When we think of robots, images of cold, rigid machines often spring to mind. However, according to US research, teaching bipedal robots to imitate human movements, including dancing, could shift our perceptions, facilitating their integration into society and improving their cooperation with humans.

Research from the University of California, San Diego has demonstrated that robots are capable of imitating more expressive, human-like gestures, thanks to an innovative motion capture method called Expressive Whole-Body Control (ExBody). This breakthrough aims to boost trust between robots and humans by making the former appear friendlier and more collaborative.

UC San Diego engineers managed to teach their robot to perform complex movements, such as dancing, shaking hands, holding a door or even hugging. Their methodology draws on a vast collection of motion capture data and dance videos to train the robot.

"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," study coauthor Xiaolong Wang explains in a news release. "We are working to help reshape public perceptions of robots as friendly and collaborative rather than terrifying like The Terminator."

After analysing 10,000 hand position points and 10,000 trajectories across 4,096 simulated environments, the team developed a coordinated policy enabling the robot to execute complex actions while simultaneously walking on a variety of surfaces such as gravel, dirt, grass and sloping concrete paths.

Tests have already demonstrated the effectiveness of humanoid robots in collaborative tasks with humans. However, thanks to this new learning technique, this robot was tested in situations performing actions such as directing vehicle traffic or making basketball signals as a referee, demonstrating its ability to respond to dynamic and complex situations.

Currently, the robot's movements are controlled by a human operator using a game controller, but the team is planning a future version equipped with a camera, enabling the robot to perform tasks and navigate autonomously.

"By extending the capabilities of the upper body, we can expand the range of motions and gestures the robot can perform," Wang concludes.

 - AFP