Communications of the ACM
Scientists Pave the Way for Resilient Robot Swarms
University of Southampton researchers say they are using bio-inspired algorithms and machine learning to develop fault-tolerant robotic swarms.
Credit: Harvard University
Researchers at the University of Southampton in the U.K. say they are developing fault-tolerant robotic swarms using bio-inspired algorithms and machine learning.
The team will conduct research designed to create the next generation of robot swarms, to be capable of sustained operation for extended periods of time without human intervention.
The researchers note the overall goal of the project is to ensure that robot swarms are able to deal with damages and faults sustained during operations.
The Southampton team has proposed that robots move beyond traditional approaches because it is not possible to predict all the scenarios a swarm may encounter while operating in complex environments for extended periods of time.
The new approach will enable robots to adopt their behavior to sustained faults within the swarm by learning through trial-and-error. The researchers believe the resulting system of working swarm behavior could result in new applications for long-term deployment.
From University of Southampton
View Full Article
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA
No entries found