Tolerance-Guided Policy Learning for Adaptable and Transferrable Delicate Industrial Insertion

TL;DR

This paper introduces a tolerance-guided policy learning approach for delicate industrial insertion tasks, enhancing transferability and defect robustness through task embedding, generative adversarial imitation learning, and probabilistic inference.

Contribution

It proposes a novel tolerance-guided policy learning framework combining task embedding, RS-GAIL, and probabilistic inference for improved adaptability and transferability in industrial insertion tasks.

Findings

RS-GAIL efficiently learns policies with sparse rewards

Tolerance embedding improves transferability across workpieces

Probabilistic inference enhances robustness to workpiece defects

Abstract

Policy learning for delicate industrial insertion tasks (e.g., PC board assembly) is challenging. This paper considers two major problems: how to learn a diversified policy (instead of just one average policy) that can efficiently handle different workpieces with minimum amount of training data, and how to handle defects of workpieces during insertion. To address the problems, we propose tolerance-guided policy learning. To encourage transferability of the learned policy to different workpieces, we add a task embedding to the policy's input space using the insertion tolerance. Then we train the policy using generative adversarial imitation learning with reward shaping (RS-GAIL) on a variety of representative situations. To encourage adaptability of the learned policy to handle defects, we build a probabilistic inference model that can output the best inserting pose based on failed insertions using the tolerance model. The best inserting pose is then used as a reference to the learned policy. This proposed method is validated on a sequence of IC socket insertion tasks in simulation. The results show that 1) RS-GAIL can efficiently learn optimal policies under sparse rewards; 2) the tolerance embedding can enhance the transferability of the learned policy; 3) the probabilistic inference makes the policy robust to defects on the workpieces.