pith. sign in

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

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
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.

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

World Models as Group Actions

cs.CV · 2026-05-23 · unverdicted · novelty 7.0

Formalizes video world models as group actions on states and uses latent regularization with synthesized supervision to enforce consistency, introducing GAC and GAR metrics that improve structural correctness in SOTA models.

citing papers explorer

Showing 1 of 1 citing paper.

  • World Models as Group Actions cs.CV · 2026-05-23 · unverdicted · none · ref 39 · internal anchor

    Formalizes video world models as group actions on states and uses latent regularization with synthesized supervision to enforce consistency, introducing GAC and GAR metrics that improve structural correctness in SOTA models.