# PASS-VLN：可通行性感知的局部命令视觉-语言导航

> 原文链接：https://robotics.hellobike.com/papers/2026-10-16-2610-22812
> 频道：papers | 更新日期：2026-10-16 | 标签：arxiv, cs.RO
> 核心摘要：PASS-VLN面向身体约束下的局部VLN执行，结合可通行性基准与模型，并在实验、规划集成和真实部署中验证。

# PASS-VLN：可通行性感知的局部命令视觉-语言导航

::: v-pre
> 原文链接：[PASS-VLN: Passability-Aware Local-Command Vision-and-Language Navigation](https://arxiv.org/abs/2610.22812)（arXiv 2610.22812 · 发布日期：2026-10-16）

**PASS-VLN: Passability-Aware Local-Command Vision-and-Language Navigation**

PASS-VLN面向身体约束下的局部VLN执行，结合可通行性基准与模型，并在实验、规划集成和真实部署中验证。

## 核心要点

- 现有VLN基准多假设指令可执行，较少检验与机器人身体相关的可通行性和无碰撞执行。
- 基准固定场景、指令、起点和参考路线，通过改变机器人宽度评估可达时完成、受阻时停止。
- 模型用障碍物膨胀在深度局部鸟瞰图中编码宽度，融合几何、视觉和语言并预测离散潜在动作码。
- 实验显示其无碰撞成功率较强基线提升约12个百分点，可适应身体约束并泛化到未见宽度；基准和模型将发布。

**验证范围与局限**：验证范围包括该局部命令基准实验、与高层规划器集成以及真实世界低层执行部署。

## 英文摘要 (Abstract)

Reliable vision-and-language navigation (VLN) requires not only understanding instructions but also determining whether and how a robot can physically execute them. However, existing VLN benchmarks typically assume executable instructions and focus on long-horizon tasks. This leaves body-dependent local execution, including passability and collision-free execution, largely unexamined. Evaluating these factors within long-horizon tasks would entangle local physical execution with task planning and long-term spatial memory, making navigation failures difficult to attribute. We therefore focus on grounding local navigation commands in executable motion under environmental and robot body constraints. We present PASS-VLN, a passability-aware local-command VLN benchmark and model. The benchmark holds the scene, instruction, start pose, and reference route fixed while varying robot body width, requiring target completion when the instructed passage is feasible and stopping before blockage otherwise. Our model encodes body width through obstacle inflation in a depth-derived local bird's-eye view, fuses geometry with visual and linguistic context, and predicts discrete latent action codes for continuous closed-loop execution. Experiments show that PASS-VLN improves collision-free success by approximately 12 percentage points over a strong VLN model fine-tuned on our benchmark, while adapting reach-versus-stop behavior to body constraints and generalizing to unseen body widths. When integrated with a high-level planner, PASS-VLN achieves higher success with fewer local commands, while real-world deployment further demonstrates its effectiveness as a low-level executor. The benchmark and model will be released.

作者：Cong Zou, Xiangsheng Shi, Xuanhui Wang, Fubin Wang, Guangjun Ge, Chao Wang, Yu Wang
:::

## 原始参考来源 (Sources)

- [arXiv 2610.22812：PASS-VLN: Passability-Aware Local-Command Vision-and-Language Navigation](https://arxiv.org/abs/2610.22812)