To address the problem of efficient and stable guidance and insertion in peg-in-hole assembly, an innovative assembly strategy combining vision and force sensing technologies was proposed. Based on existing studies, a three-point contact configuration was identified as the ideal initial condition for assembly and was set as the starting point of the insertion phase. Since it is challenging to guide the peg precisely to the hole center using only force and torque data, vision and force sensing were integrated to enhance the reliability of peg-hole alignment. During the assembly process, the peg pose was actively adjusted by the vision system before contact with the working platform, ensuring that the spatial relationship between the peg and the hole was well constrained before the insertion stage. In addition, the traditional torque control method was improved, and an optimized control scheme was proposed to simplify the calculation of torque target values and to reduce the effect of force/torque sensor drift on peg position adjustment, and to explorate of the application potential of vision and force sensing in peg-in-hole assembly. The method is expected to be achieved, providing a reliable technical approach for peg-in-hole assembly in precision automated systems.
KONG Fan-xu, ZHANG Yu-ao.
Peg-in-hole Assembly Using Vision and Force/Moment Sensing[J].
Science Technology and Engineering, 2026, 26(15): 6477-6486 DOI:10.12404/j.issn.1671-1815.2503275
ChhatparS R, BranickyM S. Search strategies for peg-in-hole assemblies with position uncertainty[C]// Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the Next Millennium. Maui: IEEE, 2001: 1465-1470.
[2]
NewmanW S, ZhaoY, PaoY H. Interpretation of force and moment signals for compliant peg-in-hole assembly[C]// Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation. Seoul: IEEE, 2001: 571-576.
[3]
SharmaK, ShirwalkarV, PalP K. Intelligent and environment-independent peg-in-hole search strategies[C]// 2013 International Conference on Control, Automation, Robotics and Embedded Systems (CARE). Jabalpur: IEEE, 2013: 1-6.
[4]
JasimI F, PlapperP W, VoosH. Position identification in force-guided robotic peg-in-hole assembly tasks[J]. Procedia CIRP, 2014, 23: 217-222.
[5]
AbdullahM W, RothH, WeyrichM, et al. An approach for peg-in-hole assembling using intuitive search algorithm based on human behavior and carried by sensors guided industrial robot[J]. IFAC-Papers on Line, 2015, 48(3): 1476-1481.
[6]
CaineM E, Lozano-perezT, SeeringW P. Assembly strategies for chamferless parts[C]// Proceedings of the 1989 IEEE International Conference on Robotics and Automation. New York: IEEE, 1989: 472-477.
[7]
KimI W, LimD J, KimK I. Active peg-in-hole of chamferless parts using force/moment sensor[C]// Proceedings of the 1999 IEEE/RSJ International Conference on Intelligent Robots and Systems: Human and Environment Friendly Robots with High Intelligence and Emotional Quotients. Kyongju: IEEE, 1999: 948-953.
[8]
SalemA, KarayiannidisY. Robotic assembly of rounded parts with and without threads[J]. IEEE Robotics and Automation Letters, 2020, 5: 2467-2474.
[9]
TangT, LinH C, ZhaoY, 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). Fort Worth: IEEE, 2016: 162-167.
[10]
HuangS, MurakamiK, YamakawaY, et al. Fast peg-and-hole alignment using visual compliance[C]// 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems. Tokyo: IEEE, 2013: 286-292.
[11]
MorelG, MalisE, BoudetS. Impedance based combination of visual and force control[C]// Proceedings of the 1998 IEEE International Conference on Robotics and Automation. Leuven: IEEE, 1998: 1743-1748.
[12]
TangT, LinH C, TomizukaM. A learning-based framework for robot peg-hole-insertion[C]// Proceedings of the ASME 2015 Dynamic Systems and Control Conference. New York: ASME, 2015, V002T27A002.
JiangYufeng, ChenDongsheng. Assembly strategy for large-diameter peg-in-hole based on deep reinforcement learning[J]. Journal of Zhejiang University (Engineering Science), 2023, 57(11): 2210-2216.
ZhuZilu, LiuYongkui, ZhangLin, et al. Simulation of robotic peg-in-hole assembly strategy based on DRL[J]. Journal of System Simulation, 2024, 36(6): 1414-1424.
NingRui, LiuZhichen, LiuYi, et al. Reinforcement learning guided variable admittance control for fuzzy pose estimation and precise adjustment of robotic precise peg-in-hole assemblys[J]. Chinese Journal of Scientific Instrument, 2024, 45(11): 170-177.
WuLiming, WangMingming, LuoJianjun, et al. Compliant control of on-orbit assembly for space robots based on reinforcement learning[J]. Robot, 2025, 47(2): 239-248, 258.
ZhangYuhang, ChenWenbai, ZhangJiaqi, et al. A flexible assembly strategy for a 6-DOF robotic arm based on deep reinforcement learning[J]. Journal of Chongqing University of Technology (Natural Science), 2024, 38(12): 148-154.
CuiQiang, LiYanjie, LangZhiming, et al. Flexible control of bolt assembly robot for tunnel pipelines[J]. Science Technology and Engineering, 2025, 25(10): 4192-4198.
[31]
BruyninckxH, DutreS, De SchutterJ. Peg-on-hole: a model based solution to peg and hole alignment[C]// Proceedings of the 1995 IEEE International Conference on Robotics and Automation. Nagoya: IEEE, 1995: 1919-1924.
[32]
LiuZ, SongL, HouZ, et al. Screw insertion method in peg-in-hole assembly for axial friction reduction[J]. IEEE Access, 2019, 7: 148313-148325.