非结构化场景下基于改进JPS算法的移动机器人路径规划

针对移动机器人在大范围非结构化场景下的路径规划问题,在改进跳点搜索(JPS)算法的基础上结合A*搜索,提出一种基于分层栅格地图的Jump A*(JA*)路径规划算法.该算法对三维点云地图进行栅格化分层处理,将环境信息划分为结构层与非结构层,并建立搜索策略切换规则,依据图层信息使用不同的搜索策略,从而有效减少计算量.为了验证JA*算法的有效性,在图层比例不同的三维地图中进行仿真,仿真结果表明,JA*算法相比于传统的A*算法遍历节点更少,搜索效率更高;相比于双向A*算法,具有更高的鲁棒性.最后将JA*算法应用在公开数据集中,实验结果表明,JA*算法能有效解决移动机器人在大范围非结构化场景下的路径规划问题.

Mobile robot path planning based on improved JPS algorithm in unstructured scenarios

Aiming at the path planning problem of mobile robots in a large range of unstructured scenes, this paper proposes a Jump A*(JA*) path planning algorithm based on a hierarchical grid map, which combines the improved jump point search(JPS) algorithm with A* search. In this algorithm, the 3D point cloud map is rasterized and stratified, and the environmental information is divided into a structural layer and a non-structural layer. In addition, the search strategy switching rules are established, and different search strategies are used according to the layer information, so as to effectively reduce the computational cost. In order to verify the effectiveness of the JA* algorithm, simulation is carried out in 3D maps with different layer proportions. Simulation results show that compared with the traditional A* algorithm, the JA* algorithm traverses fewer nodes, has higher search efficiency, and has higher robustness compared with the bidirectional A* algorithm. Finally, the JA* algorithm is applied to the public data set, and the experimental results show that the JA* algorithm can effectively solve the path planning problem of a mobile robot in a large range of unstructured scenarios.