Event
WarpWeaver: Paper on Decentralized Real-Time Planning for Multi-Robot Systems Released
1 reports · 1 sources
Shashank A. Deshpande, Blake T. Edwards, and Jonathan P. How submitted a paper proposing WarpWeaver, a decentralized real-time planner: each robot negotiates shared space rents through decentralized column generation, causing the searched dispersive tree to converge to a near-optimal consistent solution. The paper has been submitted to IEEE Transactions on Robotics. The authors report that in Dynobench simulations, WarpWeaver reduces total travel time by up to 22% compared with a centralized offline planner and by up to 37% compared with decentralized real-time baselines; on graph connectivity tasks, it nearly doubles the success rate of a specialized planner. An onboard planning experiment with six robots was used to verify practical deployability.
Report timeline
- WarpWeaver: A Decentralized Real-Time Planner for Multi-Robot Coordination
The paper proposes WarpWeaver, a decentralized real-time planner that negotiates shared-space rents among robots through decentralized column generation, so that the dispersive trees searched by each robot converge to a near-optimal consistent solution. In Dynobench simulations, its total travel time is up to 22% lower than a centralized offline planner and up to 37% lower than decentralized real-time baselines, and on a graph-connectivity task it nearly doubles the success rate of a specialized planner. Onboard planning experiments with six robots verified practical deployability.
arXiv cs.RO ·