Visual-Privileged Co-Learning for Industrial Board-to-Board Connectors Force-Guided Assembly Task
- 11 August 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (10) , 10154-10161
Abstract
Automatic assembly of board-to-board (BTB) connectors remains a significant challenge in smartphone manufacturing due to severe visual occlusion, tight assembly tolerances, and process constraints that prohibit separate visual adjustment stations. This letter proposes Visual-Privileged Co-Learning (VPCL), a novel privileged reinforcement learning (RL) algorithm specifically tailored for robust, force-guided precision assembly in partially observable environments. Leveraging additional visual privileged information only during training and relying solely on force feedback during deployment, VPCL employs a dual-actor (teacher-student) architecture within the Soft Actor-Critic (SAC) framework. To enhance teacher-student interaction in the co-learning process, VPCL introduces a Teacher Quality Loss to address modality imbalance and a probabilistic Policy Selector to mitigate data distribution shifts. Extensive comparative and ablation experiments in real-world smartphone assembly tasks demonstrate that VPCL achieves superior performance and robustness, as well as a remarkable zero-shot transfer capability, compared to existing baselines.Keywords
Funding Information
- National Natural Science Foundation of China (52375019)
This publication has 23 references indexed in Scilit:
- Robotic Object Insertion with a Soft Wrist through Sim-to-Real Privileged Training2024
- Force–vision fusion fuzzy control for robotic batch precision assembly of flexibly absorbed pegsRobotics and Computer-Integrated Manufacturing, 2024
- Bridging the Sim-to-Real Gap with Dynamic Compliance Tuning for Industrial Insertion2024
- SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning2024
- Learning Robotic Assembly by Leveraging Physical Softness and Tactile Sensing2023
- Model-driven reinforcement learning and action dimension extension method for efficient asymmetric assembly2022
- EDLines: A real-time line segment detector with a false detection controlPattern Recognition Letters, 2011
- A new learning paradigm: Learning using privileged informationNeural Networks, 2009
- Elements of Information Theory2001
- Markov Decision Processes: Discrete Stochastic Dynamic ProgrammingTechnometrics, 1995