基于改进A^*算法的无人搜救全局路径规划研究  

Research on SAR drone global path planning based on improved A^*algorithm

作　　者：李世国 苏卫华 郭鹏飞 张世月 谢鹏发 LI Shi-guo;SU Wei-hua;GUO Peng-fei;ZHANG Shi-yue;XIE Peng-fa(National Innovation Institute of Defense Technology,Academy of Military Science of Chinese PLA,Beijing 100071,China;Tianjin Artificial Intelligence Innovation Center(TAIIC),Tianjin 300457,China;School of Mechanical Engineering,Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control,Tianjin University of Technology,Tianjin 300384,China)

机构地区：[1]军事科学院国防科技创新研究院,北京100071 [2]天津(滨海)人工智能创新中心,天津300457 [3]天津理工大学机械工程学院天津市先进机电系统设计与智能控制重点实验室,天津300384

出　　处：《医疗卫生装备》2020年第12期16-20,共5页Chinese Medical Equipment Journal

基　　金：天津市科技计划项目(18ZXJMTG00160,19ZXJRGX00080)。

摘　　要：目的:研究一种改进双向A*算法来减少搜救无人机规划的路径长度和规划路径所需的时间,缩短搜救无人机到达灾害现场的时间,进而提升搜救工作效率。方法:首先对三维城市环境地图进行预处理,在障碍物周围的区域加入缓冲区;然后使用双向A^*算法,在起点和终点同步进行搜索,同时改进真实代价函数和估价函数;最后对双向A^*算法生成的路径进行进一步平滑处理。使用MATLAB软件对改进双向A^*算法和传统A^*算法在不同大小的三维城市环境地图上进行仿真实验,并对规划得到的路径长度、运行时间和转向次数进行对比。结果:与传统A^*算法相比较,改进双向A^*算法运行的时间减少了44%、路径长度减少了5.4%、转向次数减少了51%。结论:改进双向A^*算法与传统A^*算法相比,在三维城市环境地图下能有效提高搜救无人机的工作效率和安全性,具有重要的理论意义和应用价值。Objective To develop an improved bidirectional A^*algorithm so as to reduce the path length and the time required to plan the path for the SAR drone,and to shorten the time for the SAR drone to reach the disaster site.Methods The 3D urban environment map was pre-processed by adding buffers to the area around the obstacles;then a bidirectional A^*algorithm was used for searching simultaneously at the start and end points,while improving the true cost function and the valuation function;finally,the paths generated by the bidirectional A^*algorithm were further smoothed.Simulation experiments were conducted using MATLAB software to compare the planned path lengths,running time,and turning times by the improved bidirectional A*algorithm and the traditional one on different sized maps of the 3D urban environment.Results The improved A^*algorithm had the running time shortened by 44%,path length reduced by 5.4%and turning times decreased by 51%when compared with the traditional one.Conclusion Compared with the traditional A^*algorithm,the improved bidirectional A^*algorithm can effectively improve the efficiency and safety of the SAR drone in 3D urban environment map,which has important theoretical significance and application values.

关 键 词：搜救无人机 路径规划 A^*算法 改进A^*算法 双向搜索 轨迹优化 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] V279[自动化与计算机技术—控制科学与工程] X4[航空宇航科学与技术—飞行器设计]