EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Belief-Driven Hybrid Reinforcement Learning Framework for Decentralized Multi-Robot Navigation Under Partial Observability

Vineetha Malathi, Pramod Sreedharan, Rthuraj Puthiyaveedu Rajesh, Vyshnavi Anil Kumar, Anil Lal Sadasivan, Ganesha Udupa, Liam Pastorelli

Robotics · 28.07.2026 · 15 (8) · 143

DOI: 10.3390/robotics15080143 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Robotics, online erschienen am 28.07.2026. Verfasst von Vineetha Malathi und 6 weiteren Autor:innen. Die Arbeit nennt 13 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Decentralized multi-robot navigation is difficult when robots must act from local observations without centralized coordination or explicit inter-robot communication. A belief-driven hybrid reinforcement learning framework is evaluated for planar multi-robot navigation under partial observability. Each robot builds a compact local state from its position, waypoint target, sector-based proximity readings, and a decaying occupancy belief that summarizes recent obstacle evidence. A Deep Deterministic Policy Gradient (DDPG) actor produces continuous velocity proposals, and a lightweight geometric safety-blending layer combines this command with goal-seeking and reactive avoidance vectors before execution. The simulation was revised to use e-puck-compatible heading-limited forward motion rather than side-slip motion. The framework is intentionally solver-free at runtime and does not introduce online constrained optimization or new communication mechanisms. The evaluation reports a controlled five-seed study using seeds 101–105 and a 10-seed stress suite covering scalability, symmetric crossing, corridor, and dense dynamic-obstacle cases. In the controlled nominal evaluation, full three-robot completion occurred in all five runs, with 100.0% mean success, 142.2 mean steps, and no recorded collision timestep. In the hybrid stress suite, nominal, four-robot swap, five-robot crossing, symmetric-deadlock, and corridor cases achieved full success in all 10 seeds. Dense dynamic obstacles were the main failure case, with 5/10 full-success runs, 5 robot timeouts, and 10.1 mean collision events per run. These results support the feasibility of the hybrid structure in moderate tested conditions while showing that dense moving obstacles remain a practical limitation. Formal safety guarantees, matched benchmark comparisons, physical robot validation, and wider randomization remain areas requiring future work.

Zitieren

APA

Malathi, V., Sreedharan, P., Rajesh, R. P., Kumar, V. A., Sadasivan, A. L., Udupa, G., & Pastorelli, L. (2026). A Belief-Driven Hybrid Reinforcement Learning Framework for Decentralized Multi-Robot Navigation Under Partial Observability. Robotics, 15(8), 143. https://doi.org/10.3390/robotics15080143

Vancouver

Malathi V, Sreedharan P, Rajesh RP, Kumar VA, Sadasivan AL, Udupa G, et al. A Belief-Driven Hybrid Reinforcement Learning Framework for Decentralized Multi-Robot Navigation Under Partial Observability. Robotics. 2026;15(8):143. doi:10.3390/robotics15080143

BibTeX
@article{Malathi2026,
  author = {Malathi, Vineetha and Sreedharan, Pramod and Rajesh, Rthuraj Puthiyaveedu and Kumar, Vyshnavi Anil and Sadasivan, Anil Lal and Udupa, Ganesha and Pastorelli, Liam},
  title = {A Belief-Driven Hybrid Reinforcement Learning Framework for Decentralized Multi-Robot Navigation Under Partial Observability},
  journal = {Robotics},
  year = {2026},
  volume = {15},
  number = {8},
  pages = {143},
  doi = {10.3390/robotics15080143}
}
Kostenlos starten →