接触丰富的自动装配方法研究进展：机器人装配接触力控制技能学习

doi:10.3901/JME.2025.10.395

机械工程学报 ›› 2025, Vol. 61 ›› Issue (10): 395-413.doi: 10.3901/JME.2025.10.395

• 交叉与前沿 • 上一篇

扫码分享

接触丰富的自动装配方法研究进展：机器人装配接触力控制技能学习

李明富^1,2,3, 王飞鸿¹, 朱凌枫¹, 李想¹, 雷高攀^1,2, 刘翊^1,2, 李林凌⁴, 侯宇葵⁵, 胡余良⁶

1. 湘潭大学机械工程与力学学院湘潭 411105;
2. 复杂轨迹加工工艺及装备教育部工程研究中心湘潭 411105;
3. 焊接机器人与应用技术湖南省重点实验室湘潭 411105;
4. 北京空间飞行器总体设计部北京 100094;
5. 中国空间技术研究院钱学森空间技术实验室北京 100094;
6. 广东顺德为艾斯机器人有限公司佛山 528300

收稿日期:2024-06-01 修回日期:2024-11-11 发布日期:2025-07-12
作者简介:李明富(通信作者)，男，1979年出生，教授，博士研究生导师。主要研究方向为智能机器人、智能制造。E-mail：mingfuli@xtu.edu.cn；limingfu2001@foxmail.com;王飞鸿，男，1998年出生，硕士研究生。主要研究方向为机器人控制、深度学习和强化学习。E-mail：wangfeihong934@163.com;朱凌枫，男，1999年出生，硕士研究生。主要研究方向为机器人控制、深度学习和强化学习。E-mail：202221542060@smail.xtu.edu.cn;李想，男，1999年出生，硕士研究生。主要研究方向为机器人控制和机器视觉。;E-mail：18242812210@163.com;雷高攀，男，1996年出生，博士，讲师。主要研究方向为特种加工及智能制造。;E-mail：leigp@xtu.edu.cn;刘翊，男，1985年出生，教授，博士研究生导师。主要研究方向为虚拟/增强装配、智能算法、动力学仿真。E-mail：liuyi@xtu.edu.cn;李林凌，男，1973年出生，博士，研究员。主要研究方向为深空探测技术及装备。E-mail：lilinling@tsinghua.org.cn;侯宇葵，男，1968年出生，博士，研究员。主要研究方向为航天体系设计、空间技术战略规划、空间低温技术。;E-mail：321762776@qq.com;胡余良，男，1976年出生，高级工程师。主要研究方向为自动装配技术及装备。E-mail：hyl@weasi.com
基金资助:
国家自然科学基金(52375519)和国家重点研发(2021YFF0500300)资助项目。

Research Progress on Contact-rich Automated Assembly Methods：Learning Robotic Assembly Contact Force Control Skills

LI Mingfu^1,2,3, WANG Feihong¹, ZHU Lingfeng¹, LI Xiang¹, LEI Gaopan^1,2, LIU Yi^1,2, LI Linling⁴, HOU Yukui⁵, HU Yuliang⁶

1. School of Mechanical Engineering and Mechanics, Xiangtan University, Xiangtan 411105;
2. Engineering Research Center of Complex Tracks Processing Technology and Equipment of Ministry of Education, Xiangtan 411105;
3. Key Laboratory of Welding Robot and Application Technology of Hunan Province, Xiangtan 411105;
4. Beijing Institute of Spacecraft System Engineering, Beijing 100094;
5. Qian Xuesen Laboratory of Space Technology of China Academy of Space Technology, Beijing 100094;
6. Guangdong Shunde Weasi Robot Co., Ltd., Foshan 528300

Received:2024-06-01 Revised:2024-11-11 Published:2025-07-12

摘要/Abstract

摘要： 由于制造误差、定位误差、接触变形和表面质量不一致等因素的综合影响，装配接触力呈现随机扰动现象，导致具有接触丰富特点的自动装配发生卡阻、不符合工艺要求，甚至损坏零部件。最新研究表明，在解决接触丰富的自动装配问题时，基于学习方法进行装配接触控制是最有效的途径之一。鉴于目前强化学习方法在接触丰富的机器人装配中取得了显著性进展，基于机器人自动装配领域的研究现状，对具有接触丰富特点的装配特征进行分析和统计，提出甄别接触丰富装配的判别指标。通过对相关研究领域文献的分析，将机器人自动装配过程中的接触力控制技能学习方法分为基于强化学习的接触控制方法、面向奖励工程的接触控制方法和模拟到现实的接触控制方法等三大类，并对这三大类方法分别进行综述和分析。最后，对接触丰富的机器人自动装配控制技能学习的未来发展趋势进行了分析和展望。

关键词: 机器人装配, 自动装配, 接触丰富, 接触力调整技能学习, 强化学习

Abstract: Due to the combined effects of manufacturing errors, positioning errors, contact deformations, and inconsistent surface qualities, the assembly contact forces exhibit random disturbances, leading to issues such as jamming, non-compliance with process requirements, and even component damage in contact-rich automated assembly. Recent research has shown that employing learning-based approaches for assembly contact control is one of the most effective strategies to address contact-rich automated assembly problems. Considering the significant progress made by reinforcement learning methods in contact-rich robotic assembly, this paper analyzes and statistically characterizes assembly features with contact-rich characteristics in the field of robotic automated assembly. It proposes discriminative indicators for identifying contact-rich assembly situations. Through an analysis of relevant literature in the field, the methods for learning contact force control in robotic automated assembly are categorized into three main types：reinforcement learning-based contact control methods, reward-engineered contact control methods, and simulation-to-reality contact control methods. Each of these categories is reviewed and analyzed. Finally, an analysis and outlook on the future development trends of learning contact-rich robotic automated assembly control skills is provided.

Key words: robot assembly, automatic assembly, contact-rich, contact force adjustment skills learning, reinforcement learning

中图分类号:

TP249
TP183

李明富, 王飞鸿, 朱凌枫, 李想, 雷高攀, 刘翊, 李林凌, 侯宇葵, 胡余良. 接触丰富的自动装配方法研究进展：机器人装配接触力控制技能学习[J]. 机械工程学报, 2025, 61(10): 395-413.

LI Mingfu, WANG Feihong, ZHU Lingfeng, LI Xiang, LEI Gaopan, LIU Yi, LI Linling, HOU Yukui, HU Yuliang. Research Progress on Contact-rich Automated Assembly Methods：Learning Robotic Assembly Contact Force Control Skills[J]. Journal of Mechanical Engineering, 2025, 61(10): 395-413.

参考文献

[1] MARVEL J，FALCO J. Best practices and performance metrics using force control for robotic assembly[M]. New York：National Institute of Standards and Technology，2012.
[2] 刘检华，孙清超，程晖，等. 产品装配技术的研究现状，技术内涵及发展趋势[J]. 机械工程学报，2018，54(11)：2-28. LIU Jianhua，SUN Qingchao，CHENG Hui，et al. The state-of-the-art，connotation and developing trends of the products assembly technology[J]. Journal of Mechanical Engineering，2018，54(11)：2-28.
[3] LI W，WANG J，LIU M，et al. Real-time occlusion handling for augmented reality assistance assembly systems with monocular images[J]. Journal of Manufacturing Systems，2022，62：561-574.
[4] NARANG Y，STOREY K，AKINOLA I，et al. Factory：Fast contact for robotic assembly[C]// Robotics：Science and Systems 2022，June 27-July 1，2022，New York City，NY，USA：RSS，2022.
[5] 黄艳龙，徐德，谭民. 机器人运动轨迹的模仿学习综述[J]. 自动化学报，2022，48(2)：315-334. HUANG Yanlong，XU De，TAN Min. On imitation learning of robot movement trajectories：A survey[J]. Acta Automatica Sinica，2022，48(2)：315-334.
[6] 殷聪聪，张秋菊. 机器人演示学习编程技术研究综述[J]. 计算机科学与探索，2020，14(8)：1275-1287. YIN Congcong，ZHANG Qiuju. Review of research on robot programming by learning from demonstration[J]. Journal of Frontiers of Computer Science and Technology，2020，14(8)：1275-1287.
[7] JIANG J，HUANG Z，BI Z，et al. State-of-the-art control strategies for robotic pih assembly[J]. Robotics and Computer-Integrated Manufacturing，2020，65：101894.
[8] 徐德，秦方博. 机器人自动轴孔装配研究进展[J]. 智能科学与技术学报，2022，4(2)：200-211. XU De，QIN Fangbo. Research development on automated robotic peg-in-hole assembly[J]. Chinese Journal of Intelligent Science and Technology，2022，4(2)：200-211.
[9] 刘乃军，鲁涛，蔡莹皓，等. 机器人操作技能学习方法综述[J]. 自动化学报，2019，45(3)：458-470. LIU Naijun，LU Tao，CAI Yinghao，et al. A review of robot manipulation skills learning methods[J]. Acta Automatica Sinica，2019，45(3)：458-470
[10] ELGUEA-AGUINACO Í，SERRANO-MUÑOZ A，CHRYSOSTOMOU D，et al. A review on reinforcement learning for contact-rich robotic manipulation tasks[J]. Robotics and Computer-Integrated Manufacturing，2023，81：102517.
[11] HAN D，MULYANA B，STANKOVIC V，et al. A survey on deep reinforcement learning algorithms for robotic manipulation[J]. Sensors，2023，23(7)：3762.
[12] ZHAO W，QUERALTA J P，WESTERLUND T. Sim-to-real transfer in deep reinforcement learning for robotics：A survey[C]// 2020 IEEE Symposium Series on Computational Intelligence(SSCI). New York：IEEE，2020：737-744.
[13] HUA J，ZENG L，LI G，et al. Learning for a robot：Deep reinforcement learning，imitation learning，transfer learning[J]. Sensors，2021，21(4)：1278.
[14] ZHU Z，LIN K，JAIN A K，et al. Transfer learning in deep reinforcement learning：A survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence，2023，45(11)：13344-13362.
[15] WANG H N，LIU N，ZHANG Y Y，et al. Deep reinforcement learning：A survey[J]. Frontiers of Information Technology & Electronic Engineering，2020，21(12)：1726-1744.
[16] 孔松涛，刘池池，史勇，等. 深度强化学习在智能制造中的应用展望综述[J]. 计算机工程与应用，2021，57(2)：49-59. KONG Songtao，LIU Chichi，SHI Yong，et al. Review of application prospect of deep reinforcement learning in intelligent manufacturing[J]. Computer Engineering and Applications，2021，57(2)：49-59.
[17] 陈佳盼，郑敏华. 基于深度强化学习的机器人操作行为研究综述[J]. 机器人，2022，44(2)：236-256. CHEN Jiapan，ZHENG Minhua. A survey of robot manipulation behavior research based on deep reinforcement learning[J]. Robot，2022，44(2)：236-256.
[18] LI C，ZHENG P，YIN Y，et al. Deep reinforcement learning in smart manufacturing：A review and prospects[J]. CIRP Journal of Manufacturing Science and Technology，2023，40：75-101.
[19] ABU-DAKKA F J，NEMEC B，KRAMBERGER A，et al. Solving peg-in-hole tasks by human demonstration and exception strategies[J]. Industrial Robot：An International Journal，2014，41(6)：575-584.
[20] ZHU Z，HU H. Robot learning from demonstration in robotic assembly：A survey[J]. Robotics，2018，7(2)：17.
[21] PARK H，PARK J，LEE D H，et al. Compliant peg-in-hole assembly using partial spiral force trajectory with tilted peg posture[J]. IEEE Robotics and Automation Letters，2020，5(3)：4447-4454.
[22] JHA D K，ROMERES D，JAIN S，et al. Design of adaptive compliance controllers for safe robotic assembly[C]// 2023 European Control Conference(ECC). IEEE，2023：1-8. https://doi.org/10.23919/ECC57647.2023.10178229.
[23] LIU G，YAO B，XU W，et al. Optimizing non-diagonal stiffness matrix of compliance control for robotic assembly using deep reinforcement learning[C]//Journal of Physics：Conference Series. IOP Publishing，2022，2402(1)：012013. https://dx.doi.org/10.1088/1742-6596/2402/1/012013.
[24] LEE M A，ZHU Y，ZACHARES P，et al. Making sense of vision and touch：Learning multimodal representations for contact-rich tasks[J]. IEEE Transactions on Robotics，2020，36(3)：582-596.
[25] MICHALOS G，MAKRIS S，CHRYSSOLOURIS G. The new assembly system paradigm[J]. International Journal of Computer Integrated Manufacturing，2015，28(12)：1252-1261.
[26] MAKRIS S，TSAROUCHI P，SURDILOVIC D，et al. Intuitive dual arm robot programming for assembly operations[J]. CIRP Annals，2014，63(1)：13-16.
[27] SAGARDIA M，HULIN T. Multimodal evaluation of the differences between real and virtual assemblies[J]. IEEE Transactions on Haptics，2017，11(1)：107-118.
[28] CHANG R J，JAU J C. Augmented reality in peg-in-hole microassembly operations[J]. International Journal of Automation Technology，2016，10(3)：438-446.
[29] LEE D Y，CHUNG S Y，HWANG M J，et al. Adaptive modeling of robotic assembly using augmented Petri nets[C]//2007 American Control Conference. New York：IEEE，2007：3600-3605. https://doi.org/10.1109/ACC.2007.4282773
[30] BODENHAGEN L，FUGL A R，WILLATZEN M，et al. Learning peg-in-hole actions with flexible objects[C]// In 4th International Conference on Agents and Artificial Intelligence(ICAART)，Vilamoura，2012：624-631.
[31] BODENHAGEN L，FUGL A R，JORDT A，et al. An adaptable robot vision system performing manipulation actions with flexible objects[J]. IEEE Transactions on Automation Science and Engineering，2014，11(3)：749-765.
[32] YANCHUN X，YUEWEI B，YAFEI H. Assembly strategy study on the elastic deformable peg in hole[C]// 2010 The 2nd International Conference on Industrial Mechatronics and Automation：Volume 1. New York：IEEE，2010：193-197.
[33] JASIM I F，PLAPPER P W. Contact-state monitoring of force-guided robotic assembly tasks using expectation maximization-based gaussian mixtures models[J]. The International Journal of Advanced Manufacturing Technology，2014，73：623-633.
[34] JASIM I F，PLAPPER P W. Contact-state modeling of robotic assembly tasks using gaussian mixture models[J]. Procedia Cirp，2014，23：229-234.
[35] TAKAHASHI J，FUKUKAWA T，FUKUDA T. Passive alignment principle for robotic assembly between a ring and a shaft with extremely narrow clearance[J]. IEEE/ ASME Transactions on Mechatronics，2015，21(1)：196- 204.
[36] WATSON J，MILLER A，CORRELL N. Autonomous industrial assembly using force，torque，and rgb-d sensing[J]. Advanced Robotics，2020，34(7-8)：546-559.
[37] SLOTH C，KRAMBERGER A，ITURRATE I. Towards easy setup of robotic assembly tasks[J]. Advanced Robotics，2020，34(7-8)：499-513.
[38] 潘柏松，颜天野，胡鑫达，等. 基于几何约束与隐马尔可夫链模型的轴孔装配策略[J]. 计算机集成制造系统，2022，28(12)：3768-3778. PAN Baisong，YAN Tianye，HU Xinda，et al. Peg-in-hole assembly strategy based on geometric constraint and hidden Markov model[J]. Computer Integrated Manufacturing Systems，2022，28(12)：3768-3778.
[39] 罗威，李明富，赵文权，等. 基于力-位图像学习的工业机器人柔顺装配方法研究[J]. 机械工程学报，2022，58(21)：69-77. LUO Wei，LI Mingfu，ZHAO Wenquan，et al. Research on flexible assembly method of industrial robot based on force-pose-image learning[J]. Journal of Mechanical Engineering，2022，58(21)：69-77.
[40] LEVINE S，ABBEEL P. Learning neural network policies with guided policy search under unknown dynamics[J]. Advances in Neural Information Processing Systems，2014，27：1071-1079.
[41] WIRNSHOFER F，SCHMITT P S，MEISTER P，et al. State estimation in contact-rich manipulation[C]//2019 International Conference on Robotics and Automation (ICRA). New York：IEEE，2019：3790-3796.
[42] KHADER P，YIN H，KRAGIC D. Probabilistic model learning and long-term prediction forcontact-rich manipulation tasks[J]. CoRR，ArXiv：1909.04915vl，2019.
[43] 刘乃龙，刘钊铭，崔龙. 基于深度强化学习的仿真机器人轴孔装配研究[J]. 计算机仿真，2019，36(12)：296-301. LIU Nailong，LIU Zhaoming，CUI Long. Deep reinforcement learning based robotic assembly in simulation[J]. Computer Simulation，2019，36(12)：296-301.
[44] INOUE T，DE MAGISTRIS G，MUNAWAR A，et al. Deep reinforcement learning for high precision assembly tasks[C]// 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS). New York：IEEE，2017：819-825.
[45] ZOU P，ZHU Q，WU J，et al. Learning-based optimization algorithms combining force control strategies for peg-in-hole assembly[C]// 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS). New York：IEEE，2020：7403-7410.
[46] ROUILLARD T. A deep-reinforcement-learning approach to the peg-in-hole task with goal uncertainties[D]. Perth：Curtin University，2020.
[47] OIKAWA M，KUSAKABE T，KUTSUZAWA K，et al. Reinforcement learning for robotic assembly using non-diagonal stiffness matrix[J]. IEEE Robotics and Automation Letters，2021，6(2)：2737-2744.
[48] YIN R，WU H，LI M，et al. Rgb-d-based robotic grasping in fusion application environments[J]. Applied Sciences，2022，12(15)：7573.
[49] LEE Y S，VUONG N，ADRIAN N，et al. Integrating force-based manipulation primitives with deep learning- based visual servoing for robotic assembly[C/CD]//ICRA 2022 Workshop：Reinforcement Learning for Contact- Rich Manipulation. May 27，2022，Philadelphia(PA)，USA：ICRA，2022.
[50] VUONG N，PHAM H，PHAM Q C. Learning sequences of manipulation primitives for robotic assembly[C]//2021 IEEE International Conference on Robotics and Automation (ICRA). New York：IEEE，2021：4086-4092.
[51] LIU Y，VERLEYSEN A，WYFFELS F. A robust and safe strategy for robotic assembly[C/OL]//Embracing Contacts- Workshop at ICRA 2023. June 2，2023，London：ICRA，2023.
[52] REN T，DONG Y，WU D，et al. Learning-based variable compliance control for robotic assembly[J]. Journal of Mechanisms and Robotics，2018，10(6)：061008.
[53] XU J，HOU Z，WANG W，et al. Feedback deep deterministic policy gradient with fuzzy reward for robotic multiple peg-in-hole assembly tasks[J]. IEEE Transactions on Industrial Informatics，2018，15(3)：1658-1667.
[54] FAN Y，LUO J，TOMIZUKA M. A learning framework for high precision industrial assembly[C]//2019 International Conference on Robotics and Automation(ICRA). New York：IEEE，2019：811-817.
[55] LI F，JIANG Q，QUAN W，et al. Manipulation skill acquisition for robotic assembly based on multi-modal information description[J]. IEEE Access，2019，8：6282- 6294.
[56] BELTRAN-HERNANDEZ C C，PETIT D，RAMIREZ- ALPIZAR I G，et al. Learning force control for contact- rich manipulation tasks with rigid position-controlled robots[J]. IEEE Robotics and Automation Letters，2020，5(4)：5709-5716.
[57] HOPPE S，GIFTTHALER M，KRUG R，et al. Sample- efficient learning for industrial assembly using Qgraph- bounded DDPG[C]//2020 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS). New York：IEEE，2020：9080-9087.
[58] ZHAO X，ZHAO H，CHEN P，et al. Model accelerated reinforcement learning for high precision robotic assembly[J]. International Journal of Intelligent Robotics and Applications，2020，4(2)：202-216.
[59] LUO J，SUSHKOV O，PEVCEVICIUTE R，et al. Robust multi-modal policies for industrial assembly via reinforcement learning and demonstrations：A large-scale study[C/CD]//Robotics：Science and Systems 2021，July 12-16，2021，Held Virtually.
[60] APOLINARSKA A A，PACHER M，LI H，et al. Robotic assembly of timber joints using reinforcement learning[J]. Automation in Construction，2021，125：103569.
[61] LUO J，LI H. A learning approach to robot-agnostic force-guided high precision assembly[C]//2021 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS). New York：IEEE，2021：2151-2157.
[62] LI Y，XU D. Skill learning for robotic insertion based on one-shot demonstration and reinforcement learning[J]. International Journal of Automation and Computing，2021，18(3)：457-467.
[63] LI J，PANG D，ZHENG Y，et al. A flexible manufacturing assembly system with deep reinforcement learning[J]. Control Engineering Practice，2022，118：104957.
[64] GAI Y，ZHANG J，WU D，et al. Local connection reinforcement learning method for efficient robotic peg-in-hole assembly[J]. Engineering Applications of Artificial Intelligence，2024，133：108520.
[65] 双丰，卢万玉，李少东，等. 基于强化学习的机器人轴孔装配算法[J]. 机器人，2023，45(3)：321-332. SHUANG Feng，LU Wanyu，LI Shaodong，et al. Robotic peg-in-hole assembly algorithm based on reinforcement learning[J]. Robot，2023，45(3)：321-332.
[66] 王竣禾，姜勇. 基于深度强化学习的动态装配算法[J]. 智能系统学报，2023，18(1)：2-11. WANG Junhe，JIANG Yong. Dynamic assembly algorithm based on deep reinforcement learning[J]. CAAI Transactions on Intelligent Systems，2023，18(1)：2-11.
[67] WU W，ZHOU H，GUO Y，et al. Peg-in-hole assembly in live-line maintenance based on generative mapping and searching network[J]. Robotics and Autonomous Systems，2021，143：103797.
[68] ZANG Y，WANG P，ZHA F，et al. Geometric-feature representation based pre-training method for reinforcement learning of peg-in-hole tasks[J]. New York：IEEE Robotics and Automation Letters，2023，8(6)：3478-3485.
[69] DANG R，HOU Z，YANG W，et al. Fusing vision and force：A framework of reinforcement learning for elastic peg-in-hole assembly[C]//2023 WRC Symposium on Advanced Robotics and Automation(WRC SARA). New York：IEEE，2023：1-6.
[70] WANG G，YI J，JI X. Research on intelligent peg-in-hole assembly strategy based on deep reinforcement learning[C]// 2023 3rd Asia-Pacific Conference on Communications Technology and Computer Science(ACCTCS). New York：IEEE，2023：468-473.
[71] BÁLINT B A，LÄMMLE A，SALTERIS Y，et al. Benchmark of the physics engine mujoco and learning- based parameter optimization for contact-rich assembly tasks[J]. Procedia CIRP，2023，119：1059-1064.
[72] THOMAS G，CHIEN M，TAMAR A，et al. Learning robotic assembly from cad[C]//2018 IEEE International Conference on Robotics and Automation(ICRA). New York：IEEE，2018：3524-3531.
[73] LUO J，SOLOWJOW E，WEN C，et al. Deep reinforcement learning for robotic assembly of mixed deformable and rigid objects[C]// 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS). New York：IEEE，2018：2062-2069.
[74] LUO J，SOLOWJOW E，WEN C，et al. Reinforcement learning on variable impedance controller for high-precision robotic assembly[C]//2019 International Conference on Robotics and Automation(ICRA). New York：IEEE，2019：3080- 3087.
[75] LUO J，ABBEEL P. Reinforcement learning for robotic assembly with force control[D]. California：Berkeley，2020.
[76] HOPPE S，LOU Z，HENNES D，et al. Planning approximate exploration trajectories for model-free reinforcement learning in contact-rich manipulation[J]. IEEE Robotics and Automation Letters，2019，4(4)：4042-4047.
[77] WANG Y，BELTRAN-HERNANDEZ C C，WAN W，et al. Hybrid trajectory and force learning of complex assembly tasks：A combined learning framework[J]. IEEE Access，2021，9：60175-60186.
[78] WANG Y，BELTRAN-HERNANDEZ C C，WAN W，et al. Robotic imitation of human assembly skills using hybrid trajectory and force learning[C]//2021 IEEE International Conference on Robotics and Automation (ICRA). New York：IEEE，2021：11278-11284.
[79] LIU Y，ROMERES D，JHA D K，et al. Understanding multi-modal perception using behavioral cloning for peg-in-a-hole insertion tasks[C]//RSS 2020 workshop on Advances & Challenges in Imitation Learning for Robotics，July 22，2020，Broadway，Cambridge，Massac- husetts，2020：TR2020-110.
[80] LIU Q，JI Z，XU W，et al. Knowledge-guided robot learning on compliance control for robotic assembly task with predictive model[J]. Expert Systems with Applications，2023，234：121037.
[81] MING J，BARGMANN D，CAO H，et al. Flexible gear assembly with visual servoing and force feedback[C]// 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS)，2023：8276-8282.
[82] SIMONIČ M，UDE A，NEMEC B. Hierarchical learning of robotic contact policies[J]. Robotics and Computer- Integrated Manufacturing，2024，86：102657.
[83] TANAKA K，YONETANI R，HAMAYA M，et al. Trans-am：Transfer learning by aggregating dynamics models for soft robotic assembly[C]//2021 IEEE International Conference on Robotics and Automation(ICRA). New York：IEEE，2021：4627-4633.
[84] YUAN C，SHI Y，FENG Q，et al. Sim-to-real transfer of robotic assembly with visual inputs using cyclegan and force control[C]// 2022 IEEE International Conference on Robotics and Biomimetics(ROBIO). New York：IEEE，2022：1426-1432.
[85] SHI Y，YUAN C，TSITOS A，et al. A sim-to-real learning-based framework for contact-rich assembly by utilizing cyclegan and force control[J]. IEEE Transactions on Cognitive and Developmental Systems，2023，15(4)：2144-2155.
[86] SHI Y. Visual and force-driven-based assembly learning using collaborative robots[D]. Hamburg：Universitaet Hamburg，2023.
[87] GHASEMIPOUR S K S，KATAOKA S，DAVID B，et al. Blocks assemble! learning to assemble with large-scale structured reinforcement learning[C]//International Conference on Machine Learning，July 17-23，2022 Baltimore，Maryland，USA，PMLR 162，2022：7435-7469.
[88] JIN P，LIN Y，SONG Y，et al. Vision-force-fused curriculum learning for robotic contact-rich assembly tasks[J]. Frontiers in Neurorobotics，2023，17：1280773.
[89] AHN K H，NA M，SONG J B. Robotic assembly strategy via reinforcement learning based on force and visual information[J]. Robotics and Autonomous Systems，2023，164：104399.
[90] BELTRAN-HERNANDEZ C C，PETIT D，RAMIREZ- ALPIZAR I G，et al. Variable compliance control for robotic peg-in-hole assembly：A deep-reinforcement- learning approach[J]. Applied Sciences，2020，10(19)：6923.
[91] KASPAR M，OSORIO J D M，BOCK J. Sim2real transfer for reinforcement learning without dynamics randomization[C]//2020 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS). New York：IEEE，2020：4383-4388.
[92] HOU Z，FEI J，DENG Y，et al. Data-efficient hierarchical reinforcement learning for robotic assembly control applications[J]. IEEE Transactions on Industrial Electronics，2020，68(11)：11565-11575.
[93] WANG Y，BELTRAN-HERNANDEZ C C，WAN W，et al. An adaptive imitation learning framework for robotic complex contact-rich insertion tasks[J]. Frontiers in Robotics and AI，2022，8：777363.
[94] BELTRAN H C C. Reinforcement learning for contact-rich assembly[D]. Osaka：Osaka University，2022.
[95] TANG B，LIN M A，AKINOLA I，et al. Industreal：Transferring contact-rich assembly tasks from simulation to reality[C]//Robotics：Science and Systems 2023，July 10-14，2023，Daegu，Republic of Korea.
[96] WHITNEY D E. Quasi-static assembly of compliantly supported rigid parts[J]. Journal of Dynamic Systems，Measurement，and Control，1982，104(1)：65-77.
[97] HOGAN N. Impedance control：An approach to manipulation[C]//1984 American Control Conference. June 6-8，1984，SanDiego，CA，USA. New York：IEEE，1984：304-313.
[98] 李侃，汪法根，廖正菊，等. 一种用于多轴孔装配的机器人系统研究[J]. 机械设计与研究，2003，19(3)：25-26. LI Kan，WANG Fagen，LIAO Zhengju，et al. Study on a robotic system for multiaxial bore assembling[J]. Machine Design and Research，2003，19(3)：25-26.
[99] STOLT A，LINDEROTH M，ROBERTSSON A，et al. Force controlled assembly of emergency stop button[C]// 2011 IEEE International Conference on Robotics and Automation. New York：IEEE，2011：3751-3756.
[100] PARK H，BAE J H，PARK J H，et al. Intuitive peg-in-hole assembly strategy with a compliant manipulator[C/CD]//IEEE ISR 2013. New York：IEEE，2013.
[101] 曾冰，李明富，张翼，等. 基于萤火虫算法的装配序列规划研究[J]. 机械工程学报，2013，49(11)：177-184. ZENG Bing，LI Mingfu，ZHANG Yi，et al. Research on assembly sequence planning based on firefly algorithm[J]. Journal of Mechanical Engineering，2013，49(11)：177-184.
[102] 魏明明，傅卫平，蒋家婷，等. 操作机器人轴孔装配的行为动力学控制策略[J]. 机械工程学报，2015，51(5)：14-21. WEI Mingming，FU Weiping，JIANG Jiating，et al. Dynamics of behavior control strategy in peg-in-hole assembly task of manipulator[J]. Journal of Mechanical Engineering，2015，51(5)：14-21.
[103] TANG T，LIN H C，ZHAO Y，et al. Autonomous alignment of peg and hole by force/torque measurement for robotic assembly[C]// 2016 IEEE International Conference on Automation Science and Engineering (CASE). New York：IEEE，2016：162-167.
[104] 吴炳龙，曲道奎，徐方. 基于力/位混合控制的工业机器人精密轴孔装配[J]. 浙江大学学报，2018，52(2)：379-386. WU Binglong，QU Daokui，XU Fang. Industrial robot high precision peg-in-hole assembly based on hybrid force/position control[J]. Journal of Zhejiang University，2018，52(2)：379-386.
[105] 徐远，宋爱国，李会军. 基于机器视觉和力反馈的自动装配技术研究[J]. 测控技术，2019，38(4)：11-16. XU Yuan，SONG Aiguo，LI Huijun. Research on automatic assembly technology based on machine vision and force feedback[J]. Measurement and Control Technology，2019，38(4)：11-16.
[106] 董悫，张立建，易旺民，等. 基于动力学前馈的空间机器人多销孔装配力柔顺控制[J]. 机械工程学报，2020，55(4)：207-217. DONG Que，ZHANG Lijian，YI Wangmin，et al. Force compliance control of multi-peg-in-hole assembling by space robot based on dynamic feedforward[J]. Journal of Mechanical Engineering，2020，55(4)：207-217.
[107] 陈婵娟，赵飞飞，李承，等. 多传感器协助机器人精确装配[J]. 机械设计与制造，2020(3)：281-284. CHEN Chanjuan，ZHAO Feifei，LI Cheng，et al. Multi-sensor assisted robotic accurate assembly[J]. Machinery Design and Manufacture，2020(3)：281-284.
[108] 胡瑞钦，张立建，孟少华，等. 基于柔顺控制的航天器大部件机器人装配技术[J]. 机械工程学报，2018， 54(11)：85-93. HU Ruiqin，ZHANG Lijian，MENG Shaohua，et al. Robot assembly technology based on compliance control[J]. Journal of Mechanical Engineering，2018，54(11)：85-93.
[109] BROWN T，MANN B，RYDER N，et al. Language models are few-shot learners[C]// Advances in Neural Information Processing Systems 33(NeurIPS 2020). USA：Curran Associates，Inc.，2020：1877-1901.
[110] AL-SHEDIVAT M，BANSAL T，BURDA Y，et al. Continuous adaptation via meta-learning in nonstationary and competitive environments[C]//International Conference on Learning Representations(ICLR)，April 30-May 3，2018，Vancouver Convention Center，Vanc-ouver，BC，Canada：ICLR，2018.
[111] SILVER D，SINGH S，PRECUP D，et al. Reward is enough[J]. Artificial Intelligence，2021，299：103535.
[112] SCHRITTWIESER J，ANTONOGLOU I，HUBERT T，et al. Mastering atari，go，chess and shogi by planning with a learned model[J]. Nature，2020，588(7839)：604-609.
[113] LEVINE S，PASTOR P，KRIZHEVSKY A，et al. Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection[J]. The International Journal of Robotics Research，2018，37(4-5)：421-436.
[114] LEVINE S，FINN C，DARRELL T，et al. End-to-end training of deep visuomotor policies[J]. Journal of Machine Learning Research，2016，17(39)：1-40.
[115] BARGMANN D，TENBROCK P，HALT L，et al. Unobstructed programming-by-demonstration for force- based assembly utilizing external force-torque sensors[C]// 2021 IEEE International Conference on Systems，Man，and Cybernetics(SMC). New York：IEEE，2021：119-124.
[116] ARGÜZ S H. Learning of tasks with robot programming by demonstration[D]. Turkey：Izmir Institute of Technology，2022.
[117] LIU N，ZHOU X，LIU Z，et al. Learning peg-in-hole assembly using cartesian dmps with feedback mechanism[J]. Assembly Automation，2020，40(6)：895-904.
[118] 张浩，陈成军，潘勇. 基于视觉的工业机器人装配演示示教研究.[J]. 机床与液压，2023，51(19)：25-31. ZHANC Hao，CHEN Chengjun，PAN Yong. Research on demonstration and teaching of industrial robot assembly based on vision[J]. Machine Tool and Hydraulics，2023，51(19)：25-31.
[119] LEVINE S，KOLTUN V. Guided policy search[C]// International Conference on Machine Learning. June 17-19，2013，Tlanta，Georgia，USA：PMLR 28，2013：1-9.
[120] SCHULMAN J，LEVINE S，ABBEEL P，et al. Trust region policy optimization[C]// International Conference on Machine Learning，July 7-9，2015，Lille，France：PMLR 37，2015：1889-1897.
[121] DEWEY D. Reinforcement learning and the reward engineering principle[C]// 2014 AAAI Spring Symposium Series. March 24-26，2014，Stanford University，Palo Alto，California，USA：AAAI，2014.
[122] SUTTON R S，BARTO A G. Reinforcement learning：An introduction[M]. Massachusetts：MIT Press，2018.
[123] ACHIAM J，HELD D，TAMAR A，et al. Constrained policy optimization[C]//International Conference on Machine Learning. August 6-11，2017，International Convention Centre，Sydney，Australia：PMLR 70，2017：22-31.
[124] GAI Y，WANG B，ZHANG J，et al. Robotic assembly control reconfiguration based on transfer reinforcement learning for objects with different geometric features[J]. Engineering Applications of Artificial Intelligence，2024，129：107576.
[125] MATIISEN T，OLIVER A，COHEN T，et al. Teacher-student curriculum learning[J]. IEEE Transactions on Neural Networks and Learning Systems，2020，31(9)：3732-3740.
[126] RAISI M，NOOHIAN A H，KHODAYGAN S. Autonomous robotic assembly process based on hierarchical reinforcement learning[C]//The 30th Annual International Conference of lranian Society of Mechanical Engineers. May 10-12，2022，Tehran，Iran：ISME2022-IC1484.
[127] NARVEKAR S，PENG B，LEONETTI M，et al. Curriculum learning for reinforcement learning domains：A framework and survey[J]. The Journal of Machine Learning Research，2020，21(1)：7382-7431.
[128] WU Z，LIAN W，UNHELKAR V，et al. Learning dense rewards for contact-rich manipulation tasks[C/OL]//2021 IEEE International Conference on Robotics and Automation(ICRA). New York：IEEE，2021：6214-6221.

接触丰富的自动装配方法研究进展：机器人装配接触力控制技能学习

Research Progress on Contact-rich Automated Assembly Methods：Learning Robotic Assembly Contact Force Control Skills

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	胡炳涛, 钟锐锐, 冯毅雄, 杨晨, 王天跃, 洪兆溪, 谭建荣. 人-信息-物理互联环境下数字车间制造能力建模与自适应调度[J]. 机械工程学报, 2025, 61(3): 23-39.
[2]	唐小林, 甘炯鹏, 张振果. 横纵向耦合跟车场景下基于多智能体深度强化学习的混合动力车队协同能量管理研究[J]. 机械工程学报, 2025, 61(2): 236-246.
[3]	王无印, 黄子钊, 庄子龙, 方怀瑾, 秦威. 基于深度强化学习的自动化码头堆场场桥调度方法[J]. 机械工程学报, 2024, 60(6): 44-57.
[4]	赵阔, 王皂琦, 潘臻信, 潘扬华, 张中飞, 屈挺. 大数据驱动的快消品终端拜访“云-边”联动决策与优化[J]. 机械工程学报, 2024, 60(6): 58-68.
[5]	柏林, 何牧耕, 陈兵奎, 刘小峰. 基于域泛化D3QN的跨工况故障诊断方法[J]. 机械工程学报, 2024, 60(22): 165-178.
[6]	郭景华, 李文昌, 王班, 王靖瑶. 基于深度强化学习的网联混合动力汽车队列控制[J]. 机械工程学报, 2024, 60(2): 262-271.
[7]	李文礼, 张祎楠, 石晓辉, 王梦昕. 基于博弈论的右转无信号交叉口行人行为模拟[J]. 机械工程学报, 2024, 60(10): 86-101.
[8]	曾迪, 郑玲, 李以农, 杨显通. 自动驾驶奖励函数贝叶斯逆强化学习方法[J]. 机械工程学报, 2024, 60(10): 245-260.
[9]	杨硕, 李时珍, 赵中原, 黄小鹏, 黄岩军. 基于时序差分学习模型预测控制的一体化自动驾驶换道策略[J]. 机械工程学报, 2024, 60(10): 329-338.
[10]	张志勇, 黄大洋, 黄彩霞, 胡林, 杜荣华. TD3算法改进与自动驾驶汽车并道策略学习[J]. 机械工程学报, 2023, 59(8): 224-234.
[11]	郭洪飞, 陆鑫宇, 任亚平, 张超勇, 李建庆. 基于强化学习的群体进化算法求解双边多目标同步并行拆解线平衡问题[J]. 机械工程学报, 2023, 59(7): 355-366.
[12]	郑湃, 李成熙, 殷悦, 张荣, 鲍劲松, 王柏村, 谢海波, 王力翚. 增强现实辅助的互认知人机安全交互系统[J]. 机械工程学报, 2023, 59(6): 173-184.
[13]	娄山河, 冯毅雄, 郑浩, 胡炳涛, 洪兆溪, 谭建荣. 模拟人脑工作机制的机械产品概念设计行为原理启发求解方法[J]. 机械工程学报, 2023, 59(24): 344-358.
[14]	马丽莹, 魏云冰. 基于DDPG算法的发电企业报价策略研究[J]. 电气工程学报, 2023, 18(2): 192-200.
[15]	林歆悠, 叶卓明, 周斌豪. 基于DQN强化学习的自动驾驶转向控制策略[J]. 机械工程学报, 2023, 59(16): 315-324.