Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology
School of Information and Control Engineering, China University of Mining and Technology
Xuzhou Engineering Research Center of Intelligent Industry Safety and Emergency Collaboration, China University of Mining and Technology

矿井辅助运输系统是煤矿企业运输人员和重要物料、装备的必备系统，实现矿井无人驾驶是提高运输效率、保障运输安全的必然要求，也是落实国家煤矿智能化建设部署的必由之路。矿井无人驾驶依赖于准确实时的环境感知，即利用激光雷达、毫米波雷达等车载感知器件和车联网支持下的协同感知，实现车辆局部甚至矿井全局的精确详尽感知。对矿井无人驾驶环境感知技术的研究现状进行了系统梳理，指出巷道特殊环境使得矿井车载感知设备的性能都将出现不同程度的下降，并对各种车载感知设备的优劣进行了总结归纳；详细阐述了矿井无人驾驶环境感知的关键技术，包括基于可见光图像或激光点云的单传感器障碍物识别方法，多传感器融合感知的分类及可见光图像+激光点云、可见光图像+毫米波点云、可见光图像+激光点云+毫米波点云、4D毫米波雷达+其他感知器件等多传感器融合方式，智能网联协同感知的实现方式、数据处理方法及其对无人驾驶的促进作用，井下巷道交通标志检测与识别方法，井下无轨胶轮车和有轨机车的巷道可行驶区域分割方法等；对矿井无人驾驶环境感知技术的发展方向进行了展望，建议提高矿井多传感器融合性能、研究矿井自适应感知算法并突破矿井智能网联协同感知技术。

The auxiliary transportation system for coal mine is an essential system for transporting personnel, important materials, and equipment in coal mine enterprises. Realizing unmanned driving in coal mine is an inevitable requirement for improving transportation efficiency and ensuring transportation safety, and is also the only way to implement the national coal mine intelligent construction deployment. The mine unmanned driving relies on accurate and real-time environmental perception. By using onboard perception devices such as LiDAR and millimeter wave radar, as well as collaborative perception supported by the Internet of vehicles, the precise and detailed perception of local vehicles and even the entire mine is achieved. A systematic review is conducted on the research status of unmanned driving environment perception technology in mines. It is pointed out that the special environment of coal mine will lead to varying degrees of degradation in the performance of mine onboard perception devices. The advantages and disadvantages of various onboard perception devices are summarized. The key technologies of mine unmanned driving environment perception are elaborated in detail. The technologies include single-sensor obstacle recognition methods based on visible light images or laser point clouds, the classification of multi-sensor fusion perception, and multi-sensor fusion methods such as visible light images+laser point clouds, visible light images+millimeter wave point clouds, visible light images+laser point clouds+millimeter wave point clouds, 4D millimeter wave radar+other perception devices. The technologies include the implementation, data processing methods of intelligent networked collaborative perception, and their promoting effects on unmanned driving. The technologies also include methods for detecting and recognizing traffic signs in underground roadways, and methods for segmenting the driving area of underground trackless rubber wheeled vehicles and tracked locomotives in roadways. The development direction of unmanned driving environment perception technology in mines is pointed out. It is recommended to improve the fusion performance of multiple sensors in mines, study adaptive perception algorithms in mines, and break through the intelligent networked collaborative perception technology in mines.

国家自然科学基金资助项目（51874299）；中国矿业大学“双一流”建设提升自主创新能力项目（2022ZZCX01K01）；山东省重大科技创新工程项目（2019JZZY020505）；中国矿业大学“工业物联网与应急协同”创新团队资助计划项目（2020ZY002）。

0 引言
1 矿井无人驾驶环境感知的主要挑战
2 矿井无人驾驶环境感知关键技术
2.1 单传感器障碍物识别
2.1.1 基于可见光图像的障碍物识别
2.1.2 基于激光点云的障碍物识别
2.2 多传感器融合障碍物识别
2.2.1 多传感器融合算法分类及融合结构
2.2.2 矿井环境感知主流融合检测算法
2.3 智能网联协同感知
2.4 井下巷道交通标志检测与识别
2.5 井下巷道可行驶区域分割
2.5.1 无轨胶轮车可行驶区域分割
2.5.2 有轨机车可行驶区域分割
3 矿井无人驾驶环境感知技术发展方向
4 结语

胡青松，孟春蕾，李世银，等. 矿井无人驾驶环境感知技术研究现状及展望[J]. 工矿自动化，2023，49(6)：128-140.

HU Qingsong, MENG Chunlei, LI Shiyin, et al. Research status and prospects of perception technology for unmanned mining vehicle driving environment[J]. Journal of Mine Automation，2023，49(6)：128-140.