PM-Nav: Priori-Map Guided Embodied Navigation in Functional Buildings

2026-03-09

AI Summary

This work addresses the challenge of language-driven embodied navigation in functional buildings, where highly homogeneous environments limit performance due to insufficient exploitation of prior spatial knowledge. To overcome this, the authors propose a novel framework that transforms environmental maps into semantic prior maps and integrates them into a hierarchical chain-of-thought prompting template for precise path planning. Additionally, a multi-model collaborative action output mechanism is introduced to jointly handle localization decisions and execution control. This approach, the first to combine semantic prior maps with hierarchical chain-of-thought prompting, achieves substantial performance gains on a newly curated functional building dataset—yielding average improvements of 511% and 1175% over SG-Nav and InstructNav in simulation, and 650% and 400% in real-world environments, respectively.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Localization, Mapping, and Navigation
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Agentic search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Existing language-driven embodied navigation paradigms face challenges in functional buildings (FBs) with highly similar features, as they lack the ability to effectively utilize priori spatial knowledge. To tackle this issue, we propose a Priori-Map Guided Embodied Navigation (PM-Nav), wherein environmental maps are transformed into navigation-friendly semantic priori-maps, a hierarchical chain-of-thought prompt template with an annotation priori-map is designed to enable precise path planning, and a multi-model collaborative action output mechanism is built to accomplish positioning decisions and execution control for navigation planning. Comprehensive tests using a home-made FB dataset show that the PM-Nav obtains average improvements of 511\% and 1175\%, and 650\% and 400\% over the SG-Nav and the InstructNav in simulation and real-world, respectively. These tremendous boosts elucidate the great potential of using the PM-Nav as a backbone navigation framework for FBs.

Problem

• embodied navigation
• functional buildings
• priori spatial knowledge
• language-driven navigation
• semantic priori-maps

Innovation

• Priori-Map
• Embodied Navigation
• Chain-of-Thought Prompting
• Semantic Map
• Multi-model Collaboration