Sign In

Communications of the ACM

ACM TechNews

Helping Hands Guide Robots as They Learn


Rice University graduate student Dylan Losey using gentle feedback to train a robot arm to manipulate a coffee cup in real time.

Rice University researchers want to help humans and robots collaborate.

Credit: Andrea Bajcsy

Researchers at Rice University have developed a program that guides robots toward the most helpful ways to collaborate on tasks, with the goal of simplifying the training of robots to work efficiently side-by-side with humans.

The researchers say they have enhanced physical human-robot interaction with a method that enables humans to physically adjust a robot's trajectory in real time.

The program is based on the concept of impedance control, which lets a robot adjust its programmed trajectory to respond before returning to its initial trajectory when the input ends. The Rice algorithm builds on that concept by enabling the robot to adjust its path beyond the input and calculate a new route to its goal.

The researchers found robots with trajectory deformation were physically easier and required significantly less interaction in order to achieve the goal. In addition, the experiments showed interactions can program otherwise autonomous robots that have several degrees of freedom.

From Rice News
View Full Article

 

Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA


 

No entries found