Mars Planner: Improved Batch Spatio-Temporal Path Planning for Multi-Ackerman Robotic Systems

This paper introduces an innovative multi-agent path finding (MAPF) system specifically designed for navigating multi-Ackerman robotic systems in intricate environments. The Mars Planner, the proposed solution, enhances path planning by tackling collision-free path challenges encountered by groups of intelligent agents. Our contributions include the development of two key algorithms: the Fast Batch Path Finding (FBPF) and the Batch Spatio-Temporal Path Refinement (BSTPR). FBPF utilizes a hybrid A* approach to generate preliminary coarse paths within free configuration spaces, while BSTPR refines these paths using topological homotopy strategies to optimize time allocation and effectively resolve internal conflicts. Through simulations and physical experiments, we demonstrate significant enhancements in computational efficiency and path quality compared to existing methods. In conclusion, the Mars Planner stands as an efficient solution capable of managing large-scale complexity in real-world applications. It offers a robust and scalable framework suitable for diverse environments and scenarios.

I. Introduction

Recently, multi-agent path finding (MAPF) [1] has re-ceived increasing attention due to the rapid development of artificial intelligence and robotics. Since the primary goal of MAPF [2], [3] is to plan collision-free paths that satisfy kinematic constraints for clusters of agnet to reach their respective target positions, makes MAPF applicable across various domains, including warehouse material handling [4], drone delivery [5], unmanned surface vehicles [6], office robots [7], and so on. However, in practical scenarios, MAPF encounters the challenge of planning the path of large-scale agents in complex and obstruction-dense environments. Consequently, how to efficiently resolve the conflict between agents has emerged as a critical research frontier.