EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robust Contact-Rich Task Learning With Reinforcement Learning and Curriculum-Based Domain Randomization

Ali Aflakian, Jamie Hathaway, Rustam Stolkin, Alireza Rastegarpanah

IEEE Access · 2024 · 12 · 103461-103472

DOI: 10.1109/access.2024.3432644 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2024. Verfasst von Ali Aflakian und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: “Research and Development of a Highly Automated and Safe Streamlined Process for Increase Lithium-Ion Battery Repurposing and Recycling” Project called, U.K. Research and Innovation Project “Reuse and Recycling of Lithium-Ion Batteries” (RELIB) under RELiB2.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose a framework for contact-rich path following with reinforcement learning based on a mixture of visual and tactile feedback to achieve path following on unknown environments. We employ a curriculum-based domain randomisation approach with a time-varying sampling distribution, rendering our approach is robust to parametric uncertainties in the robot-environment system. Based on evaluation in simulation for compliant path-following case studies with a random uncertain environment, and comparison with LBMPC and FDM methods, the robustness of the obtained policy over a stiffness range $10^{4}$ – $10^{9}$ N/m and friction range 0.1–1.2 is demonstrated. We extend this concept to unknown surfaces with various surface curvatures to enhance the robustness of the trained policy in terms of changes in surfaces. We demonstrate $\sim 15\times $ improvement in trajectory accuracy compared to the previous LBMPC method and $\sim 18\times $ improvement compared to using the FDM approach. We suggest the applications of the proposed method for learning more challenging tasks such as milling, which are difficult to model and dependent on a wide range of process variables.

Förderung

  • “Research and Development of a Highly Automated and Safe Streamlined Process for Increase Lithium-Ion Battery Repurposing and Recycling” Project called
  • U.K. Research and Innovation Project “Reuse and Recycling of Lithium-Ion Batteries” (RELIB) under RELiB2

Zitieren

APA

Aflakian, A., Hathaway, J., Stolkin, R., & Rastegarpanah, A. (2024). Robust Contact-Rich Task Learning With Reinforcement Learning and Curriculum-Based Domain Randomization. IEEE Access, 12, 103461-103472. https://doi.org/10.1109/access.2024.3432644

Vancouver

Aflakian A, Hathaway J, Stolkin R, Rastegarpanah A. Robust Contact-Rich Task Learning With Reinforcement Learning and Curriculum-Based Domain Randomization. IEEE Access. 2024;12:103461-103472. doi:10.1109/access.2024.3432644

BibTeX
@article{Aflakian2024,
  author = {Aflakian, Ali and Hathaway, Jamie and Stolkin, Rustam and Rastegarpanah, Alireza},
  title = {Robust Contact-Rich Task Learning With Reinforcement Learning and Curriculum-Based Domain Randomization},
  journal = {IEEE Access},
  year = {2024},
  volume = {12},
  pages = {103461--103472},
  doi = {10.1109/access.2024.3432644}
}
Kostenlos starten →