Flexible Gear Assembly With Visual Servoing and Force Feedback

TL;DR

This paper introduces a two-stage robotic gear assembly method combining visual localization with YOLO, reinforcement learning, and force feedback to achieve high precision and flexibility efficiently.

Contribution

It presents a novel integrated approach using deep learning and force feedback for robust, flexible gear assembly with reduced training data requirements.

Findings

Achieves 0.3mm precision in gear insertion

Completes assembly within 15 seconds on average

Robustly handles arbitrary initial positions

Abstract

Gear assembly is an essential but challenging task in industrial automation. This paper presents a novel two-stage approach for achieving high-precision and flexible gear assembly. The proposed approach integrates YOLO to coarsely localize the workpiece in a searching phase and deep reinforcement learning (DRL) to complete the insertion. Specifically, DRL addresses the challenge of partial visibility when the on-wrist camera is too close to the workpiece. Additionally, force feedback is used to smoothly transit the process from the first phase to the second phase. To reduce the data collection effort for training deep neural networks, we use synthetic RGB images for training YOLO and construct an offline interaction environment leveraging sampled real-world data for training DRL agents. We evaluate the proposed approach in a gear assembly experiment with a precision tolerance of 0.3mm. The results show that our method can robustly and efficiently complete searching and insertion from arbitrary positions within an average of 15 seconds.