Multi-Scale Gaussian-Language Map for Zero-shot Embodied Navigation and Reasoning

TL;DR

The paper introduces GLMap, a multi-scale Gaussian-Language Map that combines explicit geometry and semantic information with a dual-modality interface, enabling efficient zero-shot embodied navigation and reasoning.

Contribution

GLMap is a novel semantic mapping method that integrates multi-scale semantics with explicit geometry and a dual-modality interface, facilitating zero-shot tasks.

Findings

Enhances target navigation and contextual reasoning in experiments.

Supports zero-shot compatibility with large models.

Enables fast rendering via Gaussian splatting.

Abstract

Understanding the geometric and semantic structure of environments is essential for embodied navigation and reasoning. Existing semantic mapping methods trade off between explicit geometry and multi-scale semantics, and lack a native interface for large models, thus requiring additional training of feature projection for semantic alignment. To this end, we propose the multi-scale Gaussian-Language Map (GLMap), which introduces three key designs: (1) explicit geometry, (2) multi-scale semantics covering both instance and region concepts, and (3) a dual-modality interface where each semantic unit jointly stores a natural language description and a 3D Gaussian representation. The 3D Gaussians enable compact storage and fast rendering of task-relevant images via Gaussian splatting. To enable efficient incremental construction, we further propose a Gaussian Estimator that analytically derives Gaussian parameters from dense point clouds without gradient-based optimization. Experiments on ObjectNav, InstNav, and SQA tasks show that GLMap effectively enhances target navigation and contextual reasoning, while remaining compatible with large-model-based methods in a zero-shot manner. The code is available at https://github.com/sx-zhang/GLMap.