EUVIMEDEUVIMED entdecken
Crossref

Cooperative Path Planning With Asynchronous Multiagent Reinforcement Learning

Jiaming Yin, Weixiong Rao, Yu Xiao, Keshuang Tang

IEEE Transactions on Mobile Computing · 2025-06 · 24 (6) · 5016-5030

DOI: 10.1109/tmc.2025.3526979 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2025-06. Verfasst von Jiaming Yin und 3 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, Shanghai Key Lab of Vehicle Aerodynamics and Vehicle Thermal Management Systems.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As the number of vehicles grows in urban cities, planning vehicle routes to avoid congestion and decrease commuting time is important. In this paper, we study the shortest path problem (SPP) with multiple source-destination pairs, namely MSD-SPP, to minimize the average travel time of all routing paths. The asynchronous setting in MSD-SPP, i.e., vehicles may not simultaneously complete routing actions, makes it challenging for cooperative route planning among multiple agents and leads to ineffective route planning. To tackle this issue, in this paper, we propose a two-stage framework of inter-region and intra-region route planning by dividing an entire road network into multiple sub-graph regions. Next, the proposed asyn-MARL model allows efficient asynchronous multi-agent learning by three key techniques. First, the model adopts a low-dimensional global state to implicitly represent the high-dimensional joint observations and actions of multi-agents. Second, by a novel trajectory collection mechanism, the model can decrease the redundancy in training trajectories. Additionally, with a novel actor network, the model facilitates the cooperation among vehicles towards the same or close destinations, and a reachability graph can prevent infinite loops in routing paths. On both synthetic and real road networks, the evaluation result demonstrates that asyn-MARL outperforms state-of-the-art planning approaches.

Förderung

  • National Key R&D Program of China
  • National Natural Science Foundation of China
  • Shanghai Key Lab of Vehicle Aerodynamics and Vehicle Thermal Management Systems

Zitieren

APA

Yin, J., Rao, W., Xiao, Y., & Tang, K. (2025). Cooperative Path Planning With Asynchronous Multiagent Reinforcement Learning. IEEE Transactions on Mobile Computing, 24(6), 5016-5030. https://doi.org/10.1109/tmc.2025.3526979

Vancouver

Yin J, Rao W, Xiao Y, Tang K. Cooperative Path Planning With Asynchronous Multiagent Reinforcement Learning. IEEE Transactions on Mobile Computing. 2025;24(6):5016-5030. doi:10.1109/tmc.2025.3526979

BibTeX
@article{Yin2025,
  author = {Yin, Jiaming and Rao, Weixiong and Xiao, Yu and Tang, Keshuang},
  title = {Cooperative Path Planning With Asynchronous Multiagent Reinforcement Learning},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2025},
  volume = {24},
  number = {6},
  pages = {5016--5030},
  doi = {10.1109/tmc.2025.3526979}
}
Kostenlos starten →