EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

End-to-End Autonomous Navigation Based on Deep Reinforcement Learning with a Survival Penalty Function

Shyr-Long Jeng iD, Chienhsun Chiang

Sensors · 23.10.2023 · 23 (20) · 8651

DOI: 10.3390/s23208651 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 23.10.2023. Verfasst von Shyr-Long Jeng und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical Engineering, Lunghwa University of Science and Technology, Taoyuan City 333326, Taiwan. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Council of Taiwan, R.O.C..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

An end-to-end approach to autonomous navigation that is based on deep reinforcement learning (DRL) with a survival penalty function is proposed in this paper. Two actor–critic (AC) frameworks, namely, deep deterministic policy gradient (DDPG) and twin-delayed DDPG (TD3), are employed to enable a nonholonomic wheeled mobile robot (WMR) to perform navigation in dynamic environments containing obstacles and for which no maps are available. A comprehensive reward based on the survival penalty function is introduced; this approach effectively solves the sparse reward problem and enables the WMR to move toward its target. Consecutive episodes are connected to increase the cumulative penalty for scenarios involving obstacles; this method prevents training failure and enables the WMR to plan a collision-free path. Simulations are conducted for four scenarios—movement in an obstacle-free space, in a parking lot, at an intersection without and with a central obstacle, and in a multiple obstacle space—to demonstrate the efficiency and operational safety of our method. For the same navigation environment, compared with the DDPG algorithm, the TD3 algorithm exhibits faster numerical convergence and higher stability in the training phase, as well as a higher task execution success rate in the evaluation phase.

Schlagwörter

Stichwörter der Autor:innen

actor–critic (AC) methodautonomousreinforcement learning (RL)wheeled mobile robots (WMRs)

Autor:innen und Institutionen

  • Department of Mechanical Engineering, Lunghwa University of Science and Technology, Taoyuan City 333326, Taiwan.
  • Department of Mechanical Engineering, National Yang Ming Chiao Tung University, Hsinchu City 300093, Taiwan.

ORCID-Profile: Shyr-Long Jeng

Förderung

  • National Science Council of Taiwan, R.O.C.

Zitieren

APA

Jeng, S. L., & Chiang, C. (2023). End-to-End Autonomous Navigation Based on Deep Reinforcement Learning with a Survival Penalty Function. Sensors, 23(20), 8651. https://doi.org/10.3390/s23208651

Vancouver

Jeng SL, Chiang C. End-to-End Autonomous Navigation Based on Deep Reinforcement Learning with a Survival Penalty Function. Sensors. 2023;23(20):8651. doi:10.3390/s23208651

BibTeX
@article{Jeng2023,
  author = {Jeng, Shyr-Long and Chiang, Chienhsun},
  title = {End-to-End Autonomous Navigation Based on Deep Reinforcement Learning with a Survival Penalty Function},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {20},
  pages = {8651},
  doi = {10.3390/s23208651}
}
Kostenlos starten →