A group of engineers at the University of California in San Diego have successfully taught a humanoid robot to perform a variety of expressive gestures such as dance moves, high fives and hugging. The study has been conducted to show the potential in the human-robot relationship, reframing common misconceptions around what robots can actually do.
“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,” said Xiaolong Wang, a professor in the Department of Electrical and Computer Engineering at the UC San Diego Jacobs School of Engineering. “We are working to help reshape public perceptions of robots as friendly and collaborative rather than terrifying like The Terminator.”
Through the use of motion capture data and dance videos, the robot has learnt to replicate the various moves through imitation. The researchers tackled the problem of the robot’s inability to directly replicate the data through the creation of the Expressive Whole-Body Control (ExBody) method. Their approach instructs the upper and lower parts of the humanoid’s body to operate separately, with the legs repeating a stepping motion to maintain balance while the arms and torso focus on mirroring the reference behaviours.
The group tested out the gestures by operating the bot on a variety of different surfaces. It was assessed on its speed, direction and ability to replicate the expressive gestures, as well as executing new movements based on what it had already learned, achieving all.
“The enhanced expressiveness and agility of this humanoid robot pave the way for improving human-robot interactions in settings such as factory assembly lines, hospitals and homes, where robots could safely operate alongside humans or even replace them in hazardous environments like laboratories or disaster sites,” the engineers said about the applications of the humanoid.
The robot is currently operated with a gaming controller, but the researchers state that their next objectives include facilitating it to operate independently through the attachment of a camera, along with increasing the complexity of the tasks it can perform.