---
title: "VLAN: Vision-Language Accessible Navigation | SI Paper Desk"
url: https://thesimind.si/papers/2611.18346/
description: "VLAN is a new benchmark showing that vision-language models often fail to adjust navigation choices and safety judgments to who is moving, such as a..."
---

Number 6 of 12 · November 17, 2026

# VLAN: Vision-Language Accessible Navigation

VLAN is a new benchmark showing that vision-language models often fail to adjust navigation choices and safety judgments to who is moving, such as a quadruped robot or a person with a mobility impairment.

Jie Hu, Yu Zheng, Wenzhi Wu and 3 more · Submitted November 13, 2026 · arXiv 2611.18346v1 · cs.AI

[Read the paper on arXiv](https://arxiv.org/abs/2611.18346) · [The PDF](https://arxiv.org/pdf/2611.18346) · [The day's 12](https://thesimind.si/papers/day/2026-11-17/)

## What they found

The authors built VLAN, a dataset of 1,000 scenes, 20K navigation trajectories, and 160K keyframes. It covers varied lighting, environments, scene types, and path shapes. Each trajectory comes with actions and accessibility features for legged and wheeled agents, including humanoid and quadruped robots and people with visual or mobility impairments. Obstacles and accessibility labels are sorted into four classes: Passable, Bypass, HighRisk, and Blocked. The authors tested modern vision-language models and found they often fail to adapt obstacle relevance, path selection, and safety criteria consistently across user profiles. The abstract gives no numbers for how large those failures are.

## Why it matters

A path that one user can walk may be closed to another, but existing benchmarks usually test only one fixed body type. VLAN scores more than whether the goal is reached. It also scores collisions and how well the route fits a user's own constraints. This points to a gap that matters for SI systems meant to help people with disabilities or to run on different kinds of robots.

## How it changes the race

This is a benchmark paper, not a new model. If the results hold, it gives developers of embodied SI a way to measure user-specific navigation, and it shows that general vision-language models do not yet handle it well.

## Safety and control

The benchmark measures physical safety and collision risk. It also checks fit with user-specific constraints, which matters when SI guides people with impairments. The reported inconsistency across user profiles is a warning against relying on current models for this.

### The abstract, by the authors

Accessible mobility is user-conditioned rather than scene-intrinsic, as walkable paths for one embodiment are inaccessible to another. Yet, existing benchmarks evaluate traversability under a fixed and limited embodiment. We present Vision-Language Accessible Navigation (VLAN), containing 1,000 scenes, 20K navigation trajectories, and 160K keyframes across diverse lighting, environmental conditions, scene semantics, and path geometries. For each trajectory, VLAN provides embodiment-specific actions and accessibility features for legged and wheeled agents, including humanoid and quadruped robots and people with visual or mobility impairments, while everyday obstacles and accessibility labels are categorized as Passable, Bypass, HighRisk, and Blocked. Unlike goal-only evaluation, our benchmark measures physical safety and alignment with user-specific constraints via goal-reaching, collision-aware, and accessibility-aligned metrics. We benchmark modern vision-language models and find they often fail to consistently adapt obstacle relevance, path selection, and safety criteria across user profiles, suggesting accessibility-aware navigation requires dedicated datasets, tasks, and metrics beyond conventional embodied navigation evaluation. All data and code open-source at https://github.com/InSAI-Lab/VLAN.

Quoted from arXiv:2611.18346. The research and its words belong to its authors.

Desk score **76** out of 100

Why it was picked

- Safety
- Alignment
- Agents
- Evals
- Accepted at NeurIPS
- Language models
- Cross-listed in 2 fields

Topics

- [Benchmarks](https://thesimind.si/papers/?tag=benchmarks)
- [Evals](https://thesimind.si/papers/?tag=evals)
- [Robotics](https://thesimind.si/papers/?tag=robotics)
- [Multimodal](https://thesimind.si/papers/?tag=multimodal)
- [Safety](https://thesimind.si/papers/?tag=safety)

**arXiv ID:** 2611.18346v1
**Submitted:** November 13, 2026
**Fields:** cs.AI (Artificial Intelligence), cs.CV (Computer Vision)
**Level:** Intermediate
**Comments:** Accepted to NeurIPS 2026 Evaluations and Datasets Track. 25 pages, 17 tables, 6 figures. Code: [https://github.com/InSAI-Lab/VLAN](https://github.com/InSAI-Lab/VLAN)

Fingerprint, SHA-256

`280608e99e68ac2064840836ce3837228f96076006461044f9f10b79b7a90ed0`

On Solana: [Proof of Mind seal, 2HNJWs...cNY9](https://solscan.io/tx/2HNJWsLa5Tp3F7wQaNr1CPR71N1aoGNptA7fgCafC5m3BwbmKwhNGTXyaSfyEa9jqug6kM55u5VmDvbSrRepcNY9)

### The exact text fingerprinted

{"arxiv":"2611.18346","version":1,"title":"VLAN: Vision-Language Accessible Navigation","authors":["Jie Hu","Yu Zheng","Wenzhi Wu","Weixing Feng","Cunlei Cheng","Jiaming Zhang"],"day":"2026-11-17","rank":6,"score":76,"status":"written","summary":{"takeaway":"VLAN is a new benchmark showing that vision-language models often fail to adjust navigation choices and safety judgments to who is moving, such as a quadruped robot or a person with a mobility impairment.","found":"The authors built VLAN, a dataset of 1,000 scenes, 20K navigation trajectories, and 160K keyframes. It covers varied lighting, environments, scene types, and path shapes. Each trajectory comes with actions and accessibility features for legged and wheeled agents, including humanoid and quadruped robots and people with visual or mobility impairments. Obstacles and accessibility labels are sorted into four classes: Passable, Bypass, HighRisk, and Blocked. The authors tested modern vision-language models and found they often fail to adapt obstacle relevance, path selection, and safety criteria consistently across user profiles. The abstract gives no numbers for how large those failures are.","matters":"A path that one user can walk may be closed to another, but existing benchmarks usually test only one fixed body type. VLAN scores more than whether the goal is reached. It also scores collisions and how well the route fits a user's own constraints. This points to a gap that matters for SI systems meant to help people with disabilities or to run on different kinds of robots.","race":"This is a benchmark paper, not a new model. If the results hold, it gives developers of embodied SI a way to measure user-specific navigation, and it shows that general vision-language models do not yet handle it well.","safety":"The benchmark measures physical safety and collision risk. It also checks fit with user-specific constraints, which matters when SI guides people with impairments. The reported inconsistency across user profiles is a warning against relying on current models for this.","level":"intermediate","tags":["benchmarks","evals","robotics","multimodal","safety"]}}

[Check it on Verify a thought](https://thesimind.si/proof-of-mind/)

## The authors

Jie Hu, Yu Zheng, Wenzhi Wu, Weixing Feng, Cunlei Cheng, Jiaming Zhang

Credit for this research belongs to its authors. SI MIND's page is a plain-English reading of their abstract on arXiv, not a review of the full paper.

Related on the desk

## More papers on these topics

[Nov 9, 2026 · Number 4HomeLoop: A Simulation Framework and Benchmark for Robot-IoT Coordination in Everyday Domestic Assistance and SafetyHomeLoop is a new simulated home benchmark where SI robots must work with smart devices and handle ambiguous alerts. The best of six models scored 61.9%, and models often over-reacted.RoboticsBenchmarksEvals](https://thesimind.si/papers/2611.08914/) · [Nov 14, 2026 · Number 3MobileProbe: Adaptive Security Evaluation of Mobile Agents via Trajectory-Aware InjectionMobileProbe tests phone-operating SI agents by adapting attacks to the route each agent takes, and the authors report it beats fixed, hand-written tests at finding weaknesses.SecurityAgentsEvals](https://thesimind.si/papers/2611.16693/) · [Nov 18, 2026 · Number 5CuRSE-Bench: A Benchmark for Probing Cultural Blind Spots in Text-to-Image Safety EvaluationSafety checks for text-to-image SI often use one culture-blind harm label, and this benchmark suggests they miss content that is harmful only within a particular culture.SafetyBenchmarksEvals](https://thesimind.si/papers/2611.20821/)

[Number 5](https://thesimind.si/papers/2611.18514/) · [All 12 for Nov 17, 2026](https://thesimind.si/papers/day/2026-11-17/) · [Number 7](https://thesimind.si/papers/2611.18130/)
