Research on Flexible Assembly Method of Industrial Robot Based on Force-pose-image Learning

doi:10.3901/JME.2022.21.069

Abstract

Abstract: When using robots for automatic assembly, it is important to control the contact force and compliance in assembly process for ensuring assembly quality. Therefore, a flexible assembly method based on force-pose-image learning is proposed, which transformed the information of pose and force/torque into force-pose-image, and obtained the flexible assembly strategy under different initial pose conditions by classifying and learning the force-pose-image. The whole scheme is as following:Firstly, the assembly operations are completed many times, the data of pose, force and torque are collected during assembly. Then, the force-pose-curves are drawn and combined into force-pose-image, based on the motion direction determination algorithm, the force-pose-image are marked with motion labels to construct the force-pose-image data set. Finally, the deep learning model is trained on the force-pose-image data set, and the robot is controlled for flexible assembly based on the trained model.In order to verify the method, the assembly experiment of RJ45 connector and port is conducted. 2 500 times of assembly operations are performed, as the result, 92 328 force-pose-images and corresponding labels are generated. The force-pose-image classification model is trained based on ResNet50 network, and the robot is controlled to conduct assembly experiments based on the model. The assembly success rate is up to 96.7%.

Key words: force-pose-image, flexible assembly, robot, automatic assembly, deep learning

CLC Number:

TP242

LUO Wei, LI Mingfu, ZHAO Wenquan, DENG Xukang. Research on Flexible Assembly Method of Industrial Robot Based on Force-pose-image Learning[J]. Journal of Mechanical Engineering, 2022, 58(21): 69-77.

References

[1] 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.
[2] 常健, 王亚珍, 李斌. 基于力/位混合算法的7自由度机械臂精细操控方法[J]. 机器人, 2016, 38(5):531-539. CHANG Jian, WANG Yazhen, LI Bin. Accurate operation control method based on hybrid force/position algorithm for 7-DOF manipulator[J]. Robot, 2016, 38(5):531-539.
[3] CHAUDHARY H, PANWAR V, PRASAD R, et al. Adaptive neuro fuzzy based hybrid force/position control for an industrial robot manipulator[J]. Journal of Intelligent Manufacturing, 2016, 27(6):1299-1308.
[4] 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.
[5] 甘亚辉, 段晋军, 戴先中. 非结构环境下的机器人自适应变阻抗力跟踪控制方法[J]. 控制与决策, 2019, 34(10):2134-2142. GAN Yahui, DUAN Jinjun, DAI Xianzhong. Adaptive variable impedance control for robot force tracking in unstructured environment[J]. Control and Decision, 2019, 34(10):2134-2142.
[6] 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, 2019, 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, 2019, 55(4):207-217.
[7] 叶伯生, 陶婕妤, 张文彬, 等. 基于动力学模型的工业机器人导纳控制研究[J]. 华中科技大学学报, 2020, 48(8):98-102, 108. YE Bosheng, TAO Jieyu, ZHANG Wenbin, et al. Research on admittance control of industrial robot based on dynamics model[J]. Journal of Huazhong University of Science and Technology, 2020, 48(8):98-102, 108.
[8] 陈钢, 王玉琦, 贾庆轩, 等. 机器航天员轴孔装配过程中的力位混合控制方法[J]. 宇航学报, 2017, 38(4):410-419. CHEN Gang, WANG Yuqi, JIA Qingxuan, et al. Hybrid force and position control strategy of robonaut performing peg-in-hole assembly task[J]. Journal of Astronautics, 2017, 38(4):410-419.
[9] 喻洋, 王耀兵, 魏世民, 等. 基于柔顺控制的机器人装配技术[J]. 北京邮电大学学报, 2020, 43(4):1-6. YU Yang, WANG Yaobing, WEI Shimin, et al. Robot assembly technology based on compliance control[J]. Journal of Beijing University of Posts and Telecommunications, 2020, 43(4):1-6.
[10] 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.
[11] RIVAS B, BAUZANO E. Force-position control for a miniature camera robotic system for single-site surgery[C]//2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), November 3-7, 2013, Tokyo. Tokyo:IEEE, 2013:3065-3070.
[12] FAN Y, LUO J, TOMIZUKA M. A learning framework for high precision industrial assembly[C]//2019 IEEE International Conference on Robotics and Automation (ICRA), May 20-24, 2019, Montreal. Montreal:IEEE, 2019:811-817.
[13] KUMAR N, PANWAR V, SUKAVANAM N, et al. Neural network based hybrid force/position control for robot manipulators[J]. International Journal of Precision Engineering and Manufacturing, 2011, 12(3):419-426.
[14] TANG T, LIN H, ZHAO Y. et al. Teach industrial robots peg-hole-insertion by human demonstration[C]//2016 IEEE International Conference on Advanced Intelligent Mechatronics (AIM), July 12-15, 2016, Banff. Banff:IEEE, 2016:488-494.
[15] INOUE T, MAGISTRIS G D, MUNAWAR A, et al. Deep reinforcement learning for high precision assembly tasks[C]//2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), September 24-28, 2017, Vancouver. Vancouver:IEEE, 2017:819-825.
[16] ABU-DAKKA F J, ROZO L, CALDWELL D G. Force-based variable impedance learning for robotic manipulation[J]. Robotics and Autonomous Systems, 2018, 109:156-167.
[17] THOMAS G, CHIEN M, TAMAR A, et al. Learning robotic assembly from CAD[C]//2018 IEEE International Conference on Robotics and Automation (ICRA), May 21-25, 2018, Brisbane. Brisbane:IEEE, 2018:3524-3531.
[18] 王斐, 齐欢, 周星群, 等. 基于多源信息融合的协作机器人演示编程及优化方法[J]. 机器人, 2018, 40(4):551-559. WANG Fei, QI Huan, ZHOU Xingqun, et al. Demonstration programming and optimization method of cooperative robot based on multi-source information fusion[J]. Robot, 2018, 40(4):551-559.
[19] 宋锐, 李凤鸣, 权威, 等. 多约束条件下机器人柔顺装配技能自学习[J]. 控制与决策, 2022, 37(5):1329-1337. SONG Rui, LI Fengming, QUAN Wei, et al. Flexible assembly skill self-learning of robot under multiple constraints[J]. Control and Decision, 2022, 37(5):1329-1337.
[20] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas. Las Vegas:IEEE, 2016:770-778.