CMP: Cooperative Motion Prediction with Multi-Agent Communication

arXiv:2403.17916v1 Announce Type: cross
Abstract: The confluence of the advancement of Autonomous Vehicles (AVs) and the maturity of Vehicle-to-Everything (V2X) communication has enabled the capability of cooperative connected and automated vehicles (CAVs). Building on top of cooperative perception, this paper explores the feasibility and effectiveness of cooperative motion prediction. Our method, CMP, takes LiDAR signals as input to enhance tracking and prediction capabilities. Unlike previous work that focuses separately on either cooperative perception or motion prediction, our framework, to the …

abstract advancement agent arxiv automated automated vehicles autonomous autonomous vehicles avs building capability communication confluence cs.ai cs.cv cs.lg cs.ma cs.ro everything multi-agent paper perception prediction type vehicles