EUVIMEDEUVIMED entdecken
Crossref

Shared autonomy between human electroencephalography and TD3 deep reinforcement learning: A multi‐agent copilot approach

Chun-Ren Phang iD, Akimasa Hirata

Annals of the New York Academy of Sciences · 2025

DOI: 10.1111/nyas.15322 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Annals of the New York Academy of Sciences, 2025. Verfasst von Chun-Ren Phang und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Mechanical Engineering, Nagoya Institute of Technology, Nagoya, Japan. Hauptthemen laut MEDLINE: Electroencephalography, Brain-Computer Interfaces, Deep Learning, Reinforcement, Psychology. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: Japan Society for the Promotion of Science.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep reinforcement learning (RL) algorithms enable the development of fully autonomous agents that can interact with the environment. Brain–computer interface (BCI) systems decipher human implicit brain signals regardless of the explicit environment. We proposed a novel integration technique between deep RL and BCI to improve beneficial human interventions in autonomous systems and the performance in decoding brain activities by considering environmental factors. Shared autonomy was allowed between the action command decoded from the electroencephalography (EEG) of the human agent and the action generated from the twin delayed DDPG (TD3) agent for a given complex environment. Our proposed copilot control scheme with a full blocker (Co‐FB) significantly outperformed the individual EEG (EEG‐NB) or TD3 control. The Co‐FB model achieved a higher target‐approaching score, lower failure rate, and lower human workload than the EEG‐NB model. We also proposed a disparity ‐index to evaluate the effect of contradicting agent decisions on the control accuracy and authority of the copilot model. We observed that shifting control authority to the TD3 agent improved performance when BCI decoding was not optimal. These findings indicate that the copilot system can effectively handle complex environments and that BCI performance can be improved by considering environmental factors.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyBrain-Computer InterfacesDeep LearningReinforcement, PsychologyHumansAlgorithmsBrainReinforcement Machine Learning

Stichwörter der Autor:innen

brain–computer interfacedeep reinforcement learningmotor imagerymulti‐agent copilotshared autonomy

Autor:innen und Institutionen

  • Department of Electrical and Mechanical Engineering, Nagoya Institute of Technology, Nagoya, Japan.
  • Center of Biomedical Physics and Information Technology, Nagoya Institute of Technology, Nagoya, Japan.
  • DNAKE BCI Lab, Brain-Computer Interaction Business Unit, DNAKE (Xiamen) Intelligent Technology CO., LTD, Xiamen, Fujian, China.

ORCID-Profile: Chun-Ren Phang

Förderung

  • Japan Society for the Promotion of Science

Zitieren

APA

Phang, C. R., & Hirata, A. (2025). Shared autonomy between human electroencephalography and TD3 deep reinforcement learning: A multi‐agent copilot approach. Annals of the New York Academy of Sciences. https://doi.org/10.1111/nyas.15322

Vancouver

Phang CR, Hirata A. Shared autonomy between human electroencephalography and TD3 deep reinforcement learning: A multi‐agent copilot approach. Annals of the New York Academy of Sciences. 2025. doi:10.1111/nyas.15322

BibTeX
@article{Phang2025,
  author = {Phang, Chun-Ren and Hirata, Akimasa},
  title = {Shared autonomy between human electroencephalography and TD3 deep reinforcement learning: A multi‐agent copilot approach},
  journal = {Annals of the New York Academy of Sciences},
  year = {2025},
  doi = {10.1111/nyas.15322}
}
Kostenlos starten →