基于改进A^(*)算法的地下自动驾驶铲运机路径规划  

Path Planning of Underground Autonomous LHD Machines Based on Improved A^(*)Algorithm

作　　者：崔冰 赵辉军 段景文 魏威 谭丽龙 刘永春 CUIBing;ZHAO Huijun;DUAN Jingwen;WEI Wei;TAN Lilong;LIU Yongchun(Northern Mining Co.,Ltd..Beijing 100053,China;Changsha Dimine Technology Co.,Ltd.,Changsha,Hunan 410205,China;Changsha Smart Technology Co.,Ltd.,Changsha,Hunan 410012,China;Intelligent Hardware and Software(Embedded)Changsha New Generation of Artificial Intelligence Open Innovation Platform,Changsha,Hunan 41o012,China)

机构地区：[1]北方矿业有限责任公司,北京100053 [2]长沙迪迈科技股份有限公司,湖南长沙410205 [3]长沙施玛特迈科技有限公司,湖南长沙410012 [4]智能软硬件(嵌入式)长沙市新一代人工智能开放创新平台,湖南长沙410012

出　　处：《矿业研究与开发》2024年第5期185-193,共9页Mining Research and Development

基　　金：湖南省重点领域研发计划项目(2022GK2061).

摘　　要：为解决自动驾驶铲运机路径规划的安全和效率问题,提出一种基于改进A^(*)算法的地下自动驾驶铲运机路径规划方法.该方法通过将A^(*)节点扩展限制在巷道骨架范围内,使得规划路径分布于巷道中央区域,并采用矿山的真实地图数据进行了对比试验和路径跟踪应用.结果表明,使用曼哈顿距离作为算法的启发函数表现最优,且相较于传统A^(*)算法,改进A^(*)算法的规划路径更接近巷道中央、平均耗时减少约76.0%,在安全性和规划速度方面具有优越性.现场应用中,自动驾驶铲运机的平均跟踪偏差为0.26m,能够根据规划路径安全抵达终点.研究结果可为地下矿无人驾驶系统的建设提供参考.To solve the problem of safety and efficiency of path planning for autonomous LHD machines,a path planning method for underground autonomous LHD machines based on an improved A^(*)algorithm was proposed.By extracting the roadway skeleton,the node expansion of the A^(*)algorithm was limited to the skeleton area,which ensured that the planned path was in the central area of the roadway.Comparative experiments and path tracking applications were conducted using real map data from mines.The results show that using Manhattan distance as the heuristic function of the algorithm performs the best,and by comparing to the traditional A^(*)algorithm,the improved A^(*)algorithm has a planning path closer to the center of the roadway,with an average time reduction of about 76.0%and superior safety and planning speed.In on-site applications,the average tracking deviation of the autonomous LHD machine is 0.26 m,and it can safely reach the endpoint according to the planned path.The research results can provide a reference for the construction of unmanned driving systems in underground mines.

关 键 词：自动驾驶 路径规划 铲运机 改进A^(*)算法 启发函数 

分 类 号：TD422.4[矿业工程—矿山机电]