PolyFit: A Peg-in-hole Assembly Framework for Unseen Polygon Shapes via Sim-to-real Adaptation

TL;DR

PolyFit is a supervised learning framework for peg-in-hole assembly that leverages force/torque data and sim-to-real adaptation to handle unseen polygon shapes with high success rates in simulation and real-world tests.

Contribution

This work introduces PolyFit, a novel supervised learning approach with sim-to-real transfer for peg-in-hole assembly of unseen polygon shapes, shifting from reinforcement learning methods.

Findings

Achieves over 97% success in simulation for seen shapes.

Attains approximately 86% success in real-world tests.

Utilizes a multi-point contact strategy for improved pose estimation.

Abstract

The study addresses the foundational and challenging task of peg-in-hole assembly in robotics, where misalignments caused by sensor inaccuracies and mechanical errors often result in insertion failures or jamming. This research introduces PolyFit, representing a paradigm shift by transitioning from a reinforcement learning approach to a supervised learning methodology. PolyFit is a Force/Torque (F/T)-based supervised learning framework designed for 5-DoF peg-in-hole assembly. It utilizes F/T data for accurate extrinsic pose estimation and adjusts the peg pose to rectify misalignments. Extensive training in a simulated environment involves a dataset encompassing a diverse range of peg-hole shapes, extrinsic poses, and their corresponding contact F/T readings. To enhance extrinsic pose estimation, a multi-point contact strategy is integrated into the model input, recognizing that identical F/T readings can indicate different poses. The study proposes a sim-to-real adaptation method for real-world application, using a sim-real paired dataset to enable effective generalization to complex and unseen polygon shapes. PolyFit achieves impressive peg-in-hole success rates of 97.3% and 96.3% for seen and unseen shapes in simulations, respectively. Real-world evaluations further demonstrate substantial success rates of 86.7% and 85.0%, highlighting the robustness and adaptability of the proposed method.