Humanoid Safety - Control Barrier Functions and Dodgeball (IMAGE)
Caption
While recent work on humanoid robots has been flashy and impressive, there is a chasm between pulling off exciting tricks in a controlled environment and being able to navigate in dynamic real-world settings. Humanoids are not yet fully capable of taking in information about and assessing rapidly changing settings. Aaron Ames of Caltech says current work on humanoid performance does not address the kinds of fundamental challenges that will arise when the robots have to sense and respond to nearby, often unfamiliar, obstacles—not step on the family dog, for example. "Little things like that are surprisingly very, very hard for robots," Ames says.
Ames invented control barrier functions (CBFs), a mathematical tool that guarantees the safety of robotic systems. His group is now applying CBFs to humanoid robots and experimenting with improvements. Here, he is shown throwing a dodgeball at a humanoid running a CBF-based safety layer that will help it avoid the ball.
Credit
AMBER Lab/Caltech
Usage Restrictions
none
License
Original content