Multi-Agent Decentralized Planning for Adversarial Robotic Teams
November 2016 • Presentation
James Edmondson
Objective of this work is to allow one person to command an entire swarm of UAS to do mission-level tasks
Publisher:
Software Engineering Institute
Watch
Abstract
To meet the challenge of distributed autonomy in real-world robotics, we have created decentralized, multi-agent planning techniques, middleware, and algorithms that take into account a potentially changing adversary model in both simulations and real-world demonstrations with robotic unmanned surface vehicles.