基于改进混合A*算法的地下无人铲运机智能路径规划

矿山无人铲运机自主定位导航是井下采矿装备智能化程度评价的重要指标，其中路径规划是铲运机自主行走的重要组成部分。而目前井下铲运机的规划路径多以巷道中心线为基础或难以执行，本文提出了一种适用于地下矿采场无人铲运机的混合A*算法进行出矿点到卸矿点的全局路径规划。首先分析了井下铲运机的运动模型，确定其路径规划参考点及车辆本身的数学结构关系，简化路径规划问题复杂度；其次针对铲运机作为非完整约束机器人，从栅格地图中当前点到目标点启发式函数构建以及子节点扩展方法两个方面设计了混合A*算法进行全局路径规划方法；最终采用地下矿采场中常见的五种巷道交岔口场景进行了路径规划试验分析，证明了以Dubins曲线、ReedsShepps曲线以及A*算法的启发式函数值中最大值作为该节点启发式函数的值进行混合A*算法搜索更新较为合理，能得到可以行驶的优化路径。为进一步推进井下铲运机无人化提供了理论基础，保证了规划路径的可执行性。

Intelligent Path Planning of Underground Unmanned LHD based on Improved Hybrid A * Algorithm

Autonomous positioning and navigation of mine unmanned LHD is an important index for evaluating the intelligence of underground mining equipment, path planning is an important part of the autonomous driving of LHD in underground mining. At present, the planning path of the underground LHD is mostly based on the center line of the roadway, or it is difficult to implement. In this paper, a hybrid A * algorithm suitable for unmanned LHD in underground mining was proposed to conduct the global path planning from the mining point to the unloading point. Firstly, the motion model of the underground LHD was analyzed, and the mathematical structure relationship between its path planning reference point and the vehicle itself is determined to simplify the complexity of the path planning problem. Secondly, as a nonholonomic constraint robot, a hybrid A* algorithm was designed for global path planning from the current point to the target point heuristic function construction in the grid map and the sub-node expansion method. Finally, the path planning analysis was carried out by using the five common roadway intersection scenes in underground mining. It is proved that it is reasonable to use the maximum value of the heuristic function value of the Dubins curve, the ReedsShepps curve, and the A* algorithm as the value of the heuristic function of the node to search and update the hybrid A* algorithm. The optimized path can be obtained. It provides a theoretical basis for further promoting the unmanned underground LHD and ensures the enforceability of the planned path.