EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Extended residual learning with one-shot imitation learning for robotic assembly in semi-structured environment

Chuang Wang, Chupeng Su, Baozheng Sun, Gang Chen, Longhan Xie

Frontiers in Neurorobotics · 29.04.2024 · 18

DOI: 10.3389/fnbot.2024.1355170 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Neurorobotics, online erschienen am 29.04.2024. Verfasst von Chuang Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Shien-Ming Wu School of Intelligent Engineering, South China University of Technology, Guangzhou, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Robotic assembly tasks require precise manipulation and coordination, often necessitating advanced learning techniques to achieve efficient and effective performance. While residual reinforcement learning with a base policy has shown promise in this domain, existing base policy approaches often rely on hand-designed full-state features and policies or extensive demonstrations, limiting their applicability in semi-structured environments.

Methods

In this study, we propose an innovative Object-Embodiment-Centric Imitation and Residual Reinforcement Learning (OEC-IRRL) approach that leverages an object-embodiment-centric (OEC) task representation to integrate vision models with imitation and residual learning. By utilizing a single demonstration and minimizing interactions with the environment, our method aims to enhance learning efficiency and effectiveness. The proposed method involves three key steps: creating an object-embodiment-centric task representation, employing imitation learning for a base policy using via-point movement primitives for generalization to different settings, and utilizing residual RL for uncertainty-aware policy refinement during the assembly phase.

Results

Through a series of comprehensive experiments, we investigate the impact of the OEC task representation on base and residual policy learning and demonstrate the effectiveness of the method in semi-structured environments. Our results indicate that the approach, requiring only a single demonstration and less than 1.2 h of interaction, improves success rates by 46% and reduces assembly time by 25%.

Discussion

This research presents a promising avenue for robotic assembly tasks, providing a viable solution without the need for specialized expertise or custom fixtures.

Schlagwörter

Stichwörter der Autor:innen

imitation learningobject-embodiment-centric task representationresidual reinforcement learningrobotic assemblysemi-structured environment

Autor:innen und Institutionen

  • Shien-Ming Wu School of Intelligent Engineering, South China University of Technology, Guangzhou, China.

Zitieren

APA

Wang, C., Su, C., Sun, B., Chen, G., & Xie, L. (2024). Extended residual learning with one-shot imitation learning for robotic assembly in semi-structured environment. Frontiers in Neurorobotics, 18. https://doi.org/10.3389/fnbot.2024.1355170

Vancouver

Wang C, Su C, Sun B, Chen G, Xie L. Extended residual learning with one-shot imitation learning for robotic assembly in semi-structured environment. Frontiers in Neurorobotics. 2024;18. doi:10.3389/fnbot.2024.1355170

BibTeX
@article{Wang2024,
  author = {Wang, Chuang and Su, Chupeng and Sun, Baozheng and Chen, Gang and Xie, Longhan},
  title = {Extended residual learning with one-shot imitation learning for robotic assembly in semi-structured environment},
  journal = {Frontiers in Neurorobotics},
  year = {2024},
  volume = {18},
  doi = {10.3389/fnbot.2024.1355170}
}
Kostenlos starten →