Guided Distillation and Risk Adaptive Evolution for Multi-Robot Navigation
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (1) · 704-711
DOI: 10.1609/aaai.v40i1.37036 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xuyang Li und 5 weiteren Autor:innen.
Abstract (Originalsprache)
Recent advancements in multi-robot navigation have explored methods that combine Large Language Models (LLMs) for tasks like scene understanding or high-level decision-making. However, these approaches face challenges with high inference latency and potential hallucinations. To address these challenges, we propose a knowledge-driven Reinforcement Learning (RL) framework, GUIDER, that utilizes an LLM in two different offline roles. First, we leverage the LLM as an offline knowledge source. Its expertise is distilled into a compact model, which is applied only when the RL agent is uncertain about its own value estimates and the model itself is confident in its prediction. Additionally, we utilize the LLM as an offline semantic engine. This process translates the LLM's high-level understanding of situational risk into a dynamic adjustment of the RL agent's behavioral style, evolving a function that optimally balances conservative and aggressive actions. We conduct extensive experiments in both terrestrial and maritime settings. Across all maritime scenarios (3–12 robots), GUIDER improves the task success rate and reduces the collision rate significantly compared to the state-of-the-art RL-based multi-robot navigation methods.
Zitieren
APA
Li, X., Fang, J., Li, L., Chen, B., Li, G., & Xue, J. (2026). Guided Distillation and Risk Adaptive Evolution for Multi-Robot Navigation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(1), 704-711. https://doi.org/10.1609/aaai.v40i1.37036
Vancouver
Li X, Fang J, Li L, Chen B, Li G, Xue J. Guided Distillation and Risk Adaptive Evolution for Multi-Robot Navigation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(1):704-711. doi:10.1609/aaai.v40i1.37036
BibTeX
@article{Li2026,
author = {Li, Xuyang and Fang, Jianwu and Li, Lin and Chen, Boyuan and Li, Guangliang and Xue, Jianru},
title = {Guided Distillation and Risk Adaptive Evolution for Multi-Robot Navigation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {1},
pages = {704--711},
doi = {10.1609/aaai.v40i1.37036}
}
EUVIMED