search menu icon-carat-right cmu-wordmark

Multi-Agent Decentralized Planning for Adversarial Robotic Teams

Robotic Teams

Software Engineering Institute


For the past four years; the SSD CPS-ULS group has been working on technologies to enable one human operator to control and interact with a team of autonomous; unmanned systems. In FY16 MADPARTS; we focused on defensive algorithms that protect a human operator or an important asset from a mobile adversary. We demonstrated our line-of-sight prevention algorithms in simulated quadcopters and in real-world demonstrations with unmanned surface vehicles in lakes near Pittsburgh. The algorithms resulted in line-of-sight prevention at over 99% success rates in simulations against mobile adversaries