Helping Robots Collaborate to Get the Job Done

An algorithm developed by researchers at the Massachusetts Institute of Technology (MIT), the University of Pennsylvania, and the University of California, San Diego aims to foster cooperation between information-gathering robot teams.

The algorithm balances data collection and energy expenditure to avoid having robots perform maneuvers that waste energy to gain only a small amount of data.

Using the researchers' Distributed Local Search approach, each robot proposes a potential trajectory for itself as part of the team, and the algorithm accepts or rejects them based whether it will increase the likelihood of achieving the team's objective function.

A test involving a simulated team of 10 robots showed that the algorithm required more computation time, but guaranteed their mission would be completed successfully.

From MIT News
View Full Article

Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA