Transferring Human Manipulation Knowledge to Industrial Robots Using Reinforcement Learning

Nestor Arana-Arexolaleibo, Nerea Urrestilla Anguiozar, Dimitrios Chrysostomou, Simon Bøgh

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

64 Downloads (Pure)

Abstract

Nowadays in the context of Industry 4.0, manufacturing companies are faced by increasing global competition and challenges, which requires them to become more flexible and able to adapt fast to rapid market changes. Advanced robot system is an enabler for achieving greater flexibility and adaptability, however, programming such systems also become increasingly more complex. Thus, new methods for programming robot systems and enabling self-learning capabilities to accommodate the natural variation exhibited in real-world tasks are needed. In this paper, we propose a Reinforcement Learning (RL) enabled robot system, which learns task trajectories from human workers. The presented work demonstrates that with minimal human effort, we can transfer manual manipulation tasks in certain domains to a robot system without the requirement for a complicated hardware system model or tedious and complex programming. Furthermore, the robot is able to build upon the learned concepts from the human expert and improve its performance over time. Initially, Q-learning is applied, which has shown very promising results. Preliminary experiments, from a use case in slaughterhouses, demonstrate the viability of the proposed approach. We conclude that the feasibility and applicability of RL for industrial robots and industrial processes, holds and unseen potential, especially for tasks where natural variation is exhibited in either the product or process.
Original languageEnglish
Title of host publication29th International Conference on Flexible Automation and Intelligent Manufacturing : FAIM 2019
Number of pages8
Volume38
PublisherElsevier
Publication date2019
Pages1508 - 1515
DOIs
Publication statusPublished - 2019
Event29th International Conference on Flexible Automation and Intelligent Manufacturing (FAIM2019) - Limerick, Ireland
Duration: 24 Jun 201928 Jun 2019
https://faim2019.org

Conference

Conference29th International Conference on Flexible Automation and Intelligent Manufacturing (FAIM2019)
CountryIreland
CityLimerick
Period24/06/201928/06/2019
Internet address
SeriesProcedia Manufacturing
Volume38
ISSN2351-9789

Keywords

  • Deep Reinforcement Learning
  • Machine Learning
  • Q-Learning
  • Robotics
  • Robot Learning
  • Artificial Intelligence (AI)
  • Reinforcement Learning

Fingerprint Dive into the research topics of 'Transferring Human Manipulation Knowledge to Industrial Robots Using Reinforcement Learning'. Together they form a unique fingerprint.

  • Projects

    MADE Digital WP5.3 - Designing Self-Configuring and Self-Learning Smart Factories

    Bøgh, S., Chrysostomou, D., Anguiozar, N. U., Andersen, R. S. & Arexolaleiba, N. A.

    01/03/201731/12/2019

    Project: Research

    Equipment

    AI Cloud Service

    CLAAUDIA

    Facility: Equipment

  • Cite this

    Arana-Arexolaleibo, N., Anguiozar, N. U., Chrysostomou, D., & Bøgh, S. (2019). Transferring Human Manipulation Knowledge to Industrial Robots Using Reinforcement Learning. In 29th International Conference on Flexible Automation and Intelligent Manufacturing: FAIM 2019 (Vol. 38, pp. 1508 - 1515). Elsevier. Procedia Manufacturing Vol. 38 https://doi.org/10.1016/j.promfg.2020.01.136