NavBench: Probing Multimodal Large Language Models for Embodied Navigation
This work addresses the underexplored ability of MLLMs to act in embodied environments, providing a benchmark for researchers, but it is incremental as it focuses on evaluation rather than new methods.
The authors tackled the problem of evaluating Multimodal Large Language Models (MLLMs) for embodied navigation by introducing NavBench, a benchmark with comprehension and execution tasks, finding that GPT-4o performs well while most models struggle with temporal understanding.
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: (1) 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 (2) 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.