Communications of the ACM
Worker Robots that Learn from Mistakes
University of Leeds scientists are using automated planning and reinforcement learning to train a robot to find an object in a cluttered space and move it.
Credit: University of Leeds (U.K.)
Computer scientists at the University of Leeds in the U.K. are using the artificial intelligence techniques of automated planning and reinforcement learning to train a robot to find an object in a cluttered space and move it.
The goal is to develop robotic autonomy, a state in which the machine can assess the unique circumstances presented in a task and find a solution.
The main challenge is that in a confined area, a robotic arm may not be able to grasp an object from above, and instead must plan a sequence of moves to reach the target object in a way that allows it to grasp the object.
Said Leeds researcher Wissam Bejjani, "Our work is significant because it combines planning with reinforcement learning. A lot of research to try and develop this technology focuses on just one of those approaches."
From University of Leeds (U.K.)
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA
No entries found