EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CPH: Collision-Avoidance-Driven Coordination for Distributed Multi-Agent Path Finding via Multi-Agent Reinforcement Learning

Yuexing Hao, Shaoyun Xu, Guotao Li

Robotics · 23.10.2026 · 15 (11) · 215

DOI: 10.3390/robotics15110215 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Robotics, online erschienen am 23.10.2026. Verfasst von Yuexing Hao und 2 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Tobacco.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-Agent Reinforcement Learning (MARL) provides an effective paradigm for distributed Multi-Agent Path Finding (MAPF) under partial observability. Due to frequent local interactions among agents, action decisions based on limited local information can induce potential collision risks and may further lead to action conflicts, posing challenges to efficient multi-agent coordination. In this paper, we propose CPH, a value-based MARL framework that proactively mitigates collision risks during path decision-making and resolves unavoidable action conflicts before execution. Specifically, we introduce a collision-risk-driven communication mechanism that selects partners according to potential collision relationships and integrates collision-aware spatial contexts with agent-centric observations via cross-attention. Moreover, we propose a potential-inspired aggregation reward shaping method, which encourages agents to disperse from collision-prone aggregation states. Additionally, we present a conflict-aware hybrid post-processing strategy that adaptively resolves different conflict scenarios through local action adjustment. Experimental results show that CPH outperforms the compared distributed MARL-based MAPF methods, while ablation studies confirm the effectiveness of all three components. These results indicate that combining proactive collision-risk mitigation with adaptive conflict resolution before execution improves path reachability and planning efficiency in distributed MAPF.

Förderung

  • China Tobacco

Zitieren

APA

Hao, Y., Xu, S., & Li, G. (2026). CPH: Collision-Avoidance-Driven Coordination for Distributed Multi-Agent Path Finding via Multi-Agent Reinforcement Learning. Robotics, 15(11), 215. https://doi.org/10.3390/robotics15110215

Vancouver

Hao Y, Xu S, Li G. CPH: Collision-Avoidance-Driven Coordination for Distributed Multi-Agent Path Finding via Multi-Agent Reinforcement Learning. Robotics. 2026;15(11):215. doi:10.3390/robotics15110215

BibTeX
@article{Hao2026,
  author = {Hao, Yuexing and Xu, Shaoyun and Li, Guotao},
  title = {CPH: Collision-Avoidance-Driven Coordination for Distributed Multi-Agent Path Finding via Multi-Agent Reinforcement Learning},
  journal = {Robotics},
  year = {2026},
  volume = {15},
  number = {11},
  pages = {215},
  doi = {10.3390/robotics15110215}
}
Kostenlos starten →