Propeller-powered underwater vehicles have long helped scientists explore and monitor aquatic environments. But they’re limited by their own mechanics: spinning blades can snag on vegetation, stir up sediment, and startle the wildlife they’re often sent to study, making them poorly suited to shallow creeks, dense weeds, or close encounters with fish.

That’s one reason roboticists have spent years building machines that swim like fish instead, bending their bodies rather than spinning a propeller. The catch is that most fish-inspired robots are built for one size and one job, so scaling them up or down usually means starting from scratch.

A team of engineers at EPFL and New York University (NYU) says it has found a way to solve that problem. They’ve unveiled ScaFi (for Scalable Fish), a robot modeled on fish like cod and mackerel. These fish swim by concentrating most of their body bending toward the tail end, a style that, in nature, spans an unusually wide range of body sizes.

“Right now, if you want to monitor a creek and then monitor a lake, you basically need two different robots, built and tested from the ground up,” says Nana Obayashi, first author on the study published in npj Robotics. “The environments we care about don’t come in one size, so we don’t think the tools should either.”

Currently an assistant professor of mechanical and aerospace engineering at the NYU Center for Robotics and Embodied Intelligence, Obayashi led the project while completing her PhD in the Computational Robot Design & Fabrication Lab, led by Josie Hughes, in EPFL’s School of Engineering.

ScaFi at 0.6, 1.1, and 2.9 meters long. 2026 CREATE Lab EPFL. CC BY SA-4.0.

Studying different environments systematically

ScaFi has a rigid front section and a flexible tail made of fiberglass rods. A single motor pulls two tendons that cross near the tail’s end, producing the “S”-shaped bend required for fish-like swimming motion.

The diameter of the rods forming the tail are the only part that must change with the size of the robot. They grow proportionally thicker as the robot scales up, to preserve similar tail-bending behavior. The underlying motor mechanism and crossed-tendon system stay the same.

That matters because it could cut the engineering effort needed to build fish-like robots for different environments. It also gives researchers a platform for studying how swimming performance changes with scale, a question that’s hard to study systematically in animals or custom-made robots alike.

Into the water!

The team built three robots — roughly 0.6, 1.1, and 2.9 meters long — and tested how well each swam. In collaboration with EPFL’s Unsteady Flow Diagnostics Lab, led by Karen Mulleners, the researchers found that the smallest robot produced swirling water patterns similar to those left by real fish, and across all three sizes, swimming motion lined up closely once adjusted for body size. This suggests that that the scaling approach preserved the fish-like gait even as the robots grew nearly fivefold in length.

They also deployed the robots in the field: the medium-sized one in a Swiss stream, the largest on Lake Geneva, the smallest in creeks only 15–30 centimeters deep. During the stream test, the robot kept swimming even after a GPS dropout.

Energy efficiency proved harder to scale. The two smaller robots performed similarly, but the largest was consistently less efficient and needed a different, more powerful motor. The authors suggest drag and inertia may be to blame, though the exact cause is unresolved, meaning the team scaled the swimming motion itself more cleanly than the energy it takes to produce it.

A similar tradeoff showed up in disturbance tests. The smallest robot was most agile but recovered slowest after being knocked off course, while the larger robots were less nimble but more stable.

The same approach, scaling around one key structural parameter, could apply to other compliant robots, including ones outside water. Whether energetic performance can be scaled as successfully as the swimming motion remains an open question.

Funding

This research was partially funded by the European Union’s Horizon 2020 program under Marie Skłodowska-Curie grant agreement No. 945363.

Reference

Obayashi, N., Anastasiadis, A., Gumowski, J. et al. ScaFi: length-scalable, compliant, parametric robotic fish design for operation in multiple environmental niches. npj Robot (2026).

By Celia Luterbacher

Imagine a robot designed to install solar panels with much greater speed and precision than a human. The robot is made from expensive materials and powered by a heavy battery that must be recharged every few hours. If the costs of building and operating the robot outweigh the benefits of the clean energy it helps produce, can it really be considered sustainable?

In a 2025 article published in Science, Aude Billard, head of the Learning Algorithms and Systems Lab in EPFL’s School of Engineering and Academic director of the Robotics Center, gives precisely this example to illustrate the tension between robotic performance and sustainability. Roboticists, she argues, can no longer ignore the fact that robots use energy-intensive power systems and electronic components made from finite resources.

At the same time, robots have the potential to contribute to addressing some of society’s most pressing sustainability challenges, for example through environmental and biodiversity monitoring, precision agriculture, and the maintenance of critical infrastructure like bridges, buildings, and power grids.

“Our ambition is not to simply make robots more sustainable; they must actively contribute to solving sustainability challenges.”

– Mirko Kovač, Laboratory of Sustainability Robotics

Beyond sustainable robotics

Current research at the intersection of robotics and sustainability follows two main paths: developing robots that enable a more sustainable use of resources, and developing robots that are themselves more sustainable due to improved energy efficiency, biodegradability, or recyclability.

Mirko Kovač heads the joint Laboratory of Sustainability Robotics at Empa and EPFL’s School of Architecture, Civil and Environmental Engineering. In a cover article recently published in Nature Machine Intelligence, Kovač and his co-authors propose a manifesto that calls on academia, industry, and governments to extend and integrate these approaches within a broader framework that evaluates robots according to their overall contribution to sustainability goals. The manifesto defines a new discipline called Sustainability Robotics (not to be confused with sustainable robotics).

“Our ambition is not to simply make robots more sustainable; they must actively contribute to solving sustainability challenges,” Kovač says.

The three core principles of Sustainability Robotics. 2026 LSR/EPFL – CC BY SA 4.0

Minimally invasive, accessible…

In their article, the researchers argue that robots should no longer be evaluated solely based on technical performance. Instead, their environmental, social, and economic impacts should become part of the equation. To guide this transition, they propose three core principles: robotic systems should be minimally invasive, universally accessible, and symbiotic, creating value for people as well as economies and ecosystems.

Rather than viewing sustainability challenges like climate change, biodiversity loss, and resource scarcity as constraints on innovation, the authors argue that they can become opportunities to develop entirely new engineering solutions. Indeed, several EPFL laboratories are already exploring what Sustainability Robotics might look like in practice.

For example, the eel-inspired Envirobot, from Auke Ijspeert’s Biorobotics Lab, supports environmental research by targeting the autonomous monitoring of water quality. The project reflects the lab’s broader efforts to draw inspiration from animals to develop robots capable of operating in complex natural environments while improving our understanding of biological locomotion.

The eel-inspired Envirobot from the Biorobotics Lab supports environmental research by targeting the autonomous monitoring of water quality. 2017 Alain Herzog / EPFL – CC BY SA 4.0.

Engineers in the Laboratory of Intelligent Systems, led by Dario Floreano, have developed an aquatic robot made from fish food. Likewise designed for environmental monitoring, the device can be equipped with biodegradable sensors for collecting data like pH, temperature, and the presence of pollutants. At the end of its life, it can also feed aquatic organisms rather than becoming electronic waste.

This edible robot from the Laboratory for Intelligent Systems is an alternative to electronic environmental monitoring devices. EPFL – CC-BY-SA 4.0.

…and symbiotic

Sustainability Robotics’ concept of symbiosis also raises questions about how robots can create value across multiple domains. One example is the RoboFood initiative, coordinated by Floreano, which explores edible robots and roboticized food systems. Although food and robots are usually considered to be two separate worlds, Floreano argues that merging them could have advantages for healthcare, food production, and environmental sustainability.

“Edible robots could be used to deliver food to endangered areas, to deliver medicines in innovative ways to people who have difficulty swallowing or to animals, or even to monitor food and its freshness using sensors that can be eaten,” he says. “They could also help limit electronic and food waste.”

Edible robotic teddy bears, created by the LIS at EPFL – 2025 EPFL/Jamani Caillet – CC-BY-SA 4.0.

Another example comes from the built environment. In the Lab for Creative Computation, Stefana Parascho investigates how robotic workflows, which typically require uniform components and predefined plans, can be adapted to use irregular and reclaimed construction materials. Such approaches could help reduce waste while allowing architects to work with available materials instead of relying exclusively on standardized products. They could also inspire fabrication processes characterized by more adaptive and collaborative human-robot interactions.

In addition to materials and applications, research in the Computational Design and Fabrication (CREATE) Lab, led by Josie Hughes, shows how sustainability can be embedded directly into robot design from the beginning. One way to do this is through simplified, energy-efficient approaches to robotic control, as demonstrated by the quadruped robot PAWS. Once set in motion, the canine-inspired robot can run by itself using compliant materials and synergistic joints, without activating any motors. The project demonstrates how nature can inspire robust locomotion through mechanical design, rather than increasingly complex control systems.

Once set in motion, the CREATE Lab’s canine-inspired PAWS robot can run by itself using compliant materials and synergistic joints, without activating any motors. 2023 Alain Herzog/EPFL CC BY SA -4.0.

A new measure of performance

Ultimately, Billard and Kovač both call for a broader definition of robotic success that accounts for social, economic, and environmental value alongside technical performance. Of course, this won’t be easy; robots designed with sustainability objectives in mind will still require energy and materials to build and operate, and their use will still carry inherent risks. However, as Kovač puts it: “the challenge is not to eliminate these trade-offs, but to make them visible, and account for them when evaluating a robot’s overall impact.”

Many of the projects already emerging from EPFL labs draw inspiration from biological systems that have been refining solutions to the trade-offs between locomotion, dexterity, efficiency, and adaptability for millions of years. In doing so, they suggest a vision of robotics that comes full circle: using lessons learned from nature to better understand and protect it.

In that sense, sustainability may become one of the most important performance metrics for the next generation of robots.

References

• Aude G. Billard. Designing and using robots for environmental sustainability. Science 388, eadx2444 (2025).
• Song, S., Mazzolai, B. & Kovač, M. A manifesto for Sustainability Robotics. Nature Machine Intelligence (2026).
• Empa press release
• Envirobot: A bio-inspired environmental monitoring platform. IEEE/OES Conference on Autonomous Underwater Vehicles (AUV), Tokyo, Japan (2016), pp. 1-6.
• RoboFood
• Skevaki, E., Duong, E., Yang, HB. et al. Crafting structural timber trusses from irregular offcuts via human–robot interaction. Construction Robotics 10, 20 (2026).
• Stefana Parascho. Construction Robotics: From Automation to Collaboration. Annual Review of Control, Robotics, and Autonomous Systems 6:183-204. 2023.
• Stella, F., Achkar, M.M., Della Santina, C. et al. Synergy-based robotic quadruped leveraging passivity for natural intelligence and behavioural diversity. Nature Machine Intelligence 7, 386–399 (2025).
• Zhang, S., Kwak, B., Zhu, R. et al. Edible aquatic robots with Marangoni propulsion. Nature Communications 16, 4238 (2025).

By Celia Luterbacher

When you blow air across the neck of a bottle, you’re not just producing a pleasant tone: you’re also demonstrating a phenomenon called Helmholtz resonance. This occurs when airflow passing across an opening causes air trapped inside a cavity (like a glass bottle) to oscillate back and forth. At certain frequencies, these oscillations become much stronger, producing the familiar humming sound.

Now, researchers in the MicroBioRobotic Systems (MICROBS) Lab in EPFL’s School of Engineering have harnessed the physics behind this phenomenon to build hollow structures that act as miniature, sound-powered machines. The innovation has been published in Science Advances.

“Instead of pushing devices around with sound waves, we have created acoustic resonators that are tuned to harness sound at specific frequencies to generate directional thrust and controlled motion,” says lab head Selman Sakar. “Our work shows the feasibility of transforming a simple, cleverly designed mechanical piece into robotic matter.”

The MICROBS Lab’s sound-powered boat. 2026 EPFL/MICROBS – CC-BY-SA 4.0.

Miniature boats and microfliers

While previous approaches have used sound waves to levitate passive objects mid-air, the EPFL team designed devices that convert sound into their own propulsive force. Their innovation lies in the fabrication of hollow round or bell-shaped structures called cavities.

When sound waves excite the air inside these cavities, the oscillating air is forced out as a concentrated jet, while the incoming airflow is more diffuse. This imbalance generates thrust that can propel small vehicles. These sound-powered cavities can be made from a variety of materials, including common 3D-printing plastics, rubber-like polymers, and glass.

The MICROBS Lab’s microflier. 2026 EPFL/MICROBS – CC-BY-SA 4.0.

At the centimeter scale, the team built miniature boats equipped with up to three cavities, each tuned to a different audible frequency and positioned to push the boat in a particular direction. By changing the frequency of sound waves from a speaker, the researchers could selectively activate different cavities to move the boats, steer them around obstacles, and even program them for autonomous navigation.

Using a 3D nanoprinting technique, the team built ‘microfliers’: ultralight flying vehicles with three microscopic cavities integrated directly into their polymer structures. In contrast to the boats, the microfliers were powered at ultrasonic frequencies inaudible to the human ear. One design weighing just 150 micrograms used its cavities to generate direct upward thrust like a rocket. Another microflier combined the cavities with tiny blades, which spun at speeds of up to 13,000 revolutions per minute, to generate stable, helicopter-like aerodynamic lift.

A microflier in flight. 2026 EPFL/MICROBS – CC-BY-SA 4.0.

Toward sound-responsive robotics

Because the devices rely on hollow cavities rather than motors, gears, or magnetic components, they can be made extremely small and lightweight using a variety of 3D-printing methods.

“Our concept is compatible with even further miniaturization, enabling advanced designs that push the boundaries of robotics and aeronautics,” says first author and MICROBS Lab PhD student Junsun Hwang.

Sakar adds that in the future, several sound-responsive structures could be built into a single flexible device, with each one reacting to a different sound frequency. “This would allow specific parts of the device to move, bend or vibrate, potentially leading to aerodynamic robotic devices that can change shape in response to sound,” he says.

Reference

Acoustic resonators as wireless actuators in air for small-scale robots, Junsun Hwang et al., Science Advances (2026).

By Jennifer Chu

Loons, gulls, puffins, and petrels are some of the 100 species of birds that can both fly and swim. These diving birds can plunge in water to swim after prey, and then leap back into the air to fly away. Now, inspired by these naturally aquatic aviators, engineers at EPFL and MIT have designed a robot that can swim underwater, and flap out of the water to continue flying through air, much like diving birds.

The “flapping-wing aerial-aquatic vehicle,” or FAAV, weighs less than 300 grams and is designed to help scientists study the mechanics that enable diving birds to fly through air and water. The robot has a central body, or fuselage, two flexible, flapping wings, and a steerable tail. The wings and tail can be swapped out for different sizes. In experiments carried out in a water tank and a lake, the engineers identified combinations of wing size, flapping frequency, and tail angle that enable the robot to smoothly transition from swimming through water, to breaking through the surface, to flying through the air.

Their results, published in Science, can help scientists understand how diving birds adapt their flight mechanics to move through air and water, which have very different physical properties. The design could also launch a new class of aerial-aquatic drones and vehicles. The researchers envision such winged robots could be deployed to fly to and sample from aquatic regions that would otherwise be too dangerous for traditional ocean vessels to access.

Image copyright: Raphael Zufferey.

“Our dream vision is for oceanographers, marine biologists and coastal communities to launch this robot from a boat, or from shore, and it would fly close to the area of interest, such as an iceberg, a port facility or over a pod of whales,” says lead author and former EPFL researcher Raphael Zufferey, now an assistant professor of mechanical engineering at MIT. “It would dive into the water to take a measurement or collect a sample, and fly back to deliver the data at a fraction of the cost of traditional methods. Then it could go back out to dive for more.”

Flight mechanics

Zufferey began working on the robot as a postdoctoral fellow in the Laboratory of Intelligent Systems (LIS) and Biorobotics Lab (BioRob) in EPFL’s School of Engineering, under the supervision of respective lab heads and co-authors Dario Floreano and Auke Ijspeert. He completed the work at MIT, where he now leads the AURA Lab, which focuses on engineering bioinspired aerial and aquatic vehicles. The study also includes co-authors from Northwest Indian College (USA).

With bird biomechanics in mind, the team developed a robot with wings made of thin membranes coated with hydrophobic nanoparticles to help wick away water. The body contains a battery and a waterproof electric motor that drives a crankshaft, which in turn pumps the wings up and down at pre-set frequencies. The tail is motorized, enabling it to change its angle to help the robot fly up or dive down.

The researchers performed experiments first in a small water tank at EPFL, and then in Lake Geneva. They found that wing size (80 centimeters) and flexibility are key; the wings need to be flexible enough to minimize flapping amplitude in water, and firm enough to keep the robot aloft in the air. The robot could swim at speeds of almost one meter per second when it flapped with a frequency of around 5 hertz (five flaps per second), and fly at around 6 meters per second when flapping at a similar frequency. These speeds and flapping frequencies are similar to those of actual diving birds. To make the leap from water to air, the robot must be pitched at a relatively steep 70 degrees to keep its wingtips from touching the water’s surface.

Image copyright: Raphael Zufferey.

Like a bird, but without feet

Interestingly, this combination of wing size, flap frequency, and tail pitch enabled the robot to swim underwater, launch off the surface, and fly without something that many diving birds require: feet. “If you look at birds, most birds need to paddle their feet at the surface to take off. And the question was, do we need the same for robots? And it turns out we don’t,” Zufferey says. “No one’s been able to fly out of the water with wings.”

Going forward, the team is improving the design of the wings to enable them to turn in addition to flapping up and down. They will also test the robot’s performance under turbulent conditions, such as swimming out of choppy waters, and flying through wind. Then, they hope to deploy the vehicle to help answer questions in ocean science.

Reference

Leaping out of the water: Aerial-aquatic locomotion with flapping wings, Raphael Zufferey, Simon L. Jeger, Moritz Hüsser, Fernando Ruiz, Anthony Lapsansky, Auke Ijspeert, Dario Floreano, Science (2026).

By Stephanie Parker

This research from the NeuroAI Lab of Martin Schrimpf, part of EPFL’s Schools of Computer and Communication Sciences and Life Sciences, uses AI models to predict exactly where to stimulate the brain to evoke images of faces and specific objects in the users instead of simply evoking spots of light. The models developed at EPFL were used by Dutch researchers for live trials on sighted monkeys. The preliminary results, presented in April at the International Conference on Learning Representations, show very promising implications for vision in humans as well.

“The motivation for this project is that there are many people with visual deficits that are irreparable, in the sense that somewhere along the visual processing stream, starting with the retina, there is a deficit which cannot be repaired,” says Johannes Mehrer, a scientist in the NeuroAI lab who led the research. “One way of tackling this problem is to develop a visual prosthesis.”

There are multiple kinds of visual prosthetics including retinal, optical nerve, and cortical. Retinal prosthetics are placed somewhere on the retina, and optical nerve prosthetics are used when the retina is too damaged for an implant and the optical nerve can be stimulated instead. When neither the retina nor optical nerve can be implanted, cortical prosthetics are used. These bypass the retina and optical nerve entirely and work instead by stimulating the visual cortex, using electrodes to “draw” images onto it. However, thus far, this approach is limited in that it targets lower-level regions of the brain where it is only possible to project light flashes and simple shapes. There are also hardware constraints because multiple electrodes are needed to stimulate different areas at the same time, but only a certain number of electrodes can be used in one area.

“The images they can elicit, in this case simple symbols, are really limited in their complexity,” Mehrer explains. “At the moment, existing approaches to visual prostheses couldn’t elicit the percept of a more complex visual object such as a house or a car.”

Higher-level visual regions of the brain underlie the processing of more complex objects and could thus serve as a target for a new generation of visual prostheses allowing for eliciting images of faces, houses, and other objects. However, these higher-level regions are less accessible, because it is not known exactly where and how to stimulate them. This is where the AI model comes in.

Towards restoring meaningful sight

“We had the idea to use an artificial neural network, in this case a specific type called a topographic neural network, to test various patterns of brain stimulations in these higher-level regions of the brain and simulate their outcomes,” Mehrer says. “We can then run all sorts of simulations using different combinations of different parameters that would otherwise take up a lot of experimental time and would cost a lot of money.”

The EPFL researchers, working entirely on computers, set up a model to select the best combination of images with the specific pattern of stimulation. Following their results, a team of resarchers in Amsterdam decided to test the model’s prediction on two of their monkeys who already had implants for other experiments not involving EPFL.

“Our model turned out to be quite efficient in predicting which stimulation pattern would yield a strong effect on the monkeys’ behavior with respect to visual object recognition,” says Martin Schrimpf, head of the NeuroAI Lab. “Our models can do the image selection, but the more crucial part is that given an image, it can tell us what the optimal stimulation pattern for a particular desired behavior is.”

What the researchers have been able to show so far with this work is that they can shape object perception, meaning that if a visual stimulus is presented, they can bias its representation in the brain. However, they cannot yet create object perception out of nothing. Stimulating the cortex while there is no visual stimulus presented would be their next step towards restoring meaningful sight to the blind.

“The monkey saw an image already, and then we were able to basically distort it to change the perception in somewhat predictable ways,” says Schrimpf. “The bigger goal will be to evoke a percept from scratch: to make someone see something meaningful even when their eyes aren’t delivering a usable image.”

This work showing that model-guided brain stimulation could lead to more advanced visual prosthetics could also be applied to hearing prosthetics. Through a grant from the Horton Health Foundation, Schrimpf and his team will next investigate if this kind of modeling works for auditory stimulation.

“Cochlear implants are great, but they are also not perfect in many ways, and they don’t really fully restore auditory processing,” says Schrimpf. “Our idea is to develop these kinds of topographic models that can predict what stimulation does to neural activity for auditory processing as well.”

By Celia Luterbacher

In today’s manufacturing environments, upgrading a robot fleet often means starting from scratch – not only replacing hardware, but also reprogramming tasks. Even when two robots are built to perform similar jobs, different joint arrangements or movement limits mean that a task programmed for one robot often can’t be used on another. Enabling skills to transfer directly between robots could make these systems more sustainable and cost-efficient.

To meet this challenge, researchers in the Learning Algorithms and Systems Laboratory (LASA) in EPFL’s School of Engineering have developed a new robotic control framework called Kinematic Intelligence. The method takes a human-demonstrated task, mathematically converts it into a general movement strategy, and then adapts it so that different robots can perform it based on their physical design. The research has been published in Science Robotics.

“This work addresses a long-standing challenge in robotics: how to transfer a learned skill across robots with different mechanical structures, while guaranteeing safe and predictable behavior,” says LASA head Aude Billard. “This approach could significantly reduce the time and expertise needed to deploy robots in real-world settings.”

Kinematic Intelligence for transferable robot learning

To build their framework, the researchers first took human-demonstrated object‑manipulation tasks – such as placing, pushing and throwing – and recorded them using motion-capture technology. Then, they mathematically converted these recorded tasks into general movement strategies. They also developed a systematic classification of the physical limits of different robot designs, including how far their joints can move and which positions they must avoid to remain stable. The framework then uses this classification to automatically tailor the general movement strategies to different robot bodies, ensuring they can carry out tasks safely within their mechanical limits.

In an assembly line experiment, a human demonstrated a task by pushing a wooden block off a conveyor belt onto a workbench, placing it on a table, and finally throwing it into a basket. By using Kinematic Intelligence, three completely different commercial robots were able to reproduce this same sequence safely and reliably.

“Each robot handled different steps of the task, and the system performed successfully even when the step allocation was changed,” explains LASA PhD student and co-first author Sthithpragya Gupta. “Each robot interprets the same skill in its own way, but always within safe and feasible limits.”

Towards scalable and future-ready robotics

The researchers aim to extend the framework to settings such as human-robot collaboration and natural language-based interaction. For example, Kinematic Intelligence could allow a person to instruct a robot with simple commands at home, with no need for technical programming. The approach is also relevant for emerging robotic platforms, where rapid hardware evolution means that today’s machines may soon be replaced by newer versions. Enabling seamless transfer of skills across such platforms could play a key role in making them practical and scalable.

“Our goal is to remove the need for technical expertise while still ensuring safe and reliable operation,” summarizes LASA scientist and co-first author Durgesh Haribhau Salunkhe. “The user brings the idea and the desired behavior, and the robot should take care of the rest.”

Reference

Demonstrate once, execute on many: Kinematic intelligence for cross-robot skill transfer, S Gupta, D H Salunkhe, A Billard, Science Robotics (2026).

By Celia Luterbacher

If the goal of a robot is to perform a function, then minimizing the possibility of failure is a top priority when it comes to robotic design. But this minimization is at odds with the robotic raison d’être: systems with multiple units, or agents, can perform more diverse functions, but they also have more different parts that can potentially fail.

Researchers led by Jamie Paik, head of the Reconfigurable Robotics Laboratory (RRL) in EPFL’s School of Engineering, have not only circumvented this problem, but flipped it: they have designed a modular robot that actually lowers its odds of failure by sharing resources among its individual agents.

“For the first time, we have found a way to reverse the trend of increasing odds of failure with increasing function,” Paik explains. “We introduce local resource sharing as a new paradigm in robotics, reducing the failure rate with a larger number of modules.”

In a paper published in Science Robotics, the team showed how exploiting redundant resources and sharing them locally enabled a modular origami robot to successfully navigate a complex terrain, even when one module was completely deprived of power, sensing, and wireless communication.

Sharing is caring

The RRL team took inspiration for their innovation from nature, where the problem of failure is often solved collectively. Birds share local sensing information through flocking behavior, some trees communicate threats to neighbors using airborne signals, and cells continuously transport nutrients across their membranes so that the death of any individual doesn’t significantly impact the overall organism.

Modular robots, which are composed of multiple units that connect to form a complete system, are analogous to multicellular or collective organisms, but until now, their design has been a source of vulnerability: the failure of one module often disables some, if not all, of the robot’s ability to perform tasks. Some modular robots get around this problem with built-in backup resources or self-reconfiguration abilities, but these approaches usually don’t completely restore functionality.

For their study, the RRL team used something called hyper-redundancy: the sharing of all critical power, communication, and sensing resources across all modules, without any change to the robot’s physical structure.

“We found that sharing just one or two resources was not enough: if each resource had an equal chance of failure, system reliability would continue to drop with an increasing number of agents. But when all resources were shared, this this trend was reversed,” Paik says.

In a locomotion task experiment with the Mori3 robot, which is composed of four triangular modules, the team experimented with cutting battery power, wireless communication, and sensing to the central module. Normally, this ‘dead’ central module would block the articulation and movement of the other three, but thanks to hyper-redundancy, the neighboring modules fully compensated for its lack of resources. This allowed the Mori3 to successfully ‘walk’ toward a barrier and contort itself effectively to pass underneath it.

“Essentially, our methodology allowed us to ‘revive’ a dead module in a collective and bring it back to full functionality. Our local resource-sharing framework therefore has the potential to support highly adaptive robots that can operate with unprecedented reliability, finally resolving the reliability-adaptability conflict,” summarizes RRL researcher and first author Kevin Holdcroft.

The researchers say that future work could focus on applying their resource sharing framework to more complex systems with increasing numbers of agents. In particular, the same concept could be extended to robotic swarms, with hardware adaptations that allow swarm members to dock to each other for energy and information transfer.

References

Scalable robot collective resilience by sharing resources, Holdcroft, K., Bolotnikova, A., Monforte, A.J., and Paik, J., Science Robotics (2026).

By Celia Luterbacher

With its opposable thumb, multiple joints and gripping skin, human hands are often considered to be the pinnacle of dexterity, and many robotic hands are designed in their image. But having been shaped by the slow process of evolution, human hands are far from optimized, with the biggest drawbacks including our single, asymmetrical thumbs and attachment to arms with limited mobility.

“We can easily see the limitations of the human hand when attempting to reach objects underneath furniture or behind shelves, or performing simultaneous tasks like holding a bottle while picking up a chip can,” says Aude Billard, head of the Learning Algorithms and Systems Laboratory (LASA) in EPFL’s School of Engineering. “Likewise, accessing objects positioned behind the hand while keeping the grip stable can be extremely challenging, requiring awkward wrist contortions or body repositioning.”

A team composed of Billard, LASA researcher Xiao Gao, and Kai Junge and Josie Hughes from the Computational Robot Design and Fabrication Lab designed a robotic hand that overcomes these challenges. Their device, which can support up to six identical silicone-tipped fingers, fixes the problem of human asymmetry by allowing any combination of fingers to form opposing pairs in a thumb-like pinch. Thanks to its reversible design, the ‘back’ and ‘palm’ of the robotic hand are interchangeable. The hand can even detach from its robotic arm and ‘crawl’, spider-like, to grasp and carry objects beyond the arm’s reach.

“Our device reliably and seamlessly performs ‘loco manipulation’ — stationary manipulation combined with autonomous mobility – which we believe has great potential for industrial, service, and exploratory robotics,” Billard summarizes. The research has been published in Nature Communications.

Human applications – and beyond

While the robotic hand looks like something from a futuristic sci-fi movie, the researchers say they drew inspiration from nature.

“Many organisms have evolved versatile limbs that seamlessly switch between different functionalities like grasping and locomotion. For example, the octopus uses its flexible arms both to crawl across the seafloor and open shells, while in the insect world, the praying mantis use specialized limbs for locomotion and prey capture,” Billard says.

Indeed, the EPFL robot can crawl while maintaining a grip on multiple objects, holding them under its ‘palm’, on its ‘back’, or both. With five fingers, the device can replicate most of the traditional human grasps. When equipped with more than five fingers, it can single-handedly tackle tasks usually requiring two human hands – such as unscrewing the cap on a large bottle or driving a screw into a block of wood with a screwdriver.

“There is no real limitation in the number of objects it can hold; if we need to hold more objects, we simply add more fingers,” Billard says.

The researchers foresee applications of their innovative design in real-world settings that demand compactness, adaptability, and multi-modal interaction. For example, the technology could be used to retrieve objects in confined environments or expand the reach of traditional industrial arms. And while the proposed robotic hand is not itself anthropomorphic, they also believe it could be adapted for prosthetic applications.

“The symmetrical, reversible functionality is particularly valuable in scenarios where users could benefit from capabilities beyond normal human function,” Billard says. “For example, previous studies with users of additional robotic fingers demonstrate the brain’s remarkable adaptability to integrate additional appendages, suggesting that our non-traditional configuration could even serve in specialized environments requiring augmented manipulation abilities.”

Reference

A detachable crawling robotic hand, Xiao Gao (高霄), Kunpeng Yao (姚坤鹏), Kai Junge, Josie Hughes & Aude Billard, Nat Commun 17, 428 (2026).

By Celia Luterbacher

Although many roboticists today turn to nature to inspire their designs, even bioinspired robots are usually fabricated from non-biological materials like metal, plastic and composites. But a new experimental robotic manipulator from the Computational Robot Design and Fabrication Lab (CREATE Lab) in EPFL’s School of Engineering turns this trend on its head: its main feature is a pair of langoustine abdomen exoskeletons.

Although it may look unusual, CREATE Lab head Josie Hughes explains that combining biological elements with synthetic components holds significant potential not only to enhance robotics, but also to support sustainable technology systems.

“Exoskeletons combine mineralized shells with joint membranes, providing a balance of rigidity and flexibility that allows their segments to move independently. These features enable crustaceans’ rapid, high-torque movements in water, but they can also be very useful for robotics. And by repurposing food waste, we propose a sustainable cyclic design process in which materials can be recycled and adapted for new tasks.”

In a paper published in Advanced Science, Hughes and her team demonstrate three robotic applications by augmenting the exoskeletons of langoustines, which had previously been harvested and processed for the food industry, with the precise control and longevity of synthetic components: a manipulator that can handle objects weighing up to 500g, grippers that can bend and grasp various objects, and a swimming robot.

Design, operate, recycle, repeat

For their study, the CREATE Lab decided to bring together the structural robustness and flexibility of the exoskeletons of langoustines with the precise control and longevity of synthetic components.

They achieved this by embedding an elastomer inside the exoskeleton to control each of its segments and then mounting it on a motorized base to modulate its stiffness response (extension and flexion). Finally, the team covered the exoskeleton in a silicon coating to reinforce it and extend its lifespan.

When mounted on the motorized base, the device can be used to move an object weighing up to 500 g into a target zone. When mounted as a gripping pair, two exoskeletons can successfully grasp a variety of objects ranging in size and shape from a highlighter pen to a tomato. The robotic system can even be used to propel a swimming robot with two flapping exoskeletal ‘fins’ at speeds of up to 11 centimeters per second.

After use, the exoskeleton and its robotic base can be separated and most of the synthetic components can be reused. “To our knowledge, we are the first to propose a proof of concept to integrate food waste into a robotic system that combines sustainable design with reuse and recycling,” says CREATE Lab researcher and first author Sareum Kim.

One limitation of the approach lies in the natural variation in biological structures; for example, the unique shape of each langoustine tail means that the two- ‘fingered’ gripper bends slightly differently on each side. The researchers say this challenge will require the development of more advanced synthetic augmentation mechanisms like tunable controllers. With such improvements, the team sees potential for future systems integrating bioderived structural elements, for example in biomedical implants or bio-system monitoring platforms.

“Although nature does not necessarily provide the optimal form, it still outperforms many artificial systems and offers valuable insights for designing functional machines based on elegant principles,” Hughes summarizes.

Read the work in full

Dead Matter, Living Machines: Repurposing Crustaceans’ Abdomen Exoskeleton for Bio-Hybrid Robots, S. Kim, K. Gilday, and J. Hughes, Adv. Sci. (2025).

By Melissa Anchisi and Florian Meyer

In July, EPFL, ETH Zurich, and the Swiss National Supercomputing Centre (CSCS) announced their joint initiative to build a large language model (LLM). Now, this model is available and serves as a building block for developers and organisations for future applications such as chatbots, translation systems, or educational tools.

The model is named Apertus – Latin for “open” – highlighting its distinctive feature: the entire development process, including its architecture, model weights, and training data and recipes, is openly accessible and fully documented.

AI researchers, professionals, and experienced enthusiasts can either access the model through the strategic partner Swisscom or download it from Hugging Face – a platform for AI models and applications – and deploy it for their own projects. Apertus is freely available in two sizes – featuring 8 billion and 70 billion parameters, the smaller model being more appropriate for individual usage. Both models are released under a permissive open-source license, allowing use in education and research as well as broad societal and commercial applications.

A fully open-source LLM

As a fully open language model, Apertus allows researchers, professionals and enthusiasts to build upon the model and adapt it to their specific needs, as well as to inspect any part of the training process. This distinguishes Apertus from models that make only selected components accessible.

“With this release, we aim to provide a blueprint for how a trustworthy, sovereign, and inclusive AI model can be developed,” says Martin Jaggi, Professor of Machine Learning at EPFL and member of the Steering Committee of the Swiss AI Initiative. The model will be regularly updated by the development team which includes specialized engineers and a large number of researchers from CSCS, ETH Zurich and EPFL.

A driver of innovation

With its open approach, EPFL, ETH Zurich and CSCS are venturing into new territory. “Apertus is not a conventional case of technology transfer from research to product. Instead, we see it as a driver of innovation and a means of strengthening AI expertise across research, society and industry,” says Thomas Schulthess, Director of CSCS and Professor at ETH Zurich. In line with their tradition, EPFL, ETH Zurich and CSCS are providing both foundational technology and infrastructure to foster innovation across the economy.

Trained on 15 trillion tokens across more than 1,000 languages – 40% of the data is non-English – Apertus includes many languages that have so far been underrepresented in LLMs, such as Swiss German, Romansh, and many others.

“Apertus is built for the public good. It stands among the few fully open LLMs at this scale and is the first of its kind to embody multilingualism, transparency, and compliance as foundational design principles”, says Imanol Schlag, technical lead of the LLM project and Research Scientist at ETH Zurich.

“Swisscom is proud to be among the first to deploy this pioneering large language model on our sovereign Swiss AI Platform. As a strategic partner of the Swiss AI Initiative, we are supporting the access of Apertus during the Swiss {ai} Weeks. This underscores our commitment to shaping a secure and responsible AI ecosystem that serves the public interest and strengthens Switzerland’s digital sovereignty”, commented Daniel Dobos, Research Director at Swisscom.

Accessibility

While setting up Apertus is straightforward for professionals and proficient users, additional components such as servers, cloud infrastructure or specific user interfaces are required for practical use. The upcoming Swiss {ai} Weeks hackathons will be the first opportunity for developers to experiment hands-on with Apertus, test its capabilities, and provide feedback for improvements to future versions.

Swisscom will provide a dedicated interface to hackathon participants, making it easier to interact with the model. As of today, Swisscom business customers will be able to access the Apertus model via Swisscom’s sovereign Swiss AI platform.

Furthermore, for people outside of Switzerland, the Public AI Inference Utility will make Apertus accessible as part of a global movement for public AI. “Currently, Apertus is the leading public AI model: a model built by public institutions, for the public interest. It is our best proof yet that AI can be a form of public infrastructure like highways, water, or electricity,” says Joshua Tan, Lead Maintainer of the Public AI Inference Utility.

Transparency and compliance

Apertus is designed with transparency at its core, thereby ensuring full reproducibility of the training process. Alongside the models, the research team has published a range of resources: comprehensive documentation and source code of the training process and datasets used, model weights including intermediate checkpoints – all released under the permissive open-source license, which also allows for commercial use. The terms and conditions are available via Hugging Face.

Apertus was developed with due consideration to Swiss data protection laws, Swiss copyright laws, and the transparency obligations under the EU AI Act. Particular attention has been paid to data integrity and ethical standards: the training corpus builds only on data which is publicly available. It is filtered to respect machine-readable opt-out requests from websites, even retroactively, and to remove personal data, and other undesired content before training begins.

The beginning of a journey

“Apertus demonstrates that generative AI can be both powerful and open,” says Antoine Bosselut, Professor and Head of the Natural Language Processing Laboratory at EPFL and Co-Lead of the Swiss AI Initiative. “The release of Apertus is not a final step, rather it’s the beginning of a journey, a long-term commitment to open, trustworthy, and sovereign AI foundations, for the public good worldwide. We are excited to see developers engage with the model at the Swiss {ai} Weeks hackathons. Their creativity and feedback will help us to improve future generations of the model.”

Future versions aim to expand the model family, improve efficiency, and explore domain-specific adaptations in fields like law, climate, health and education. They are also expected to integrate additional capabilities, while maintaining strong standards for transparency.

The robotic system is shown in an experimental hive © Artificial Life Lab/U. of Graz/Hiveopolis

By Celia Luterbacher

Honeybees are famously finicky when it comes to being studied. Research instruments and conditions and even unfamiliar smells can disrupt a colony’s behavior. Now, a joint research team from the Mobile Robotic Systems Group in EPFL’s School of Engineering and School of Computer and Communication Sciences and the Hiveopolis project at Austria’s University of Graz have developed a robotic system that can be unobtrusively built into the frame of a standard honeybee hive.

Composed of an array of thermal sensors and actuators, the system measures and modulates honeybee behavior through localized temperature variations.

“Many rules of bee society – from collective and individual interactions to raising a healthy brood – are regulated by temperature, so we leveraged that for this study,” explains EPFL PhD student Rafael Barmak, first author on a paper on the system recently published in Science Robotics. “The thermal sensors create a snapshot of the bees’ collective behavior, while the actuators allow us to influence their movement by modulating thermal fields.”

“Previous studies on the thermal behavior of honeybees in winter have relied on observing the bees or manipulating the outside temperature,” adds Martin Stefanec of the University of Graz. “Our robotic system enables us to change the temperature from within the cluster, emulating the heating behavior of core bees there, and allowing us to study how the winter cluster actively regulates its temperature.”

A ‘biohybrid superorganism’ to mitigate colony collapse

Bee colonies are challenging to study in winter since they are sensitive to cold, and opening their hives risks harming them in addition to influencing their behavior. But thanks to the researchers’ biocompatible robotic system, they were able to study three experimental hives, located at the Artificial Life Lab at the University of Graz, during winter and to control them remotely from EPFL. Inside the device, a central processor coordinated the sensors, sent commands to the actuators, and transmitted data to the scientists, demonstrating that the system could be used to study bees with no intrusion – or even cameras – required.

Mobile Robotic Systems Group head Francesco Mondada explains that one of the most important aspects of the system – which he calls a ‘biohybrid superorganism’ for its combination of robotics with a colony of individuals acting as a living entity – is its ability to simultaneously observe and influence bee behavior.

“By gathering data on the bees’ position and creating warmer areas in the hive, we were able to encourage them to move around in ways they would never normally do in nature during the winter, when they tend to huddle together to conserve energy. This gives us the possibility to act on behalf of a colony, for example by directing it toward a food source, or discouraging it from dividing into too-small groups, which can threaten its survival.”

The robotic system is shown in an experimental hive © MOBOTS / EPFL / Hiveopolis

The scientists were able to prolong the survival of a colony following the death of its queen by distributing heat energy via the actuators. The system’s ability to mitigate colony collapse could have implications for bee survivability, which has become a growing environmental and food security concern as the pollinators’ global populations have declined.

Never-before-seen behaviors

In addition to its potential to support colonies, the system has shed light on honeybee behaviors that have never been observed, opening new avenues in biological research.

“The local thermal stimuli produced by our system revealed previously unreported dynamics that are generating exciting new questions and hypotheses,” says EPFL postdoctoral researcher and corresponding author Rob Mills. “For example, currently, no model can explain why we were able to encourage the bees to cross some cold temperature ‘valleys’ within the hive.”

The researchers now plan to use the system to study bees in summertime, which is a critical period for raising young. In parallel, the Mobile Robotic Systems Group is exploring systems using vibrational pathways to interact with honeybees.

“The biological acceptance aspect of this work is critical: the fact that the bees accepted the integration of electronics into the hive gives our device great potential for different scientific or agricultural applications,” says Mondada.

This work was supported by the EU H2020 FET project HIVEOPOLIS (no. 824069), coordinated by Thomas Schmickl, and by the Field of Excellence COLIBRI (Complexity of Life in basic Research and Innovation) at the University of Graz.

• PAPER – A robotic honeycomb for interaction with a honeybee colony. R. Barmak and M. Stefanec, D. N. Hofstadler, L. Piotet, S. Schönwetter-Fuchs-Schistek, F. Mondada, T. Schmickl, and R. Mills. Science Robotics, vol 8, Issue 76. https://doi.org/10.1126/scirobotics.add7385

When it comes to the future of intelligent robots, the first question people ask is often: how many jobs will they make disappear? Whatever the answer, the second question is likely to be: how can I make sure that my job is not among them?

In a study just published in Science Robotics, a team of roboticists from EPFL and economists from the University of Lausanne offers answers to both questions. By combining the scientific and technical literature on robotic abilities with employment and wage statistics, they have developed a method to calculate which of the currently existing jobs are more at risk of being performed by machines in the near future. Additionally, they have devised a method for suggesting career transitions to jobs that are less at risk and require smallest retraining efforts.

“There are several studies predicting how many jobs will be automated by robots, but they all focus on software robots, such as speech and image recognition, financial robo-advisers, chatbots, and so forth. Furthermore, those predictions wildly oscillate depending on how job requirements and software abilities are assessed. Here, we consider not only artificial intelligence software, but also real intelligent robots that perform physical work and we developed a method for a systematic comparison of human and robotic abilities used in hundreds of jobs”, says Prof. Dario Floreano, Director of EPFL’s Laboratory of Intelligent Systems, who led the study at EPFL.

The key innovation of the study is a new mapping of robot capabilities onto job requirements. The team looked into the European H2020 Robotic Multi-Annual Roadmap (MAR), a strategy document by the European Commission that is periodically revised by robotics experts. The MAR describes dozens of abilities that are required from current robot or may be required by future ones, ranging, organised in categories such as manipulation, perception, sensing, interaction with humans. The researchers went through research papers, patents, and description of robotic products to assess the maturity level of robotic abilities, using a well-known scale for measuring the level of technology development, “technology readiness level” (TRL).

For human abilities, they relied on the O*net database, a widely-used resource database on the US job market, that classifies approximately 1,000 occupations and breaks down the skills and knowledge that are most crucial for each of them

After selectively matching the human abilities from O*net list to robotic abilities from the MAR document, the team could calculate how likely each existing job occupation is to be performed by a robot. Say, for example, that a job requires a human to work at millimetre-level precision of movements. Robots are very good at that, and the TRL of the corresponding ability is thus the highest. If a job requires enough such skills, it will be more likely to be automated than one that requires abilities such as critical thinking or creativity.

The result is a ranking of the 1,000 jobs, with “Physicists” being the ones who have the lowest risk of being replaced by a machine, and “Slaughterers and Meat Packers”, who face the highest risk. In general, jobs in food processing, building and maintenance, construction and extraction appear to have the highest risk.

“The key challenge for society today is how to become resilient against automation” says Prof. Rafael Lalive. who co-led the study at the University of Lausanne. “Our work provides detailed career advice for workers who face high risks of automation, which allows them to take on more secure jobs while re-using many of the skills acquired on the old job. Through this advice, governments can support society in becoming more resilient against automation.”

The authors then created a method to find, for any given job, alternative jobs that have a significantly lower automation risk and are reasonably close to the original one in terms of the abilities and knowledge they require – thus keeping the retraining effort minimal and making the career transition feasible. To test how that method would perform in real life, they used data from the US workforce and simulated thousands of career moves based on the algorithm’s suggestions, finding that it would indeed allow workers in the occupations with the highest risk to shift towards medium-risk occupations, while undergoing a relatively low retraining effort.

The method could be used by governments to measure how many workers could face automation risks and adjust retraining policies, by companies to assess the costs of increasing automation, by robotics manufacturers to better tailor their products to the market needs; and by the public to identify the easiest route to reposition themselves on the job market.

Finally, the authors translated the new methods and data into an algorithm that predicts the risk of automation for hundreds of jobs and suggests resilient career transitions at minimal retraining effort, publicly accessible at http://lis2.epfl.ch/resiliencetorobots.

This research was funded by the CROSS (Collaborative Research on Science and Society) Program in EPFL’s College of Humanities; by the Enterprise for Society Center at EPFL; as a part of NCCR Robotics, a National Centres of Competence in Research, funded by the Swiss National Science Foundation (SNSF grant number 51NF40_185543); by the European Commission through the Horizon 2020 projects AERIAL-CORE (grant agreement no. 871479) and MERGING (grant agreement no. 869963); and by SNSF grant no. 100018_178878.

• PAPER – How to compete with robots by assessing job automation risks and resilient alternatives Antonio Paolillo, Fabrizio Colella, Nicola Nosengo, Fabrizio Schiano, William Stewart, Davide Zambrano, Isabelle Chappuis, Rafael Lalive, and Dario Floreano. Science Robotics, Vol 7, Issue 65

Enrica Soria, a PhD student at LIS © Alain Herzog / 2021 EPFL

By Clara Marc

There is strength in numbers. That’s true not only for humans, but for drones too. By flying in a swarm, they can cover larger areas and collect a wider range of data, since each drone can be equipped with different sensors.

Preventing drones from bumping into each other
One reason why drone swarms haven’t been used more widely is the risk of gridlock within the swarm. Studies on the collective movement of animals show that each agent tends to coordinate its movements with the others, adjusting its trajectory so as to keep a safe inter-agent distance or to travel in alignment, for example.

“In a drone swarm, when one drone changes its trajectory to avoid an obstacle, its neighbors automatically synchronize their movements accordingly,” says Dario Floreano, a professor at EPFL’s School of Engineering and head of the Laboratory of Intelligent Systems (LIS). “But that often causes the swarm to slow down, generates gridlock within the swarm or even leads to collisions.”

Not just reacting, but also predicting
Enrica Soria, a PhD student at LIS, has come up with a new method for getting around that problem. She has developed a predictive control model that allows drones to not just react to others in a swarm, but also to anticipate their own movements and predict those of their neighbors. “Our model gives drones the ability to determine when a neighbor is about to slow down, meaning the slowdown has less of an effect on their own flight,” says Soria. The model works by programing in locally controlled, simple rules, such as a minimum inter-agent distance to maintain, a set velocity to keep, or a specific direction to follow. Soria’s work has just been published in Nature Machine Intelligence.

With Soria’s model, drones are much less dependent on commands issued by a central computer. Drones in aerial light shows, for example, get their instructions from a computer that calculates each one’s trajectory to avoid a collision. “But with our model, drones are commanded using local information and can modify their trajectories autonomously,” says Soria.

A model inspired by nature
Tests run at LIS show that Soria’s system improves the speed, order and safety of drone swarms in areas with a lot of obstacles. “We don’t yet know if, or to what extent, animals are able to predict the movements of those around them,” says Floreano. “But biologists have recently suggested that the synchronized direction changes observed in some large groups would require a more sophisticated cognitive ability than what has been believed until now.”

References

• PAPER – Predictive control of aerial swarms in cluttered environments. Soria, E., Schiano, F. and Floreano, D., Nat Mach Intell (2021). DOI: 10.1038/s42256-021-00341-y