Can Vision Foundation Models Navigate? Zero-Shot Real-World Evaluation and Lessons Learned

Maeva Guerrier, Karthik Soma, Jana Pavlasek, Giovanni Beltrame
Paper Code Data BibTex

Abstract

Visual Navigation Models (VNMs) promise generalizable, robot navigation by learning from large-scale visual demonstrations. Despite growing real-world deployment, existing evaluations rely almost exclusively on success rate, whether the robot reaches its goal, which conceals trajectory quality, collision behavior, and robustness to environmental change. We present a real-world evaluation of five state-of-the-art VNMs (GNM, ViNT, NoMaD, NaviBridger, and CrossFormer) across two robot platforms and five environments spanning indoor and outdoor settings. Beyond success rate, we combine path-based metrics with vision-based goal-recognition scores and assess robustness through controlled image perturbations (motion blur, sunflare). Our analysis uncovers three systematic limitations: (a) even architecturally sophisticated diffusion and transformer-based models exhibit frequent collisions, indicating limited geometric understanding; (b) models fail to discriminate between different locations that are perceptually similar, however some semantics differences are present, causing goal prediction errors in repetitive environments; and (c) performance degrades under distribution shift. We will publicly release our evaluation codebase and dataset to facilitate reproducible benchmarking of VNMs

Robots Used

Bunker

Spot

Environments Used

Office loop
Corridor
Snow
Stairs
Arena

Models Used

BibTeX

@misc{guerrier2026visionfoundationmodelsnavigate,
      title     = {Can Vision Foundation Models Navigate? Zero-Shot Real-World Evaluation and Lessons Learned},
      author    = {Maeva Guerrier and Karthik Soma and Jana Pavlasek and Giovanni Beltrame}  
      year      = {2026},
      eprint    = {2603.25937},
      archivePrefix = {arXiv},
      primaryClass = {cs.RO},
      url       = {https://arxiv.org/abs/2603.25937}, 
}