EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Inspection Robot Navigation Based on Improved TD3 Algorithm

Bo Huang, Jiacheng Xie, Jiawei Yan

Sensors · 15.04.2024 · 24 (8) · 2525

DOI: 10.3390/s24082525 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.04.2024. Verfasst von Bo Huang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical Engineering, Sichuan University of Science and Engineering, Zigong 643099, China. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Science & Technology Department of Sichuan Province, grant number 2021YFG0050; the Graduate Innovation Fund of Sichuan University of Science & Engineering,…, Scientific Research and Innovation Team Program of Sichuan University of Science and Engineering, Graduate Innovation Fund of Sichuan University of Science & Engineering.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The swift advancements in robotics have rendered navigation an essential task for mobile robots. While map-based navigation methods depend on global environmental maps for decision-making, their efficacy in unfamiliar or dynamic settings falls short. Current deep reinforcement learning navigation strategies can navigate successfully without pre-existing map data, yet they grapple with issues like inefficient training, slow convergence, and infrequent rewards. To tackle these challenges, this study introduces an improved two-delay depth deterministic policy gradient algorithm (LP-TD3) for local planning navigation. Initially, the integration of the long–short-term memory (LSTM) module with the Prioritized Experience Re-play (PER) mechanism into the existing TD3 framework was performed to optimize training and improve the efficiency of experience data utilization. Furthermore, the incorporation of an Intrinsic Curiosity Module (ICM) merges intrinsic with extrinsic rewards to tackle sparse reward problems and enhance exploratory behavior. Experimental evaluations using ROS and Gazebo simulators demonstrate that the proposed method outperforms the original on various performance metrics.

Schlagwörter

Stichwörter der Autor:innen

curiosity-drivendeep reinforcement learninginspection robot navigationlong- and short-term memory

Autor:innen und Institutionen

  • School of Mechanical Engineering, Sichuan University of Science and Engineering, Zigong 643099, China.

Förderung

  • the Science & Technology Department of Sichuan Province, grant number 2021YFG0050; the Graduate Innovation Fund of Sichuan University of Science & Engineering,…
  • Scientific Research and Innovation Team Program of Sichuan University of Science and Engineering
  • Graduate Innovation Fund of Sichuan University of Science & Engineering

Zitieren

APA

Huang, B., Xie, J., & Yan, J. (2024). Inspection Robot Navigation Based on Improved TD3 Algorithm. Sensors, 24(8), 2525. https://doi.org/10.3390/s24082525

Vancouver

Huang B, Xie J, Yan J. Inspection Robot Navigation Based on Improved TD3 Algorithm. Sensors. 2024;24(8):2525. doi:10.3390/s24082525

BibTeX
@article{Huang2024,
  author = {Huang, Bo and Xie, Jiacheng and Yan, Jiawei},
  title = {Inspection Robot Navigation Based on Improved TD3 Algorithm},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {8},
  pages = {2525},
  doi = {10.3390/s24082525}
}
Kostenlos starten →