“Through expressive and more human-like body motions, we aim to build trust and showcase the potential for robots to co-exist in harmony with humans,” says Xiaolong Wang, Ph.D., a professor of electrical and computer engineering at UC San Diego. “We are working to help reshape public perceptions of robots as friendly and collaborative rather than terrifying like The Terminator.”

Wang and his colleagues used an extensive collection of motion capture data and dance videos. They trained the robot’s upper and lower body separately. This approach allowed the machine’s upper body to replicate various reference motions, such as dancing and high-fiving, while its legs focused on a steady stepping motion to maintain balance and traverse different terrains.

“The main goal here is to show the ability of the robot to do different things while it’s walking from place to place without falling,” explains Wang. “By extending the capabilities of the upper body, we can expand the range of motions and gestures the robot can perform.”

Despite the separate training of the upper and lower body, the robot operates under a unified policy that governs its entire structure. This ensures that it can perform complex upper body gestures while walking steadily on surfaces like gravel, dirt, wood chips, grass and inclined concrete paths.