Vision and force guided robots boost precise peg insertion accuracy
Vision-Force Admittance Learning for Peg Insertion into a Movable Hole
Robotics
Summary
Inserting a peg into a moving hole is hard because the hole can shift unexpectedly. The authors developed a system combining visual information from cameras with force feedback to guide the robot with great precision. This system updates its strategy in real time even if the target moves, helping the robot successfully complete the task. They tested their approach on real robots with different pegs and moving holes and found it worked reliably.
What this means in practice
- •For industrial automation engineers: Control robotic arms performing precise assembly tasks when parts or fixtures can move or shift unexpectedly.
- •For warehouse robotics teams: Enable robots to insert components into containers or moving racks with high accuracy despite uncertain motion.
Authors
Yuzhong Chen, Yongqing Liang, Yunzhi Xu, Irving Fang, Chase Kidder, Hui-ping Wang, Raihan Haque, Yubiao Zhang, Chen Feng
Abstract
Precise manipulation in dynamic environments, whether induced by a mobile robot base or a target with unknown motion, remains a major challenge in robotics. Manipulation in dynamic environments introduces substantial uncertainty, which fundamentally conflicts with the tight precision requirement of precise tasks such as peg-in-the-hole. We propose a Vision-Force Admittance Learning (VFAL) framework that fuses asynchronous visual feedback with a high-frequency force-based model, using visual pose estimations as a regularization term. VFAL adapts insertion strategies online to dynamic motion while maintaining millimeter-level precision. To obtain robust, low-frequency pose information, we employ state-of-the-art vision foundation models for visual pose estimation. Additionally, we incorporate failure recovery mechanisms to enhance overall robustness. We validate our approach in real-world experiments, demonstrating high success rates and strong adaptability to various pegs and dynamic environments.