acm-header
Sign In

Communications of the ACM

ACM TechNews

Robots on the March to Walking Like Humans


View as: Print Mobile App Share:
Honda's ASIMO bipedal robot.

University of Manchester researchers have found that the better a robot can balance, the better prepared it is for walking like a human.

Credit: Reza Ghorbani

Researchers at the University of Manchester in the U.K. have found that the better a robot can balance, the better prepared it will be for walking like a human.

The researchers analyzed what happens when standard algorithms for driving a self-balancing robot were replaced with those based on perceptual control theory, a model of behavior based on the principles of negative feedback that has been widely used in psychological therapies, education, and parenting interventions.

This theory was encoded into a small droid, allowing it to control what it sensed and move around more effectively than other robotic systems.

Said Manchester's Warren Mansell, "It is tantalizing to see how a scientific theory used to help people with mental health problems might actually help engineers to improve their designs of artificially intelligent devices."

From University of Manchester (U.K.)
View Full Article

 

Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account