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

TL;DR

PM-Nav introduces a novel approach for embodied navigation in functional buildings by leveraging priori semantic maps, significantly improving navigation accuracy in complex environments through hierarchical planning and multi-model collaboration.

Contribution

The paper presents a new framework that transforms environmental maps into semantic priori-maps and employs a hierarchical prompt and multi-model system for precise navigation in functional buildings.

Findings

Achieved over 500% improvement in simulation and real-world tests.

Demonstrated the effectiveness of priori-maps in complex building navigation.

Showed potential of PM-Nav as a backbone framework for functional building navigation.

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.