Interpreting Contact Interactions to Overcome Failure in Robot Assembly Tasks

TL;DR

This paper presents a hierarchical probabilistic method enabling robots to learn from tactile interactions during assembly, improving robustness and speed in uncertain part matching and fitting tasks.

Contribution

It introduces a novel differentiable filtering approach that uses tactile feedback to update beliefs about part types and positions during assembly.

Findings

Achieves higher precision in object position and type estimation.

Faster completion of object fitting tasks compared to baseline methods.

Demonstrates robustness to uncertainties in part matching.

Abstract

A key challenge towards the goal of multi-part assembly tasks is finding robust sensorimotor control methods in the presence of uncertainty. In contrast to previous works that rely on a priori knowledge on whether two parts match, we aim to learn this through physical interaction. We propose a hierarchical approach that enables a robot to autonomously assemble parts while being uncertain about part types and positions. In particular, our probabilistic approach learns a set of differentiable filters that leverage the tactile sensorimotor trace from failed assembly attempts to update its belief about part position and type. This enables a robot to overcome assembly failure. We demonstrate the effectiveness of our approach on a set of object fitting tasks. The experimental results indicate that our proposed approach achieves higher precision in object position and type estimation, and accomplishes object fitting tasks faster than baselines.