Category Robotics Classification

In our paper, published today in Nature, we introduce AlphaTensor, the first artificial intelligence (AI) system for discovering novel, efficient, and provably correct algorithms for fundamental tasks such as matrix multiplication. This sheds light on a 50-year-old open question in mathematics about finding the fastest way to multiply two matrices. This paper is a stepping stone in DeepMind’s mission to advance science and unlock the most fundamental problems using AI. Our system, AlphaTensor, builds upon AlphaZero, an agent that has shown superhuman performance on board games, like chess, Go and shogi, and this work shows the journey of AlphaZero from playing games to tackling unsolved mathematical problems for the first time.

In our paper, published today in Nature, we introduce AlphaTensor, the first artificial intelligence (AI) system for discovering novel, efficient, and provably correct algorithms for fundamental tasks such as matrix multiplication. This sheds light on a 50-year-old open question in mathematics about finding the fastest way to multiply two matrices. This paper is a stepping stone in DeepMind’s mission to advance science and unlock the most fundamental problems using AI. Our system, AlphaTensor, builds upon AlphaZero, an agent that has shown superhuman performance on board games, like chess, Go and shogi, and this work shows the journey of AlphaZero from playing games to tackling unsolved mathematical problems for the first time.

In our paper, published today in Nature, we introduce AlphaTensor, the first artificial intelligence (AI) system for discovering novel, efficient, and provably correct algorithms for fundamental tasks such as matrix multiplication. This sheds light on a 50-year-old open question in mathematics about finding the fastest way to multiply two matrices. This paper is a stepping stone in DeepMind’s mission to advance science and unlock the most fundamental problems using AI. Our system, AlphaTensor, builds upon AlphaZero, an agent that has shown superhuman performance on board games, like chess, Go and shogi, and this work shows the journey of AlphaZero from playing games to tackling unsolved mathematical problems for the first time.

In our paper, published today in Nature, we introduce AlphaTensor, the first artificial intelligence (AI) system for discovering novel, efficient, and provably correct algorithms for fundamental tasks such as matrix multiplication. This sheds light on a 50-year-old open question in mathematics about finding the fastest way to multiply two matrices. This paper is a stepping stone in DeepMind’s mission to advance science and unlock the most fundamental problems using AI. Our system, AlphaTensor, builds upon AlphaZero, an agent that has shown superhuman performance on board games, like chess, Go and shogi, and this work shows the journey of AlphaZero from playing games to tackling unsolved mathematical problems for the first time.

In our paper, published today in Nature, we introduce AlphaTensor, the first artificial intelligence (AI) system for discovering novel, efficient, and provably correct algorithms for fundamental tasks such as matrix multiplication. This sheds light on a 50-year-old open question in mathematics about finding the fastest way to multiply two matrices. This paper is a stepping stone in DeepMind’s mission to advance science and unlock the most fundamental problems using AI. Our system, AlphaTensor, builds upon AlphaZero, an agent that has shown superhuman performance on board games, like chess, Go and shogi, and this work shows the journey of AlphaZero from playing games to tackling unsolved mathematical problems for the first time.

In our paper, published today in Nature, we introduce AlphaTensor, the first artificial intelligence (AI) system for discovering novel, efficient, and provably correct algorithms for fundamental tasks such as matrix multiplication. This sheds light on a 50-year-old open question in mathematics about finding the fastest way to multiply two matrices. This paper is a stepping stone in DeepMind’s mission to advance science and unlock the most fundamental problems using AI. Our system, AlphaTensor, builds upon AlphaZero, an agent that has shown superhuman performance on board games, like chess, Go and shogi, and this work shows the journey of AlphaZero from playing games to tackling unsolved mathematical problems for the first time.

In our paper, published today in Nature, we introduce AlphaTensor, the first artificial intelligence (AI) system for discovering novel, efficient, and provably correct algorithms for fundamental tasks such as matrix multiplication. This sheds light on a 50-year-old open question in mathematics about finding the fastest way to multiply two matrices. This paper is a stepping stone in DeepMind’s mission to advance science and unlock the most fundamental problems using AI. Our system, AlphaTensor, builds upon AlphaZero, an agent that has shown superhuman performance on board games, like chess, Go and shogi, and this work shows the journey of AlphaZero from playing games to tackling unsolved mathematical problems for the first time.

In our paper, published today in Nature, we introduce AlphaTensor, the first artificial intelligence (AI) system for discovering novel, efficient, and provably correct algorithms for fundamental tasks such as matrix multiplication. This sheds light on a 50-year-old open question in mathematics about finding the fastest way to multiply two matrices. This paper is a stepping stone in DeepMind’s mission to advance science and unlock the most fundamental problems using AI. Our system, AlphaTensor, builds upon AlphaZero, an agent that has shown superhuman performance on board games, like chess, Go and shogi, and this work shows the journey of AlphaZero from playing games to tackling unsolved mathematical problems for the first time.

Fifteen bachelor's and master's degree students from the Barcelona School of Industrial Engineering (ETSEIB) of the Universitat Politècnica de Catalunya · BarcelonaTech (UPC) share the same dream: improving the quality of life of people with disabilities using assistive technologies. Specifically, the young biomedical engineering team Arm2u is developing a transradial prosthesis—which replaces an arm missing below the elbow—with myoelectric control (i.e., controlled by the natural electrical signals produced by muscle contraction).

A team led by the University of California San Diego has developed a new system of algorithms that enables four-legged robots to walk and run on challenging terrain while avoiding both static and moving obstacles.

Powered by AI, CMES Robotics enables 3D vision for factory robots. CMES AI vision software enables robots to recognize unstructured, flexible, or deformed objects, pick them up, and loading and unloading. CMES Vision software has been deployed worldwide for random palletization and depalletization along with void filling applications. CMES Robotics automates your warehouse, logistics, and supply chain. For more information, please visit: cmesrobotics.com or email info@cmesrobotics.com.

The palletizing magnet design recently modified by Goudsmit Magnetics consists of modules that vary in design. The low-maintenance magnet is suitable for palletizing and depalletizing cans, aerosols, canisters and glass jars with steel lids.

By Wafa Johal (Senior Lecturer, Computing & Information Systems, The University of Melbourne)

In August 2021, Tesla CEO Elon Musk announced the electric car manufacturer was planning to get into the robot business. In a presentation accompanied by a human dressed as a robot, Musk said work was beginning on a “friendly” humanoid robot to “navigate through a world built for humans and eliminate dangerous, repetitive and boring tasks”.

Musk has now unveiled a prototype of the robot, called Optimus, which he hopes to mass-produce and sell for less than US$20,000 (A$31,000).

At the unveiling, the robot walked on a flat surface and waved to the crowd, and was shown doing simple manual tasks such as carrying and lifting in a video. As a robotics researcher, I didn’t find the demonstration very impressive – but I am hopeful it will lead to bigger and better things.

Why would we want humanoid robots?

Most of the robots used today don’t look anything like people. Instead, they are machines designed to carry out a specific purpose, like the industrial robots used in factories or the robot vacuum cleaner you might have in your house.

So why would you want one shaped like a human? The basic answer is they would be able to operate in environments designed for humans.

Unlike industrial robots, humanoid robots might be able to move around and interact with humans. Unlike robot vacuum cleaners, they might be able to go up stairs or traverse uneven terrain.

And as well as practical considerations, the idea of “artificial humans” has long had an appeal for inventors and science-fiction writers!

Room for improvement

Based on what we saw in the Tesla presentation, Optimus is a long way from being able to operate with humans or in human environments. The capabilities of the robot showcased fall far short of the state of the art in humanoid robotics.

The Atlas robot made by Boston Dynamics, for example, can walk outdoors and carry out flips and other acrobatic manoeuvres.

And while Atlas is an experimental system, even the commercially available Digit from Agility Robotics is much more capable than what we have seen from Optimus. Digit can walk on various terrains, avoid obstacles, rebalance itself when bumped, and pick up and put down objects.

Bipedal walking (on two feet) alone is no longer a great achievement for a robot. Indeed, with a bit of knowledge and determination you can build such a robot yourself using open source software.

There was also no sign in the Optimus presentation of how it will interact with humans. This will be essential for any robot that works in human environments: not only for collaborating with humans, but also for basic safety.

It can be very tricky for a robot to accomplish seemingly simple tasks such as handing an object to a human, but this is something we would want a domestic humanoid robot to be able to do.

Sceptical consumers

Others have tried to build and sell humanoid robots in the past, such as Honda’s ASIMO and SoftBank’s Pepper. But so far they have never really taken off.

Amazon’s recently released Astro robot may make inroads here, but it may also go the way of its predecessors.

Consumers seem to be sceptical of robots. To date, the only widely adopted household robots are the Roomba-like vacuum cleaners, which have been available since 2002.

To succeed, a humanoid robot will need be able to do something humans can’t to justify the price tag. At this stage the use case for Optimus is still not very clear.

Hope for the future

Despite these criticisms, I am hopeful about the Optimus project. It is still in the very early stages, and the presentation seemed to be aimed at recruiting new staff as much as anything else.

Tesla certainly has plenty of resources to throw at the problem. We know it has the capacity to mass produce the robots if development gets that far.

Musk’s knack for gaining attention may also be helpful – not only for attracting talent to the project, but also to drum up interest among consumers.

Robotics is a challenging field, and it’s difficult to move fast. I hope Optimus succeeds, both to make something cool we can use – and to push the field of robotics forward.

Wafa Johal receives funding from the Australian Research Council.

This article appeared in The Conversation.

The e.DO Learning Center is an educational environment for students and teachers that uses the e.DO robot to explore STEM subjects, coding, robotics, and to spread a new working culture

Cassie the robot sets 100-metre record, photo by Kegan Sims.

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.”