Communications of the ACM
Self-Learning Robots Go Full Steam Ahead
Researchers have shown that a group of small autonomous self-learning robots can adapt easily to changing circumstances.
Credit: Soft Robotic Matter group/AMOLF
AMOLF researchers in the Netherlands demonstrated that a group of small autonomous self-learning robots can easily change what they are doing in response to changing conditions.
The team induced individual robotic carts that are interlinked and move on a track to maximize their speed in a certain direction without a programmed route or knowing what the others were doing.
The system is comprised of a microcontroller, a motion sensor, a pump that pumps air into a bellows, and a needle for deflation; linking a second robot to a robot's bellows causes the robots to push each other away, driving the robotic train.
Each robot is fed a set of rules via a short algorithm, while a chip continuously measures speed.
The AMOLF researchers found the robots could better adapt to changing situations with an algorithm that only uses the last speed measurement to decide the best moment for the pump to be switched on in each cycle.
From AMOLF (Netherlands)
View Full Article
Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA
No entries found