New Scientist
A new AI system, ExBody2, enables humanoid robots to learn movements by mirroring human actions. By using motion-capture data and reinforcement learning, ExBody2 helps robots replicate complex movements like walking and dancing, including waltzing with humans. This advancement improves robots’ fluidity and coordination, making their movements more human-like.
Humanoid robot learns to waltz by mirroring people’s movements
Author: Alex Wilkins
An artificial intelligence that helps humanoid robots replicate a person’s movement could allow robots to walk and dance in more human ways.
The most agile and fluid robotic movements are typically narrow, pre-programmed sequences. Teaching robots to perform a wider repertoire of convincingly human movements is still difficult.
To overcome this hurdle, Xuanbin Peng at the University of California, San Diego, and his colleagues have developed an artificial intelligence system called ExBody2, which lets robots copy and smoothly perform many different human movements in more lifelike ways.
Peng and his team first created a database of actions that a humanoid robot might be capable of performing, from standing to tricky dance moves. This included motion-capture recordings of people collected in previous projects.
“Since humanoid robots share a similar physical structure with us, it makes sense to take advantage of the vast amounts of human motion data already available,” says Peng. “By learning to mimic this kind of motion, the robot can quickly pick up a wide variety of human-like behaviours.”
Peng and his team next trained ExBody2 using reinforcement learning, giving the AI an example of a successful movement and then tasking it with figuring out how to do it itself by trial and error.
ExBody2 was then put in control of two different humanoid robots. It was able to smoothly string together simple movements, such as walking and crouching, as well as perform trickier moves, such as waltzing with a human (arXiv, doi.org/n24g).
“Humanoid robots work best when they coordinate all their limbs and joints together,” says Peng. “Full- body coordination greatly expands the robot’s range of capabilities.”
Credits: TCA, LLC.