news    views    podcast    learn    |    about    contribute     republish    


by   -   March 18, 2020

Reinforcement learning has seen a great deal of success in solving complex decision making problems ranging from robotics to games to supply chain management to recommender systems. Despite their success, deep reinforcement learning algorithms can be exceptionally difficult to use, due to unstable training, sensitivity to hyperparameters, and generally unpredictable and poorly understood convergence properties. Multiple explanations, and corresponding solutions, have been proposed for improving the stability of such methods, and we have seen good progress over the last few years on these algorithms. In this blog post, we will dive deep into analyzing a central and underexplored reason behind some of the problems with the class of deep RL algorithms based on dynamic programming, which encompass the popular DQN and soft actor-critic (SAC) algorithms – the detrimental connection between data distributions and learned models.

by   -   March 11, 2020

Roboticists are developing automated robots that can learn new tasks solely by observing humans. At home, you might someday show a domestic robot how to do routine chores.
Image: Christine Daniloff, MIT

By Rob Matheson

Training interactive robots may one day be an easy job for everyone, even those without programming expertise. Roboticists are developing automated robots that can learn new tasks solely by observing humans. At home, you might someday show a domestic robot how to do routine chores. In the workplace, you could train robots like new employees, showing them how to perform many duties.

by   -   March 11, 2020

By Leah Burrows

Of all the cool things about octopuses (and there are a lot), their arms may rank among the coolest.

Two-thirds of an octopus’s neurons are in its arms, meaning each arm literally has a mind of its own. Octopus arms can untie knots, open childproof bottles, and wrap around prey of any shape or size. The hundreds of suckers that cover their arms can form strong seals even on rough surfaces underwater.

Imagine if a robot could do all that.

by   -   March 11, 2020
AIhub | Horizon | Keolis autonomous shuttle
Autonomous vehicles must be well-integrated into public transport systems if they are to take off in Europe’s cities, say researchers. Image credit – Keolis

By Julianna Photopoulos

Jutting out into the sea, the industrial port area of Nordhavn in Denmark’s capital, Copenhagen, is currently being transformed into a futuristic waterfront city district made up of small islets. It’s billed as Scandinavia’s largest metropolitan development project and, when complete, will have living space for 40,000 people and workspace for another 40,000.

At the moment, Nordhavn is only served by a nearby S-train station and bus stops located near the station. There are no buses or trains running within the development area, although there are plans for an elevated metro line, and parking will be discouraged in the new neighbourhood. This is a great opportunity for autonomous vehicles (AVs) to operate as a new public transport solution

by   -   January 26, 2020

By Glen Berseth

All living organisms carve out environmental niches within which they can maintain relative predictability amidst the ever-increasing entropy around them (1), (2). Humans, for example, go to great lengths to shield themselves from surprise — we band together in millions to build cities with homes, supplying water, food, gas, and electricity to control the deterioration of our bodies and living spaces amidst heat and cold, wind and storm. The need to discover and maintain such surprise-free equilibria has driven great resourcefulness and skill in organisms across very diverse natural habitats. Motivated by this, we ask: could the motive of preserving order amidst chaos guide the automatic acquisition of useful behaviors in artificial agents?

by   -   January 23, 2020

An AI model developed at MIT and Qatar Computing Research Institute that uses only satellite imagery to automatically tag road features in digital maps could improve GPS navigation, especially in countries with limited map data.
Image: Google Maps/MIT News

By Rob Matheson

A model invented by researchers at MIT and Qatar Computing Research Institute (QCRI) that uses satellite imagery to tag road features in digital maps could help improve GPS navigation.  

by   -   December 24, 2019

Thanks to all those that sent us their holiday videos. Here’s a selection of 20+ videos to get you into the spirit this season.

by   -   December 18, 2019

A group of EPFL researchers have developed a foldable device that can fit in a pocket and can transmit touch stimuli when used in a human-machine interface.

When browsing an e-commerce site on your smartphone, or a music streaming service on your laptop, you can see pictures and hear sound snippets of what you are going to buy. But sometimes it would be great to touch it too – for example to feel the texture of a garment, or the stiffness of a material. The problem is that there are no miniaturized devices that can render touch sensations the way screens and loudspeakers render sight and sound, and that can easily be coupled to a computer or a mobile device.

by   -   December 18, 2019

A researcher’s hand hovers over the water’s surface in the Intelligent Towing Tank (ITT), an automated experimental facility guided by active learning to explore vortex-induced vibrations (VIVs), revealing a path to accelerated scientific discovery.
Image: Dixia Fan and Lily Keyes/MIT Sea Grant

By Lily Keyes/MIT Sea Grant

In its first year of operation, the Intelligent Towing Tank (ITT) conducted about 100,000 total experiments, essentially completing the equivalent of a PhD student’s five years’ worth of experiments in a matter of weeks.

by   -   December 7, 2019


That’s right! You better not run, you better not hide, you better watch out for brand new robot holiday videos on Robohub!

by   -   December 7, 2019

By Aviral Kumar

One of the primary factors behind the success of machine learning approaches in open world settings, such as image recognition and natural language processing, has been the ability of high-capacity deep neural network function approximators to learn generalizable models from large amounts of data. Deep reinforcement learning methods, however, require active online data collection, where the model actively interacts with its environment. This makes such methods hard to scale to complex real-world problems, where active data collection means that large datasets of experience must be collected for every experiment – this can be expensive and, for systems such as autonomous vehicles or robots, potentially unsafe. In a number of domains of practical interest, such as autonomous driving, robotics, and games, there exist plentiful amounts of previously collected interaction data which, consists of informative behaviours that are a rich source of prior information. Deep RL algorithms that can utilize such prior datasets will not only scale to real-world problems, but will also lead to solutions that generalize substantially better. A data-driven paradigm for reinforcement learning will enable us to pre-train and deploy agents capable of sample-efficient learning in the real-world.

At Danfoss in Gråsten, the Danish Technological Institute (DTI) is testing, as part of a pilot project in the European robot network ROBOTT-NET, several robot technologies: Manipulation using force sensors, simpler separation of items and a 3D-printed three-in-one gripper for handling capacitors, nuts and a socket handle.

by   -   December 7, 2019

An MIT-invented model demonstrates an understanding of some basic “intuitive physics” by registering “surprise” when objects in simulations move in unexpected ways, such as rolling behind a wall and not reappearing on the other side.
Image: Christine Daniloff, MIT
By Rob Matheson

Humans have an early understanding of the laws of physical reality. Infants, for instance, hold expectations for how objects should move and interact with each other, and will show surprise when they do something unexpected, such as disappearing in a sleight-of-hand magic trick.

by   -   December 7, 2019

By Sudeep Dasari

This post is cross-listed at the SAIL Blog and the CMU ML blog.

In the last decade, we’ve seen learning-based systems provide transformative solutions for a wide range of perception and reasoning problems, from recognizing objects in images to recognizing and translating human speech. Recent progress in deep reinforcement learning (i.e. integrating deep neural networks into reinforcement learning systems) suggests that the same kind of success could be realized in automated decision making domains. If fruitful, this line of work could allow learning-based systems to tackle active control tasks, such as robotics and autonomous driving, alongside the passive perception tasks to which they have already been successfully applied.

by   -   December 7, 2019

MIT researchers have invented a way to efficiently optimize the control and design of soft robots for target tasks, which has traditionally been a monumental undertaking in computation.

← previous page        ·         next page →

Solid State Lidar – the 3D Camera
June 29, 2020

Are you planning to crowdfund your robot startup?

Need help spreading the word?

Join the Robohub crowdfunding page and increase the visibility of your campaign