煤矸石分拣是提高煤炭质量的基本工艺，传统的煤矸石分拣方法存在人员需求多、分拣效率低、劳动强度大、工作环境劣等问题，严重影响煤炭安全高效生产。随着煤矿智能化建设的不断发展，将多机械臂机器人应用于煤矸石分拣已经成为研究热点，不仅需求迫切，而且挑战严峻。针对多机械臂煤矸石分拣机器人机械臂动态目标跟踪、抓取与协同控制难题，提出了多机械臂煤矸石智能协同分拣机器人系统方案，深入研究机械臂动态目标同步跟踪轨迹规划、机械臂动态目标稳定抓取和多目标多机械臂协同控制等关键科学问题，旨在实现煤矸石的智能精准分拣，解放生产力，提高拣矸效率。

煤矸石大小不一、形状复杂、速度快、数量多和分布随机，直接影响煤矸石分拣机器人的稳定抓取和高效分拣。深入分析了煤矸石分拣特征，构建了基于功能分析法的煤矸石分拣机器人功能模型，结合煤矸石分拣特征与分拣机器人关键技术匹配关系，构建了多机械臂煤矸石分拣机器人系统原理模型和实验平台。建立了机械臂动态目标跟踪轨迹规划原理模型、机械臂动态目标稳定抓取原理模型和多目标多机械臂协同控制原理模型，为破解煤矸石分拣机器人关键技术奠定了基础。

煤矸运输具有速度快、矸石质量大等特征，机械手直接抓取存在冲击载荷，极易造成抓取失败或机械手损坏。对此，深入研究了全局规划和局部优化的机械臂动态目标同步跟踪轨迹规划方法。通过构建基于余弦定理的煤矸石预抓取点求解模型和梯形速度轨迹规划模型，实现了机械臂对目标矸石的快速逼近。基于七段式加速度模型，建立了多约束条件下机械臂同步跟踪动态目标数学模型，提出了基于粒子群算法的机械臂动态目标同步跟踪轨迹规划求解方法，实现了机械臂对动态目标同步跟踪。实验结果表明，该方法能够在最优时间内实现机械臂对目标矸石进行同步跟踪，位置跟踪平均误差为2.1mm，速度跟踪平均误差为5.4mm/s，跟踪误差满足机械手抓取要求。

针对煤矸石形状复杂、大小不一、机械手抓取稳定性差难题，深入研究了基于抓取立方体和“形-力”混合机械手稳定抓取方法。通过构建煤矸石抓取特征数学模型，利用点云数据对煤矸石空间信息进行提取，提出了基于OBB算法的煤矸石抓取立方体提取方法，获取煤矸石抓取特征；提出了“形-力”混合机械手自适应抓取方法，构建机械手运动学、动力学模型，分析机械手运动特性和抓取性能。通过虚拟样机进行仿真实验验证，结果表明，该机械手能够根据矸石粒度实现“形-力”混合自适应稳定抓取。

针对煤矸石随机分布、任务量大和分拣效率低等难题，提出了基于免疫动态工作空间的多机械臂煤矸石分拣机器人协同控制方法。构建了基于机械臂综合收益的多目标多机械臂任务分配模型和基于免疫动态工作空间多机械臂协同控制模型，通过焦躁函数解决机械臂“死锁”，提出了基于免疫动态工作空间的多机械臂协同控制方法。实验结果表明，该方法能最大限度提高机械臂利用率，提升系统稳定性，分拣率较基于动态工作空间多机械臂协同控制方法高9%，比基于固定工作空间多机械臂控制方法高19%。

研发了双机械臂煤矸石分拣机器人并在铜川矿业玉华煤矿进行了工业性实验，对机械臂动态目标跟踪、机械臂动态目标抓取和多机械臂协同分拣等方法进行了验证。实验结果表明，机械臂跟踪目标矸石平均位置误差为3.8mm，平均速度误差为7mm/s，机械臂抓取成功率为96.4%，双机械臂煤矸石分拣机器人分拣能力为1.96t/min，分拣频次为50次/min，实现了煤矸石的高效、稳定、精准、智能分拣。

Coal gangue sorting is the basic process for improving coal quality. However, traditional methods suffer from problems such as high manpower requirements, low sorting efficiency, high labor intensity, and poor working conditions, which seriously restrict the safe and efficient production of coal. With the continuous development of intelligent construction in coal mines, applying multi-arm robots to the coal gangue sorting has become a research hotspot, which is not only urgent but also challenging. To solve the problem of multi-arm robot dynamic target tracking, grabbing and collaborative control in coal gangue sorting, this paper proposes a scheme for the intelligent collaborative coal gangue sorting robot system. Key scientific problems such as dynamic target synchronization tracking and trajectory planning of mechanical arms, stable grabbing of dynamic targets, and multi-target and multi-arm collaborative control were deeply studied. The system achieved intelligent and accurate sorting of coal gangue, liberated productivity, and improved efficiency.

Coal gangue has the characteristics of different sizes, various shapes, fast speed, large quantities, and random distribution, which directly affect the stable grabbing and efficient sorting of coal gangue sorting robots. This paper analyzes the characteristics of coal gangue sorting, constructs a coal gangue sorting robot functional model based on functional analysis, and builds a multi-arm coal gangue sorting robot system principle model and an experimental platform based on the relationship between coal gangue sorting characteristics and sorting robot key technologies. The principles of mechanical arm dynamic target tracking trajectory planning, stable grabbing of mechanical arm dynamic targets, and multi-target and multi-arm collaborative control were built, laying a foundation for solving the key technologies of coal gangue sorting robots.

Due to the fast speed and large quality of coal gangue transportation, the direct grabbing of mechanical arm may cause impact load and easy grabbing failure or mechanical arm damage. To address this issue, the globally planned and locally optimized method of the mechanical arm dynamic target synchronous tracking trajectory planning was studied in-depth. By constructing a coal gangue pre-grabbing point solving model based on the cosine theorem and a trapezoidal speed trajectory planning model, the mechanical arm achieved rapid approach to the target gangue. Based on the seven-segment acceleration model, a mathematical model of mechanical arm synchronous tracking dynamic targets under multiple constraints was established, and a particle swarm algorithm-based method for solving the mechanical arm dynamic target synchronous tracking trajectory planning was proposed, achieving synchronous tracking of dynamic targets by the mechanical arm. Experimental results showed that the method could achieve synchronous tracking of the target gangue by the mechanical arm in the optimal time, with an average positional tracking error of 2.1 mm and an average velocity tracking error of 5.4 mm/s, meeting the grabbing requirements of the mechanical arm.

To address the problem of stable grabbing of coal gangue, a stable grabbing method based on the grabbing cuboid and "form-force" hybrid manipulator was studied in-depth. By constructing a mathematical model of coal gangue grabbing features and using point cloud data to extract spatial information of coal gangue, a coal gangue grabbing cuboid extraction method based on the OBB algorithm was proposed to obtain coal gangue grabbing features. An adaptive grabbing method of "form-force" hybrid manipulator was proposed, constructing the manipulator kinematics and dynamics models to analyze the manipulator motion characteristics and grabbing performance. Through virtual prototype simulation experiments, the results showed that the manipulator could achieve "form-force" hybrid adaptive stable grabbing according to the particle size of coal gangue.

To solve the problems of random distribution and low sorting efficiency of coal gangue, this paper proposes a multi-arm coal gangue sorting robot collaborative control method based on immune dynamic workspace. The multi-objective and multi-arm task allocation model based on mechanical arm comprehensive benefits and the multi-arm collaborative control model based on immune dynamic workspace are constructed. By solving mechanical arm "deadlock" through anxiety function and proposing a multi-arm collaborative control method based on immune dynamic workspace, the system stability is improved, and the sorting rate is 9% higher than that of the dynamic workspace multi-arm collaborative control method and 19% higher than that of the fixed workspace multi-arm control method.

Finally, a multi-arm coal gangue sorting robot industrial experiment is conducted to verify methods such as mechanical arm dynamic target tracking, mechanical arm dynamic target grabbing, and multi-arm collaborative sorting. The experimental results show that the average position error of the mechanical arm tracking target coal gangue is 3.8 mm, the average speed error is 7mm/s, the success rate of mechanical arm grabbing is 96.4%, the sorting capacity of the dual-arm coal gangue sorting robot is 1.96 t/min, and the sorting frequency is 50, which realizes efficient, stable, accurate, and intelligent sorting of coal gangue.

[1]煤炭工业“十四五”安全高效煤矿建设指导意见.中国煤炭工业协会,2021.12.7.

[2]煤监局行管司.国家煤矿安全监察局公告(2019年第1号):煤矿机器人重点研发目录[EB](2019-1-9).

[3]工业和信息化部.工业和信息化部等十七部门关于印发《“机器人+”应用行动实施方案》的通知.[EB](2023-1-19).

[4]赵明辉,宣鹏程,张少宾.并联煤矸石分拣机器人的结构设计及分析[J].机床与液压,2021,49(5):55-59．

[5]刘鹏,马宏伟,乔心州,等.柔索驱动拣矸机器人最小索拉力等值曲面研究[J].西安科技大学学报,2020,40(5):797-804.

[6]韩成石,董长双,周西军,等.煤和矸石γ-射线分选系统的研究[J].山西矿业学院学报,1997(02):45-49.

[7]刘文中,孔力.煤矸石自适应神经元网络识别方法研究[J].选煤技术,2002(3):22-24.

[8]程葳,孔力,袁树风,等.基于模糊神经网络的煤矸石模式识别方法研究[J].华中科技大学学报(自然科学版),1999,27(6):30-32.

[9]徐琦,孔力,程晶晶.基于生态遗传算法的煤矸石自适应模糊模式识别[J].华中科技大学学报(自然科学版),2003,31(12):22-24.

[10]范振,陈乃建,黄玉林,等.基于支持向量机与多种特征的煤矸石识别[J/OL].济南大学学报(自然科学版),2021(03):1-6.

[11]李文斌,杨剑瑜,文建国.光电选矸识别系统的研制与测试[J].仪器仪表学报,2001,22(3):265-268.

[12]王文鑫,黄杰,王秀宇,史玉林,吴高昌.X 射线透射煤矸智能识别方法[J].工矿自动化,2022,48(11):27-32+62.

[13]司垒,谭超,朱嘉皓,王忠宾,李嘉豪.基于 X 射线图像和激光点云的煤矸识别方法[J].仪器仪表学报,2022,43(09):193-205.

[14]尹建强.基于X射线煤矸智能识别的机理研究[D].安徽理工大学,2021.

[15]杨晨光,冯岸岸,朱金波,张勇,尹建强.智能分选中煤矸 X 射线识别技术的研究[J].安徽化工,2020,46(03):25-29+33.

[16]刘富强,钱建生,王新红,等.基于图像处理与识别技术的煤矿矸石自动分选[J].煤炭学报,2000,25(5):534-537.

[17]马宪民,田红,龚尚福.煤矸石在线识别与自动分选系统的研究[C].中国智能自动化会议,2001:66-68.

[18]Ma X M, Liang C.Application of rough set theory in coal gangue image process[C].Information Assurance and Security, International Symposium on. IEEE, 2009:87-90.

[19]余乐.一种煤和煤矸石图像识别的新方法[J].现代计算机(专业版),2017(17):66-70.

[20]徐志强,吕子奇,王卫东,等.煤矸智能分选的机器视觉识别方法与优化[J].煤炭学报,2020,45(6):2207-2216．

[21]李亚坤,马宏伟,王鹏.基于VGG_16网络的煤和矸石识别技术研究[J].煤炭技术,2022,41(09):156-159.

[22]郜亚松,张步勤,郎利影.基于深度学习的煤矸石识别技术与实现[J].煤炭科学技术,2021,49(12):202-208.

[23]来文豪,周孟然,胡锋,卞凯,宋红萍.基于多光谱成像和改进YOLO v4的煤矸石检测[J].光学学报,2020,40(24):72-80.

[24]张勇,杨鹏,王亮,李飞.基于经典卷积神经网络的智能煤矸识别[J].邵阳学院学报(自然科学版),2021,18(01):34-44.

[25]陈立,杜文华,曾志强,等.基于小波变换的煤矸石自动分选方法[J].工矿自动化,2018,44(22):60-64．

[26]任云鹏.基CAN控制器的煤矸石自动分选系统的设计[J].工矿自动化,2005(3):1-3.

[27]马宪民,宋晓茹.基于ARM核和CAN总线的煤矸石分选系统[J].仪器仪表学报,2005,26(z1):305-307.

[28]王鹏,曹现刚,夏晶,吴旭东,马宏伟.基于机器视觉的多机械臂煤矸石分拣机器人系统研究[J].工矿自动化,2019,45(09):47-53.

[29]马宏伟,张烨,王鹏,魏小荣,周文剑.多机械臂煤矸石智能分拣机器人关键共性技术研究[J].煤炭科学技术,2023,51(01):427-436.

[30]张烨,马宏伟,王鹏,曹现刚,魏小荣,周文剑.煤矸石智能分拣机器人研究进展与关键技术[J].工矿自动化,2022,48(12):42-48+56.

[31]Bardzinski P, Jurdziak L, Kawalec W, et al. Copper ore quality tracking in a belt conveyor system using simulation tools[J]. Natural Resources Research, 2020, 29: 1031-1040.

[32]Na J, Jing B, Huang Y, et al. Unknown system dynamics estimator for motion control of nonlinear robotic systems[J]. IEEE Transactions on Industrial Electronics, 2019, 67(5): 3850-3859.

[33]Malak S, Al Hajjar H, Dupont E, et al. Optical localization and tracking method of a mobile micro-conveyor over a smart surface[J]. IEEE Sensors Journal, 2021, 21(9): 10618-10627.

[34]Dai K, Wang D, Lu H, et al. Visual tracking via adaptive spatially-regularized correlation filters[C].Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019: 4670-4679.

[35]Qu C, He J, Li J, et al. Moving target interception considering dynamic environment[C].2022 American Control Conference (ACC).IEEE,2022:1194-1199.

[36]徐德.单目视觉伺服研究综述[J].自动化学报,2018,44(10):1729-1746.

[37]孙敬陶,钟杭,王耀南,李希.旋翼飞行机械臂的混合视觉伺服和分层控制方法[J].仪器仪表学报,2018,39(07):56-65.

[38]Li W, Xiong R, Li A W, et al.一种同时控制非完整约束底盘和机械臂的混合视觉伺服方法[J].2021,22(02):141-155.

[39]贾丙西,刘山,张凯祥,陈剑.机器人视觉伺服研究进展:视觉系统与控制策略[J]. 自动化学报,2015,41(05):861-873.

[40]Li Y, Huo J, Liu J, et al. Calibration of quad-camera measurement systems using a one-dimensional calibration object for three-dimensional point reconstruction[J]. Optical Engineering, 2019, 58(6): 064107-064107.

[41]Yang F, Zhao Y, Wang X. Camera calibration using projective invariants of sphere images[J]. IEEE Access, 2020, 8: 28324-28336.

[42]Parsapour M,Taghirad H D.Position based sliding mode control for visual servoing system[A].RSI Intemational Conference on Robotics and Mechatronics[C].Iran:IEEE Computer Press,2013,337-342.

[43]Luo Z,Fang H J.Modified state prediction algorithm based on UKF[J].Journal of systems Engineering and Electronics,2013,24(1):135-140.

[44]Huang Y, Su J. Visual servoing of nonholonomic mobile robots: A review and a novel perspective[J]. IEEE Access, 2019, 7: 134968-134977.

[45]Xu T, Guan Y, Liu J, et al. Image-based visual servoing of helical microswimmers for planar path following[J]. IEEE Transactions on Automation Science and Engineering, 2019,17(1):325-333.

[46]Zhang K, Shi Y, Sheng H. Robust nonlinear model predictive control based visual servoing of quadrotor UAVs[J]. IEEE/ASME Transactions on Mechatronics, 2021, 26(2): 700-708.

[47]Sato T,Sato J.Visual servoing from uncalibrated cameras for uncalibrated robots [J].Systems and Computers in Japan,2000,31(14):11-19.

[48]Liu H, Lyu Y, Zhao W. Robust visual servoing formation tracking control for quadrotor UAV team[J]. Aerospace Science and Technology, 2020, 106: 106061.

[49]Kragic D,Miller A T,Allen P K.Real-time tracking meets online grasp planning[C].Proceeding of IEEE International Conference on Robotics and Automation,2011:2460-2465.

[50]Arai S, Fukuchi N, Hashimoto K. Fast detection algorithm for 3D keypoints (FADA-3K)[J]. IEEE Access, 2020, 8: 189556-189564.

[51]Ren X, Li H, Li Y. Image-based visual servoing control of robot manipulators using hybrid algorithm with feature constraints[J].IEEE Access, 2020, 8: 223495-223508.

[52]Glover A, Bartolozzi C. Robust visual tracking with a freely-moving event camera[C].2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2017: 3769-3776.

[53]Yang Z, Sun H, Fei S, et al. A new method on uncalibrated visual servo based on image for dynamics model of robot manipulators[J].Journal of Computational Information Systems,2015,11(11):3903-3910.

[54]Ghasemi A, Xie W F. Adaptive image-based visual servoing of 6 DOF robots using switch approach[C].2018 IEEE International Conference on Information and Automation (ICIA).IEEE,2018:1210-1215.

[55]He Z, Wu C, Zhang S, et al. Moment-based 2.5-D visual servoing for textureless planar part grasping[J]. IEEE Transactions on Industrial Electronics, 2018, 66(10): 7821-7830.

[56]Gallego G, Delbrück T, Orchard G, et al. Event-based vision: A survey[J].IEEE transactions on pattern analysis and machine intelligence, 2020, 44(1): 154-180.

[57]孟琭,杨旭.目标跟踪算法综述[J].自动化学报,2019,45(7):1244-1260.

[58]程旭,周琳,张毅锋.基于多损失的生成式对抗目标跟踪算法[J].东南大学学报(自然科学版),2018,48(03):400-405.

[59]Kumah Charles,Zhang Ning,Raji Rafiu King,Li Zhongjian,Pan Ruru.Unsupervised segmentation of printed fabric patterns based on mean shift algorithm[J]. The Journal of The Textile Institute,2022,113(1).

[60]Li Dashe,Sun Yuanwei,Sun Jiajun,Wang Xueying,Zhang Xuan. An advanced approach for the precise prediction of water quality using a discrete hidden markov model[J]. Journal of Hydrology,2022,609.

[61]程旭,刘丽华,王莹莹,余梓彤,赵国英.基于多帧一致性修正的自监督孪生网络目标跟踪方法[J].计算机学报,2022,45(12):2544-2560.

[62]徐佳伟,罗倩.基于遗传非参数MDL-BW方法的HMM结构优化[J].电子学报,2022,50(11):2765-2772.

[63]赵钦君,张勇,赵东标.一种尺度和旋转自适应的目标跟踪算法[J].中南大学学报(自然科学版),2013,44(06):2354-2360.

[64]王洪雁,张莉彬,陈国强,汪祖民,管志远.结合粒子滤波及度量学习的目标跟踪方法[J].通信学报,2021,42(05):98-110.

[65]王爱丽,董宝田,武鸿源,武威.基于联合特征直方图的均值漂移目标跟踪算法[J].控制与决策,2016,31(10):1845-1852.

[66]崔洲涓,安军社,张羽丰,崔天舒.面向无人机的轻量级Siamese注意力网络目标跟踪[J].光学学报,2020,40(19):132-144.

[67]Zhang Y. Detection and tracking of human motion targets in video images based on camshift algorithms[J]. IEEE Sensors Journal, 2019, 20(20): 11887-11893.

[68]Kalal, Z., Mikolajczyk, K. and Matas, J. (2012) Tracking-learning-detection[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34, 1409-1422.

[69]Henriques J F,Caseiro R,Martins P. High-speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015,37(3):583-596.

[70]Danelljan M,Shahbaz Khan F,Felsberg M,et al.Adaptive color attributes for real-time visual tracking[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014: 1090-1097.

[71]Danelljan M，Hager G，Khan F，et al．Accurate scale estimation for robust visual tracking［C］.British Machine Vision Confer- ence.Nottingham: BMVA Press,2014:1-11.

[72]Liu Yuhan,Yan He,Zhang Wei,Li Mengxue,Liu Lingkun. An adaptive spatiotemporal correlation filtering visual tracking method.[J]. PloS one,2023,18(1):e0279240.

[73]Kumar A. Vision-less autonomous tracking and landing of a micro aerial vehicle on a slow maneuvering ground moving target using distance sensors[J]. Multimedia Tools and Applications, 2022, 81(24): 35261-35281.

[74]Ghaderi H, Yadegar M, Meskin N, et al. A novel proportional navigation based method for robotic interception planning with final velocity control[J]. IEEE Access, 2021, 9: 106428-106440.

[75]Jeddi M, Khoogar A R. A modified eye‐in‐hand stereo visual control for grasping unknown objects via Scara robot[J]. IET Image Processing, 2023.

[76]苏剑波,席裕庚.机器人动态抓取的变比例导引路径规划方法(英文)[J].控制理论与应用,2000(03):341-346.

[77]王斐,梁宸,韩晓光,等.基于焊件识别与位姿估计的焊接机器人视觉引导[J].控制与决策,2020,35(8):1873-1878.

[78]敖建华.基于改进比例导引法的机器人动态避障算法[J].计算机测量与控制,2015,23(4):1276-1278.

[79]谢国坤,张培培,王宁宁.基于点云分割的移动机器人运动目标跟踪方法[J].兵器装备工程学报,2022,43(11):225-230.

[80]关英姿,宋春林,董惠娟.空间自由漂浮机器人对运动目标抓捕的路径规划[J].机器人,2017 (6): 803-811.

[81]刘安全等.一种面向机器鱼的高精度位姿控制算法设计与实现[J].机器人,2016,38(2):241-247

[82]张朝阳等.基于金字塔形寻优的传送带动态抓取研究[J].制造业自动化,2015,37(5):92-95.

[83]张朝阳.基于视觉的机器人废金属分拣系统研究[D],中国农业大学,2015.

[84]王铮等.面向传送带作业系统的机器人目标跟踪与抓取策略研究[J].计算机测量与控制,2016,24(11):85-90.

[85]寿开荣,钟鹏飞,陈昆,等.基于机器视觉的锯条自动化装盒系统设计[J].计算机测量与控制,2015,12:4060-4063.

[86]蔡世波,陶志成,万伟伟,等.机器人多指灵巧手的研究现状、趋势与挑战[J].机械工程学报,2021,57(15):1-14.

[87]Ni W, Jiang Z, Li H, et al.Mechanical design and drive control of a novel dexterous hand for on-orbit servicing[J].Journal of Beijing Institute of Technology,2019,28(3):410-417.

[88]Li T,Cao W.Research on a method of creating digital shadow puppets based on parameterized templates[J]. Multimedia Tools and Applications,2021,80(13): 20403-20422.

[89]Gosselin C M.Adaptive robotic mechanical systems: A design paradigm[J].Journal of mechanical design,2006,128(1):192-198.

[90]Zhang W, Chen Q,Sun Z,et al.Passive adaptive grasp multi-fingered humanoid robot hand with high under-actuated function[C].2004 IEEE International Conference on Robotics and Automation Proceedings. New Orleans,USA:IEEE, 2004:2216-2221.

[91]Dollar A M, Howe R D. The highly adaptive sdm hand:design and performance evaluation[J]. The international journal of robotics research,2010,29(5):585-597.

[92]Dechev N, Cleghorn W L, Naumann S. Multiple finger, passive adaptive grasp prosthetic hand[J]. Mechanism and machine theory,2001,36(10):1157-1173.

[93]Kobayashi A, Kinugawa J, Arai S, et al. Design and development of compactly folding parallel open-close gripper with wide stroke[C].2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019).Macau, China:IEEE, 2019: 2408-2414.

[94]Morino K, Kikuchi S, Chikagawa S, et al. Sheet-based gripper featuring passive pull-in functionality for bin picking and for picking up thin flexible objects[J]. IEEE Robotics and Automation Letters, 2020, 5(2): 2007-2014.

[95]李小彭,郭军强,孙万琪,等.混合工作模式欠驱动手设计及其接触力分析[J].机械工程学报,2021,57(01):8-18.

[96]Nishimura T, Mizushima K, Suzuki Y, et al. Variable-grasping-mode underactuated soft gripper with environmental contact-based operation[J]. IEEE Robotics and Automation Letters, 2017, 2(2): 1164-1171.

[97]Pons J L, Rocon E, Ceres R, et al. The manus-hand dextrous robotics upper limb prosthesis: mechanical and manipulation aspects[J]. Autonomous Robots, 2004, 16(2): 143-163.

[98]Carrozza M C, Suppo C, Sebastiani F, et al. The spring hand: development of a self-adaptive prosthesis for restoring natural grasping[J]. Autonomous Robots, 2004, 16(2): 125-141.

[99]刘菲,何广平,陆震.弹性欠驱动四指灵巧手设计与实验[J].机械工程学报,2014,50(15):53-59.

[100]Tian J, Wei C, Luo M, et al. Parametric research on underactuated tendon-driven grasping mechanism for space capture operation[J]. International Journal of Precision Engineering and Manufacturing, 2020, 21(2): 237-247.

[101]马涛,杨冬,赵海文,等.一种新型欠驱动机械手爪的抓取分析和优化设计[J].机器人,2020,42(03):354-364.

[102]Li G, Liu H, Zhang W. Development of multi-fingered robotic hand with coupled and directly self-adaptive grasp[J]. International Journal of Humanoid Robotics, 2012, 9(04): 1250034.

[103]Li G, Li B, Sun J, et al. Development of a directly self-adaptive robot hand with pulley-belt mechanism[J].International Journal of Precision Engineering and Manufacturing,2013,14(8):1361-1368.

[104]Li G, Zhang C, Zhang W, et al. Coupled and self-adaptive under-actuated finger with a novel s-coupled and secondly self-adaptive mechanism[J]. Journal of Mechanisms and Robotics, 2014, 6(4): 041010.

[105]蔡军,左俊伟,顾逸霏,等.基于行星齿轮机构的牵引式欠驱动机械手设计[J].机器人,2022,44(06):641-648.

[106]Zheng E, Zhang W. An underactuated pasa finger capable of perfectly linear motion with compensatory displacement[J].Journal of Mechanisms and Robotics, 2019, 11(1): 014505.

[107]吴立成,孔岩萱,李霞丽.全转动关节欠驱动手指机构及其运动学分析[J].机械工程学报,2017,53(01):47-54.

[108]Tae-Uk K, Yonghwan O. Design of spatial adaptive fingered gripper using spherical five-bar mechanism[C].Proceedings of the 2014 International Conference on Advanced Mechatronic Systems. Kumamoto, Japan:IEEE 2014: 145-150.

[109]Bohg J,Morales A, Asfour T,et al.Data-driven grasp synthesis—a survey[J]. IEEE Transactions on Robotics,2014,30(2):289-309.

[110]Rosales C, Porta J M, Ros L.Global optimization of robotic grasps[J].Proceedings of Robotics: Science and Systems VII,2011,3.

[111]Weisz J,Allen P K.Pose error robust grasping from contact wrench space metrics[C].2012 IEEE International Conference on Robotics and Automation. St Paul,USA :Institute of Electrical and Electronics Engineers,2012:557-562.

[112]Shafii N,Kasaei S H,Lopes L S.Learning to grasp familiar objects using object view recognition and template matching[C].2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2016). Daejeon, Korea:[s.n.]2016:2895 -2900.

[113]Guo D,Sun F,Liu C. A system of robotic grasping with experience acquisition[J].Science China Information Sciences,2014, 57(12):1-11.

[114]Yang Y, Cao Q X. Monocular vision based 6D object localization for service robot’s intelligent grasping[J].Computers & Mathematics with Applications, 2012, 64(5): 1235-1241.

[115]Saxena A,Driemeyer J,Ng A Y. Robotic grasping of novel objects using vision[J]. The International Journal of Robotics Research, 2008, 2 7(2):157-173.

[116]Balaguer B,Carpin S.Efficient grasping of novel objects through dimensionality reduction[C].2010 IEEE International Conference on Robotics and Automation (ICRA 2010).Anchorage, Alaska:IEEE,2010: 1279-1285.

[117]El-Khoury S, Sahbani A. A new strategy combining empirical and analytical approaches for grasping unknown 3D objects[J]. Robotics and Autonomous Systems, 2010, 58(5): 497-507.

[118]Le Q V, Kamm D, Kara A F, et al. Learning to grasp objects with multiple contact points[C].2010 IEEE International Conference on Robotics and Automati-on.Anchorage, Alaska:IEEE,2010:5062-5069.

[119]Jiang Y, Moseson S,Saxena A. Efficient grasping from rgbd images: Learning using a new rectangle representation[C].2011 IEEE International Conference on Robotics and Automation. Shanghai,China:IEEE,2011:3304-3311.

[120]Lenz I, Lee H,Saxena A.Deep learning for detecting robotic grasps[J].The International Journal of Robotics Research, 2015,34(4-5):705-724.

[121]Redmon J, Angelova A. Real-time grasp detection using convolutional neural networks[C].2015 IEEE international conference on robotics and automation (ICRA). Seattle,USA:IEEE, 2015: 1316-1322.

[122]Pinto L,Gupta A.Supersizing self-supervision:Learning to grasp from 50k tries and 700 robot hours[C].2016 IEEE International Conference on Robotics and Automation(ICRA).Stockholm,Sweden:IEEE,2016:3406-3413.

[123]Wei J, Liu H,Yan G,et al.Robotic grasping recognition using multi -modal deep extreme learning machine[J]. Multidimensional Systems and Signal Proces sing,2016:1-17.

[124]Sun C,Yu Y, Liu H, et al. Robotic grasp detection using extreme learning machine[C].2015 IEEE International Conference on Robotics and Biomimetics (ROBIO).Zhuihai,China:IEEE,2015:1115-1120.

[125]仲训杲,徐敏,仲训昱,等.基于多模特征深度学习的机器人抓取判别方法[J].自动化学报,2016,42(7):1022-1029.

[126]Varley J,Weisz J,Weiss J,et al.Generating multi-fingered robotic grasps via deep learning[C].2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) .Washington,USA:IEEE Computer Society,2015: 4415-4420.

[127]Zhang H, Zhou X, Lan X, et al. A real-time robotic grasping approach with oriented anchor box[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2019, 51(5): 3014-3025.

[128]Pinto L,Gupta A.Supersizing self-supervision: Learning to grasp from 50k tries and 700 robot hours[C].Robotics and Automation (ICRA).2016 IEEE International Conference on. Stockholm, Sweden:[s.n.],2016: 3406-3413.

[129]Gualtieri M, Ten Pas A, Saenko K, et al.High precision grasp pose detection in dense clutter[C].Intelligent Robots and Systems (IROS). 2016 IEEE/RSJ International Conference on. Daejeon, Kore:[s.n.],2016:598-605.

[130]Choi C, Schwarting W, DelPreto J, et al. Learning object grasping for soft robot hands[J]. IEEE Robotics and Automation Letters, 2018, 3(3): 2370-2377.

[131]Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.

[132]Szegedy C, Liu W, Jia Y,et.al.Going deeper with convolutions[C].Proceedings of the IEEE conference on computer vision and pattern recognition.Boston,USA:IEEE Computer Society,2015:1-9.

[133]Socher R, Huval B, Bath B, et al. Convolutional-recursive deep learning for 3d object classification[J]. Advances in neural information processing systems, 2012, 25.

[134]卢良锋,谢志军,叶宏武.基于RGB特征与深度特征融合的物体识别算法[J].计算机工程, 2016,42(5):186-193.

[135]Weng Y, Sun Y, Jiang D, et al. Enhancement of real‐time grasp detection by cascaded deep convolutional neural networks[J]. Concurrency and Computation: Practice and Experience, 2021, 33(5): e5976.

[136]Schwarz M,Schulz H,Behnke S.RGB-D object recognition and pose estimation based on pre-trained convolutional neural network features[C].2015 IEEE International Conference on Robotics and Automation.Seattle,USA:IEEE，2015:1329 -1335.

[137]Lai K, Bo L, Ren X, et al. A scalable tree-based approach for joint object and pose recognition[C].Proceedings of the AAAI Conference on Artificial Intelligence. San Francisco, USA：AAAI Press ,2011: 1474-1480.

[138]Gupta S, Girshick R, Arbeláez P, et al. Learning rich features from RGB-D images for object detection and segmentation[C].European Conference on Computer Vision.Zurich, Switzerland:Springer International Publishing,2014: 345-360.

[139]Dai W, Yu Q, Xiao J, et al. Communication-Less cooperation between soccer robots[C].RoboCup 2016: Robot World Cup XX 20. Springer International Publishing, 2017:356-367.

[140]Wang Sen, Chen Guodong, Xu Hui, et al. A robotic peg-in-hole assembly strat-egy based on variable compliance center[J]. IEEE Access,2019,7: 167534-167546.

[141]Zheng Y, Zhang X, Chen Y, et al. Peg-in-hole assembly based on hybrid vision/force guidance and dual-arm coordination[C].2017 IEEE International Conference on Robotics and Biomimetics (ROBIO). Macau, China: IEEE, 2017:418-423.

[142]Alkilabi M H M, Narayan A, Tuci E. Cooperative object transport with a swarm of e-puck robots: robustness and scalability of evolved collective strategies[J]. Swarm intelligence, 2017, 11(3/4): 185–209.

[143]陈阳,郑甲红,王婧.双机器人协同控制研究综述[J].计算机系统应用,2022,31(02):13-21.

[144]潘继炜,滕游,刘安东,等.基于眼到手视觉伺服的移动机器人模型预测控制[J].计算机测量与控制,2021,29(05):122-125+140.

[145]袁宇鹏,胡杨,李军,等.基于动态矩阵控制的自主移动机器人模型预测控制方法研究[J].重庆邮电大学学报(自然科学版),2018,30(04):537-543.

[146]谭辉.移动机器人控制方法综述[J].科技创新与应用,2021,11(20):125-127.

[147]Zheng S,Lin Z,Zeng Q, et al.IAPcloud:A cloud control platform for heterogeneous robots[J].IEEE Access,2018,PP:1-1.

[148]董美英.模糊免疫算法的轮式移动机器人PID控制优化设计[J].安庆师范大学学报(自然科学版),2017,23(02):9-14.

[149]Zhang F, Gao X, Xie Z & Liu Y.Multi-robot rounding strategy based on artificial pot ential field method in dynamic environment[C].2019 Chinese Automation Congress (CAC).Chicago USA:IEEE,2019: 2294-2299.

[150]Zhang L, Li T, Huang T, et al. Adaptive impulsive consensus of multi-agent nonlinear systems with uncertain parameters[C].2017 29th Chinese Control and Decision Conference (CCDC). Chongqing, China: IEEE, 2017: 6331-6336.

[151]蒙奎全,秦远田,蒋祺,等.机器人末端复杂环境下力自适应控制[J].机床与液压,2022,50(17):12-18.

[152]王荪馨,王经国.一种领航-跟随型多移动机器人编队控制方法[J].重型机械,2019(01):14-21.

[153]刘慧博,孙昌琦,任彦.机械臂轨迹的阻抗滑膜控制[J].机械设计与制造,2022(05):56-59.

[154]Kuhn H W.The Hungarian method for the assignment problem[J]. Naval research logistics quarterly, 1955, 2(1-2):83-97.

[155]李廷鹏,钱彦岭,李岳.基于改进匈牙利算法的多技能人员调度方法[J].国防科技大学学报,2016,38(02):144-149.

[156]Moon S T, Lee D, Lee D, et al. Energy-efficient swarming flight formation transitions using the improved fair Hungarian algorithm[J]. Sensors, 2021, 21(4): 1260.

[157]Smithr G.The contract net protocol:high level communication and control in a distributed problem solver[J].IEEE Trans on Computers,1980(6):1104-1113.

[158]Jiang Dapeng,Pang Yongjie,Qin Zaibai.Coordinated control of multiple autonomous under water vehicle system[C]. Proceedings of 2010 8th World Congress on Intelligent Control and Automation.Jinan,China,2010:4901-4906P

[159]Liu Yifan,Liu Fei,Tang Li,et al. Multirobot adaptive task allocation of intelligent warehouse based on evolutionary strategy[J]. Journal of Sensors,2022,2022.

[160]赵辉,郝梦雅,王红君等.基于资源拍卖的农业多机器人任务分配[J].计算机应用与软件,2021,38(12):286-290+313.

[161]Xiao Q, Zhang Q, Wu X, et al. Learning binary code features for uav target tracking[C].2017 3rd IEEE International Conference on Control Science and Systems Engineering (ICCSSE). Beijing China:IEEE,2017:65-68.

[162]陈飞军,贺俊,刘栋,等.基于行为的智能塔机路径规划算法与动态避让策略[J].建筑机械化,2022,43(10):38-41.

[163]郭戈,张茜,张振宇.具有预设瞬稳态性能的有限时间智能车辆固定构型编队控制[J].2022.35(3):28-42.

[164]Zaid T,Qureshi A H, Yasar A, et al.Potentially guided bi-directionalized RRT for fast optimal path planning in cluttered environments[J]. Robotics and Autonomous Systems,2018,108:13-27.

[165]甘文洋,朱大奇.基于行为策略的AUV全覆盖信度函数路径规划算法[J].系统仿真学报,2018,30(05):1857-1868.

[166]邵壮,祝小平,周洲,等.三维动态环境下多无人机编队分布式保持控制[J].控制与决策,2016,31(06):1065-1072.

[167]Geng L, Zhang Y F, Wang J J, et al. Cooperative task planning for multiple autonomous UAVs with graph representation and genetic algorithm[C].2013 10th IEEE International Conference on Control and Automation (ICCA).Hangzhou China: IEEE, 2013: 394-399.

[168]Li S, Xu X, Zuo L. Task assignment of multi-robot systems based on improved genetic algorithms[C].2015 IEEE International Conference on Mechatronics and Automation (ICMA). Beijing China: IEEE, 2015: 1430-1435.

[169]何凡,任向东,吴桐.改进遗传算法求解电力网攻击无人机分队任务分配[J].火力与指挥控制,2015(4):51-54.

[170]王庆贺,万刚,柴峥,李登峰.基于改进遗传算法的多机协同多目标分配方法[J].计算机应用研究,2018,35(09):2597-2601.

[171]Sun W, Zhang F, Xue M, et al. An som-based algorithm with locking mechanism for task assignment[C].2017 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM).Ningbo China: IEEE, 2017: 36-41.

[172]李翠明,王宁,张晨.基于改进遗传算法的光伏板清洁分级任务规划[J].上海交通大学学报,2021,55(09):1169-1174.

[173]胡章芳,冯淳一,罗元.改进粒子群优化算法的移动机器人路径规划[J].计算机应用研究,2021,38(10):3089-3092.

[174]刘俊贤,王宏强,陶新龙.基于改进多目标粒子群优化算法的雷达资源分配方法[J].中国电子科学研究院学报,2022,17(06):549-556+565.

[175]Ouyang H, Gao L, Li S, et al. Improved global-best-guided particle swarm optimization with learning operation for global optimization problems[J]. Applied Soft Computing,2017,52:987-1008.

[176]Talbi E G, Roux O, Fonlupt C, et al. Parallel ant colonies for combinatorial optimization problems[C].Parallel and Distributed Processing: 11th IPPS/SPDP’99 Workshops Held in Conjunction with the 13th International Parallel Processing Symposium and 10th Symposium on Parallel and Distributed Processing San Juan, Puerto Rico, USA, April 12–16,1999 Proceedings 13. Springer Berlin Heidelberg, 1999: 239-247.

[177]曹如月,李世超,季宇寒等.基于蚁群算法的多机协同作业任务规划[J].农业机械学报,2019,50(S1):34-39.

[178]何心,李志恒,李冰等.一种改进蚁群算法的移动机器人路径规划研究[J].现代制造工程,2023,No.509(02):36-43.

[179]钱平,顾才东,鲜学丰等.基于改进蚁群算法的水下机器人路径规划研究[J].制造业自动化,2022,44(12):181-184+208.

[180]秦新立,宗群等.基于改进蚁群算法的多机器人任务分配[J].空间控制与应用,2018，1574-1579.

[181]曹海.人工免疫算法的船舶避碰智能策略研究[J].舰船科学技术,2016,38(02):10-12.

[182]Yi Shen, Qi Wang, Zhaoli Ye, et al. Motion control of mobile robot based on immuneclonal algorithm evolved by virus[J] Applied Mechanics and Materials,2012,143:269-273.

[183]Zhu P, Dai W, Yao W, et al. Multi-robot flocking control based on deep reinforcement learning[J]. IEEE Access,2020, 8: 150397-150406.

[184]张文璐,霍子龙,赵西雨,等.面向智能工厂多机器人定位的无线分布式协同决策[J].无线电通信技术,2022,48(04):718-727.

[185]丁玲,任雪娇,赵昆.基于改进智能算法的多机器人舞蹈表演避障系统设计[J].自动化与仪器仪表,2022(11):216-219.

[186]陈明智,钱同惠,张仕臻,等.基于强化学习的多机器人仓储调度方法研究[J].现代电子技术,2019,42(14):165-168.

[187]徐雪松,曾智,邵红燕,等.基于个体-协同触发强化学习的多机器人行为决策方法[J].仪器仪表学报,2020,41(05):66-75.

[188]Mehrandezh,m.,sela,m.n.,fenton,r.g.,and benhabib,b.Robotic interception of moving objects using ideal proportional navigation guidance technique,J.Robotic Autonom systems,33(1)(2002):1-23.

[189]曹现刚,李 宁,王 鹏,等.基于比例导引法的机械臂拣矸过程轨迹规划方法研究[J].煤炭工程,2019,51(5):154-158．

[190]曹现刚,乔欢乐,吴旭东,王鹏,范智海.考虑含矸率时变性的多臂协同策略优化方法[J/OL].机械科学与技术.https://doi.org/10.13433/j.cnki.1003-8728.20220159.

[191]曹现刚,吴旭东,王鹏,等.面向煤矸分拣机器人的多机械臂协同策略[J],煤炭学报,2019,44(S2):763-774．