Decentralized, Safe, Multi-agent Motion Planning for Drones Under Uncertainty via Filtered Reinfo...

Decentralized, Safe, Multi-agent Motion Planning for Drones Under Uncertainty via Filtered Reinforcement Learning
This video demonstrates our recent work on decentralized, multi-agent motion planning under stochastic uncertainty. Our scalable approach generates safe motion plans in real-time using off-the-shelf, single-agent reinforcement learning rendered safe using distributionally-robust, convex optimization and buffered Voronoi cells. The associated paper is under review at an IEEE journal.
Related prior work: Safaoui, Sleiman, Abraham P. Vinod, Ankush Chakrabarty, Rien Quirynen, Nobuyuki Yoshikawa, and Stefano Di Cairano. "Safe multi-agent motion planning under uncertainty for drones using filtered reinforcement learning." IEEE Transactions on Robotics (2024).
DOI: doi.org/10.1109/TRO.2024.3387010
Paper: www.merl.com/publications/doc...
Video: • [TRO 2024] Safe Multia...