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:
- An “EPIC” Way To Evaluate Reward Functions In Reinforcement Learningon April 30, 2021 at 1:30 am
Unlike a typical neural network, used for photo tagging, RL's use cases -- self driving, robotics for medical surgeries -- are more critical.
- Computational medication regimen for Parkinson’s disease using reinforcement learningon April 29, 2021 at 9:49 am
Our objective is to derive a sequential decision-making rule on the combination of medications to minimize motor symptoms using reinforcement learning (RL). Using an observational longitudinal cohort ...
- Multiagent Meta-Reinforcement Learning for Adaptive Multipath Routing Optimizationon April 27, 2021 at 9:35 pm
In this article, we investigate the routing problem of packet networks through multiagent reinforcement learning (RL), which is a very challenging topic in distributed and autonomous networked systems ...
- A Reinforcement Learning-Based Vehicle Platoon Control Strategy for Reducing Energy Consumption in Traffic Oscillationson April 27, 2021 at 12:12 pm
The vehicle platoon will be the most dominant driving mode on future roads. To the best of our knowledge, few reinforcement learning (RL) algorithms have been applied in vehicle platoon control, which ...
- AWS open-sources DeepRacer machine learning software to let developers tinker at homeon April 27, 2021 at 11:08 am
AWS DeepRacer provides a fast way to learn about machine learning programming by putting it into practical terms using autonomous vehicles as a real-world example of its use. In DeepRacer’s case, it ...
Go deeper with Google Headlines on:
Go deeper with Bing News on:
- Attabotics Partners With AltaML and Amii on Artificial Intelligence and Machine Learning Capabilities for Supply Chainson April 30, 2021 at 12:46 pm
Attabotics, a 3D robotics supply chain company, today announced a partnership with AltaML, a Canadian applied artificial intelligence and machine learning company, and the Alberta Machine Intelligence ...
- Science Learning: How to inspire a little Einsteinon April 30, 2021 at 7:00 am
When our kids grow up, if they want to land a robot on Mars or cure a deadly disease, they’ll need strong science skills, and that learning starts early.
- STATE-OF-THE-ART INNOVATION INCUBATOR AND LEARNING CENTER IN THE EECon April 30, 2021 at 3:05 am
Embracing the significance of automation and robotics as the key transformative force for global productivity, the Thai government has laid strong groundwork for the growth of the country’s automation ...
- Samsung Bespoke Jet Bot AI Robot Vacuum Cleaner launched in Koreaon April 29, 2021 at 8:49 pm
Samsung has unveiled the Bespoke Jet Bot AI Robot Vacuum Cleaner designed to significantly improve home cleaning duties. The robot vacuum cleaner features enhanced capabilities for object recognition ...
- Vision for ultra-precision ag: Machine learning, plant sensing, robots tending cropson April 29, 2021 at 1:42 pm
A gardener hoping for a crop of the juiciest summer tomatoes might tend to each and every plant in a plot. But a farmer working to feed the world?