NavBench: Probing Multimodal Large Language Models for Embodied Navigation

Yanyuan Qiao, Haodong Hong, Wenqi Lyu, Dong An, Siqi Zhang, Yutong Xie, Xinyu Wang, Qi Wu

EPFL· University of Queensland· CSIRO Data61· Adelaide University· Mohamed bin Zayed University of Artificial Intelligence· Tongji University

Embodied Navigation Multimodal Large Language Models

⋅ NeurIPS ⋅ Poster ⋅OpenReview

Abstract

Multimodal Large Language Models (MLLMs) have demonstrated strong generalization in vision-language tasks, yet their ability to understand and act within embodied environments remains underexplored.

We present NavBench, a benchmark to evaluate the embodied navigation capabilities of MLLMs under zero-shot settings. NavBench consists of two components:

navigation comprehension, assessed through three cognitively grounded tasks including global instruction alignment, temporal progress estimation, and local observation-action reasoning, covering 3,200 question-answer pairs; and
step-by-step execution in 432 episodes across 72 indoor scenes, stratified by spatial, cognitive, and execution complexity.

To support real-world deployment, we introduce a pipeline that converts MLLMs' outputs into robotic actions. We evaluate both proprietary and open-source models, finding that GPT-4o performs well across tasks, while lighter open-source models succeed in simpler cases.

Results also show that models with higher comprehension scores tend to achieve better execution performance. Providing map-based context improves decision accuracy, especially in medium-difficulty scenarios. However, most models struggle with temporal understanding, particularly in estimating progress during navigation, which may pose a key challenge.