CausalNav: A Long-term Embodied Navigation System for Autonomous Mobile Robots in Dynamic Outdoor Scenarios

TL;DR

CausalNav introduces a scene graph-based semantic navigation framework for outdoor robots, integrating real-time perception with offline data to enable robust, long-term autonomous navigation in dynamic environments.

Contribution

It is the first to utilize a multi-level scene graph with LLMs for semantic navigation in outdoor scenarios, combining real-time perception and long-term planning.

Findings

Outperforms existing methods in robustness and efficiency

Successfully operates in real-world outdoor environments

Handles dynamic objects explicitly in navigation planning

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 Embodied Graph, 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 Embodied Graph 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 Embodied Graph 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.