EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A human-centered safe robot reinforcement learning framework with interactive behaviors

Shangding Gu, Alap Kshirsagar, Yali Du, Guang Chen, Jan Peters, Alois Knoll

Frontiers in Neurorobotics · 09.11.2023 · 17

DOI: 10.3389/fnbot.2023.1280341 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Neurorobotics, online erschienen am 09.11.2023. Verfasst von Shangding Gu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Technical University of Munich, Munich, Germany. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 84 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deployment of Reinforcement Learning (RL) algorithms for robotics applications in the real world requires ensuring the safety of the robot and its environment. Safe Robot RL (SRRL) is a crucial step toward achieving human-robot coexistence. In this paper, we envision a human-centered SRRL framework consisting of three stages: safe exploration, safety value alignment, and safe collaboration. We examine the research gaps in these areas and propose to leverage interactive behaviors for SRRL. Interactive behaviors enable bi-directional information transfer between humans and robots, such as conversational robot ChatGPT. We argue that interactive behaviors need further attention from the SRRL community. We discuss four open challenges related to the robustness, efficiency, transparency, and adaptability of SRRL with interactive behaviors.

Schlagwörter

Stichwörter der Autor:innen

bi-direction informationinteractive behaviorssafe collaborationsafe explorationvalue alignment

Autor:innen und Institutionen

  • Department of Computer Science, Technical University of Munich, Munich, Germany.
  • Department of Computer Science, Technical University of Darmstadt, Darmstadt, Germany.
  • Department of Informatics, King's College London, London, United Kingdom.
  • College of Electronic and Information Engineering, Tongji University, Shanghai, China.

Zitieren

APA

Gu, S., Kshirsagar, A., Du, Y., Chen, G., Peters, J., & Knoll, A. (2023). A human-centered safe robot reinforcement learning framework with interactive behaviors. Frontiers in Neurorobotics, 17. https://doi.org/10.3389/fnbot.2023.1280341

Vancouver

Gu S, Kshirsagar A, Du Y, Chen G, Peters J, Knoll A. A human-centered safe robot reinforcement learning framework with interactive behaviors. Frontiers in Neurorobotics. 2023;17. doi:10.3389/fnbot.2023.1280341

BibTeX
@article{Gu2023,
  author = {Gu, Shangding and Kshirsagar, Alap and Du, Yali and Chen, Guang and Peters, Jan and Knoll, Alois},
  title = {A human-centered safe robot reinforcement learning framework with interactive behaviors},
  journal = {Frontiers in Neurorobotics},
  year = {2023},
  volume = {17},
  doi = {10.3389/fnbot.2023.1280341}
}
Kostenlos starten →