High-voltage connectors for new energy applications are simultaneously affected by sealing resistance, secondary locking, and the traction of thick wire harnesses during assembly. Even small positional deviations can translate into lateral loads, further increasing terminal stress. To address this issue, this paper proposes an adaptive admittance control method for contact risk constraints and constructs a high-voltage connector characteristic model in Gazebo, incorporating CPA, HVIL, and elastic terminals. The method learns short-term risks from real connector trajectories, identifies contact parameters using successful, stalled, and retraction trajectories, and then corrects the local model within the distribution through projection recursion estimation. The controller uses the risk to tighten the predicted lateral force constraints, optimizing only the propulsion speed and lateral stiffness, with damping determined by a fixed damping ratio. Results show that the risk model has an AUROC of 0.79. Under combined perturbations, the constraint violation rate is reduced to 18.5%, and the median peak lateral force is reduced to 6.74 N; the complete success rate of the Gazebo characteristic case is 74.0%. This method can improve contact constraints, but further validation is needed for physical high-voltage connectors.

Boyu Cao. Research on Adaptive Control Strategy of New Energy Engineering Robots in Advanced Manufacturing Environment. International Journal of Big Data Intelligent Technology (2026), Vol. 7, Issue 3: 65-75. https://doi.org/10.38007/IJBDIT.2026.070307.

[1] Li S, Gong H, Liu J, Li J, Deng X. Advances in Robotic Peg-in-Hole Assembly: A Comprehensive Review[J]. Chinese Journal of Mechanical Engineering, 2025, 38: 196. DOI: 10.1186/s10033-025-01349-w.

[2] Saputra H M, Mohd Nor N S, Rijanto E, et al. Characterization of plugging and unplugging process for electric vehicle charging connectors based on force/torque measurements[J]. Measurement, 2025, 242: 115876. DOI: 10.1016/j.measurement.2024.115876.

[3] Yang W, Zhao H, He C, Qin L. Electrical connector assembly based on compliant tactile finger with fingernail[J]. Biomimetics, 2025, 10(8): 512. DOI: 10.3390/biomimetics10080512.

[4] Yun J W, Na M, Hwang Y, Song J B. Similar assembly state discriminator for reinforcement learning-based robotic connector assembly[J]. Robotics and Computer-Integrated Manufacturing, 2025, 91: 102842. DOI: 10.1016/j.rcim.2024.102842.

[5] Zhou Z, Yang X, Zhang X. Variable impedance control on contact-rich manipulation of a collaborative industrial mobile manipulator: An imitation learning approach[J]. Robotics and Computer-Integrated Manufacturing, 2025, 92: 102896. DOI: 10.1016/j.rcim.2024.102896.

[6] Seo J, Prakash N P S, Zhang X, et al. Contact-rich SE(3)-equivariant robot manipulation task learning via geometric impedance control[J]. IEEE Robotics and Automation Letters, 2024, 9(2): 1508-1515. DOI: 10.1109/LRA.2023.3346748.

[7] Silva Filho T, Song H, Perello-Nieto M, et al. Classifier calibration: A survey on how to assess and improve predicted class probabilities[J]. Machine Learning, 2023, 112(9): 3211-3260. DOI: 10.1007/s10994-023-06336-7.

[8] Correia L, Goos J C, Klein P, et al. Online model-based anomaly detection in multivariate time series: Taxonomy, survey, research challenges and future directions[J]. Engineering Applications of Artificial Intelligence, 2024, 138: 109323. DOI: 10.1016/j.engappai.2024.109323.

[9] Zhang J, Zhao H, Liu Z, et al. A unified framework for dynamic parameter identification of elastic joint robots with hysteresis and friction nonlinearities[J]. Mechanical Systems and Signal Processing, 2025, 238: 113208. DOI: 10.1016/j.ymssp.2025.113208.

[10] Gao Z, Chen C, Peng F, et al. Adaptive safety-critical control using a variable task energy tank for collaborative robot tasks under dynamic environments[J]. Robotics and Computer-Integrated Manufacturing, 2025, 94: 102964. DOI: 10.1016/j.rcim.2025.102964.

[11] Mae R, Kikuuwe R. An admittance controller with a jerk limiter for position-controlled robots[J]. Journal of Robotics and Mechatronics, 2024, 36(2): 483-493. DOI: 10.20965/jrm.2024.p0483.

[12] Yamazaki K, Nozaki K, Matsuura Y, Arnold S. Wiring connector-terminated cables based on manipulation planning with collision-free EMD net[J]. Robotics and Autonomous Systems, 2024, 175: 104673. DOI: 10.1016/j.robot.2024.104673.