via MIT Technology Review
A pair of robot legs called Cassie has been taught to walk using reinforcement learning, the training technique that teaches AIs complex behavior via trial and error. The two-legged robot learned a range of movements from scratch, including walking in a crouch and while carrying an unexpected load.
But can it boogie? Expectations for what robots can do run high thanks to viral videos put out by Boston Dynamics, which show its humanoid Atlas robot standing on one leg, jumping over boxes, and dancing. These videos have racked up millions of views and have even been parodied. The control Atlas has over its movements is impressive, but the choreographed sequences probably involve a lot of hand-tuning. (Boston Dynamics has not published details, so it’s hard to say how much.)
“These videos may lead some people to believe that this is a solved and easy problem,” says Zhongyu Li at the University of California, Berkeley, who worked on Cassie with his colleagues. “But we still have a long way to go to have humanoid robots reliably operate and live in human environments.” Cassie can’t yet dance, but teaching the human-size robot to walk by itself puts it several steps closer to being able to handle a wide range of terrain and recover when it stumbles or damages itself.
Virtual limitations: Reinforcement learning has been used to train many bots to walk inside simulations, but transferring that ability to the real world is hard. “Many of the videos that you see of virtual agents are not at all realistic,” says Chelsea Finn, an AI and robotics researcher at Stanford University, who was not involved in the work. Small differences between the simulated physical laws inside a virtual environment and the real physical laws outside it—such as how friction works between a robot’s feet and the ground—can lead to big failures when a robot tries to apply what it has learned. A heavy two-legged robot can lose balance and fall if its movements are even a tiny bit off.
Double simulation: But training a large robot through trial and error in the real world would be dangerous. To get around these problems, the Berkeley team used two levels of virtual environment. In the first, a simulated version of Cassie learned to walk by drawing on a large existing database of robot movements. This simulation was then transferred to a second virtual environment called SimMechanics that mirrors real-world physics with a high degree of accuracy—but at a cost in running speed. Only once Cassie seemed to walk well there was the learned walking model loaded into the actual robot.
The real Cassie was able to walk using the model learned in simulation without any extra fine-tuning. It could walk across rough and slippery terrain, carry unexpected loads, and recover from being pushed. During testing, Cassie also damaged two motors in its right leg but was able to adjust its movements to compensate. Finn thinks that this is exciting work. Edward Johns, who leads the Robot Learning Lab at Imperial College London agrees. “This is one of the most successful examples I have seen,” he says.
The Berkeley team hopes to use their approach to add to Cassie’s repertoire of movements. But don’t expect a dance-off anytime soon.
Original Article: Forget Boston Dynamics. This robot taught itself to walk
More from: University of California Berkeley
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Reinforcement learning
- Game-changing Assistive Technology: Toward Robotic Leg Control that Interacts with the Brain
And we’re using all of this with sensor fusion and machine learning to decode, ‘What does the patient want to do?’ This is then translated to the mid-level controller, which uses either reinforcement ...
- Report, experts suggest AI will simplify, not replace, majority of jobs in New York
A report by the UK Department of Education found that management consultants and business analysts are most likely to have their jobs taken by artificial intelligence, with manual labor less likely to ...
- China creating AI air combat system that can explain decisions it makes
The US initiated AI integration into air combat ahead of China. While China was still conducting live aerial engagements between human-piloted and AI-driven drones, US test pilots had already begun ...
- What Is a Large Language Model (LLM) and How Does It Affect You
Large language models (LLMs) play a big role in AI development. Discover what LLMs are and how they are reshaping how we use technology.
- MIT's Mighty Morphing Bots Set to Stretch and Squeeze into the Future!
MIT researchers have created a control algorithm that allows soft robots to change shape for tasks such as navigating tight spaces or manipulating objects.
Go deeper with Google Headlines on:
Reinforcement learning
[google_news title=”” keyword=”reinforcement learning” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
Robot learning
- AI robot gives commencement speech at D’Youville University
A robot with artificial intelligence gave a commencement presentation during D'Youville University's graduation ceremony.
- AI robotics learning booms in US education
A small robot ran around the field, turning back and forth and then swiftly from left to right, picking up triballs, a ball in the shape of a triangle, and moving them into a net goal zone, then ...
- Exploration-focused training lets robotics AI immediately handle new tasks
Reinforcement-learning algorithms in systems like ChatGPT or Google’s Gemini can work wonders, but they usually need hundreds of thousands of shots at a task before they get good at it. That’s why ...
- A better way to control shape-shifting soft robots
A new machine-learning technique can train and control a reconfigurable soft robot that can dynamically change its shape to complete a task. The researchers also built a simulator that can evaluate ...
- Dexterous robot hand can take a beating in the name of AI research
A robotics company likely most famous for a demo of its dexterous robot hand at ICRA 2019 with Jeff Bezos has now unveiled a new robust model designed for machine learning research, which was ...
Go deeper with Google Headlines on:
Robot learning
[google_news title=”” keyword=”robot learning” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]