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

arXiv: https://arxiv.org/abs/2603.25937 · HTML: https://mlsanity.com/paper/2603.25937/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 32 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data](https://mlsanity.com/paper/2306.09344/) (2023)
- [Navigation World Models](https://mlsanity.com/paper/2412.03572/) (2024)
- [NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration](https://mlsanity.com/paper/2310.07896/) (2023)
- [Real-World Robot Learning with Masked Visual Pre-training](https://mlsanity.com/paper/2210.03109/) (2022)
- [ViNT: A Foundation Model for Visual Navigation](https://mlsanity.com/paper/2306.14846/) (2023)
- [GNM: A General Navigation Model to Drive Any Robot](https://mlsanity.com/paper/2210.03370/) (2022)
- [Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation](https://mlsanity.com/paper/2203.15041/) (2022)
- [Rapid Exploration for Open-World Navigation with Latent Goal Models](https://mlsanity.com/paper/2104.05859/) (2021)
- [Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation](https://mlsanity.com/paper/2408.11812/) (2024)
- [Semantic Visual Navigation by Watching YouTube Videos](https://mlsanity.com/paper/2006.10034/) (2020)
- [Deep Visual MPC-Policy Learning for Navigation](https://mlsanity.com/paper/1903.02749/) (2019)
- [LVI-SAM: Tightly-coupled Lidar-Visual-Inertial Odometry via Smoothing and Mapping](https://mlsanity.com/paper/2104.10831/) (2021)
- [Super Odometry: IMU-centric LiDAR-Visual-Inertial Estimator for Challenging Environments](https://mlsanity.com/paper/2104.14938/) (2021)
- [NaviDiffusor: Cost-Guided Diffusion Model for Visual Navigation](https://mlsanity.com/paper/2504.10003/) (2025)
- [Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Models](https://mlsanity.com/paper/2504.10041/) (2025)
- [SELFI: Autonomous Self-Improvement with Reinforcement Learning for Social Navigation](https://mlsanity.com/paper/2403.00991/) (2024)
- [CARE: Enhancing Safety of Visual Navigation through Collision Avoidance via Repulsive Estimation](https://mlsanity.com/paper/2506.03834/) (2025)
- [MetricNet: Recovering Metric Scale in Generative Navigation Policies](https://mlsanity.com/paper/2509.13965/) (2025)
- [DGMem: Learning Visual Navigation Policy without Any Labels by Dynamic Graph Memory](https://mlsanity.com/paper/2311.18473/) (2023)

## Built on by (most cited first, 3 of 3)

- [World Models as Group Actions](https://mlsanity.com/paper/2605.24578/) (2026)
- [SeeSE3: Emergence of 3D Space in Vision Features](https://mlsanity.com/paper/2607.14228/) (2026)
- [VISTA: Scale-Aware Visual Navigation via Action History Conditioning](https://mlsanity.com/paper/2606.17294/) (2026)

## Abstract (arXiv)

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.