ParaMaP: Real-time Robot Manipulation with Parallel Mapping and Planning

This paper addresses the challenge of real-time, collision-free motion planning for robotic manipulation in dynamic environments. It proposes a novel framework, ParaMaP, that integrates GPU-accelerated Euclidean Distance Transform (EDT) for environment representation with a sampling-based Model Predictive Control (SMPC) planner. The key innovation lies in the parallel execution of mapping and planning, enabling high-frequency replanning and reactive behavior. The use of a robot-masked update mechanism and a geometrically consistent pose tracking metric further enhances the system's performance. The paper's significance lies in its potential to improve the responsiveness and adaptability of robots in complex and uncertain environments.