A Learning-Based Assembly Framework for Contact-Intensive Tight-Tolerance Tasks

Anonymous

Keywords: Robotic assembly, contact sensing, pose estimation, reinforcement learning

TL;DR: A two-stage framework integrates a learning-based estimator and controller for contact-intensive tasks like nut tightening and transfer to the experiments.

Abstract: We propose a two-stage framework that integrates a learning-based estimator and a controller to effectively manage contact-intensive tasks. The estimator utilizes a Bayesian particle filter combined with a Mixture Density Network (MDN) structure, which is proficient at solving non-injective issues from contact data. The controller merges self-supervised and reinforcement learning (RL) methods, separating the parameters of the low-level admittance controller into labeled and unlabeled parameters. To improve reliability and generalization capabilities, a transformer model is utilized in self-supervised learning. The suggested framework is validated on a bolting task using a precise real-time simulator and is successfully applied in an experimental setting.