, has been core to her work. She began by summarising three very different academic projects.

Creativity and robotics

The objective of this project was to design, fabricate, and evaluate robots as creativity-provoking tools for kids. Patrícia created a social robot named YOLO (or Your Own Living Object) that she designed to be child-proof (in other words, it could withstand being dropped and knocked over), with the aim of trying to help children explore their creativity during play. A machine learning algorithm learns the pattern of play that the child has and adapts the robot behaviour accordingly. You can see the robot in action in the demo below:

FLEXI robot

As a postdoc project, Patrícia worked on building FLEXI, a social robot embodiment kit. This kit consists of a robot (with a face, and a torso with a screen on the front), which can be customised, and an open-source end-user programming interface designed to be user-friendly. The customisation element means that it can be used for many applications. The team has deployed FLEXI across three application scenarios: community-support, mental health, and education, with the aim of assessing the flexibility of the system. You can see the robot in action, in different scenarios, here.

Social dining

This project centred on a robotic arm for people with impaired mobility. Such systems already exist for assisting people with tasks such as eating. However, in a social context they can often form a barrier between the user and the rest of the group. The idea behind this project was to consider how such a robot could be adapted to work well in a social context, for example, during a meal with family or friends. The team interviewed people with impaired mobility to assess their needs, and came up with a set of design principles for creating robot-assisted feeding systems and an implementation guide for future research in this area. You can read the research paper on this project here.

You can find out more about these three projects, and the other projects that Patrícia has been involved in, here.

Astro robot

Patrícia has long been interested in robots for the real world, and how this real-world experience is aligned with the study of robots in academia and industry. She decided to leave academia and join the Astro robot programme, which she felt was a great opportunity to work on a large-scale real-world robot project.

The Astro robot is a home robot designed to assist with tasks such as monitoring your house, delivering small objects within the home, recognising your pet, telling a story, or playing games.

Patrícia took us through a typical day in the life of a designer where she always has in mind the bigger picture of what the team is aiming for, in other words, what the ideal robot, and its interactions with humans, would look like. Coupled to that, the process is governed by core design tenets, such as the customer needs, and non-negotiable core elements that the robot should include. When considering a particular element of the robot design, for example, the delivery of an item in the robot tray, Patrícia uses storyboards to map out details of potential human-robot interactions. An important aspect of design concerns edge cases, which occur regularly in the real world. Good design will consider potential edge cases and incorporate ways to deal with them.

Patrícia closed by emphasising the importance of teamwork in the design process, in particular, the need for interdisciplinary teams; by considering design from many different points of view, the chance of innovation is higher.

You can find out more about the Artificial Intelligence for Human-Robot Interaction (AI-HRI) symposium here.

Code to Joy: Why Everyone Should Learn a Little Programming is a new book from Michael Littman, Professor of Computer Science at Brown University and a founding trustee of AIhub. We spoke to Michael about what the book covers, what inspired it, and how we are all familiar with many programming concepts in our daily lives, whether we realize it or not.

Could you start by telling us a bit about the book, and who the intended audience is?

The intended audience is not computer scientists, although I have been getting a very warm reception from computer scientists, which I appreciate. The idea behind the book is to try to help people understand that telling machines what to do (which is how I view much of computer science and AI) is something that is really accessible to everyone. It builds on skills and practices that people already have. I think it can be very intimidating for a lot of people, but I don’t think it needs to be. I think that the foundation is there for everybody and it’s just a matter of tapping into that and building on top of it. What I’m hoping, and what I’m seeing happening, is that machine learning and AI is helping to meet people part way. The machines are getting better at listening as we try to get better at telling them what to do.

What made you decide to write the book, what was the inspiration behind it?

I’ve taught large introductory computer science classes and I feel like there’s an important message in there about how a deeper knowledge of computing can be very empowering, and I wanted to bring that to a larger audience.

Could you talk a bit about the structure of the book?

The meat of the book talks about the fundamental components that make up programs, or, in other words, that make up the way that we tell computers what to do. Each chapter covers a different one of those topics – loops, variables, conditionals, for example. Within each chapter I talk about the ways in which this concept is already familiar to people, the ways that it shows up in regular life. I point to existing pieces of software or websites where you can make use of that one particular concept to tell computers what to do. Each chapter ends with an introduction to some concepts from machine learning that can help create that particular programming construct. For example, in the chapter on conditionals, I talk about the ways that we use the word “if” in regular life all the time. Weddings, for example, are very conditionally structured, with statements like “if anyone has anything to say, speak now or forever hold your peace”. That’s kind of an “if-then” statement. In terms of tools to play with, I talk about interactive fiction. Partway between video games and novels is this notion that you can make a story that adapts itself while it’s being read. What makes that interesting is this notion of conditionals – the reader can make a choice and that will cause a branch. There are really wonderful tools for being able to play with this idea online, so you don’t have to be a full-fledged programmer to make use of conditionals. The machine learning concept introduced there is decision trees, which is an older form of machine learning where you give a system a bunch of examples and then it outputs a little flowchart for decision making.

Do you touch on generative AI in the book?

The book was already in production by the time ChatGPT came out, but I was ahead of the curve, and I did have a section specifically about GPT-3 (pre-ChatGPT) which talks about what it is, how machine learning creates it, and how it itself can be helpful in making programs. So, you see it from both directions. You get the notion that this tool actually helps people tell machines what to do, and also the way that humanity created this tool in the first place using machine learning.

Did you learn anything while you were writing the book that was particularly interesting or surprising?

Researching the examples for each chapter caused me to dig into a whole bunch of topics. This notion of interactive fiction, and that there’s tools for creating interactive fiction, I found pretty interesting. When researching another chapter, I found an example from a Jewish prayer book that was just so shocking to me. So, Jewish prayer books (and I don’t know if this is true in other belief systems as well, but I’m mostly familiar with Judaism), contain things you’re supposed to read, but they have little conditional markings on them sometimes. For example, one might say “don’t read this if it’s a Saturday”, or “don’t read this if it’s a full moon”, or “don’t read if it’s a full moon on a Saturday”. I found one passage that actually had 14 different conditions that you had to check to decide whether or not it was appropriate to read this particular passage. That was surprising to me – I had no idea that people were expected to do so much complex computation during a worship activity.

Why is it important that everybody learns a little programming?

It’s really important to keep in mind the idea that at the end of the day what AI is doing is making it easier for us to tell machines what to do, and we should share that increased capability with a broad population. It shouldn’t just be the machine learning engineers who get to tell computers what to do more easily. We should find ways of making this easier for everybody.

Because computers are here to help, but it’s a two-way street. We need to be willing to learn to express what we want in a way that can be carried out accurately and automatically. If we don’t make that effort, then other parties, companies often, will step in and do it for us. At that point, the machines are working to serve some else’s interest instead of our own. I think it’s become absolutely essential that we restore a healthy relationship with these machines before we lose any more of our autonomy.

Any final thoughts or takeaways that we should bear in mind?

I think there’s a message here for computer science researchers, as well. When we tell other people what to do, we tend to combine a description or a rule, something that’s sort of program-like, with examples, something that’s more data-like. We just intermingle them when we talk to each other. At one point when I was writing the book, I had a dishwasher that was acting up and I wanted to understand why. I read through its manual, and I was struck by how often it was the case that in telling people what to do with the dishwasher, the authors would consistently mix together a high-level description of what they are telling you to do with some particular, vivid examples: a rule for what to load into the top rack, and a list of items that fit that rule. That seems to be the way that people want to both convey and receive information. What’s crazy to me is that we don’t program computers that way. We either use something that’s strictly programming, all rules, no examples, or we use machine learning, where it’s all examples, no rules. I think the reason that people communicate this way with each other is because those two different mechanisms have complementary strengths and weaknesses and when you combine the two together, you maximize the chance of being accurately understood. And that’s the goal when we’re telling machines what to do. I want the AI community to be thinking about how we can combine what we’ve learned about machine learning with something more programming-like to make a much more powerful way of telling machines what to do. I don’t think this is a solved problem yet, and that’s something that I really hope that people in the community think about.

Code to Joy: Why Everyone Should Learn a Little Programming is available to buy now.

Michael L. Littman is a University Professor of Computer Science at Brown University, studying machine learning and decision making under uncertainty. He has earned multiple university-level awards for teaching and his research on reinforcement learning, probabilistic planning, and automated crossword-puzzle solving has been recognized with three best-paper awards and three influential paper awards. Littman is co-director of Brown’s Humanity Centered Robotics Initiative and a Fellow of the Association for the Advancement of Artificial Intelligence and the Association for Computing Machinery. He is also a Fellow of the American Association for the Advancement of Science Leshner Leadership Institute for Public Engagement with Science, focusing on Artificial Intelligence. He is currently serving as Division Director for Information and Intelligent Systems at the National Science Foundation.

In July this year, 2500 participants congregated in Bordeaux for RoboCup2023. The competition comprises a number of leagues, and among them is RoboCupJunior, which is designed to introduce RoboCup to school children, with the focus being on education. There are three sub-leagues: Soccer, Rescue and OnStage.

Marek Šuppa serves on the Executive Committee for RoboCupJunior, and he told us about the competition this year and the latest developments in the Soccer league.

What is your role in RoboCupJunior and how long have you been involved with this league?

I started with RoboCupJunior quite a while ago: my first international competition was in 2009 in Graz, where I was lucky enough to compete in Soccer for the first time. Our team didn’t do all that well in that event but RoboCup made a deep impression and so I stayed around: first as a competitor and later to help organise the RoboCupJunior Soccer league. Right now I am serving as part of the RoboCupJunior Execs who are responsible for the organisation of RoboCupJunior as a whole.

How was the event this year? What were some of the highlights?

I guess this year’s theme or slogan, if we were to give it one, would be “back to normal”, or something like that. Although RoboCup 2022 already took place in-person in Thailand last year after two years of a pandemic pause, it was in a rather limited capacity, as COVID-19 still affected quite a few regions. It was great to see that the RoboCup community was able to persevere and even thrive throughout the pandemic, and that RoboCup 2023 was once again an event where thousands of robots and roboticists meet.

It would also be difficult to do this question justice without thanking the local French organisers. They were actually ready to organise the event in 2020 but it got cancelled due to COVID-19. But they did not give up on the idea and managed to put together an awesome event this year, for which we are very thankful.

Examples of the robots used by the RoboCupJunior Soccer teams.

Turning to RoboCupJunior Soccer specifically, could you talk about the mission of the league and how you, as organisers, go about realising that mission?

The mission of RoboCupJunior consists of two competing objectives: on one hand, it needs to be a challenge that’s approachable, interesting and relevant for (mostly) high school students and at the same time it needs to be closely related to the RoboCup “Major” challenges, which are tackled by university students and their mentors. We are hence continuously trying to both make it more compelling and captivating for the students and at the same time ensure it is technical enough to help them grow towards the RoboCup “Major” challenges.

One of the ways we do that is by introducing what we call “SuperTeam” challenges, in which teams from respective countries form a so-called “SuperTeam” and compete against another “SuperTeam” as if these were distinct teams. In RoboCupJunior Soccer the “SuperTeams” are composed of four to five teams and they compete on a field that is six times larger than the “standard” fields that are used for the individual games. While in the individual matches each team can play with two robots at most (resulting in a 2v2 game) in a SuperTeam match each SuperTeam fields five robots, meaning there are 10 robots that play on the SuperTeam field during a SuperTeam match. The setup is very similar to the Division B of the Small Size League of RoboCup “Major”.

The SuperTeam games have existed in RoboCupJunior Soccer since 2013, so for quite a while, and the feedback we received on them was overwhelmingly positive: it was a lot of fun for both the participants as well as the spectators. But compared to the Small Size League games there were still two noticeable differences: the robots did not have a way of communicating with one another and additionally, the referees did not have a way of communicating with the robots. The result was that not only was there little coordination among robots of the same SuperTeam, whenever the game needed to be stopped, the referees had to physically run after the robots on the field to catch them and do a kickoff after a goal was scored. Although hilarious, it’s far from how we would imagine the SuperTeam games to look.

The RoboCupJunior Soccer Standard Communication Modules aim to do both. The module itself is a small device that is attached to each robot on the SuperTeam field. These devices are all connected via Bluetooth to a single smartphone, through which the referee can send commands to all robots on the field. The devices themselves also support direct message exchange between robots on a single SuperTeam, meaning the teams do not have to invest into figuring out how to communicate with the other robots but can make use of a common platform. The devices, as well as their firmware, are open source, meaning not only that everyone can build their own Standard Communication Module if they’d like but also that the community can participate in its development, which makes it an interesting addition to RoboCupJunior Soccer.

RoboCupJunior Soccer teams getting ready for the competition.

How did this new module work out in the competition? Did you see an improvement in experience for the teams and organisers?

In this first big public test we focused on exploring how (and whether) these modules can improve the gameplay – especially the “chasing robots at kickoff”. Although we’ve done “lab experiments” in the past and had some empirical evidence that it should work rather well, this was the first time we tried it in a real competition.

All in all, I would say that it was a very positive experiment. The modules themselves did work quite well and for some of us, who happened to have experience with “robot chasing” mentioned above, it was sort of a magical feeling to see the robots stop right on the main referee’s whistle.

We also found out potential areas for improvement in the future. The modules themselves do not have a power source of their own and were powered by the robots themselves. We didn’t think this would be a problem but in the “real world” test it transpired that the voltage levels the robots are capable of providing fluctuates significantly – for instance when the robot decides to aggressively accelerate – which in turn means some of the modules disconnect when the voltage is lowered significantly. However, it ended up being a nice lesson for everyone involved, one that we can certainly learn from when we design the next iterations.

The livestream from Day 4 of RoboCupJunior Soccer 2023. This stream includes the SuperTeam finals and the technical challenges. You can also view the livestream of the semifinals and finals from day three here.

Could you tell us about the emergence of deep-learning models in the RoboCupJunior leagues?

This is something we started to observe in recent years which surprised us organisers, to some extent. In our day-to-day jobs (that is, when we are not organising RoboCup), many of us, the organisers, work in areas related to robotics, computer science, and engineering in general – with some of us also doing research in artificial intelligence and machine learning. And while we always thought that it would be great to see more of the cutting-edge research being applied at RoboCupJunior, we always dismissed it as something too advanced and/or difficult to set up for the high school students that comprise the majority of RoboCupJunior students.

Well, to our great surprise, some of the more advanced teams have started to utilise methods and technologies that are very close to the current state-of-the-art in various areas, particularly computer vision and deep learning. A good example would be object detectors (usually based on the YOLO architecture), which are now used across all three Junior leagues: in OnStage to detect various props, robots and humans who perform on the stage together, in Rescue to detect the victims the robots are rescuing and in Soccer to detect the ball, the goals, and the opponents. And while the participants generally used an off-the-shelf implementations, they still needed to do all the steps necessary for a successful deployment of this technology: gather a dataset, finetune the deep-learning model and deploy it on their robots – all of which is far from trivial and is very close to how these technologies get used in both research and industry.

Although we have seen only the more advanced teams use deep-learning models at RoboCupJunior, we expect that in the future we will see it become much more prevalent, especially as the technology and the tooling around it becomes more mature and robust. It does show, however, that despite their age, the RoboCupJunior students are very close to cutting-edge research and state-of-the-art technologies.

Action from RoboCupJunior Soccer 2023.

How can people get involved in RCJ (either as a participant or an organiser?)

A very good question!

The best place to start would be the RoboCupJunior website where one can find many interesting details about RoboCupJunior, the respective leagues (such as Soccer, Rescue and OnStage), and the relevant regional representatives who organise regional events. Getting in touch with a regional representative is by far the easiest way of getting started with RoboCup Junior.

Additionally, I can certainly recommend the RoboCupJunior forum, where many RoboCupJunior participants, past and present, as well as the organisers, discuss many related topics in the open. The community is very beginner friendly, so if RoboCupJunior sounds interesting, do not hesitate to stop by and say hi!

About Marek Šuppa

Marek stumbled upon AI as a teenager when building soccer-playing robots and quickly realised he is not smart enough to do all the programming by himself. Since then, he’s been figuring out ways to make machines learn by themselves, particularly from text and images. He currently serves as the Principal Data Scientist at Slido (part of Cisco), improving the way meetings are run around the world. Staying true to his roots, he tries to provide others with a chance to have a similar experience by organising the RoboCupJunior competition as part of the Executive Committee.

By Deborah Pirchner

Malaria is an infectious disease claiming more than half a million lives each year. Because traditional diagnosis takes expertise and the workload is high, an international team of researchers investigated if diagnosis using a new system combining an automatic scanning microscope and AI is feasible in clinical settings. They found that the system identified malaria parasites almost as accurately as experts staffing microscopes used in standard diagnostic procedures. This may help reduce the burden on microscopists and increase the feasible patient load.

Each year, more than 200 million people fall sick with malaria and more than half a million of these infections lead to death. The World Health Organization recommends parasite-based diagnosis before starting treatment for the disease caused by Plasmodium parasites. There are various diagnostic methods, including conventional light microscopy, rapid diagnostic tests and PCR.

The standard for malaria diagnosis, however, remains manual light microscopy, during which a specialist examines blood films with a microscope to confirm the presence of malaria parasites. Yet, the accuracy of the results depends critically on the skills of the microscopist and can be hampered by fatigue caused by excessive workloads of the professionals doing the testing.

Now, writing in Frontiers in Malaria, an international team of researchers has assessed whether a fully automated system, combining AI detection software and an automated microscope, can diagnose malaria with clinically useful accuracy.

“At an 88% diagnostic accuracy rate relative to microscopists, the AI system identified malaria parasites almost, though not quite, as well as experts,” said Dr Roxanne Rees-Channer, a researcher at The Hospital for Tropical Diseases at UCLH in the UK, where the study was performed. “This level of performance in a clinical setting is a major achievement for AI algorithms targeting malaria. It indicates that the system can indeed be a clinically useful tool for malaria diagnosis in appropriate settings.”

AI delivers accurate diagnosis

The researchers sampled more than 1,200 blood samples of travelers who had returned to the UK from malaria-endemic countries. The study tested the accuracy of the AI and automated microscope system in a true clinical setting under ideal conditions.

They evaluated samples using both manual light microscopy and the AI-microscope system. By hand, 113 samples were diagnosed as malaria parasite positive, whereas the AI-system correctly identified 99 samples as positive, which corresponds to an 88% accuracy rate.

“AI for medicine often posts rosy preliminary results on internal datasets, but then falls flat in real clinical settings. This study independently assessed whether the AI system could succeed in a true clinical use case,” said Rees-Channer, who is also the lead author of the study.

Automated vs manual

The fully automated malaria diagnostic system the researchers put to the test includes hard- as well as software. An automated microscopy platform scans blood films and malaria detection algorithms process the image to detect parasites and the quantity present.

Automated malaria diagnosis has several potential benefits, the scientists pointed out. “Even expert microscopists can become fatigued and make mistakes, especially under a heavy workload,” Rees-Channer explained. “Automated diagnosis of malaria using AI could reduce this burden for microscopists and thus increase the feasible patient load.” Furthermore, these systems deliver reproducible results and can be widely deployed, the scientists wrote.

Despite the 88% accuracy rate, the automated system also falsely identified 122 samples as positive, which can lead to patients receiving unnecessary anti-malarial drugs. “The AI software is still not as accurate as an expert microscopist. This study represents a promising datapoint rather than a decisive proof of fitness,” Rees-Channer concluded.

Read the research in full

Evaluation of an automated microscope using machine learning for the detection of malaria in travelers returned to the UK, Roxanne R. Rees-Channer, Christine M. Bachman, Lynn Grignard, Michelle L. Gatton, Stephen Burkot, Matthew P. Horning, Charles B. Delahunt, Liming Hu, Courosh Mehanian, Clay M. Thompson, Katherine Woods, Paul Lansdell, Sonal Shah, Peter L. Chiodini, Frontiers in Malaria (2023).

We’ve collected some of the articles, opinion pieces, videos and resources relating to large language models (LLMs). Some of these links also cover other generative models. We will periodically update this list to add any further resources of interest. This article represents the third in the series. (The previous versions are here: v1 | v2.)

What LLMs are and how they work

• What are Generative AI models?, Kate Soule, video from IBM Technology.
• Introduction to Large Language Models, John Ewald, video from Google Cloud Tech.
• What is GPT-4 and how does it differ from ChatGPT?, Alex Hern, The Guardian.
• What Is ChatGPT Doing … and Why Does It Work?, Stephen Wolfram.
• Understanding Large Language Models — A Transformative Reading List, Sebastian Raschka.
• How ChatGPT is Trained, video by Ari Seff.
• ChatGPT – what is it? How does it work? Should we be excited? Or scared?, Deep Dhillon, The Radical AI podcast.
• Everything you need to know about ChatGPT, Joanna Dungate, Turing Institute Blog.
• Turing video lecture series on foundation models: Session 1 | Session 2 | Session 3 | Session 4.
• Bard: What is Google’s Bard and how is it different to ChatGPT?, BBC.
• Bard FAQs, Google.
• Large Language Models from scratch | Large Language Models: Part 2, videos from Graphics in 5 minutes.
• What are Large Language Models (LLMs)?, video from Google for Developers.
• Risks of Large Language Models (LLM), Phaedra Boinodiris, video from IBM Technology.
• How ChatGPT and Other LLMs Work—and Where They Could Go Next, David Nield, Wired.
• What are Large Language Models, Machine Learning Mastery.
• How To Delete Your Data From ChatGPT, Matt Burgess, Wired.
• 5 Ways ChatGPT Can Improve, Not Replace, Your Writing, David Nield, Wired.
• AI prompt engineering: learn how not to ask a chatbot a silly question, Callum Bains, The Guardian.

Journal, conference, arXiv, and other articles

• Scientists’ Perspectives on the Potential for Generative AI in their Fields, Meredith Ringel Morris, arXiv.
• LaMDA: Language Models for Dialog Applications, Romal Thoppilan et al, arXiv.
• What Language Model to Train if You Have One Million GPU Hours?, Teven Le Scao et al, arXiv.
• Alpaca: A Strong, Replicable Instruction-Following Model, Rohan Taori et al.
• Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets, Irene Solaiman, Christy Dennison, NeurIPS 2021.
• On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? ?, Emily Bender, Timnit Gebru, Angelina McMillan-Major, Shmargaret Shmitchell, FAccT 2021.
• A Survey of Large Language Models, Wayne Xin Zhao et al, arXiv.
• A Watermark for Large Language Models, John Kirchenbauer, Jonas Geiping, Yuxin Wen, Jonathan Katz, Ian Miers, Tom Goldstein, arXiv.
• Between Subjectivity and Imposition: Power Dynamics in Data Annotation for Computer Vision, Milagros Miceli, Martin Schuessler, Tianling Yang, Proceedings of the ACM on Human-Computer Interaction.
• AI classifier for indicating AI-written text, OpenAI.
• Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling, Stella Biderman et al, arXiv.
• GPT-4 Technical Report, OpenAI, arXiv.
• GPT-4 System Card, OpenAI.
• BloombergGPT: A Large Language Model for Finance, Shijie Wu et al, arXiv.
• Evading Watermark based Detection of AI-Generated Content, Zhengyuan Jiang, Jinghuai Zhang, Neil Zhenqiang Gong, arXiv.
• PaLM 2 Technical Report, Google.
• Large language models (LLM) and ChatGPT: what will the impact on nuclear medicine be?, Ian L. Alberts, Lorenzo Mercolli, Thomas Pyka, George Prenosil, Kuangyu Shi, Axel Rominger, and Ali Afshar-Oromieh, Eur J Nucl Med Mol Imaging.
• Ethics of large language models in medicine and medical research, Hanzhou Li, John T Moon, Saptarshi Purkayastha, Leo Anthony Celi, Hari Trivedi and Judy W Gichoya, The Lancet.
• Science in the age of large language models, Abeba Birhane, Atoosa Kasirzadeh, David Leslie & Sandra Wachter, Nature.
• Standardizing chemical compounds with language models, Miruna T Cretu, Alessandra Toniato, Amol Thakkar, Amin A Debabeche, Teodoro Laino and Alain C Vaucher, Machine Learning: Science and Technology.
• How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processing, Samuel Sousa & Roman Kern, Artificial Intelligence Review.
• Material transformers: deep learning language models for generative materials design, Nihang Fu, Lai Wei, Yuqi Song, Qinyang Li, Rui Xin, Sadman Sadeed Omee, Rongzhi Dong, Edirisuriya M Dilanga Siriwardane and Jianjun Hu, Machine Learning: Science and Technology.
• Large language models encode clinical knowledge, Karan Singhal et al, Nature.
• SELFormer: molecular representation learning via SELFIES language models, Atakan Yüksel, Erva Ulusoy, Atabey Ünlü and Tunca Doğan, Machine Learning: Science and Technology.
• GPT-4 + Stable-Diffusion = ?: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models, Long Lian, Boyi Li, Adam Yala, and Trevor Darrell, BAIR blog.

Newspaper, magazine, University website, and blogpost articles

• Why exams intended for humans might not be good benchmarks for LLMs like GPT-4, Ben Dickson, Venture Beat.
• Does GPT-4 Really Understand What We’re Saying?, David Krakauer, Nautilus.
• Large language models are biased. Can logic help save them?, Rachel Gordon, MIT News.
• Ecosystems graph for ML models and their relationships, researchers at Stanford University.
• ChatGPT struggles with Wordle puzzles, which says a lot about how it works, Michael G. Madden, The Conversation.
• AIhub coffee corner: Large language models for scientific writing, AIhub.
• ChatGPT Is a Blurry JPEG of the Web, Ted Chiang, The New Yorker.
• ChatGPT, Galactica, and the Progress Trap, Abeba Birhane and Deborah Raji, Wired.
• ChatGPT can’t lie to you, but you still shouldn’t trust it, Mackenzie Graham, The Conversation.
• AI information retrieval: A search engine researcher explains the promise and peril of letting ChatGPT and its cousins search the web for you, Chirag Shah, The Conversation.
• A small step for research but a giant leap for utility, Interview with Fredrik Heintz, Linköping University.
• ChatGPT threatens language diversity. More needs to be done to protect our differences in the age of AI, Collin Bjork, The Conversation.
• Column: Afraid of AI? The startups selling it want you to be, Brian Merchant, Los Angeles Times.
• Three ways AI chatbots are a security disaster, Melissa Heikkilä, MIT Tech Review.
• Time: OpenAI Used Kenyan Workers on Less Than $2 Per Hour to Make ChatGPT Less Toxic, Billy Perrigo, TIME.
• Misplaced fears of an ‘evil’ ChatGPT obscure the real harm being done, John Naughton, The Guardian.
• Darktrace warns of rise in AI-enhanced scams since ChatGPT release, Mark Sweney, The Guardian.
• Lawmakers struggle to differentiate AI and human emails, Kate Blackwood, Cornell Chronicle.
• Colombian judge says he used ChatGPT in ruling, Luke Taylor, The Guardian.
• Bhashini: At your service an Indian language chatbot powered by ChatGPT, video from The Economic Times.
• ChatGPT & Co.: Conversational abilities of large language models, Marisa Tschopp, Luca Gafner, Teresa Windlin, Yelin Zhang, SCIP.
• AI machines aren’t ‘hallucinating’. But their makers are, Naomi Klein, The Guardian
• Google launches new AI PaLM 2 in attempt to regain leadership of the pack, Alex Hern, The Guardian.
• Executives fear accidental sharing of corporate data with ChatGPT: Report, Victor Dey, Venture Beat.
• Letter from the editor: How generative AI is shaping the future of journalism and our newsroom, Michael Nuñez, Venture Beat.
• The inside story of how ChatGPT was built from the people who made it, Will Douglas Heaven, MIT Tech Review.
• A chatbot that asks questions could help you spot when it makes no sense, Melissa Heikkilä, MIT Tech Review.
• Building LLM applications for production, Chip Huyen.
• Generative AI Won’t Revolutionize Search — Yet, Ege Gurdeniz and Kartik Hosanagar, Harvard Business Review.
• If AI image generators are so smart, why do they struggle to write and count?, Seyedali Mirjalili, The Conversation.
• ‘It’s destroyed me completely’: Kenyan moderators decry toll of training of AI models, Niamh Rowe, The Guardian.
• OpenAI launches web crawling GPTBot, sparking blocking effort by website owners and creators, Bryson Masse, Venture Beat
• Why it’s impossible to build an unbiased AI language model, Melissa Heikkilä, MIT Technology Review.
• How to Use Generative AI Tools While Still Protecting Your Privacy, David Nield, Wired.
• Don’t quit your day job: Generative AI and the end of programming, Mike Loukides, Venture Beat.
• OpenAI adds ‘huge set’ of ChatGPT updates, including suggested prompts, multiple file uploads, Carl Franzen, Venture Beat.
• Ageism, sexism, classism and more: 7 examples of bias in AI-generated images, T.J. Thomson and Ryan J. Thomas, The Conversation.
• ‘Open’ alternatives to ChatGPT are on the rise, but how open is AI really?, Radboud University.
• Visual captions: Using large language models to augment video conferences with dynamic visuals, Ruofei Du and Alex Olwal, Google.
• Why watermarking AI-generated content won’t guarantee trust online, Claire Leibowiczarchive page, MIT Technology Review.

Reports

• ChatGPT And More: Large Scale AI Models Entrench Big Tech Power, part of AI Now Institute report.

Podcasts and video discussions

• The Limitations of ChatGPT with Emily M. Bender and Casey Fiesler, Radical AI Podcast.
• CLAIRE AQuA: “ChatGPT and Large Language Models”, CLAIRE.
• Su Lin Blodgett on Creating Just Language Technologies, The Good Robot Podcast.
• The TWIML AI Podcast with Sam Charrington has a number of episodes on the topic of LLMs and generative AI.

Focus on LLMs and education

• Opinion: ChatGPT – what does it mean for academic integrity?, Giselle Byrnes, Massey University.
• Debate: ChatGPT offers unseen opportunities to sharpen students’ critical skills, Erika Darics, Lotte van Poppel, The Conversation.
• ChatGPT and cheating: 5 ways to change how students are graded, Louis Volante, Christopher DeLuca, Don A. Klinger, The Conversation.
• ChatGPT: students could use AI to cheat, but it’s a chance to rethink assessment altogether, Sam Illingworth, The Conversation.
• A Teacher’s Prompt Guide to ChatGPT, @herfteducator.
• Should educators worry about ChatGPT?, interview with Jodi Heckel, Illinois University.
• Large language models challenge the future of higher education, Silvia Milano, Joshua A. McGrane & Sabina Leonelli, Nature.
• ChatGPT, (We need to talk), Q&A with Vaughan Connolly and Steve Watson, University of Cambridge.
• Don’t fret about students using ChatGPT to cheat – AI is a bigger threat to educational equality, Collin Bjork, The Conversation.
• Large Language Models in Medical Education: Opportunities, Challenges, and Future Directions, Alaa Abd-alrazaq, Rawan AlSaad, Dari Alhuwail, Arfan Ahmed, Padraig Mark Healy, Syed Latifi, Sarah Aziz, Rafat Damseh, Sadam Alabed Alrazak, and Javaid Sheikh, JMIR Medical Education.
• Large Language Models and Education, Maastricht University.

Relating to art and other creative processes

• ‘ChatGPT said I did not exist’: how artists and writers are fighting back against AI, Vanessa Thorpe, The Guardian.
• AI and the future of work: 5 experts on what ChatGPT, DALL-E and other AI tools mean for artists and knowledge workers, Lynne Parker, Casey Greene, Daniel Acuña, Kentaro Toyama Mark Finlayson, The Conversation.
• Is there a way to pay content creators whose work is used to train AI? Yes, but it’s not foolproof, Brendan Paul Murphy, The Conversation.
• ChatGPT is the push higher education needs to rethink assessment, Sioux McKenna, Dan Dixon, Daniel Oppenheimer, Margaret Blackie, Sam Illingworth, The Conversation.
• AI Art: How artists are using and confronting machine learning, YouTube video from the Museum of Modern Art.
• ‘We got bored waiting for Oasis to re-form’: AIsis, the band fronted by an AI Liam Gallagher, Rich Pelley, The Guardian.
• Photographer admits prize-winning image was AI-generated, Jamie Grierson, The Guardian.
• The folly of making art with text-to-image generative AI, Ahmed Elgammal, The Conversation.
• Computer-written scripts and deepfake actors: what’s at the heart of the Hollywood strikes against generative AI, Jasmin Pfefferkorn, The Conversation.
• Actors are really worried about the use of AI by movie studios – they may have a point, Dominic Lees, The Conversation.

Pertaining to robotics

• ChatGPT for Robotics: Design Principles and Model Abilities, Microsoft.
• Inner Monologue: Embodied Reasoning through Planning with Language Models, Wenlong Huang et al., arXiv.
• PaLM-E: An embodied multimodal language model, Danny Driess, Google.
• Consciousness, Embodiment, Language Models (with Professor Murray Shanahan), YouTube video from Machine Learning Street Talk.
• RoCo: Dialectic Multi-Robot Collaboration with Large Language Models, Zhao Mandi, Shreeya Jain and Shuran Song, arXiv.
• Awesome LLM robotics, GitHub repository which contains a curative list of papers using LLMs for Robotics and reinforcement learning.
• How can LLMs transform the robotic design process?, Francesco Stella, Cosimo Della Santina and Josie Hughes, Nature.

Misinformation, fake news and the impact on journalism

• Misinformation Monitor: March 2023, focus on GPT-4, NewsGuard.
• A fake news frenzy: why ChatGPT could be disastrous for truth in journalism, Emily Bell, The Guardian.
• Defending Against Neural Fake News, Rowan Zellers et al, arXiv.
• Doctored Sunak picture is just latest in string of political deepfakes, Dan Milmo, The Guardian.

Regulation and policy

• ‘Political propaganda’: China clamps down on access to ChatGPT, Helen Davidson, The Guardian.
• Chatbots, deepfakes, and voice clones: AI deception for sale, USA Federal Trade Commission blog post.
• ‘I didn’t give permission’: Do AI’s backers care about data law breaches?, Alex Hern and Dan Milmo, The Guardian.
• Italy’s ChatGPT ban attracts EU privacy regulators, Supantha Mukherjee, Elvira Pollina and Rachel More, Reuters.
• Training large generative AI models based on publicly available personal data: a GDPR conundrum that the AI act could solve, Sebastião Barros Vale, The Digital Constitutionalist.
• ChatGPT: what the law says about who owns the copyright of AI-generated content, Sercan Ozcan, Joe Sekhon and Oleksandra Ozcan, The Conversation.
• ChatGPT and lawful bases for training AI: a blended approach?, Sophie Stalla-Bourdillon and Pablo Trigo Kramcsák, The Digital Constitutionalist.
• How can we imagine the generative AIs regulatory scheme? Perspectives from Asia, Kuan-Wei Chen, The Digital Constitutionalist.

When was your first RoboCup event and which competition did you take part in?

I started in 2016 in the Junior leagues with my high school and I took part in the rescue simulation competition (although I originally joined the on-stage competition). This first event actually happened in Portugal, and it was similar to a workshop. We qualified to go to the world cup in rescue simulation, in Leipzig, Germany, and we ended up in second place. That was really nice, and it was my first contact with RoboCup, and with robotics generally. I’d been working with electronics in the past, but simulation gave me a bit of an introduction to the more theoretical aspects of robotics, and to AI in general. Rescue simulation makes you think of ways to make the robots independent and not manually controlled by humans.

Roberto’s first RoboCup in 2016, Leipzig, pictured with the Singapore team celebrating after the finals.

Could you tell us about the subsequent RoboCup events that you took part in?

In 2017 we qualified to go to Nagoya, Japan, which was not just an amazing RoboCup, but an amazing trip. That’s another good thing about robotics, you get to meet a lot of new people in new countries. We did quite well in this competition as well, I think we reached 5th place.

After that we went to European RoboCup Junior in Italy. The following year was my last RoboCup as a junior, which was in Sydney. That was also an interesting event and I got to chat a bit more with the majors and understand how their teams worked. By this point, I had gained more experience, and I felt ready to get involved with a major league RoboCup team.

There is a big gap between the junior and major leagues. When I joined my team (the Bold Hearts), most of the team were PhDs and I was just a second year bachelor’s student so it was quite hard to pick up all the knowledge. However, if you are persistent enough and you are interested in, and passionate about, robotics you’ll get the hang of it and you’ll learn by trial and error.

EuroRoboCup 2022 in Portugal. Roberto (kneeling in photo) was part of the organising committee.

When was your first competition with the team in the major league?

My first competition was actually last year, in Thailand. We didn’t perform as we would like to, however, there is much more to RoboCup than just the competition – it is now more of a scientific and knowledge-sharing event, it’s unique. Just this year, in Bordeaux, we had a problem with our robots. Every time we disconnected the ethernet cable, the robot just stopped playing, and we couldn’t figure out what was happening. I asked another team that was using the same software – they had figured out the problem before and they told us how to solve it. I don’t think you’ll see that in other competitions. Every team has a joint objective which is making science progress, making friendships, and making other teams better by sharing their knowledge. That’s really unique.

How did you join the Bold Hearts team?

I decided to do my master’s in the UK (at the University of Hertfordshire), to experience a different country and a different style of education. When I joined, I knew there was a team so I was already looking forward to joining. After a couple of years of work, we finally got to go to a competition as a team. It’s been an amazing time and a huge learning experience.

What is your role on the team?

In our team, everyone does a bit of everything. We still have a lot of problems to solve – on both the hardware and software side. All of us currently are computer scientists so it’s a bit more of a struggle to work on the hardware side. So, I do a bit of everything, both AI and non-AI related problems. For example, I’ve done some 3d modelling for the robots, and I’m currently working on the balancing problem. We all work together on the problems which is amazing because you get to see a bit of everything and learn from everyone. Robotics is a very multidisciplinary field. You get to learn about all kinds of topics: mechanical engineering, electrical engineering, machine learning, coding in general.

The Bold Hearts’ qualification video for this year’s RoboCup competition

Could you tell us about this year’s competition (which took place in Bordeaux)?

This year we were a lot more prepared than last year, when we’d just come back from COVID, and all of our experienced members had recently left the team, due to finishing their PhDs and starting work. Creating a successful robot team is a huge integration problem. There are so many pieces that need to go together and work perfectly for the robots to function, and if one fails it looks like your system isn’t doing anything. We got walking working perfectly this year, we had vision working well too, and we had a stable decision tree, and we were able to listen to the controller (which is like a referee and passes on information about fouls, game start and stops etc.). However, we had some bugs in the decision tree that made everything fall apart and we spent a lot of time trying to debug it. This happens to a lot of teams. However, you can still appreciate the work and progress of what they have done.

RoboCup 2023 in Bordeaux. Roberto (left) with Bold Hearts teammates.

What are the immediate plans for the team?

We are now thinking about joining the simulation competition, which is part of our league. It takes place in the winter season and we’re planning on joining to work on our software. The transition between simulation and hardware is quite hard. You need a good simulation base to be able to transfer directly the knowledge to the robot. We’re working on having a very good simulation so we can transfer, at least more easily, the knowledge learnt in simulation to the robots.

RoboCup is moving more towards AI and learning, which we can see in the 3d simulation. The robots learn a lot of the motion through reinforcement learning, for example. In the physical leagues it’s not as easy as we have to transfer that to the real world, where there is play in the joints, there’s backlash, there’s play in the 3d parts – there are a lot of variables that are not taken into account in simulations.

How has being part of RoboCup inspired your studies and research?

Every time I go to RoboCup I come out thinking about what I’m going to do next. I couldn’t be more inspired. It’s a really intense field but I love it. It makes you want to work really hard and it makes you passionate about science. I did my bachelor’s project related to RoboCup, I joined a master’s course on robotics, I keep asking my Professors if they want to start a team back in Portugal. I’m going to do my master’s thesis on robotics, on humanoids. I think humanoids are a very complex and interesting challenge. There is no one single solution.

About Roberto

Roberto Figueiredo is a Portuguese, AI-focused computer scientist with a bachelor’s degree from the University of Hertfordshire. He currently pursuing a master’s in Robotics and Intelligent Systems from the University of Aveiro, and is passionate about advancing his expertise in robotics. He has long been very enthusiastic about robots and AI, being a participant in RoboCup since 2016 in the Rescue Simulation league. He has since become local representative for the Rescue League in Portugal and joined a Major team, Bold Hearts, in the Kid Size league, one of the most challenging in RoboCup Humanoid Soccer.

As this year’s RoboCup draws to a close, we take a look back at some of the highlights from the second half of the conference. Over the course of the weekend, the event focussed on the latter stages of the competitions, with the winners in all the different leagues decided. If you missed our round-up of the first half of RoboCup, you can catch up here.

#robocup2023 Day 5: Today the finalists will be known! It will be a day of intense games. #robocup #robotics pic.twitter.com/AL38hRPlyN

— Asad Norouzi (@asadnorouzi) July 8, 2023

#Robocup2023 ?
C’est parti ! Nos équipes néo-aquitaines ont fait leur entrée dans la @RoboCupJuniorFr ! Rescue Line, Rescue Maze, Soccer, On stage… les élèves représentent la France dans les différentes ligues de cette compétition internationale ?? On est tous derrière vous ? pic.twitter.com/w6AeKowGos

— Région académique Nouvelle-Aquitaine (@RANouvAquitaine) July 8, 2023

Time is flying when you are having fun. So we captured some shots for you of day 2. You don't want to miss out on the highlights and thrilling moments at Robocup 2023. https://t.co/IrKOJ5eMbI#Soccer #Team #Tue #Robocup2023 #Worldcup #Champions #Bordeaux #Techunited

— Tech United (@TechUnited) July 8, 2023

#robocup2023 Day 6: This is the final day of the competitions! The finalists are prepared to show their best. The engineering and AI behind every action and decision is amazing. It is great to see how much we have evolved since 1997. #robocup #robotics pic.twitter.com/eNvyVz6tbK

— Asad Norouzi (@asadnorouzi) July 9, 2023

Our NimbRo soccer robots won the Humanoid AdultSize final 8:0 vs. HERoEHS (Korea). #RoboCup2023https://t.co/Pn7WCDzSAR pic.twitter.com/MxVeUN6nmA

— Sven Behnke (@SvenBehnke) July 9, 2023

Por fin hemos podido transmitir una final de SSL en las finales mundiales de #Robocup2023, impresionante el nivel y sobre todo la espectacularidad de la categoría. https://t.co/yV6Q1fjq5Y

— liga de robots (@liga_de_robots) July 9, 2023

Super proud of a successful RoboCup for our LCASTOR team! #RoboCup2023

We have learned a lot from this experience, made new friends and connections, and are looking forward to improving our robotics solutions for the next year! @LCAS_UoL @UoLScience pic.twitter.com/XXurKTxWGf

— Francesco (@fdelduchetto) July 10, 2023

フランスで開催のAI・ロボット技術チャレンジRoboCup(ロボカップ)世界大会のAIヒト型 #二足歩行ロボット サッカー部門60cm以下クラスは、日本代表のCIT Brains(千葉工業大学)は準優勝で、フランスのRhoban(ボルドー大学)が優勝でした。#robocup2023 #千葉工業大学 #robotics pic.twitter.com/8aum3YcLnJ

— Yoshihiro Shibata (@shiba_8ro) July 10, 2023

They have done it again: World Champions! ? Huge congratulations to our TechUnited Eindhoven team for winning the world title at #RoboCup2023 with their soccer robots!
?https://t.co/4BduZlYRLU#ai #robotics pic.twitter.com/VFOd9fCQ5D

— TU/e Artificial Intelligence Systems Institute (@TUeEAISI) July 10, 2023

Felicidades a los alumnos del #Cideb de la @uanl y los maestros asesores Erick y Héctor por ganar el primer lugar en la categoría “Rescue Rapidly Manufactured Robot Challenge” del Torneo Internacional de #Robótica #RoboCup2023 celebrado en Burdeos #Francia #OrgulloUANL pic.twitter.com/bVF4kaEpQh

— Informativo365 (@Informativo3651) July 9, 2023

#robocup2023 Here is short video (longer version will be available later) of robot vs human soccer game. Robots are completely autonomous without any human intervention. #robotics #robocup pic.twitter.com/9p5jZkbEOH

— Asad Norouzi (@asadnorouzi) July 9, 2023

This year’s RoboCup kicked off on 4 July and will run until 10 July. Taking place in Bordeaux, the event will see around 2500 participants, from 45 different countries take part in competitions, training sessions, and a symposium. Find out what attendees have been up to in preparation for, and in the first half of, the event.

Bags are packed, best of luck to our staff/students competing this week @RoboCup 2023 @maynoothuni @MU_research @MU_CompSci #bordeaux @scienceireland#robocup #robocupspl #STEM #ROBOCUP23 #Robotics @RudiVilling @ralf_bierighttps://t.co/TE9hWXh2Zb pic.twitter.com/fGb5aPDcgi

— MU Engineering (@MaynoothEEng) July 1, 2023

Integrantes de #Gentlebots, que están compitiendo estos días en Burdeos Francia pic.twitter.com/kdsjG0F8h0

— Intelligent Robotics Lab URJC (@IntellRobotLabs) July 5, 2023

Bold Hearts setup day ?@RoboCup2023 #robocup2023 #robotsoccer @UniofHerts pic.twitter.com/G0XhQrNdhs

— Bold Hearts (@BoldHeartsUH) July 4, 2023

@RoboCup2023 Setup Day 1! Teams are arriving. The arenas are being prepared. Thousands of robiticists and robots are gathering here for another round of RoboCup!! Let’s RoboCup ? #robocup2023 #Robotics pic.twitter.com/L6wr8tZtVw

— Asad Norouzi (@asadnorouzi) July 4, 2023

#robocup2023 Day 2: Robots performing their final tests before the first day of the competitions. #robocup pic.twitter.com/Q8GjQ4xIR3

— Asad Norouzi (@asadnorouzi) July 5, 2023

Preparando el streaming de la #Robocup2023 desde #Burdeos pic.twitter.com/7NZNgk9VOf

— liga de robots (@liga_de_robots) July 6, 2023

Last preparations for the world championship in Bordeaux! #RoboCup2023 @naoteamhumboldt @HumboldtUni @RobocupSpl #BerlinUnitedhttps://t.co/xSrpmMqVgq pic.twitter.com/GprJNZ7gqM

— Adaptive Systems Group (@adapt_berlin) July 6, 2023

https://t.co/aDysJ9xU68 #RoboCup #RoboCup2023 set-up days #robotics by @TechU

— Loy (@loybeek) July 6, 2023

Wishing all the best to Team ORIon-UTBMan as they compete at #RoboCup2023 in France! ? After two days of rigorous testing and preparation, this incredible joint robotics team from @UniofOxford and UTBMan is ready to shine?? #TeamORIonUTBMan pic.twitter.com/6AsXxUHgN9

— Oxford Robotics Institute (@oxfordrobots) July 6, 2023

First day at #RoboCup2023 pic.twitter.com/pOA3FzdqxU

— Miguel Santamarta (@miggsant) July 4, 2023

Training #ARTEMIS #humanoid #robot for #RoboCup2023 in Bordeaux, France
??
Go Team RoMeLa! ?@RoboCup2023 @robocup_org @RoMeLaUCLA @UCLAengineering pic.twitter.com/yuvPVTw4ZY

— Dennis Hong (@DennisHongRobot) July 2, 2023

? On vous propose de revivre les moments forts de ce premier jour de RoboCup23 : vous venez avec nous ? ?

Rendez-vous demain pour la suite ! ?@univbordeaux @robocup_org @BxMetro @NvelleAquitaine @AcBordeaux @united_robotics @Festo_FR @MathWorks @Airbus pic.twitter.com/Z2Cq1I7Gs1

— RoboCup2023 Bordeaux (@RoboCup2023) July 6, 2023

On the first competition day of #RoboCup2023, our NimbRo soccer robots clearly won the Drop-In tournament of the Humanoid AdultSize league. They scored 26:0 goals in four games.
Further info: https://t.co/Pn7WCDzSAR pic.twitter.com/3AVYG2MSHh

— Sven Behnke (@SvenBehnke) July 7, 2023

Humanoides teen size en rondas preliminares #Robocup2023 pic.twitter.com/884HLUntQg

— liga de robots (@liga_de_robots) July 6, 2023

The leagues and their competitions

The league competitions will take place on 6-9 July. You can find out more about the different leagues at these links:

• RoboCupSoccer
  • Humanoid
  • Standard platform
  • Middle size
  • Small size
  • Simulation
• RoboCupRescue
  • Robot
  • Simulation
• RoboCup@Home
  • This league comprises: Open platform, Domestic standard platform, and Social standard platform
• RoboCupIndustrial
  • RoboCup@Work
  • Logistics
• RoboCupJunior
  • Soccer
  • Onstage
  • Rescue

Symposium

The RoboCup symposium will take place on 10 July. The programme can be found here.

There will be three keynote talks:

• Cynthia Breazeal, Social Robots: Reflections and Predictions of Our Future Relationship with Personal Robots
• Ben Moran and Guy Lever, Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning
• Laurence Devillers, Socio-affective robots: ethical issues

Find out more at the event website.

On 9 December, CLAIRE and euRobotics jointly hosted an All Questions Answered (AQuA) event. This one hour session focussed on humanoid robotics, and participants could ask questions regarding the current and future state of AI, robotics and human augmentation in Europe.

The questions were fielded by an expert panel, comprising:

• Rainer Bischoff, euRobotics
• Wolfram Burgard, Professor of Robotics and AI, University of Technology Nuremberg
• Francesco Ferro, CEO, PAL Robotics
• Holger Hoos, Chair of the Board of Directors, CLAIRE

The session was recorded and you can watch in full below:

Teleoperation is one of the longest-standing application fields in robotics. While full autonomy is still work in progress, the possibility to remotely operate a robot has already opened scenarios where humans can act in risky environments without endangering their own safety, such as when defusing explosives or decommissioning nuclear waste. It also allows one to be present and act even at great distance: underwater, in space, or inside a patient miles away from the surgeon. These are all critical applications, where skilled and qualified operators control the robot after receiving specific training to learn to use the system safely.

Teleoperation for everyone?

The recent pandemic has yet made even more apparent the need for immersive telepresence and remote action also for non-expert users: not only could teleoperated robots take vitals or bring drugs to infectious patients, but we could assist our elderly living far away with chores like moving heavy stuff, or cooking, for example. Also, numerous physical jobs could be executed from home.

The recent ANA-Xprize finals have shown how far teleoperation can go (see this impressive video of the winning team), but in such situations both the perceptual and control load lie entirely on the operator. This can be quite taxing on a cognitive level: both perception and action are mediated, by cameras and robotic arms respectively, reducing the user’s situation awareness and natural eye-hand coordination. While robot sensing capabilities and actuators have undergone relevant technological progress, the interface with the user still lacks intuitive solutions facilitating the operator’s job (Rea & Seo, 2022).

Human and robot joining forces

Shared control has gained popularity in recent years, as an approach championing human-machine cooperation: low-level motor control is carried out by the robot, while the human is focused on high-level action planning. To achieve such a blend, the robotic system still needs a timely way to infer the operator intention, so as to consequently assist with the execution. Usually, motor intentions are inferred by tracking arm movements or motion control commands (if the robot is operated by means of a joystick), but especially during object manipulation the hand is tightly following information collected by the gaze. In the last decades, increasing evidence in eye-hand coordination studies has shown that gaze reliably anticipates the hand movement target (Hayhoe et al., 2012), providing an early cue about human intention.

Gaze and motion features to estimate intentions

In a contribution presented at IROS 2022 last month (Belardinelli et al., 2022), we introduced an intention estimation model that relies on both gaze and motion features. We collected pick-and-place sequences in a virtual environment, where participants could operate two robotic grippers to grasp objects on a cluttered table. Motion controllers were used to track arm motions and to grasp objects by button press. Eye movements were tracked by the eye-tracker embedded in the virtual reality headset.

Gaze features were computed by defining a Gaussian distribution centered at the gaze position and taking for each object the likelihood for it to be the target of visual attention, which was given by the cumulative distribution collected by the object bounding box. For the motion features, the hand pose and velocity were used to estimate the hand’s current trajectory which was compared to an estimated optimal trajectory to each object. The normalized similarity between the two trajectories defined the likelihood of each object to be the target of the current movement.

Figure 1: Gaze features (top) and motion features (bottom) used for intention estimation. In both videos the object highlighted in green is the most likely target of visual attention and of hand movement, respectively.

These features along with the binary grasping state were used to train two Gaussian Hidden Markov Models, one on pick and one on place sequences. For 12 different intentions (picking of 6 different objects and placing at 6 different locations) the general accuracy (F1 score) was above 80%, even for occluded objects. Importantly, for both actions already 0.5 seconds before the end of the movement a prediction with over 90% accuracy was available for at least 70% of the observations. This would allow for an assisting plan to be instantiated and executed by the robot.

We also conducted an ablation study to determine the contribution of different feature combinations. While the models with gaze, motion, and grasping features performed better in the cross validation, the improvement with respect to only gaze and grasping state was minimal. Even when checking obstacles nearby at first, in fact, the gaze was already on the target before the hand trajectory became sufficiently discriminative.

We also ascertained that our models could generalize from one hand to the other (when fed the corresponding hand motion features), hence the same models could be used to concurrently estimate each hand intention. By feeding each hand prediction to a simple rule-based framework, basic bimanual intentions could also be recognized. So, for example, reaching for an object with the left hand while the right hand is going to place the same object on the left hand is considered a bimanual handover.

Figure 2: Online intention estimation: the red frame denotes the current right-hand intention prediction, the green frame the left-hand prediction. Above the scene, the bimanual intention is shown in capital letters.

Such an intention estimation model could help an operator to execute such manipulations without focusing on selecting the parameters for the exact motor execution of the pick and place, something we don’t usually do consciously in natural eye-hand coordination, since we automated such cognitive processes. For example, once a grasping intention is estimated with enough confidence, the robot could autonomously select the best grasp and grasping position and execute the grasp, relieving the operator of carefully monitoring a grasp without tactile feedback and possibly with inaccurate depth estimation.

Further, even if in our setup motion features were not decisive for early intention prediction, they might play a larger role in more complex settings and when extending the spectrum of bimanual manipulations.

Combined with suitable shared control policies and feedback visualizations, such systems could also enable untrained operators to control robotic manipulators transparently and effectively for longer times, improving the general mental workload of remote operation.

References

Belardinelli, A., Kondapally, A. R., Ruiken, D., Tanneberg, D., & Watabe, T. (2022). Intention estimation from gaze and motion features for human-robot shared-control object manipulation. 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022.

Hayhoe, M. M., McKinney, T., Chajka, K., & Pelz, J. B. (2012). Predictive eye movements in natural vision. Experimental brain research, 217(1), 125-136.

Rea, D. J., & Seo, S. H. (2022). Still Not Solved: A Call for Renewed Focus on User-Centered Teleoperation Interfaces. Frontiers in Robotics and AI, 9.

By Steve Lundeberg

Cassie the robot, invented at the Oregon State University College of Engineering and produced by OSU spinout company Agility Robotics, has established a Guinness World Record for the fastest 100 metres by a bipedal robot.

Cassie clocked the historic time of 24.73 seconds at OSU’s Whyte Track and Field Center, starting from a standing position and returning to that position after the sprint, with no falls.

The 100-metre record builds on earlier achievements by the robot, including traversing five kilometres in 2021 in just over 53 minutes. Cassie, the first bipedal robot to use machine learning to control a running gait on outdoor terrain, completed the 5K on Oregon State’s campus untethered and on a single battery charge.

Cassie was developed under the direction of Oregon State robotics professor Jonathan Hurst. The robot has knees that bend like an ostrich’s and operates with no cameras or external sensors, essentially as if blind.

Since Cassie’s introduction in 2017, in collaboration with artificial intelligence professor Alan Fern, OSU students have been exploring machine learning options in Oregon State’s Dynamic Robotics and AI Lab.

“We have been building the understanding to achieve this world record over the past several years, running a 5K and also going up and down stairs,” said graduate student Devin Crowley, who led the Guinness effort. “Machine learning approaches have long been used for pattern recognition, such as image recognition, but generating control behaviors for robots is new and different.”

The Dynamic Robotics and AI Lab melds physics with AI approaches more commonly used with data and simulation to generate novel results in robot control, Fern said. Students and researchers come from a range of backgrounds including mechanical engineering, robotics and computer science.

“Cassie has been a platform for pioneering research in robot learning for locomotion,” Crowley said. “Completing a 5K was about reliability and endurance, which left open the question of, how fast can Cassie run? That led the research team to shift its focus to speed.”

Cassie was trained for the equivalent of a full year in a simulation environment, compressed to a week through a computing technique known as parallelization – multiple processes and calculations happening at the same time, allowing Cassie to go through a range of training experiences simultaneously.

“Cassie can perform a spectrum of different gaits but as we specialized it for speed we began to wonder, which gaits are most efficient at each speed?” Crowley said. “This led to Cassie’s first optimized running gait and resulted in behavior that was strikingly similar to human biomechanics.”

The remaining challenge, a “deceptively difficult” one, was to get Cassie to reliably start from a free-standing position, run, and then return to the free-standing position without falling.

“Starting and stopping in a standing position are more difficult than the running part, similar to how taking off and landing are harder than actually flying a plane,” Fern said. “This 100-metre result was achieved by a deep collaboration between mechanical hardware design and advanced artificial intelligence for the control of that hardware.”

Hurst, chief technology officer at Agility Robotics and a robotics professor at Oregon State, said: “This may be the first bipedal robot to learn to run, but it won’t be the last. I believe control approaches like this are going to be a huge part of the future of robotics. The exciting part of this race is the potential. Using learned policies for robot control is a very new field, and this 100-metre dash is showing better performance than other control methods. I think progress is going to accelerate from here.”

RoboCup is an international scientific initiative with the goal of advancing the state of the art of intelligent robots, AI and automation. The annual RoboCup event returned to an in-person format for 2022, taking place from 13-17 July in Bangkok. RoboCup comprises a number of leagues, with perhaps the most well-known being the soccer leagues.

In the Humanoid League, autonomous robots with a human-inspired body plan and senses play soccer against each other. We spoke to Jasper Güldenstein, a member of the technical committee, about the competition at RoboCup 2022, and also about the Humanoid League Virtual Season. As a biweekly virtual competition taking place between the physical RoboCup events it provides teams with an opportunity to test their ideas and keep in touch throughout the year.

Could you give us an overview of the Humanoid League competition at RoboCup this year?

This year we had the first in-person event after a three year break. It was really good to have the majority of the teams coming back together and working on their robots again. Although a lot of teams came with fewer participants than they usually do, we still managed to have 12 teams in the kid size league and three teams in the adult size. Unfortunately, some teams could not participate due to travel restrictions, but we hope to see them back next year.

Humanoid league finalists with their robots

What was the format for the competition?

At the beginning we had a drop-in round, which is where we play games with one robot from each team participating in a joint team. So, we have eight robots playing from eight different teams. That is useful for finding out which teams are likely to perform the best in the competition. Next, the results from the drop-in games were used as seeding for the round robin phase of the regular competition, with the strongest teams separated into different groups. After the round robin, we have a knockout competition. The seeding method means that we can hopefully avoid the situation where very good teams get kicked out early. We saw that the most interesting games were towards the end of the competition when the teams performed really well.

Have you noticed improvements since the last physical competition?

I’d say definitely that one big thing that has improved for a lot of teams is the localisation. A lot of teams are more easily able to localise themselves on the field, and they don’t run off randomly. They are more certain that they are in the correct position.

Furthermore, I think the kicking has improved. The robots kick the ball much further than they used to. People have been tuning their kicking motions to increase the distance.

In terms of computer vision, this has definitely improved quite a bit. Something we did differently this time, which was inspired by what we did in the virtual season, is that we had a set of six different balls, all from previous FIFA competitions. For each game a ball was drawn randomly, so the teams couldn’t really prepare for all the balls. Although they were visually quite different, the teams didn’t really have any problems detecting the ball. We’ve seen, in general, that computer vision approaches have improved and these improvements have been transferred to the RoboCup competition. I think that almost all teams are using a neural network to detect the ball. This is a change from three, four, five years ago, where many teams used hand-tuned classical computer vision algorithms.

To talk a bit more about ball detection, it will be interesting to see what happens if we move to an environment with natural and/or varying light conditions. This year we were in a convention hall with uniform lighting. I believe next year, in Bordeaux, there is going to be some form of natural light coming in, and perhaps even fields that are outside. It’s still at the planning stage but we are looking forward to that. It will be a challenge and I strongly believe that the participants will find approaches to make their vision approach robust against these varying conditions.

The setup and testing for the Humanoid League competition at RoboCup 2022, Bangkok.

Thinking about the transfer from the simulation to the real world, are there any specific elements that lend themselves well to being transferred?

In terms of computer vision, we had a bit of transfer. In the virtual season we concentrated a lot on changing the lighting conditions and having varied backgrounds, to be able to emulate the real world a bit better. I think a few teams used their vision approaches from the virtual season in the real world.

However, I think the strongest part is behaviour. Teams were able to test their strategies in the virtual competition and adapt every other week. For example, CIT Brains, which won the virtual season and the physical competition, made quite a few changes to their strategy and they had robust systems running. Their strategy worked really well, and in the final they managed to score several goals win against the previous world champions (Rhoban Football Club).

How did the competition go for your team (Hamburg Bit-Bots)?

We actually had quite a few hardware problems, especially on the mechanics side. The motors are wearing out and warped due to wear, and flexed more than we expected. This meant we had difficulties walking stably. And, if you can’t walk in a stable manner that defeats the purpose of everything else. It’s a really integrated system – if one component breaks, you are out of luck as you are very restricted in what you can change during the competition as you don’t have much spare equipment with you.

However, what was good for us was that we had a lot of software up and running, and a lot of it had been tested really well during the virtual league. We had to try and find a way round the walking problem algorithmically, to try to find walking parameters that were more stable. We also switched from [robot operating system] ROS 1 to ROS 2 which brought with it many challenges. We actually did a write up on the issues we faced, with some tricks and tips.

Will there be a new virtual league season this year?

Yes, we’ve discussed this in our technical committee and we plan on doing it again. The last event was successful and the teams enjoyed it. We plan on making some changes, such as logging the games to extract some interesting metrics and doing some analysis on those.

Another thing we want to do is domain randomisation, making the environment a bit more varied. This means that the approaches have to be more robust. The hope is that, when they are more robust, they can be transferred more easily to the real world. We were thinking about making the terrain slightly uneven. Another approach could be to modify the models of the robots such that the joints emulate a bit of wear, so they simulated actuators might be a bit weaker or stronger randomly, and teams have to find robust approaches to deal with that.

We won’t do everything at the beginning. We’ll move through the season and talk to the teams and form some organising groups to develop the simulation further, to run the games and to organise the competition itself. We are always happy to have input and we always talk to the teams to see what they think. It’s a competition but it’s something we build together.

Humanoid robots at RoboCup 2022, Bangkok.

Could you tell us about the satellite event that took place at RoboCup?

This was a discussion about how to get teams more interested in participating and how to bridge the junior leagues and the major leagues.

We know that some people who participated in RoboCup Junior specifically selected a University that has a RoboCup team so that they could join that team. It would be awesome for more people to do this, and for more juniors to know what the major league is about.

To bridge the gap between the junior and major leagues we don’t want to introduce another league, but we want some form of events where the two groups can meet, and where the juniors can show off how well they are doing. It would be good to have more interaction between the leagues, although we haven’t decided on the exact format yet.

About Jasper

Jasper Güldenstein is a PhD student at University of Hamburg. His research focuses on humanoid navigation. He has been participating in RoboCup as a member of the Hamburg Bit-Bots since 2016 where his focus is developing not only the software of the team but also the electronics of the robot platform. In his recent master thesis he evaluated using reinforcement learning to perform path planning and execution for humanoid robots.

The 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence (IJACI-ECAI 2022) took place from 23-29 July, in Vienna. In this post, we summarise the presentation by Ana Paiva, University of Lisbon and INESC-ID. The title of her talk was “Engineering sociality and collaboration in AI systems”.

Robots are widely used in industrial settings, but what happens when they enter our everyday world, and, specifically, social situations? Ana believes that social robots, chatbots and social agents have the potential to change the way we interact with technology. She envisages a hybrid society where humans and AI systems work in tandem. However, for this to be realised we need to carefully consider how such robots will interact with us socially and collaboratively. In essence, our world is social, so when machines enter they need to have some capabilities to interact with this social world.

Ana took us through the theory of what it means to the social. There are three aspects to this:

1. Social understanding: the capacity to perceive others, exhibit theory of mind and respond appropriately.
2. Intrapersonal competencies: the capability to communicate socially, establish relationships and adapt to others.
3. Social responsibility: the capability to take actions towards the social environment, follow norms and adopt morally appropriate actions.

Screenshot from Ana’s talk.

Ana wants to go from this notion of social intelligence to what is called artificial social intelligence, which can be defined as: “the capability to perceive and understand social signals, manage and participate in social interactions, act appropriately in social settings, establish social relations, adapt to others, and exhibit social responsibility.”

As an engineer, she likes to build things, and, on seeing the definition above, wonders how she can pass from said definition to a model that will allow her to build social machines. This means looking at social perception, social modelling and decision making, and social acting. A lot of Ana’s work revolves around design, study and development for achieving this kind of architecture.

Ana gave us a flavour of some of the projects that she and her groups have carried out with regards to trying to engineer sociality and collaboration in robots and other agents.

One of these projects was called “Teach me how to write”, and it centres on using robots to improve the handwriting abilities of children. In this project the team wanted to create a robot that kids could teach to write. Through teaching the robot it was hypothesised that they would, in turn, improve their own skills.

The first step was to create and train a robot that could learn how to write. They used learning from demonstration to train a robotic arm to draw characters. The team realised that if they wanted to teach the kids to write, the robot had to learn and improve, and it had to make mistakes in order to be able to improve. They studied the taxonomy of handwriting mistakes that are made by children, so that they could put those mistakes into the system, and so that the robot could learn from the kids how to fix the mistakes.

You can see the system architecture in the figure below, and it includes the handwriting task element, and social behaviours. To add these social behaviours they used a toolkit developed in Ana’s lab, called FAtiMA. This toolkit can be integrated into a framework and is an affective agent architecture for creating autonomous characters that can evoke empathic responses.

Screenshot from Ana’s talk. System architecture.

In terms of actually using and evaluating the effectiveness of the robot, they couldn’t actually put the robot arm in the classroom as it was too big, unwieldy and dangerous. Therefore, they had to use a Nao robot, which moved its arms like it was writing, but it didn’t actually write.

Taking part in the study were 24 Portuguese-speaking children, and they participated in four sessions over the course of a few weeks. They assigned the robot two contrasting competencies: “learning” (where the robot improved over the course of the sessions) and “non-learning” (where the robot’s abilities remained constant). They measured the kids’ writing ability and improvement, and they used questionnaires to find out what the children thought about the friendliness of the robot, and their own teaching abilities.

They found that the children who worked with learning robot significantly improved their own abilities. They also found that the robot’s poor writing abilities did not affect the children’s fondness for it.

You can find out more about this project, and others, on Ana’s website.

Using fluids for 3D printing may seem paradoxical at first glance, but not all fluids are watery. Many useful materials are more viscous, from inks to hydrogels, and thus qualify for printing. Yet their potential has been relatively unexplored due to the limited control over their behaviour. Now, researchers of the Bickel group at the Institute of Science and Technology Austria (ISTA) are employing machine learning in virtual environments to achieve better results in real-world experiments.

3D printing is on the rise. Many people are familiar with the characteristic plastic structures. However, attention has also turned to different printing materials, such as inks, viscous pastes and hydrogels, which could be potentially be used to 3D-print biomaterials and even food. But printing such fluids is challenging. Exact control over them requires painstaking trial-and-error experiments, because they typically tend to deform and spread after application.

A team of researchers, including Michal Piovarči and Bernd Bickel, are tackling these challenges. In their laboratories at the Institute of Science and Technology Austria (ISTA), they are using reinforcement learning – a type of machine learning – to improve the printing technique of viscous materials. The results were presented at the SIGGRAPH conference, the annual meeting of simulation and visual computing researchers.

A critical component of manufacturing is identifying the parameters that consistently produce high-quality structures. Certainly, an assumption is implicit here: the relationship between parameters and outcome is predictable. However, real processes always exhibit some variability due to the nature of the materials used. In printing with viscous materials, this notion is more prevalent, because they take significant time to settle after deposition. The question is: how can we understand, and deal with, the complex dynamics?

“Instead of printing thousands of samples, which is not only expensive, but rather tedious, we put our expertise in computer simulations to action,” responds Piovarči, lead-author of the study. While computer graphics often trade physical accuracy for faster simulation, here, the team came up with a simulated environment that mirrors the physical processes with accuracy. “We modelled the ink’s current and short-horizon future states based on fluid physics. The efficiency of our model allowed us to simulate hundreds of prints simultaneously, more often than we could ever have done in the experiment. We used the dataset for reinforcement learning and gained the knowledge of how to control the ink and other materials.”

Learning in virtual environments how to control the ink. © Michal Piovarči/ISTA

The machine learning algorithm established various policies, including one to control the movement of the ink-dispensing nozzle at a corner such that no unwanted blobs occur. The printing apparatus would not follow the baseline of the desired shape anymore, but rather take a slightly altered path which eventually yields better results. To verify that these rules can handle various materials, they trained three models using liquids of different viscosity. They tested their method with experiments using inks of various thicknesses.

The team opted for closed-loop forms instead of simple lines or writing, because “closed loops represent the standard case for 3D printing and that is our target application,” explains Piovarči. Although the single-layer printing in this project is sufficient for the use cases in printed electronics, he wants to add another dimension. “Naturally, three dimensional objects are our goal, such that one day we can print optical designs, food or functional mechanisms. I find it fascinating that we as computer graphics community can be the major driving force in machine learning for 3D printing.”

Read the research in full

Closed-Loop Control of Direct Ink Writing via Reinforcement Learning
Michal Piovarči, Michael Foshey, Jie Xu, Timmothy Erps, Vahid Babaei, Piotr Didyk, Szymon Rusinkiewicz, Wojciech Matusik, Bernd Bickel

This Sunday sees the start of the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). This year the event is online and free for anyone to attend. Content will be available from the platform on demand, with access available from 25 October to 25 November 2020.

IROS conferences have traditionally had a theme and this year is no different with the emphasis being on “consumer robotics and our future”. You can sign up here.

Plenaries

IROS will feature three plenary talks. The speakers and topics are as follows:

• Danica Kragic Robotics and artificial intelligence impacts on the fashion industry
• Cynthia Breazeal Living with social robots: from research to commercialization and back
• Yukie Nagai Cognitive development in humans and robots: new insights into intelligence

Keynote speakers

There are also nine keynote talks covering a number of topics.

• Frank Dellaert Air, sea, and space robots
• Anya Petrovskaya Driverless vehicles and field robots
• Ashish Deshpande Rehabilitation robotics
• Jonathan Hurst Humanoids
• I-Ming Chen Food handling robotics
• Steve LaValle Perception, action and control
• Nikolaus Correll Grasping, haptics and end-effectors
• Andrea Thomaz Human-robot interaction
• Sarah Bergbreiter Design, micro and bio-inspired robotics

Technical talks

The technical talks have been divided into 12 topic areas.

• Air, sea, and space robots
• Driverless vehicles and field robots
• Medical, cellular, micro and nano robots
• Humanoids, exoskeletons, and rehab robots
• Localization, mapping and navigation
• Dynamics, control and learning
• Design, mechanisms, actuators, soft and bio-inspired robots
• Perception, action, and cognition
• Grasping, haptics and end-effectors
• Human-robot interaction, teleoperation, and virtual reality
• Swarms and multi-robots
• Industry 4.0

Each talk will feature its digest slide, pre-recorded video presentation, and the paper’s PDF. These will be available from 25 October, so keep an eye on the website.

Workshops

There are a whopping 35 workshops to choose from. These have on-demand content and also live sessions (dates vary so visit the webpages below for more information about each specific workshop).

1. 3rd workshop on proximity perception in robotics: towards multi-modal cognition, Stefan Escaida Navarro*, Stephan Mühlbacher-Karrer, Hubert Zangl, Keisuke Koyama, Björn Hein, Ulrike Thomas, Hosam Alagi, Yitao Ding, Christian Stetco
2. Bringing geometric methods to robot learning, optimization and control, Noémie Jaquier*, Leonel Rozo, Søren Hauberg, Hans-Peter Schröcker, Suvrit Sra
3. 12th IROS20 workshop on planning, perception and navigation for intelligent vehicles, Philippe Martinet*, Christian Laugier, Marcelo H Ang Jr, Denis Fernando Wolf
4. Robot-assisted training for primary care: how can robots help train doctors in medical examinations?, Thrishantha Nanayakkara*, Florence Ching Ying Leong, Thilina Dulantha Lalitharatne, Liang He, Fumiya Iida, Luca Scimeca, Simon Hauser, Josie Hughes, Perla Maiolino
5. Workshop on animal-robot interaction, Cesare Stefanini and Donato Romano*
6. Ergonomic human-robot collaboration: opportunities and challenges, Wansoo Kim*, Luka Peternel, Arash Ajoudani, Eiichi Yoshida
7. New advances in soft robots control, Concepción A. Monje*, Egidio Falotico, Santiago Martínez de la Casa
8. Autonomous system in medicine: current challenges in design, modeling, perception, control and applications, Hang Su, Yue Chen*, Jing GUO, Angela Faragasso, Haoyong Yu, Elena De Momi
9. MIT MiniCheetah workshop, Sangbae Kim*, Patrick M. Wensing, Inhyeok Kim
10. Workshop on humanitarian robotics, Garrett Clayton*, Raj Madhavan, Lino Marques
11. Robotics-inspired biology, Nick Gravish*, Kaushik Jayaram, Chen Li, Glenna Clifton, Floris van Breugel
12. Robots building robots. Digital manufacturing and human-centered automation for building consumer robots, Paolo Dario*, George Q. Huang, Peter Luh, MengChu Zhou
13. Cognitive robotic surgery, Michael C. Yip, Florian Richter*, Danail Stoyanov, Francisco Vasconcelos, Fanny Ficuciello, Emmanuel B Vander Poorten, Peter Kazanzides, Blake Hannaford, Gregory Scott Fischer
14. Application-driven soft robotic systems: Translational challenges, Sara Adela Abad Guaman, Lukas Lindenroth, Perla Maiolino, Agostino Stilli*, Kaspar Althoefer, Hongbin Liu, Arianna Menciassi, Thrishantha Nanayakkara, Jamie Paik, Helge Arne Wurdemann
15. Reliable deployment of machine learning for long-term autonomy, Feras Dayoub*, Tomáš Krajník, Niko Sünderhauf, Ayoung Kim
16. Robotic in-situ servicing, assembly, and manufacturing, Craig Carignan*, Joshua Vander Hook, Chakravarthini Saaj, Renaud Detry, Giacomo Marani
17. Benchmarking progress in autonomous driving, Liam Paull*, Andrea Censi, Jacopo Tani, Matthew Walter, Felipe Codevilla, Sahika Genc, Sunil Mallya, Bhairav Mehta
18. ROMADO: RObotic MAnipulation of Deformable Objects, Miguel Aranda*, Juan Antonio Corrales Ramon, Pablo Gil, Gonzalo Lopez-Nicolas, Helder Araujo, Youcef Mezouar
19. Perception, learning, and control for autonomous agile vehicles, Giuseppe Loianno*, Davide Scaramuzza, Sertac Karaman
20. Planetary exploration robots: challenges and opportunities, Hendrik Kolvenbach*, William Reid, Kazuya Yoshida, Richard Volpe
21. Application-oriented modelling and control of soft robots, Thomas George Thuruthel*, Cosimo Della Santina, Seyedmohammadhadi Sadati, Federico Renda, Cecilia Laschi
22. State of the art in robotic leg prostheses: where we are and where we want to be, Tommaso Lenzi*, Robert D. Gregg, Elliott Rouse, Joost Geeroms
23. Worskhop on perception, planning and mobility in forestry robotics (WPPMFR 2020), João Filipe Ferreira* and David Portugal
24. Why robots fail to grasp? – failure ca(u)ses in robot grasping and manipulation, Joao Bimbo*, Dimitrios Kanoulas, Giulia Vezzani, Kensuke Harada
25. Trends and advances in machine learning and automated reasoning for intelligent robots and systems, Abdelghani Chibani, Craig Schlenoff, Yacine Amirat*, Shiqi Zhang, Jong-Hwan Kim, Ferhat Attal
26. Learning impedance modulation for physical interaction: insights from humans and advances in robotics, Giuseppe Averta*, Franco Angelini, Meghan Huber, Jongwoo Lee, Manolo Garabini
27. New horizons of robot learning – from industrial challenges to future capabilities, Kim Daniel Listmann* and Elmar Rueckert
28. Robots for health and elderly care (RoboHEC), Leon Bodenhagen*, Oskar Palinko, Francois Michaud, Adriana Tapus, Julie Robillard
29. Wearable SuperLimbs: design, communication, and control, Harry Asada*
30. Human Movement Understanding for Intelligent Robots and Systems, Emel Demircan*, Taizo Yoshikawa, Philippe Fraisse, Tadej Petric
31. Construction and architecture robotics, Darwin Lau*, Yunhui Liu, Tobias Bruckmann, Thomas Bock, Stéphane Caro
32. Mechanisms and design: from inception to realization, Hao Su*, Matei Ciocarlie, Kyu-Jin Cho, Darwin Lau, Claudio Semini, Damiano Zanotto
33. Bringing constraint-based robot programming to real-world applications, Wilm Decré*, Herman Bruyninckx, Gianni Borghesan, Erwin Aertbelien, Lars Tingelstad, Darwin G. Caldwell, Enrico Mingo, Abderrahmane Kheddar, Pierre Gergondet
34. Managing deformation: a step towards higher robot autonomy, Jihong Zhu*, Andrea Cherubini, Claire Dune, David Navarro-Alarcon
35. Social AI for human-robot interaction of human-care service robots, Ho Seok Ahn*, Hyungpil Moon, Minsu Jang, Jongsuk Choi

Robot challenges

Another element of the conference that sounds interesting is the robot challenges. There are three of these and you should be able to watch the competitions in action next week.

1. Open cloud robot table organization challenge (OCRTOC). This competition focusses on table organisation tasks. Participants will need to organize the objects in the scene according to a target configuration. This competition will be broadcast on 25-27 October.
2. 8th F1Tenth autonomous Grand Prix @ IROS 2020. This competition will take the form of a virtual race with standardised vehicles and hardware. The qualifying phase is a timed trial. The Grand Prix phase pits virtual competitors against each other on the same track. The race will be broadcast on 27 October.
3. Robotic grasping and manipulation competition. There are two sections to this competition. In the first the robot has to make five cups of iced Matcha green tea. The second involves disassembly and assembly using a NIST Task Board.

This year the International Conference on Robotics and Automation (ICRA) is being run as a virtual event. One interesting feature of this conference is that it has been extended to run from 31 May to 31 August. A number of workshops were held on the opening day and here we focus on two of them: “Learning of manual skills in humans and robots” and “Emerging learning and algorithmic methods for data association in robotics”.

Learning of manual skills in humans and robots

This workshop was organised by Aude Billard, EPFL and Dagmar Sternad, Northeastern University. It brought together researchers from human motor control and from robotics to answer questions such as: How do humans achieve manual dexterity? What kind of practice schedules can shape these skills? Can some of these strategies be transferred to robots? To which extent is robot manual skill limited by the hardware, what can be learned and what cannot?

The third session of the workshop focussed on “Learning skills” and you can watch the two talks and the discussions below:

Jeannette Bohg – Learning to scaffold the development of robotic manipulation skills

Dagmar Sternad – Learning and control in skilled interactions with objects: A task-dynamic approach

Discussion with Jeannette Bohg and Dagmar Sternad

Emerging learning and algorithmic methods for data association in robotics

This workshop covered emerging algorithmic methods based on optimization and graph-theoretic techniques, learning and end-to-end solutions based on deep neural networks, and the relationships between these techniques.

You can watch the workshop in full here:

Below is the programme with the times indicating the position of that talk in the YouTube video:
11:00 Ayoung Kim – Learning motion and place descriptor from LiDARs for long-term navigation
34:11 Xiaowei Zhou – Learning correspondences for 3D reconstruction and pose estimation
51:30 Florian Bernard – Higher-order projected power iterations for scalable multi-matching
1:11:24 Cesar Cadena – High level understanding in the data association problem
1:34:55 Spotlight talk 1: Daniele Cattaneo – CMRNet++: map and camera agnostic monocular visual localization in LiDAR maps
1:50:45 Nicholas Roy – The role of semantics in perception
2:11:12 Kostas Daniilidis – Learning representations for matching
2:33:26 Jonathan How – Consistent multi-view data association
2:51:40 John Leonard – A research agenda for robust semantic SLAM
3:17:58 Luca Carlone – Towards certifiably robust spatial perception
3:39:36 Roberto Tron – Fast, consistent distributed matching for robotics applications
3:59:22 Randal Beard – Tracking moving objects from a moving camera in 3d environments
4:18:49 Nikolay Atanasov – A unifying view of geometry, semantics, and data association in SLAM
4:39:03 Spotlight talk 2: Nathaniel Glaser – Enhancing multi-robot perception via learned data association

The YouTube originals series “The Age of A.I.” was released in December 2019. If you haven’t already seen it now could be a good time to catch up – with much of the world in enforced or voluntary isolation many of us will be stuck at home with hours to fill. Sit back and marvel at the many incredible, and often heart-warming, applications of AI.

Episode 1 features researchers Mark Sagar, University of Auckland and Gil Weinberg, Georgia Tech. Mark works with will.i.am on a digital avatar and presents BabyX – a virtual animated baby that learns and reacts like a human baby. Gil makes music using AI and has teamed up other researchers at Georgia Tech to create smart prosthetics for amputees, combining ultrasound signals and machine learning.

Watch the other episodes:
Episode 2: Healed through A.I.

Episode 3: Using A.I. to build a better human

Episode 4: Love, art and stories: decoded

Episode 5: The ‘Space Architects’ of Mars

Episode 6: Will a robot take my job?

Episode 7: Saving the world one algorithm at a time

Episode 8: How A.I. is searching for Aliens

You can access the full series here.