An Efficient and Lightweight Multi-Goal Path Planning Based on Enhanced Sampling Planner

Abstract

In this work, we propose a novel lightweight and efficient multi-goal path planning (MGPP) framework tailored for complex environments with obstacles. The framework adopts a hierarchical architecture consisting of two layers: a visiting order decision layer and an incremental sampling-based planning layer. In the visiting order decision layer, a lightweight feature node graph (FNG) is constructed to capture the connectivity structure of the environment. Based on the FNG, a multi-query strategy is employed to efficiently build the goal-to-goal cost matrix, achieving both computational efficiency and completeness. Given this cost matrix, a near-optimal Hamiltonian path with fixed start and end points is computed to determine the visiting order of the goal set. In the path planning layer, an enhanced sampling-based path planner is developed to perform efficient goal-to-goal path planning. The proposed enhanced sampling method explores multiple homotopy classes of interest, which improves planning efficiency and helps avoid local minima. Finally, extensive simulations and experiments in complex scenarios validate the effectiveness and advantages of the proposed method.