Research on Robotic Peg-in-Hole Assembly Method Based on Variable Admittance
Source abstract
Abstract
To address the complex challenge of identifying the contact state between a shaft and a hole and to improve the efficiency of robotic shaft-hole assembly tasks, a robotic shaft-hole assembly method based on variable admittance control is proposed. In this method, admittance control serves as the foundational force controller for shaft-hole assembly. On this basis, the Twin Delayed Deep Deterministic policy gradient (TD3) algorithm from deep reinforcement learning is utilized to optimize the parameters of the admittance controller. Additionally, a nonlinear reward function is designed, which not only prevents the assembly strategy from converging to local optima but also further accelerates the training speed of the assembly task. Experiments conducted with a collaborative robotic arm performing 15° inclined hole assembly demonstrated that the assembly efficiency of the variable admittance method was 9.6% higher than that of the fixed admittance parameter method, validating the feasibility and effectiveness of the proposed variable admittance shaft-hole assembly method.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Robot Manipulation and Learning · Manufacturing Process and Optimization · Robotic Mechanisms and Dynamics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Mechanical Electrical Engineering School, Beijing Information Science & Technology University, Beijing 100192, China
School of Mechanical Engineering and Automation, Beihang University, Beijing 100191, China
Funding
General Program of National Natural Science Foundation of China
References (31)
Show source-provided references
1. Skill Learning for Robotic Insertion Based on One-shot Demonstration and Reinforcement Learning10.1007/s11633-021-1290-3 ↗
2. Research on impact resistance and active–passive compliance control of rope-driven joint unit10.1007/s40430-021-03123-0 ↗
3. Adaptive hybrid system framework for unified impedance and admittance control10.1007/s10846-017-0732-1 ↗
4. How to train your robot with deep reinforcement learning: Lessons we have learned10.1177/0278364920987859 ↗
5. State-of-the-Art control strategies for robotic PiH assembly10.1016/j.rcim.2019.101894 ↗
6. Wang, Z., Li, F., Men, Y., Fu, T., Yang, X., and Song, R. (2022). Deep deterministic policy gradient with reward function based on fuzzy logic for robotic peg-in-hole assembly tasks. Appl. Sci., 12.10.3390/app12063181 ↗
7. Tirmizi, A., De Cat, B., Janssen, K., Pane, Y., Leconte, P., and Witters, M. (2019, January 23–24). User-friendly programming of flexible assembly applications with collaborative robots. Proceedings of the 2019 20th International Conference on Research and Education in Mechatronics (REM), Wels, Austria.10.1109/REM.2019.8744135 ↗
8. Liu, S., Liu, G., and Zhang, X. (2024). High-Precision Peg-in-Hole Assembly with Flexible Components Based on Deep Reinforcement Learning. Machines, 12.10.3390/machines12050287 ↗
9. Beltran-Hernandez, C.C., Petit, D., Ramirez-Alpizar, I.G., and Harada, K. (2020). Variable compliance control for robotic peg-in-hole assembly: A deep-reinforcement-learning approach. Appl. Sci., 10.10.3390/app10196923 ↗
10. Model accelerated reinforcement learning for high precision robotic assembly10.1007/s41315-020-00138-z ↗
11. Yan, C., Wu, J., and Zhu, Q. (October, January 27). Learning-based contact status recognition for peg-in-hole assembly. Proceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Prague, Czech Republic.10.1109/IROS51168.2021.9636147 ↗
12. Design of an intelligent robotic precise assembly system for rapid teaching and admittance control10.1016/j.rcim.2020.101946 ↗
13. Compliant peg-in-hole assembly using partial spiral force trajectory with tilted peg posture10.1109/LRA.2020.3000428 ↗
14. Force/torque sensorless compliant control strategy for assembly tasks using a 6-DOF collaborative robot10.1109/ACCESS.2019.2931515 ↗
15. Feature-based compliance control for precise peg-in-hole assembly10.1109/TIE.2021.3112990 ↗
16. Multi-robot assembly strategies and metrics10.1145/3150225 ↗
17. Fujimoto, S., Hoof, H., and Meger, D. (2018, January 10–15). Addressing function approximation error in actor-critic methods. Proceedings of the International Conference on Machine Learning, Stockholm, Sweden.
18. Fuzzy logic-driven variable time-scale prediction-based reinforcement learning for robotic multiple peg-in-hole assembly10.1109/TASE.2020.3024725 ↗
19. Geometric-feature representation based pre-training method for reinforcement learning of peg-in-hole tasks10.1109/LRA.2023.3261759 ↗
20. Kaspar, M., Osorio, J.D.M., and Bock, J. (2020–24, January 24). Sim2real transfer for reinforcement learning without dynamics randomization. Proceedings of the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV, USA.10.1109/IROS45743.2020.9341260 ↗
21. Learning-based variable compliance control for robotic assembly10.1115/1.4041331 ↗
22. Feedback deep deterministic policy gradient with fuzzy reward for robotic multiple peg-in-hole assembly tasks10.1109/TII.2018.2868859 ↗
23. Li, S., Yuan, X., and Niu, J. (2022). Robotic peg-in-hole assembly strategy research based on reinforcement learning algorithm. Appl. Sci., 12.10.3390/app122111149 ↗
24. Yazar, O., Coskun, S., Li, L., Zhang, F., and Huang, C. (2023, January 8–10). Actor-critic TD3-based deep reinforcement learning for energy management strategy of HEV. Proceedings of the 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), Istanbul, Turkey.10.1109/HORA58378.2023.10156727 ↗
25. Zhao, X., and Zheng, S. (2023, January 10–12). Robot Trajectory Planning Optimization Algorithm Based on Improved TD3 Algorithm. Proceedings of the 2023 International Conference on Intelligent Communication and Networking (ICN), Changzhou, China.10.1109/ICN60549.2023.10425941 ↗
26. Eschmann, J. (2021). Reward function design in reinforcement learning. Reinf. Learn. Algorithms Anal. Appl., 25–33.10.1007/978-3-030-41188-6_3 ↗
27. Safe peg-in-hole automatic assembly using virtual guiding force: A deep reinforcement learning solution10.1016/j.robot.2024.104894 ↗
28. Variable Impedance Skill Learning for Contact-Rich Manipulation10.1109/LRA.2022.3187276 ↗
29. Zou, P., Zhu, Q., Wu, J., and Xiong, R. (2020–24, January 24). Learning-Based Optimization Algorithms Combining Force Control Strategies for Peg-in-Hole Assembly. Proceedings of the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV, USA.10.1109/IROS45743.2020.9341678 ↗
30. Feng, X., Shi, T., Li, W., Lu, P., and Pan, Y. (2022, January 9–11). Reinforcement Learning-Based Impedance Learning for Robot Admittance Control in Industrial Assembly. Proceedings of the 2022 International Conference on Advanced Robotics and Mechatronics (ICARM), Guilin, China.10.1109/ICARM54641.2022.9959152 ↗
31. Local connection reinforcement learning method for efficient robotic peg-in-hole assembly10.1016/j.engappai.2024.108520 ↗