SHaRe-RL: Structured, Interactive Reinforcement Learning for Contact-Rich Industrial Assembly Tasks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Stranghöner, Jannick, Hartmann, Philipp, Braun, Marco, Wrede, Sebastian, Neumann, Klaus
Format:	Preprint
Published:	2025
Subjects:	Robotics I.2.9
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866912970068459520
author	Stranghöner, Jannick Hartmann, Philipp Braun, Marco Wrede, Sebastian Neumann, Klaus
author_facet	Stranghöner, Jannick Hartmann, Philipp Braun, Marco Wrede, Sebastian Neumann, Klaus
contents	High-mix low-volume (HMLV) industrial assembly, common in small and medium-sized enterprises (SMEs), requires the same precision, safety, and reliability as high-volume automation while remaining flexible to product variation and environmental uncertainty. Current robotic systems struggle to meet these demands. Manual programming is brittle and costly to adapt, while learning-based methods suffer from poor sample efficiency and unsafe exploration in contact-rich tasks. To address this, we present SHaRe-RL, a reinforcement learning framework that leverages multiple sources of prior knowledge. By (i) structuring skills into manipulation primitives, (ii) incorporating human demonstrations and online corrections, and (iii) bounding interaction forces with per-axis compliance, SHaRe-RL enables efficient and safe online learning for long-horizon, contact-rich industrial assembly tasks. Experiments on the insertion of industrial Harting connector modules with 0.2-0.4 mm clearance demonstrate that SHaRe-RL achieves reliable performance within practical time budgets. Our results show that process expertise, without requiring robotics or RL knowledge, can meaningfully contribute to learning, enabling safer, more robust, and more economically viable deployment of RL for industrial assembly.
format	Preprint
id	arxiv_https___arxiv_org_abs_2509_13949
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	SHaRe-RL: Structured, Interactive Reinforcement Learning for Contact-Rich Industrial Assembly Tasks Stranghöner, Jannick Hartmann, Philipp Braun, Marco Wrede, Sebastian Neumann, Klaus Robotics I.2.9 High-mix low-volume (HMLV) industrial assembly, common in small and medium-sized enterprises (SMEs), requires the same precision, safety, and reliability as high-volume automation while remaining flexible to product variation and environmental uncertainty. Current robotic systems struggle to meet these demands. Manual programming is brittle and costly to adapt, while learning-based methods suffer from poor sample efficiency and unsafe exploration in contact-rich tasks. To address this, we present SHaRe-RL, a reinforcement learning framework that leverages multiple sources of prior knowledge. By (i) structuring skills into manipulation primitives, (ii) incorporating human demonstrations and online corrections, and (iii) bounding interaction forces with per-axis compliance, SHaRe-RL enables efficient and safe online learning for long-horizon, contact-rich industrial assembly tasks. Experiments on the insertion of industrial Harting connector modules with 0.2-0.4 mm clearance demonstrate that SHaRe-RL achieves reliable performance within practical time budgets. Our results show that process expertise, without requiring robotics or RL knowledge, can meaningfully contribute to learning, enabling safer, more robust, and more economically viable deployment of RL for industrial assembly.
title	SHaRe-RL: Structured, Interactive Reinforcement Learning for Contact-Rich Industrial Assembly Tasks
topic	Robotics I.2.9
url	https://arxiv.org/abs/2509.13949