CAUSALNAV: A Long-Term Embodied Navigation System for Autonomous Mobile Robots in Dynamic Outdoor Scenarios
Hongbo Duan, Shangyi Luo, Zhiyuan Deng, Yanbo Chen, Yuanhao Chiang, Yi Liu, Fangming Liu, Xueqian Wang
Abstract
Autonomous language-guided navigation in large-scale outdoor environments remains a key challenge in mobile robotics, due to difficulties in semantic reasoning, dynamic conditions, and long-term stability. We propose CausalNav, the first scene graph-based semantic navigation framework tailored for dynamic outdoor environments. We construct a multi-level semantic scene graph using LLMs, referred to as the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Embodied Graph</i>, that hierarchically integrates coarse-grained map data with fine-grained object entities. The constructed graph serves as a retrievable knowledge base for Retrieval-Augmented Generation (RAG), enabling semantic navigation and long-range planning under open-vocabulary queries. By fusing real-time perception with offline map data, the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Embodied Graph</i> supports robust navigation across varying spatial granularities in dynamic outdoor environments. Dynamic objects are explicitly handled in both the scene graph construction and hierarchical planning modules. The <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Embodied Graph</i> is continuously updated within a temporal window to reflect environmental changes and support real-time semantic navigation. Extensive experiments in both simulation and real-world settings demonstrate superior robustness and efficiency.
BibTeX
@inproceedings{ral2026_causalnavalongte,
title = {CAUSALNAV: A Long-Term Embodied Navigation System for Autonomous Mobile Robots in Dynamic Outdoor Scenarios},
author = {Hongbo Duan and Shangyi Luo and Zhiyuan Deng and Yanbo Chen and Yuanhao Chiang and Yi Liu and Fangming Liu and Xueqian Wang},
booktitle = {RA-L 2026},
year = {2026}
}