LLM-Driven Hierarchical Planning: Long-horizon Task Allocation for Multi-Robot Systems in Cross-Regional Environments
Yachao Wang, Yangshuo Dong, Yunting Yang, Xiang Zhang, Yinchuan Wang, Yuhan Wang, Chaoqun Wang, Max Q.-H. Meng
Abstract
Long-horizon composite task planning for multi-robot systems in cross-regional complex scenarios faces dual challenges: spatial-semantic comprehension of natural language described tasks and collaborative optimization of subtask al-location. To address these challenges, this paper proposes a progressive three-stage task planning framework. First, an augmented scene graph is constructed to enable large language models (LLMs) to comprehend environmental structures, thereby generating simplified Linear Temporal Logic (LTL) task sequences. Subsequently, a novel heuristic function is employed to select optimal task allocation plans. Finally, LLMs are used to generate low-level executable robot instructions based on robotic system instruction templates. We establish a long-horizon composite task dataset for experimental validation on real-world quadrupedal multi-robot systems. Experimental results demonstrate the effectiveness of our approach in resolving cross-regional composite tasks.
BibTeX
@inproceedings{iros2025_llmdrivenhierarc,
title = {LLM-Driven Hierarchical Planning: Long-horizon Task Allocation for Multi-Robot Systems in Cross-Regional Environments},
author = {Yachao Wang and Yangshuo Dong and Yunting Yang and Xiang Zhang and Yinchuan Wang and Yuhan Wang and Chaoqun Wang and Max Q.-H. Meng},
booktitle = {IROS 2025},
year = {2025}
}