随着煤矿智能化快速发展，矿用车辆无人驾驶技术已经成为研究热点方向，其技术关键是矿井巷道的实时定位与地图构建技术（Simultaneous Localization and Mapping，SLAM）和路径规划技术。但由于矿井环境特殊，存在巷道建图退化、路径规划效率低等问题，因此，本文对矿用无人车路径规划方法开展研究，主要内容如下：

（1）研究多传感器融合SLAM系统框架。首先，针对矿井巷道建图退化问题，采用融合单目相机/激光雷达和惯性测量单元SLAM方法构建高精度地图；其次，对巷道三维点云地图进行栅格化处理；最后，提出一种路径融合方法来实现在三维点云地图上的全局路径规划，为后续研究矿用无人车路径规划方法奠定基础。

（2）以A*算法作为全局路径规划基础开展矿用无人车路径规划方法研究。首先，通过量化障碍物信息，将其引入A*算法，建立自适应式启发函数，提高算法的搜索效率；其次，提出一种关键节点选取策略，优化全局路径节点的选择方式；最后，利用3次Clamped-B样条曲线对路径进行平滑处理，提高路径平滑度。

（3）以动态窗口法（Dynamic Window Approach，DWA）作为局部路径规划基础开展矿用无人车路径规划方法研究。首先，基于模糊控制原理，定义模糊系统的输入/输出量；其次，通过建立模糊规则，利用重心法解模糊化，完成模糊推理；最后，通过设计的DWA模糊控制器，实时调整权重系数，提高改进DWA算法的鲁棒性。

改进A*算法和改进模糊控制DWA混合的矿用无人车路径规划方法研究及实验验证。首先，将全局路径关键节点作为DWA动态规划的局部目标点，实现改进A*算法和改进模糊控制DWA混合路径规划方法设计；其次，根据矿井巷道行车规则设计路径规划实验，通过自行搭建的智能车辆实验平台进行模拟巷道路径规划实验，对混合方法的可行性和有效性进行验证；最后，实验结果表明，混合路径规划方法的效率更高，路径长度更短，在动态环境下路径的安全性更好，满足矿用车辆的驾驶需求。

With the rapid development of intelligent coal mine construction, the exploration of unmanned driving technology for mine vehicles has become a hot spot. The simultaneous localization and mapping (SLAM) technology and path planning technology of mine tunnels are key to the research of unmanned driving technology for mine vehicles. However, due to the special environment of mines, there are problems such as degradation of tunnels mapping and low efficiency of path planning. Therefore, this paper conducts research on the path planning method of unmanned mining vehicles, and the main content is as follows:

(1) The framework of multi-sensor fusion SLAM system is studied. Firstly, in order to solve the problem of degradation in mine roadway mapping, a high-precision map is constructed by using a fusion monocular camera / lidar, and inertial measurement unit SLAM method. Secondly, the 3D point cloud map of the roadway is rasterized. Finally, a path fusion method is proposed to achieve global path planning on 3D point cloud maps, laying the foundation for subsequent research on path planning methods for mining unmanned vehicles.

(2) Research on path planning methods for mine unmanned vehicles by using A* algorithm as the basis for global path planning. Firstly, the obstacle information is quantified and introduced it into the A * algorithm, which an adaptive heuristic function is established to improve the search efficiency of the algorithm in different environments. Secondly, a strategy for selecting key nodes is proposed and the selection method of global path node is optimized. Finally, the path is smoothed by using 3 times Clamped-B spline to improve the smoothness of the path.

(3) Research on path planning methods for mine unmanned vehicles by using the dynamic window approach (DWA) algorithm as the basis for local path planning. Firstly, based on the principle of fuzzy control, the input/output quantities of the fuzzy system are defined. Secondly, the fuzzy rules are by establishing and the centroid method is used to solve ambiguity, the fuzzy reasoning is completed. Finally, a DWA fuzzy controller is designed. The weight coefficients are adjusted in real-time, the robustness of the improved DWA algorithm can be improved.

(4) Research and experimental verification of a hybrid path planning method for mining unmanned vehicles based on improved A * algorithm and improved fuzzy control DWA. Firstly, the global path key nodes are used as local target points for DWA dynamic planning, and the improved A * algorithm and improved fuzzy control DWA hybrid path planning method are designed. Secondly, a path planning experiment is designed based on the driving rules of the mine tunnel, and a simulated tunnel path planning experiment is conducted using a self-built intelligent vehicle experimental platform to verify the feasibility and effectiveness of the hybrid method. Finally, The experimental results show that the hybrid path planning method has higher efficiency, shorter path length, and better path safety in dynamic environments, which meet the driving needs of mine vehicles.

[1]Yu H, Li S. The function design for the communication-based train control (cbtc) system: how to solve the problems in the underground mine rail transportation?[J]. Applied System Innovation, 2021, 4(2): 31.

[2]卞泽宇, 杜聿静, 董妍. 无轨胶轮车在煤矿辅助运输中的应用研究[J]. 机械管理开发, 2024, 39(01): 265-266+269.

[3]Zhou X, Yu X, Zhang Y. Trajectory planning and tracking strategy applied to an unmanned ground vehicle in the presence of obstacles[J]. IEEE Transactions on Automation Science and Engineering, 2020, 18(4): 1575-1589.

[4]Wang M, Bao J, Yuan X. Research status and development trend of unmanned driving technology in coal mine transportation[J]. Energies, 2022, 15(23): 9133.

[5]邓永胜. 煤矿井下无轨胶轮车的现状及应用[J]. 矿业装备, 2023, 13(02): 165-167.

[6]何佳, 戎辉, 王文扬.百度谷歌无人驾驶汽车发展综述[J]. 汽车电器, 2017, 58(12): 19-21.

[7]陈静. 无人驾驶汽车路径规划与路径跟踪研究[D]. 成都: 西华大学, 2019.

[8]丁震, 孟峰. 矿用无人卡车国内外研究现状及关键技术[J]. 中国煤炭, 2020, 46(02): 42-49.

[9]孔晋华. 煤矿机器人重点研发目录[R]. 北京: 国家煤矿安全监察局, 2019．

[10]高小强, 李程, 张沙. 露天矿大吨位自卸车无人驾驶系统及技术研究[J]. 武汉理工大学学报, 2023, 45(11): 148-156.

[11]韩江洪, 卫星, 陆阳等. 煤矿井下机车无人驾驶系统关键技术[J]. 煤炭学报, 2020, 45(06): 2104-2115.

[12]张金钟. 中色非矿东南矿体数字化矿山建设[J]. 中国金属通报, 2017, 25(12): 101-103.

[13]丁震, 孟峰. 矿用无人卡车国内外研究现状及关键技术[J]. 中国煤炭, 2020, 46(02): 42-49.

[14]袁瑜. 矿用卡车的无人驾驶技术[J]. 矿业装备, 2013, 3(10): 72-74.

[15]张斌. 镜铁山2520m电机车无人应用与研究[J]. 矿业工程, 2018, 16(04): 57-59.

[16]张毅力, 汪令辉, 黄寿元. 地下矿无人驾驶电机车运输关键技术方案研究[J]. 金属矿山, 2013, 48(05): 117-120.

[17]李洪文. 5G电机车无人驾驶技术的应用[J]. 中国矿山工程, 2021, 50(01): 47-51.

[18]王建斌, 韩江洪, 魏振春. 井下无人驾驶机车运行过程控制的建模与验证[J]. 合肥工业大学学报, 2018, 41(6): 773-779.

[19]闫晶. 基于4G通信技术的煤矿井下防爆车辆无人驾驶可行性研究[J]. 煤矿机械, 2016, 37(06): 186-188.

[20]周菲鑫. 煤矿井下电机车无人驾驶测控系统研究[D]. 淮南: 安徽理工大学, 2019.

[21]赵翾. 无人驾驶地下矿用汽车路径跟踪与速度决策研究[D]. 北京: 北京科技大学, 2016.

[22]鲍久圣, 王陈, 阴妍. 一种无人驾驶的无轨胶轮车标准化运输平台及其控制方法[P]. 中国专利: 202110487267.8, 2021-06-11.

[23]骆彬. 井下蓄电池无轨胶轮车无人驾驶系统设计研究[D]. 徐州: 中国矿业大学, 2019.

[24]谢厚抗. 无人驾驶无轨胶轮车多传感信息融合与智能感知技术研究[D]. 徐州: 中国矿业大学, 2021.

[25]刘琴. 无人驾驶无轨胶轮车路径规划与路径跟踪技术研究[D]. 徐州: 中国矿业大学, 2021.

[26]Zhang J, Singh S. LOAM: lidar odometry and mapping in real-time[C]//Robotics: Science and Systems. 2014: 1-9.

[27]Shan T, Englot B. LeGO-LOAM: lightweight and ground-optimized lidar odometry and mapping on variable terrain[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems, 2018: 4758-4765.

[28]Ye H, Chen Y, Liu M. Tightly coupled 3d lidar inertial odometry and mapping[C]//2019 International Conference on Robotics and Automation. IEEE, 2019: 3144-3150.

[29]Shan T, Englot B, Meyers D, et al. LIO-SAM: tightly-coupled lidar inertial odometry via smoothing and mapping[C]//2020 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, 2020: 5135-5142.

[30]杨林, 马宏伟, 王岩. 基于激光惯性融合的煤矿井下移动机器人SLAM算法[J]. 煤炭学报, 2022, 47(9): 3523-3534.

[31]Davison, Andrew J, et al. MonoSLAM: real-time single camera slam[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(6): 1052-1067.

[32]揭云飞, 王峰, 智凯旋. 视觉SLAM系统分析[J]. 电脑知识与技术, 2018, 14(19): 227-229.

[33]Engel J, Schöps T, Cremers D. LSD-SLAM: large-scale direct monocular slam[C]//European conference on computer vision. Cham: Springer International Publishing, 2014: 834-849.

[34]Mur-Artal R, Montiel J M M, Tardos J D. ORB-SLAM: a versatile and accurate monocular slam system[J]. IEEE Transactions on Robotics, 2015 ,31(5): 1147-1163.

[35]Mur-Artal R, Tardos J D. ORB-SLAM2: an open-source slam system for monocular, stereo and rgb-d cameras[J]. IEEE Transactions on Robotics, 2017, 33(5): 1255-1262.

[36]Campos C, Elvira R, Rodríguez J J G, et al. ORB-SLAM3: an accurate open-source library for visual, visual–inertial, and multimap slam[J]. IEEE Transactions on Robotics, 2021, 37(6): 1874-1890.

[37]Zhang G , Liu H , Dong Z. ENFT: efficient non-consecutive feature tracking for robust structure-from-motion[J]. IEEE Trans Image Process, 2015, 25(12): 5957-5970.

[38]谷晓琳, 杨敏, 张燚. 一种基于半直接视觉里程计的RGB-D SLAM算法[J]. 机器人, 2020, 42(1): 39-48.

[39]GE G Y, ZHANG Y, JIANG Q. Visual features assist-ed robot localization in symmetrical environment using laser slam[J]. Sensors, 2021, 21(5): 1772.

[40]ZHANG J, SINGH S. Visual-lidar odometry and mapping: low-drift, robust, and fast[C]//2015 IEEE International Conference on Robotics and Automation. IEEE, 2015: 2174-2181.

[41]郑宇宏, 曾庆喜, 冀徐芳. 基于改进YOLOv5s和传感器融合的目标检测定位[J/OL]. 河北科技大学学报, 2024-01-12.

[42]林泽南. 基于全局改进势场与局部动态避障的移动机器人路径规划方法研究[D]. 大连: 大连理工大学, 2021.

[43]郑好, 冯虢靓雯, 蒲文杰等. 基于Dijkstra算法的封闭环境全局路径规划[J]. 汽车实用技术, 2023, 48(16): 7-11.

[44]Wang Z, Gao F, Zhao Y, et al. Improved A* algorithm and model predictive control-based path planning and tracking framework for hexapod robots[J]. Industrial Robot: the international journal of robotics research and application, 2022, 50(1): 135-144.

[45]Ma Q, Yang R, Lian T, et al. Path planning for mobile robots based on improving dijkstra algorithm[C]//International Conference on Cloud Computing, Performance Computing, and Deep Learning. SPIE, 2023: 367-372.

[46]Han C, Li B. Mobile robot path planning based on improved A* algorithm[C]//2023 IEEE 11th Joint International Information Technology and Artificial Intelligence Conference (ITAIC). IEEE, 2023: 672-676.

[47]王锋, 李凯璇, 朱子文等. 基于改进A* 蚁群融合算法的路径规划研究[J]. 火力与指挥控制, 2024, 49(01): 111-117+123.

[48]Li Q, Xu Y, Bu S, Yang J. Smart vehicle path planning based on modified PRM algorithm[J]. Sensors, 2022, 22(7): 6581.

[49]封澳, 杨锦宇, 谢玉阳. 基于改进PRM算法的机器人路径规划[J]. 计算机技术与发展, 2024, 34(02): 127-133.

[50]李琼琼, 徐溢琪, 布升强. 基于修正PRM算法的智能车辆路径规划研究[J]. 森林工程, 2022, 38(05): 179-186.

[51]Noreen I, Khan A, Habib Z. A comparison of RRT, RRT* and RRT*-smart path planning algorithms[J]. International Journal of Computer Science and Network Security, 2016, 16(10): 20.

[52]施杨洋, 杨家富, 布升强. 基于RRT改进的智能车辆路径规划算法[J]. 计算技术与自动化, 2019, 38(04): 81-86.

[53]张涌, 高峰, 赵奉奎. 基于改进RRT的自动驾驶车辆路径规划算法研究[J]. 重庆交通大学学报, 2023, 42(11): 118-125+140.

[54]Wang J, Wu N, Zhao W X, et al. Empowering A* search algorithms with neural networks for personalized route recommendation[C]//Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. 2019: 539-547.

[55]Zhang Y, Gong D, Zhang J. Robot path planning in uncertain environment using multi-objective particle swarm optimization[J]. Neurocomputing, 2013, 103: 172-185.

[56]Yun S C, Parasuraman S, Ganapathy V. Dynamic path planning algorithm in mobile robot navigation[C]//2011 IEEE Symposium on Industrial Electronics and Applications. IEEE, 2011: 364-369.

[57]Oleiwi B K, Al-Jarrah R, Roth H, et al. Multi objective optimization of trajectory planning of non-holonomic mobile robot in dynamic environment using enhanced GA by fuzzy motion control and A[C]//Neural Networks and Artificial Intelligence: 8th International Conference, ICNNAI 2014, 2014: 34-49.

[58]金跃强. 静态场中机器人避障最短时间路径规划模型[J]. 机床与液压, 2018, 46(15): 88-93.

[59]Quan L, Han L, Zhou B, et al. Survey of UAV motion planning[J]. IET Cyber‐systems and Robotics, 2020, 2(1): 14-21.

[60]Agirrebeitia J, Avilés R, De Bustos I F, et al. A new APF strategy for path planning in environments with obstacles[J]. Mechanism and Machine Theory, 2005, 40(6): 645-658.

[61]马小陆, 梅宏. 基于改进势场蚁群算法的移动机器人全局路径规划[J]. 机械工程学报, 2021, 57(01): 19-27.

[62]Masahiko M, Toshio M. Online path planner for autonomous mobile robots by combining laplace potential method and graph theory[J]. Japan Society of Mechanical Engineers, 2015, 6(0): 201-202.

[63]Liu C, Zhai L, Zhang X Y. Research on local real-time obstacle avoidance path planning of unmanned vehicle based on improved artificial potential field method[C]//2022 6th CAA International Conference on Vehicular Control and Intelligence. IEEE, 2022: 1-6.

[64]Qi N, Ma B, Zhang Z, et al. A modified artificial potential field algorithm for mobile robot path planning[C]//2008 7th World Congress on Intelligent Control and Automation. IEEE, 2008: 2603-2607.

[65]张宇迪, 龚鹏, 胡为. 改进人工势场法的智能车路径规划[J/OL]. 机械科学与技术, 2024-01-07.

[66]Gao Y, Dai Z, Yuan J. A multiobjective hybrid optimization algorithm for path planning of coal mine patrol robot[J]. Computational Intelligence and Neuroscience, 2022.

[67]Guan C, Wang S. Robot dynamic path planning based on improved A* and DWA algorithms[C]//2022 4th International Conference on Control and Robotics. IEEE, 2022: 1-6.

[68]Zhong X, Tian J, Hu H, et al. Hybrid path planning based on safe A* algorithm and adaptive window approach for mobile robot in large-scale dynamic environment[J]. Journal of Intelligent & Robotic Systems, 2020, 99(1): 65-77.

[69]LIU Y, HUANG H, FAN Q, et al. Mobile robot path planning based on improved A*-DWA algorithm[J]. Computer Integrated Manufacturing System, 2024, 30(1): 158.

[70]李承远. 基于改进TEB算法的自主导航控制[D]. 杭州: 杭州电子科技大学, 2020.

[71]陈曦, 石博强, 郭辉. 优化TEB算法的四轮差速机器人局部路径规划[J]. 软件, 2022, 43(06): 133-137+145.

[72]郑凯林, 韩宝玲, 王新达. 基于改进TEB算法的阿克曼机器人运动规划系统[J]. 科学技术与工程, 2020, 20(10): 3997-4003.

[73]代婉玉, 张丽娟, 吴佳峰等. 改进TEB算法的局部路径规划算法研究[J]. 计算机工程与应用, 2022, 58(08): 283-288.

[74]Pan H, Guo C, Wang Z. Research for path planning based on improved astart algorithm[C]//2017 4th International Conference on Information, Cybernetics and Computational Social Systems. IEEE, 2017: 225-230.

[75]Shan T, Englot B. Lego-loam: Lightweight and ground-optimized lidar odometry and mapping on variable terrain[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, 2018: 4758-4765.

[76]Cheng J, Zhang L, Chen Q, et al. Position detection for electric vehicle DWCS using VI-SLAM method[J]. Energy Reports, 2021, 7: 1-9.

[77]Noreen I. Collision free smooth path for mobile robots in cluttered environment using an economical clamped cubic B-Spline[J]. Symmetry, 2020, 12(9): 1567.

[78]张振, 张华良, 邓永胜, 白士宇. 融合改进A*算法与DWA算法的机器人实时路径规划[J]. 无线电工程, 2022, 52(11): 1984-1993.

[79]Lin Z, Yue M, Chen G, et al. Path planning of mobile robot with PSO-based APF and fuzzy-based DWA subject to moving obstacles[J]. Transactions of the Institute of Measurement and Control, 2022, 44(1): 121-132.

[80]鲍久圣, 张牧野, 葛世荣. 基于改进A*和人工势场算法的无轨胶轮车井下无人驾驶路径规划[J]. 煤炭学报, 2022, 47(03): 1347-1360.