Simulation-Informed Diffusion for Decentralized Multi-robot Motion Planning

ArXi:2605.27697v1 Announce Type: cross Decentralized multi-robot motion planning requires each robot to generate collision-free trajectories from local observations, without global sensing or reliable communication. However, most existing planners, whether classical or learning-based, generate trajectories from a static snapshot of the local observation, which limits their ability to anticipate the future behavior of neighboring robots. This limitation is critical as the number of robots increases and the environment becomes cluttered. To overcome this challenge, this paper