EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

VN-MADDPG: A Variable-Noise-Based Multi-Agent Reinforcement Learning Algorithm for Autonomous Vehicles at Unsignalized Intersections

Hao Zhang, Yu Du, Shixin Zhao, Ying Yuan, Qiuqi Gao

Electronics · 11.08.2024 · 13 (16) · 3180

DOI: 10.3390/electronics13163180 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 11.08.2024. Verfasst von Hao Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Vehicle–Road Cooperative Autonomous Driving Fusion Control Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The decision-making performance of autonomous vehicles tends to be unstable at unsignalized intersections, making it difficult for them to make optimal decisions. We propose a decision-making model based on the Variable-Noise Multi-Agent Deep Deterministic Policy Gradient (VN-MADDPG) algorithm to address these issues. The variable-noise mechanism reduces noise dynamically, enabling the agent to utilize the learned policy more effectively to complete tasks. This significantly improves the stability of the decision-making model in making optimal decisions. The importance sampling module addresses the inconsistency between outdated experience in the replay buffer and current environmental features. This enhances the model’s learning efficiency and improves the robustness of the decision-making model. Experimental results on the CARLA simulation platform show that the success rate of decision making at unsignalized intersections by autonomous vehicles has significantly increased, and the pass time has been reduced. The decision-making model based on the VN-MADDPG algorithm demonstrates stable and excellent decision-making performance.

Förderung

  • Vehicle–Road Cooperative Autonomous Driving Fusion Control Project

Zitieren

APA

Zhang, H., Du, Y., Zhao, S., Yuan, Y., & Gao, Q. (2024). VN-MADDPG: A Variable-Noise-Based Multi-Agent Reinforcement Learning Algorithm for Autonomous Vehicles at Unsignalized Intersections. Electronics, 13(16), 3180. https://doi.org/10.3390/electronics13163180

Vancouver

Zhang H, Du Y, Zhao S, Yuan Y, Gao Q. VN-MADDPG: A Variable-Noise-Based Multi-Agent Reinforcement Learning Algorithm for Autonomous Vehicles at Unsignalized Intersections. Electronics. 2024;13(16):3180. doi:10.3390/electronics13163180

BibTeX
@article{Zhang2024,
  author = {Zhang, Hao and Du, Yu and Zhao, Shixin and Yuan, Ying and Gao, Qiuqi},
  title = {VN-MADDPG: A Variable-Noise-Based Multi-Agent Reinforcement Learning Algorithm for Autonomous Vehicles at Unsignalized Intersections},
  journal = {Electronics},
  year = {2024},
  volume = {13},
  number = {16},
  pages = {3180},
  doi = {10.3390/electronics13163180}
}
Kostenlos starten →