State Space Sampling for Adaptive Path Planning in Outdoor Unstructured Environments

Le résumé fourni par la source

This paper addresses the challenges faced by autonomous ground robot navigation in unstructured outdoor environments. Traditional control space sampling methods lack task orientation and may lead to collisions. This paper proposed a state space sampling-based path planning method. The method takes the global path as input and samples a set of attitudes parallel to the sub-goal points in the state space. It then generates multiple local paths with end states parallel to each other by applying two-point boundary value constraints. We select the optimal local path that avoids obstacles and closely follows the global path. Then the selected path is integrated with global path planning from a bi-layer planner, enabling safe robot navigation in complex outdoor environments. Experiments in various scenarios validate the method's effectiveness and compare its performance with other local path-planning approaches.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.