Ken Goldberg at the University of California, Berkeley, and colleagues developed a robot system to efficiently pick up strewn clothes.
The researchers tried two approaches in conjunction with clothes-recognizing artificial intelligence, one using a depth-perception camera and the other using a standard color camera, to help the system sort a pile of 10 articles of clothing.
Once the robot finished putting the items in the bin, it would tip them out and start the task again, learning as it went. It went through the process more than 200 times.
After comparing the two approaches, Goldberg and his team combined them.
They also programmed the robot to perform tidying movements on the ground before it picked up the clothes.
The AI-enhanced system was found to be nearly 70% more efficient than a robot that just grasps random items of clothing one by one.
From New Scientist
View Full Article
Abstracts Copyright © 2023 SmithBucklin, Washington, D.C., USA
No entries found