煤矿智能化是煤炭工业转型升级和高质量发展的核心方向，对于构建现代能源保障体系具有重要意义。近年来，我国煤矿智能化开采技术体系日趋完善，已形成综采工作面智能协同控制、远程集中监控等多种智能开采模式，显著提升了采煤效率。然而，在巷道掘进过程中，从定位、路径规划到截割控制等关键环节均需人工干预，导致其智能化水平进展缓慢，这种技术发展的不平衡已经成为制约煤矿智能化发展的主要瓶颈。此外，煤矿井下的复杂工况限制了掘进工作面智能化的发展。为了解决掘进工作面自动化程度低、环境干扰严重的问题，本文以悬臂式掘进机为研究对象，结合机器视觉、智能控制与强化学习等先进技术，从航迹控制、移机控制和截割控制等方面系统研究悬臂式掘进机巷道成形截割智能控制方法，旨在提升掘进机在复杂环境下的自主作业能力，提高作业的安全性和智能化水平。完成的主要研究内容如下：

针对煤矿井下低照度与强光并存的复杂工况导致视觉稳定性不足的问题，本文提出一种融合点线特征的掘进机双目视觉定位方法，提高定位精度与稳定性。设计一种自适应多区间图像增强算法，抑制低照度问题并避免局部过度曝光，提高图像特征提取的鲁棒性。引入边缘绘制线段检测算法进行线特征提取，并结合点特征进行联合优化，利用基于普吕克坐标的线段特征表示方法，构建点线投影误差的雅克比矩阵，通过点线特征动态加权融合实现掘进机精确定位。该方法在低光照、粉尘及强光干扰环境下具有良好的适应性，降低了定位误差，为移机控制提供可靠的定位数据。

针对掘进巷道高安全阈值条件下的机身路径规划与控制问题，本文提出一种融合碰撞预测的改进A*移机路径规划算法，并采用强化学习辅助模型预测控制方法，确保狭窄巷道中的掘进机移机控制精度。建立掘进机运动学模型，设计人工势场构建巷道环境模型，计算碰撞预测因子实时判断碰撞风险。考虑掘进机航向约束调整A*算法搜索邻域，引入碰撞预测因子设计分段启发函数，提高路径规划安全性。考虑巷道底板对移机控制的不确定性影响，设计了强化学习辅助模型预测控制的智能控制策略，提高移机控制鲁棒性。构建包含位姿误差的状态空间与速度补偿动作空间，设计自定义奖励函数，构建深度确定性策略梯度控制模块，应对系统与环境不确定项。将其与模型预测控制相融合，实现移机路径的高精度跟踪控制。该方法在狭窄巷道环境下能够有效避障并实现平滑移机，且在复杂底板条件下具有更好地路径跟踪效果，满足煤矿巷道施工要求。

针对高精度成形截割质量要求下的成形截割轨迹规划与跟踪控制问题，提出一种基于改进非支配排序遗传算法II的截割轨迹规划方法，并设计径向基函数神经网络滑模鲁棒跟踪控制器，以保证巷道断面成形精度。建立悬臂式掘进机截割部运动模型，设计机身位姿驱动下的可行截割控制空间，构建截割轨迹最短与总转角最小的双目标旅行商问题，应用具有邻接约束的改进NSGA-II算法提高求解速度，获得可行截割轨迹。设计径向基神经网络鲁棒滑模跟踪控制器，补偿系统不确定项，提高截割轨迹控制的鲁棒性。该方法在轨迹规划与控制精度方面具有显著优势，可满足复杂地质条件下的成形截割需求。

此外，本文构建了掘进机巷道成形截割智能控制系统，并搭建系统实验平台，验证了航迹控制、移机控制、截割控制等核心功能的可行性与有效性。该系统在复杂巷道环境下具有良好的适应性与工程可行性，为解决煤矿井下掘进作业中定位稳定性不足、自动化程度低等问题提供了有效的理论支持与技术方案。研究成果为煤矿掘进作业的自动化、智能化发展奠定了重要基础，具有良好的应用前景和工程价值。

Coal mine intelligence is the core of intelligent transformation and high-quality development of coal industry, which is of great significance for building a modern energy security system. In recent years, China’s intelligent mining technology has become increasingly mature. The technology enables intelligent collaborative operations and centralized remote supervision in fully mechanized mining faces, effectively enhancing coal extraction efficiency. However, during roadway excavation, critical processes still require manual intervention including positioning, path planning, and cutting control, resulting in slow progress in intelligence. The technological imbalance has become a major bottleneck restricting the intelligent development of coal mines. Furthermore, the complex working conditions in underground coal mines limit the advancement of intelligent tunneling face. To address the low automation level and severe environmental interference in excavation faces, this study focuses on boom-type roadheader. By integrating advanced technologies such as machine vision, intelligent control, and reinforcement learning, intelligent control methods for accurate positioning, relocation, and cutting operations are systematically investigated. The study aims to enhance the autonomous capabilities in complex environments, thereby improving operational safety and intelligence. The main work contents completed are as follows:

To address the insufficient visual stability caused by complex underground coal mine conditions featuring coexisting low illumination and intense light interference, a binocular vision positioning method for roadheader is proposed that integrates point and line features to enhance positioning accuracy and stability. An adaptive multi-interval image enhancement method is designed to effectively suppress the low illumination and avoid overexposure in local areas of picture, which improves the robustness of image feature extraction. The Edge Drawing Lines is introduced to detect the line feature, and the point features are combined for joint optimization. The line feature representation method based on the Plücker coordinate is used to construct the Jacobian matrix of the point-line projection error, and pose estimation for the dynamic weighted fusion of the point-line features is realized. The experimental results show that the method has good adaptability in low light, dust and strong light interference environment, effectively reduces the positioning error, provides a reliable positioning basis for subsequent path planning and tracking control.

To address the safety challenges in roadheader relocation within confined roadways, an improved A* path planning algorithm is proposed incorporating collision prediction, along with a reinforcement learning assisted model predictive control approach to ensure precise relocation control in narrow underground spaces. A kinematic model of the roadheader is established and a roadway environment model is constructed using artificial potential field theory, incorporating real-time collision prediction factors for risk assessment. To enhance path planning safety, the A* algorithm is modified by adjusting its search neighborhood according to the heading constraints and introducing a segmented heuristic function that integrates collision prediction factors. Addressing the uncertainty caused by uneven roadway floors during relocation, a robust intelligent control strategy is developed combining RL with MPC. The approach features a specifically designed state space incorporating pose errors and an action space for velocity compensation, along with a custom reward function. A Deep Deterministic Policy Gradient control module is implemented to handle system and environmental uncertainties, which is then integrated with MPC to achieve high-precision path tracking control. Experimental results demonstrate that the proposed method effectively enables obstacle avoidance and smooth relocation in confined roadways while maintaining superior path-tracking performance under complex floor conditions, fully meeting the operational requirements for coal mine roadway construction.

To address the insufficient consideration of cutterhead dimensions and target cross-section constraints in the cutting trajectory planning for boom-type roadheader, an optimized trajectory planning method is proposed based on an improved Non-dominated Sorting Genetic Algorithm II. Additionally, a Radial Basis Function Neural Network-based sliding mode robust tracking controller is designed to ensure the formation accuracy of roadway profiles. First, a kinematic model of the roadheader’s cutting unit is established, and a feasible cutting control space is designed based on the machine's posture. A bi-objective Traveling Salesman Problem formulation is constructed to simultaneously minimize both the cutting trajectory length and total rotation angle. An improved NSGA-II algorithm with adjacency constraints is applied to enhance solution efficiency and obtain feasible cutting trajectories. Furthermore, a Radial Basis Function Neural Network-based sliding mode tracking controller is developed to compensate for system uncertainties and improve the robustness of cutting trajectory control. The proposed method demonstrates significant advantages in both trajectory planning and control precision, effectively meeting the requirements for profile cutting under complex geological conditions.

Furthermore, an intelligent control system for roadway profile cutting of the roadheader is established and an experimental platform is constructed. The feasibility and effectiveness of core functions, including precise positioning, movement control, and cutting control, have been experimentally validated. The proposed system demonstrates strong adaptability and engineering viability in complex roadway environments, providing both theoretical support and technical solutions to address critical challenges such as insufficient positioning stability and low automation levels in underground coal mining operations. These work outcomes lay a solid foundation for advancing automation in coal mine excavation operations, exhibiting significant application potential and engineering value.

[1] 中华人民共和国自然资源部. 中国矿产资源报告(2024)[R]. 北京: 地质出版社, 2024.

[2] 王国法, 徐亚军, 张金虎, 等. 煤矿智能化开采新进展[J]. 煤炭科学技术, 2021, 49 (01): 1-10.

[3] 王国法, 煤矿智能化最新技术进展与问题探讨山[J]. 煤炭科学技术, 2022, 50(1): 27

[4] 王国法, 加快煤矿智能化建设推进煤炭行业高质量发展[J]. 中国煤炭, 2021, 47 (01): 2-10.

[5] 毛君, 杨润坤, 谢苗, 等. 煤矿智能快速掘进关键技术研究现状及展望[J]. 煤炭学报, 2024, 49(02): 1214-1229.

[6] 王国法, 任怀伟, 富佳兴. 煤矿智能化建设高质量发展难题与路径 [J]. 煤炭科学技术, 2025, 53 (01): 1-18.

[7] 马源, 符世琛, 张子悦, 等. 悬臂式掘进机位姿检测方法研究现状[J]. 工矿自动化, 2020, 46(08): 15-20.

[8] 张旭辉, 张超, 周创, 等. 一种基于单棱镜旋转装置的掘进机位姿测量方法及系统[P]. 发明专利: ZL202011164836.7, 2022-08-16.

[9] 刘博兴. 煤矿井下全站仪定位与设备姿态角测量方法研究[D]. 西安, 西安科技大学, 2021.

[10] 吴淼, 贾文浩, 华伟, 等. 基于空间交汇测量技术的悬臂式掘进机位姿自主测量方法[J]. 煤炭学报, 2015, 40(11): 2596-2602.

[11] 孙凌飞, 刘亚, 彭继国, 等. 基于惯性技术的掘进机组合定位方法[J]. 煤炭科学技术, 2024, 52(12): 300-310.

[12] 万继成, 张旭辉, 杨文娟, 等. 基于视觉与惯导的掘进机组合定位方法[J/OL].煤炭科学技术, 1-12[2024-05-27].

[13] 毛清华,周庆,柴建权,等. 煤矿掘进机光纤惯导自适应零速修正方法研究[J/OL]. 煤炭科学技术, 1-12[2024-05-13].

[14] 陶云飞, 李瑞, 李嘉赓, 等. iGPS 的单站多点分时测量系统对掘进机偏向位移精度研究[J]. 煤炭技术, 2017 (2): 246-247.

[15] 符世琛, 成龙, 陈慎金, 等. 面向掘进机的超宽带位姿协同检测方法[J]. 煤炭学报, 2018, 43(10): 2918-2925.

[16] 田立勇, 孙业新, 于宁, 等. 基于组合方式的掘进机导航系统研究[J]. 工程设计学报, 2022, 29(02): 254-262.

[17] 薛光辉, 张云飞, 候称心, 等. 基于激光靶向扫描的掘进机位姿测量方法[J]. 煤炭科学技术, 2020, 48(11): 19-25.

[18] 杜雨馨. 矿井悬臂式掘进机位姿感知及定位方法研究[D]. 北京, 中国矿业大学, 2019.

[19] 陈双叶, 牛经龙, 温世波, 等. 自行走地下掘进机器人导向系统的测量方法[J]. 北京工业大学学报, 2014, 40(07): 1091-1098.

[20] 杨文娟, 张旭辉, 马宏伟等. 悬臂式掘进机机身及截割头位姿视觉测量系统研究[J]. 煤炭科学技术, 2019, 47(06): 50-57.

[21] 张旭辉, 沈奇峰, 杨文娟, 等. 基于三激光点标靶的掘进机机身视觉定位技术研究[J]. 电子测量与仪器学报, 2022, 36(06): 178-186.

[22] 张旭辉, 陈鑫, 杨文娟, 等. 基于单激光束信息的掘锚装备视觉定位方法研究[J]. 煤炭科学技术, 2024, 52(01): 311-322.

[23] 张超, 张旭辉, 杜昱阳, 等. 基于双目视觉的悬臂式掘进机位姿测量技术研究[J]. 煤炭科学技术, 2021, 49(11): 225-235.

[24] 王学, 周红旭, 张雷, 等. 基于近红外双目立体视觉的悬臂式掘进机定位研究[J]. 工矿自动化, 2022, 48(07): 43-51+57.

[25] 万继成, 张旭辉, 杨文娟, 等.基于红外LED线型标靶的掘进机视觉定位方法研究[J]. 煤炭学报, 2024, 49 (S2): 1173-1183.

[26] 张凯. 基于顶板视觉的掘进机空间位姿检测方法研究[D]. 北京, 煤炭科学研究总院, 2021.

[27] 谢楠. 单目视觉与激光雷达融合的巷道三维重建与掘进机定位方法[D]. 西安, 西安科技大学, 2021.

[28] 李正龙. 捷联惯导与双目里程计融合的掘进机组合定位系统研究[D]. 太原, 太原理工大学, 2023.

[29] Zhang W, Zhai G, Yue Z, et al. Research on visual positioning of a roadheader and construction of an environment map[J]. Applied Sciences, 2021, 11(11): 4968.

[30] Wu H, Liu S, Cheng C, et al. Multiscale variational autoencoder aided convolutional neural network for pose estimation of tunneling machine using a single monocular image[J]. IEEE Transactions on Industrial Informatics, 2021, 18(8): 5161-5170.

[31] Cui Y, Pu J, Hu N, et al. Autonomous Positioning for Mobile Vehicles Based on Visual‐Inertial Fusion in Challenging Dark Roadway Scenes[J]. Journal of Field Robotics, 2025, 42(4): 1333-1343.

[32] Wu H, Cheng C, Zhang D, et al. Multi-scale latent space sequential fusion of images for pose estimation of underground tunneling machinery[J]. Engineering Applications of Artificial Intelligence, 2025, 141: 109786.

[33] 龚坤, 徐鑫, 陈小庆, 等. 弱纹理环境下融合点线特征的双目视觉同步定位与建图[J]. 光学精密工程, 2024, 32(05): 752-763.

[34] 朱旭, 徐熙平, 张宁, 等. 基于改进ELSED线检测算法的双目视觉SLAM[J].激光与光电子学进展, 2025, 62(10): 272-282.

[35] 李丹, 李俊祥, 赵文杰, 等. 基于改进的点线融合和关键帧选择的视觉SLAM方法[J/OL]. 2025, 47(02): 200-212.

[36] 程向红, 刘路辉, 唐兴邦. 一种室内环境下点线特征综合的RGB-D VO算法[J]. 中国惯性技术学报, 2024, 32(06): 579-585.

[37] Chen Q, Cao Y, Hou J, et al. VPL-SLAM: a vertical line supported point line monocular SLAM system[J]. IEEE Transactions on Intelligent Transportation Systems, 2024, 25(8):9749-9761.

[38] Huang S, Ren W, Li M. PLFF-SLAM: A Point and Line Feature Fused Visual SLAM Algorithm for Dynamic Illumination Environments[J]. IEEE Access, 2025, 13: 34946-34953.

[39] Xu K, Hao Y, Yuan S, et al. Airslam: An efficient and illumination-robust point-line visual slam system[J]. IEEE Transactions on Robotics, 2025, 41: 1673-1692.

[40] 王浩森. 基于深度相机的煤矿井下机器人SLAM技术研究[D]. 西安, 西安科技大学, 2021.

[41] 牟琦, 梁鑫, 郭媛婕, 等. 边缘感知增强的煤矿井下视觉SLAM方法[J]. 煤田地质与勘探, 2025, 53(03): 231-242.

[42] 孙航. 基于点线特征融合的双目SLAM方法研究[D]. 长春, 吉林大学,2024.

[43] 蒲国强. 适用于低纹理环境的视觉SLAM算法研究[D]. 杭州, 杭州电子科技大学, 2024.

[44] 金凌云, 王从庆, 李宏光. 一种基于线特征约束的无人机双目视觉SLAM算法[J]. 电光与控制, 2024, 31(04): 1-5.

[45] 孙浩. 复杂环境下基于点线特征的视觉SLAM算法研究[D]. 北京, 中国石油大学, 2023.

[46] 白克强, 朱亚兰, 杨秀清, 等. 融合动态目标跟踪的视觉SLAM算法[J]. 信息与控制, 2024, 53(05): 574-584.

[47] 宋立业, 张冰. 基于RBF神经网络掘进机掘进姿态自适应PID控制[C]//2019航空装备服务保障与维修技术论坛暨中国航空工业技术装备工程协会年会论文集. 2019: 767-770+775.

[48] 张敏骏, 蔡岫航, 吕馥言, 等. 受限巷道空间区域栅格化掘进机自主纠偏研究[J]. 仪器仪表学报, 2018, 39(03): 62-70.

[49] 瞿圆媛, 宋林珂, 吉晓冬, 等. 井下掘进机行进纠偏调度规划与控制研究[J]. 矿业科学学报, 2020, 5(02): 194-202.

[50] 吴淼, 沈阳, 吉晓冬, 等. 悬臂式掘进机行走轨迹及偏差感知方法[J]. 煤炭学报, 2021, 46(07): 2046-2056.

[51] 张旭辉, 赵建勋, 杨文娟, 等. 悬臂式掘进机视觉导航与定向掘进控制技术[J]. 煤炭学报, 2021, 46(07): 2186-2196.

[52] Ji X, Zhang M, Qu Y, et al. Travel dynamics analysis and intelligent path rectification planning of a roadheader on a roadway[J]. Energies, 2021, 14(21): 7201.

[53] 张旭辉, 郑西利, 杨文娟, 等. 煤矿井下悬臂式掘进机路径规划方法研究[J]. 煤田地质与勘探, 2024, 52(04): 152-163.

[54] 杨春雨, 张鑫. 煤矿机器人环境感知与路径规划关键技术[J]. 煤炭学报, 2022, 47(07): 2844-2872.

[55] 董翔宇, 季坤, 朱俊, 等. 对特高压变电站巡检机器人路径规划改进蚁群算法的研究[J]. 电力系统保护与控制, 2021, 49(18): 154-160.

[56] 薛光辉, 刘爽, 王梓杰等. 基于改进概率路线图算法的煤矿机器人路径规划方法[J]. 工矿自动化, 2023, 49(06): 175-181.

[57] 刘卓, 贾明涛, 王李管. 地下巷道动态受限空间移动装备路径规划研究[J]. 黄金科学技术, 2023, 31(02): 302-312.

[58] 王鹤, 陈静, 滕瑛瑶. 基于新型栅格启发式算法的矿井机器人路径规划[J]. 工矿自动化, 2020, 46(08): 64-69.

[59] 杨林, 马宏伟, 王岩等. 煤矿井下移动机器人运动规划方法研究[J]. 工矿自动化, 2020, 46(06): 23-30.

[60] 姜媛媛, 丰雪艳. 基于改进A*算法的煤矿救援机器人路径规划[J]. 工矿自动化, 2023, 49(08): 53-59.

[61] Fransen K, Eekelen J. Efficient path planning for automated guided vehicles using A* algorithm incorporating turning costs in search heuristic[J]. International Journal of Production Research, 2023, 61(3): 707-725.

[62] 杜青炎, 任助理, 马宏超. 基于改进混合A*算法的地下无人铲运机智能路径规划[J]. 有色金属(矿山部分), 2023, 75(02): 1-12.

[63] 张伟民, 张月, 张辉. 基于改进A*算法的煤矿救援机器人路径规划[J]. 煤田地质与勘探, 2022, 50(12): 185-193.

[64] 蒋浩辰, 查正清, 段云. 基于自适应粒子—蚁群算法的掘进面机器人装药路径智能优化[J]. 有色金属(矿山部分), 2022, 74(04): 6-13.

[65] 鲍久圣, 张牧野, 葛世荣等. 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.

[66] 谭玉新, 杨维, 徐子睿. 面向煤矿井下局部复杂空间的机器人三维路径规划方法[J]. 煤炭学报, 2017, 42(06): 1634-1642.

[67] 高爱云, 吕元博, 付主木, 等. 基于改进人工势场的自适应采样轨迹规划[J/OL]. 吉林大学学报(工学版), 1-12[2025-03-05].

[68] Chou J S, Cheng M Y, Hsieh Y M, et al. Optimal path planning in real time for dynamic building fire rescue operations using wireless sensors and visual guidance[J]. Automation in construction, 2019, 99: 1-17.

[69] Li X, Wang L, An Y, et al. Dynamic path planning of mobile robots using adaptive dynamic programming[J]. Expert Systems with Applications, 2024, 235: 121112.

[70] Cheng B, Deng L. Vision detection and path planning of mobile robots for rebar binding[J]. Journal of Field Robotics, 2024, 41(6): 1864-1886.

[71] Patle Patle B K, Pandey A, Parhi D R K, et al. A review: On path planning strategies for navigation of mobile robot[J]. Defence Technology, 2019, 15(4): 582-606.

[72] Herrmann F, Zach S, Banfi J, et al. Safe and Efficient Path Planning under Uncertainty via Deep Collision Probability Fields[J]. IEEE Robotics and Automation Letters, 2024, 9(11), 9327-9334.

[73] Ji J, Khajepour A, Melek W W, et al. Path planning and tracking for vehicle collision avoidance based on model predictive control with multiconstraints[J]. IEEE Transactions on Vehicular Technology, 2016, 66(2): 952-964.

[74] Wang H, Huang Y, Khajepour A, et al. Crash mitigation in motion planning for autonomous vehicles[J]. IEEE transactions on intelligent transportation systems, 2019, 20(9): 3313-3323.

[75] Chen Y, Chen S, Ren H, et al. Path tracking and handling stability control strategy with collision avoidance for the autonomous vehicle under extreme conditions[J]. IEEE transactions on vehicular technology, 2020, 69(12): 14602-14617.

[76] Türkkol B Z, Altuntaş N, Çekirdek Yavuz S. A Smooth Global Path Planning Method for Unmanned Surface Vehicles Using a Novel Combination of Rapidly Exploring Random Tree and Bézier Curves[J]. Sensors, 2024, 24(24): 8145.

[77] Bi Q Z, Shi J, Wang Y H, et al. Analytical curvature-continuous dual-Bézier corner transition for five-axis linear tool path[J]. International Journal of Machine Tools and Manufacture, 2015, 91: 96-108.

[78] 王苏彧, 高峰, 李睿, 等. 基于PCC的任意巷道断面自动截割成形控制系统[J]. 煤炭学报, 2013, 38(S1): 261-266.

[79] 彭天好, 储安圆, 何兴川, 等. 悬臂式掘进机截割轨迹控制联合仿真研究[J]. 机床与液压, 2023, 51(08): 130-136.

[80] 马宏伟, 王赛赛, 王川伟, 等. 短横轴截割机器人直墙拱形巷道自动成形控制方法[J]. 西安科技大学学报, 2024, 44(03): 418-429.

[81] 张义. 掘进机自动截割断面边界控制方法研究[D]. 阜新, 辽宁工程技术大学, 2022.

[82] 张旭辉, 汤杜炜, 杨文娟, 等. 基于改进GWO算法的掘进机断面成形轨迹规划方法研究[J/OL]. 工程设计学报, 1-12[2024-11-08].

[83] 田劼, 银晓琦, 文艺成. 基于混合IWO—PSO算法的掘进机截割轨迹规划方法[J]. 工矿自动化, 2021, 47(12): 55-61.

[84] Dong Z, Zhang X, Yang W, et al. Ant colony optimization-based method for energy-efficient cutting trajectory planning in axial robotic roadheader[J]. Applied Soft Computing, 2024, 163: 111965.

[85] Wang S, Wu M. Cutting trajectory planning of sections with complex composition for roadheader[J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2019, 233(4): 1441-1452.

[86] JI X, Zhang M, Qu Y, et al. Travel dynamics analysis and intelligent path rectification planning of a roadheader on a roadway[J]. Energies, 2021, 14(21): 7201.

[87] Liu Z, Zou K, Xie M, et al. Modeling and characteristic analysis of roadway profile under the influence of multiple factors[J]. Scientific Reports, 2022, 12(1): 19879.

[88] 王苏彧. 悬臂式掘进机记忆截割及自动截割控制方法研究[D]. 北京, 中国矿业大学, 2014.

[89] 张德义, 刘送永, 贾新庆, 等. 基于红外热像的夹矸巷道断面记忆截割试验研究[J]. 煤炭学报, 2021, 46(10): 3377-3385.

[90] 张旭辉, 王甜, 张超, 等. 数字孪生驱动的悬臂式掘进机虚拟示教记忆截割方法[J]. 煤炭学报, 2023, 48(11): 4247-4260.

[91] Zhang D, Liu S, Jia X, et al. Full coverage cutting path planning of robotized roadheader to improve cutting stability of the coal lane cross-section containing gangue[J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2022, 236(1): 579-592.

[92] Su Y, Dai Y, Liu Y. A hybrid parallel Harris hawks optimization algorithm for reusable launch vehicle reentry trajectory optimization with no-fly zones[J]. Soft Computing, 2021, 25(23): 14597-14617.

[93] Sun J, Han X, Zuo Y, et al. Trajectory planning in joint space for a pointing mechanism based on a novel hybrid interpolation algorithm and NSGA-II algorithm[J]. IEEE Access 2020, 8, 228628-228638.

[94] Gao Y, Cui J, Wang N. Multi-Objective Drilling Trajectory Optimization Under Parameter Uncertainty[C]//2024 4th International Conference on Computer Science and Blockchain (CCSB). IEEE, 2024: 11-14.

[95] Chai R, Savvaris A, Tsourdos A, et al. Solving multiobjective constrained trajectory optimization problem by an extended evolutionary algorithm[J]. IEEE transactions on cybernetics 2018, 50(4), 1630-1643.

[96] Zhang D, Zhang Z, Li Y, et al. An NSGA-II-based multi-objective trajectory planning method for autonomous driving[C]//2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD). IEEE, 2024: 2140-2146.

[97] Barrett J M, Gennert M A, Michalson W R, et al. Development of a low-cost, self-contained, combined vision and inertial navigation system[C]//IEEE International Conference on Technologies for Practical Robot Applications. IEEE, 2013: 1-6.

[98] 符世琛, 李一鸣, 杨健健. 基于超宽带技术的掘进机自主定位定向方法研究[J]. 煤炭学报, 2015, 40(11): 2603-2610.

[99] 臧富雨, 王凯硕, 吉晓冬. 悬臂式掘进机俯仰角调控系统仿真研究[J]. 工矿自动化, 2019, 45(05): 62-67.

[100] 张旭辉, 石硕, 杨红强,等. 悬臂式掘进机自主调速截割控制系统[J]. 工矿自动化, 2023, 49(01): 80-89.

[101] 邵诚俊, 廖建峰, 刘之涛. 基于自适应鲁棒控制算法的硬岩巷道掘进机水平方向轨迹纠偏控制[J]. 机械工程学报, 2018, 54(01): 113-119.

[102] 杜毅博, 穆晶, 李睿. 悬臂式掘进机机身位姿误差消除策略的研究[J]. 工矿自动化, 2012, 38(02): 29-31.

[103] 谭明. 掘进机智能行走控制系统的设计与实现[D]. 武汉, 武汉理工大学, 2012.

[104] 吉晓冬, 瞿圆媛, 符世琛, 等. 基于 SVD-Unscented 卡尔曼滤波的掘进机行进调度纠偏研究[J]. 矿业科学学报, 2022, 7(3): 354-363.

[105] 毛清华, 张旭辉, 马宏伟, 等. 多传感器信息的悬臂式掘进机空间位姿监测系统研究 [J]. 煤炭科学技术, 2018, 46(12): 41-47.

[106] Aradi S. Survey of deep reinforcement learning for motion planning of autonomous vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 23(2): 740-759.

[107] 张伟, 王强, 吴奇阳, 等. 带有扰动观测模型预测控制的水下无人航行器对接控制[J/OL]. 哈尔滨工程大学学报, 1-8 [2025-02-05].

[108] Lin M, Sun Z, Xia Y, et al. Reinforcement learning-based model predictive control for discrete-time systems[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023, 35(3): 3312-3324.

[109] Bohn E, Gros S, Moe S, et al. Optimization of the model predictive control meta-parameters through reinforcement learning[J]. Engineering Applications of Artificial Intelligence, 2023, 123: 106211.

[110] Hassanpour H, Mhaskar P, Corbett B. A practically implementable reinforcement learning control approach by leveraging offset-free model predictive control[J]. Computers & Chemical Engineering, 2024, 181: 108511.

[111] Cui Y, Peng L, Li H. Filtered probabilistic model predictive control-based reinforcement learning for unmanned surface vehicles[J]. IEEE Transactions on Industrial Informatics, 2022, 18(10): 6950-6961.

[112] Chen L, Meng F, Zhang Y. MBRL-MC: An HVAC control approach via combining model-based deep reinforcement learning and model predictive control[J]. IEEE Internet of Things Journal, 2022, 9(19): 19160-19173.

[113] 温佳, 梁喜凤, 王永维. 基于DDPG+MPC的水稻授粉机器人路径跟踪控制[J]. 农机化研究, 2025, 47(06): 18-25.

[114] 丛坤地. 基于强化学习和模型预测控制的无人车规划与跟踪研究[D]. 哈尔滨, 哈尔滨工业大学, 2024.

[115] 汪洪波, 王春阳, 赵林峰, 等. 基于强化学习的智能车辆路径跟踪变参数MPC多目标控制[J]. 中国公路学报, 2024, 37(03): 157-169.

[116] 王苏彧, 田劼, 吴淼. 纵轴式掘进机自动截割断面边界控制误差分析[J]. 工矿自动化, 2016 (5): 14-18.

[117] 张旭辉, 赵建勋, 张超, 等. 悬臂式掘进机视觉伺服截割控制系统研究[J]. 煤炭科学技术, 2022, 50(2): 263-270.

[118] 杨立云, 徐辉东, 张鲁鲁, 等. 新型凿井提升系统在煤矿井筒施工中的应用[J]. 煤炭科学技术, 2016 (4).

[119] 苏杭. 悬臂式掘进机巷道断面自动精确成形系统研发[D]. 济南, 山东大学, 2015.

[120] 李海斌. 悬臂式掘进机自动截割控制系统设计[J]. 中国矿业, 2016, 25(10): 150-153.

[121] 王苏彧, 吴淼. 纵轴式掘进机记忆截割控制方法研究[J]. 煤炭技术, 2016, 35(11): 266-268.

[122] 张旭辉, 谢亚洲. 基于DSP的悬臂式掘进机控制系统设计[J]. 煤炭工程, 2019, 51(12): 172-176.

[123] 张超, 张旭辉, 张楷鑫, 等. 数字孪生驱动掘进机远程自动截割控制技术[J]. 工矿自动化, 2020, 46(09): 15-20+32.

[124] 王苏彧, 吴淼. 基于PCC的纵轴式掘进机自主截割控制系统研究[J]. 煤炭工程, 2016, 48(06): 132-135.

[125] 毛清华, 陈磊, 闫昱州. 煤矿悬臂式掘进机截割头位置精确控制方法[J]. 煤炭学报, 2017, 42(S2): 562-567.

[126] 温承永, 应宗权, 王东, 等. 基于多传感器混合体系的悬臂式掘进机截割可视化系统研究[J]. 巷道建设(中英文), 2025, 45(01): 209-218.

[127] 杨文娟, 张旭辉, 张超, 等. 悬臂式悬臂式掘进机巷道成形智能截割控制系统研究[J]. 工矿自动化, 2019, 45(09): 40-46.

[128] 张付凯, 王福忠, 高庆华. 掘进机截割臂运动轨迹的迭代学习控制[J]. 电子测量与仪器学报, 2014, 28(12): 1355-1362.

[129] 张建广. 悬臂式掘进机自适应截割控制系统研究[J]. 煤炭科学技术, 2016, 44(02): 148-152.

[130] 王东杰, 王鹏江, 李悦, 等. 掘进机截割臂自适应截割控制策略研究[J]. 中国机械工程, 2022, 33(20): 2492.

[131] 宗凯, 张鹏, 王鹏江, 等. 固定截割方向掘进机截割臂摆角垂直跳动规律[J]. 煤炭学报, 2018 (5): 1455-1463.

[132] 李建刚. 自动化掘进机仿形截割控制策略研究[D]. 阜新, 辽宁工程技术大学, 2012.

[133] 马宏伟, 孙思雅, 王川伟, 等. 论“掘进就是掘模型”的学术思想[J]. 煤炭学报, 2025, 50(01): 661-675.

[134] Ehret T, Morel J M. Line segment detection: A review of the 2022 state of the art[J]. Image Processing On Line, 2024, 14: 41-63.

[135] Teplyakov L, Erlygin L, Shvets E. Lsdnet: Trainable modification of lsd algorithm for real-time line segment detection[J]. IEEE Access, 2022, 10: 45256-45265.

[136] Kumar U, Patel G A, Patel H P, et al. Impact of frontline demonstration programme on the yield of chickpea (Cicer arietinum L.) in Patan District of Gujarat, India[J]. Legume Research-An International Journal, 2021, 44(2): 221-224.

[137] Dai J S, Sun J. Geometrical revelation of correlated characteristics of the ray and axis order of the Plücker coordinates in line geometry[J]. Mechanism and Machine Theory, 2020, 153: 103983.

[138] 杨官学, 刘岳松, 刘慧, 等. 弱纹理环境下点线融合鲁棒视觉SLAM算法[J/OL]. 计算机工程与应用, 1-14[2024-12-30].

[139] Burri M, Nikolic J, Gohl P, et al. The EuRoC micro aerial vehicle datasets[J]. The International Journal of Robotics Research, 2016, 35(10): 1157-1163.

[140] Geiger A, Lenz P, Stiller C, et al. Vision meets robotics: The kitti dataset[J]. The International Journal of Robotics Research, 2013, 32(11): 1231-1237.

[141] Gomez-Ojeda R, Moreno F A, Zuniga-Noël D, et al. PL-SLAM: A stereo SLAM system through the combination of points and line segments[J]. IEEE Transactions on Robotics, 2019, 35(3): 734-746.

[142] 毕泗兴, 宫金良, 张彦斐. 基于改进A*与DWA算法的农业机器人路径规划[J]. 山东理工大学学报(自然科学版), 2024, 38(05): 40-46.

[143] Zhang K, Sun Q, Shi Y. Trajectory tracking control of autonomous ground vehicles using adaptive learning MPC[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(12): 5554-5564.

[144] Kong Y, Jiang Y, Han R, et al. A generalized varying-parameter recurrent neural network for super solution of quadratic programming problem[J]. Neurocomputing, 2021, 437: 238-248.

[145] Wisniewski R, Bujorianu M L. Probabilistic safety guarantees for Markov decision processes[J]. IEEE Transactions on Automatic Control, 2023, 68(12): 8095-8102.

[146] 鲁韵, 王姣. 一种基于改进贝尔曼方程的最短路径规划算法[J]. 武汉理工大学学报(交通科学与工程版), 2022, 46(06): 1003-1007.

[147] 马克西姆 拉潘. 深度强化学习实践(原书第2版)[M]. 机械工业出版社: 2021.

[148] 井征淼, 刘宏杰, 周永录. 基于改进Q-learning算法的移动机器人路径规划[J]. 火力与指挥控制, 2024, 49(03): 135-141.

[149] Cao S, Wang X, Cheng Y. Robust Offline Actor-Critic With On-policy Regularized Policy Evaluation[J]. IEEE/CAA Journal of Automatica Sinica, 2024, 11(12): 2497-2511.

[150] 丁天雲, 夏逸, 梅泽伟, 等. 基于DDPG的变外形航天飞行器碰撞规避的轨迹规划方法[J]. 兵工学报, 2024, 45(11): 3903-3914.

[151] 杨琰, 张瑞瑞, 张林焕, 等. 基于DQN的智能农机路径跟踪控制研究[J]. 农机化研究, 2025, 47(03): 28-34.

[152] Shi X, Li Y, Hu W, et al. Optimal lateral path-tracking control of vehicles with partial unknown dynamics via DPG-based reinforcement learning methods[J]. IEEE Transactions on Intelligent Vehicles, 2023, 9(1): 1701-1710.

[153] 曹学鹏, 脱帅华, 张弓, 等. 焊接机器人焊缝跟踪方法及路径规划研究[J]. 工程科学与技术, 2022, 54(02): 196-204.

[154] 王敏, 孙景健, 丁基恒, 等. 基于D-H参数与拉格朗日联立方程的仿生水蛇机器人运动学分析及动力学建模[J]. 机械工程学报, 2024, 60(15): 134-148.

[155] 冯盖亚, 贾山, 陈金宝, 等. 可行走着陆器的牛顿-欧拉法动力学研究[J]. 航天返回与遥感, 2024, 45(01): 53-64.

[156] 张毅, 宋传静, 翟相华. 变加速动力学系统的广义高斯最小拘束原理[J]. 力学学报, 2023, 55(05): 1174-1180.

[157] Traub V, Vygen J, Zenklusen R. Reducing path TSP to TSP[C]//Proceedings of the 52nd Annual ACM SIGACT Symposium on Theory of Computing. 2020: 14-27.

[158] Qamar N, Akhtar N, Younas I. Comparative analysis of evolutionary algorithms for multi-objective travelling salesman problem[J]. International Journal of Advanced Computer Science and Applications, 2018, 9(2): 371-379.

[159] Hobbie J G, Gandomi A H, Rahimi I. A comparison of constraint handling techniques on NSGA-II[J]. Archives of Computational Methods in Engineering, 2021, 28(5): 3475-3490.

[160] 倪建云, 薛晨阳, 吴杰, 等. 障碍物密集环境下基于NSGA-II的DWA路径规划算法[J/OL]. 天津理工大学学报, 1-8[2024-05-15].

[161] 章政, 夏小云, 陈泽丰, et al. 融合强化学习的分阶段策略求解旅行背包问题[J]. 计算机工程与科学, 2025, 47(01): 140-149.

[162] Shi F, Soman R K, Han J, et al. Addressing adjacency constraints in rectangular floor plans using Monte-Carlo Tree Search[J]. Automation in Construction, 2020, 115: 103187.

[163] 杨欣华, 李思坤, 廖陆峰,等. 基于深度优先搜索的全芯片光源掩模优化关键图形筛选方法[J]. 光学学报, 2022, 42(10): 210-219.

[164] 雷孟宇, 张旭辉, 杨文娟, 等. 钻锚机器人钻臂轨迹规划方法研究[J]. 煤田地质与勘探, 2023, 51(10): 180-190.

[165] Legnani G, Fassi I, Tasora A, et al. A practical algorithm for smooth interpolation between different angular positions[J]. Mechanism and Machine Theory, 2021, 162: 104341.

[166] Saab S S, Shen D, Orabi M, et al. Iterative learning control: Practical implementation and automation[J]. IEEE Transactions on Industrial Electronics, 2021, 69(2): 1858-1866.

[167] Qiong L, Dong L, et al. Adaptive bias RBF neural network control for a robotic manipulator[J]. Neurocomputing, 2021, 447: 213-223.

[168] Anjum Z, Zhou H, Ahmed S, et al. Fixed time sliding mode control for disturbed robotic manipulator[J]. Journal of Vibration and Control, 2024, 30(7-8): 1580-1593.

[169] Rui-Dong X, Xiao X, et al. Adaptive sliding mode disturbance observer based robust control for robot manipulators towards assembly assistance[J]. IEEE Robotics and Automation Letters, 2022, 7(3): 6139-6146.

[170] Yin X, Pan L, Cai S. Robust adaptive fuzzy sliding mode trajectory tracking control for serial robotic manipulators[J]. Robotics and Computer-Integrated Manufacturing, 2021, 72: 101884.

[171] 张旭辉 , 刘彦徽, 杨文娟, 等. 数字孪生驱动的巷道自动成形截割虚拟调试方法研究[J]. 工矿自动化, 2024, 50(07): 1-11+31.