HRO: Hierarchical Room-to-Object Framework for Zero-Shot Object Goal Navigation with Large Language Models

2026-07-12

AI Summary

This work addresses the limitations in zero-shot object goal navigation—namely, the absence of human-like hierarchical spatial cognition, inefficient exploration, and inaccurate semantic associations—by proposing a large language model (LLM)-driven Hierarchical Room-to-Object (HRO) framework. HRO introduces, for the first time, a human-inspired hierarchical spatial reasoning mechanism that jointly models room-level semantics and object localization to guide agents from coarse to fine granularity toward unseen target objects in unknown environments. By leveraging the commonsense reasoning capabilities of LLMs, the framework unifies room-object semantic association with zero-shot navigation policy generation. Experimental results demonstrate that HRO significantly outperforms existing LLM-based methods on the Gibson and HM3D datasets, achieving substantial improvements in both navigation success rate and generalization performance.

Abstract

Zero-shot object-goal navigation aims to enable an intelligent agent to explore and navigate to objects of unknown categories in an unfamiliar environment without specific target training. In zero-shot navigation tasks, pre-trained large models are usually employed to leverage their prior knowledge for guiding the agent's navigation. However, existing zero-shot object-goal navigation methods based on large language models (LLMs) merely utilize LLMs as flat reasoning tools to directly associate objects or regions. They lack the hierarchical spatial cognition modeling of human-like room semantics to object localization, which leads to strong blindness in exploration, insufficient accuracy in semantic association, and failure to fully unleash the common-sense reasoning potential of LLMs. This paper proposes an LLM-driven hierarchical room-to-object (HRO) framework for zero-shot object-goal navigation, which guides the agent to explore and navigate to the target object in a coarse-to-fine manner. Experiments on Gibson and HM3D datasets verify that our HRO framework achieves superior success rate and generalization over existing LLM-based methods, underscoring LLMs' strong potential for zero-shot object-goal navigation.

Problem

• zero-shot object-goal navigation
• large language models
• hierarchical spatial cognition
• semantic association
• room-to-object reasoning

Innovation

• zero-shot object-goal navigation
• large language models
• hierarchical spatial reasoning
• room-to-object framework
• common-sense reasoning