# 看见不可见之物：面向温度与辐射感知 VLA 导航的物理引导视觉提示

> 原文链接：https://robotics.hellobike.com/papers/2026-10-06-2610-07558
> 频道：papers | 更新日期：2026-10-06 | 标签：arxiv, cs.RO
> 核心摘要：PG-VP通过物理引导动态视觉提示，让冻结VLA绕开温度和辐射隐患，并在OmniNav和真实机器人上验证。

# 看见不可见之物：面向温度与辐射感知 VLA 导航的物理引导视觉提示

::: v-pre
> 原文链接：[Seeing the Invisible: Physics-Guided Visual Prompting for Temperature- and Radiation-Aware VLA Navigation](https://arxiv.org/abs/2610.07558)（arXiv 2610.07558 · 发布日期：2026-10-06）

**Seeing the Invisible: Physics-Guided Visual Prompting for Temperature- and Radiation-Aware VLA Navigation**

PG-VP通过物理引导动态视觉提示，让冻结VLA绕开温度和辐射隐患，并在OmniNav和真实机器人上验证。

## 核心要点

- 安全关键设施中的辐射或温度突升无法由RGB相机发现，逐类处理还需新编码器、数据与重训。
- PG-VP对近距热源或辐射源做物理引导风险评估，叠加随帧移动的虚拟障碍。
- OmniNav上低风险动作引导率为84.9%/83.2%，成功率代价为6.8/7.9个百分点。
- 真机实际热源/辐射源测试无需重训，最差10%平均轨迹安全性提升63.45%/32.59%。

**验证范围与局限**：验证范围为OmniNav的R2R-CE与RxR-CE val-unseen划分，以及一台真实机器人上的热源和辐射源场景。

## 英文摘要 (Abstract)

Vision-Language-Action (VLA) models have become a major paradigm for Vision-and-Language Navigation (VLN). However, in safety-critical facilities, invisible risks such as radiation or temperature spikes cannot be detected by an RGB camera, and handling each risk is expensive, requiring a new encoder, new data, and model retraining. We propose Physics-Guided Visual Prompting (PG-VP), a plug-and-play multimodal perception module that instead reuses what a frozen VLA model already does well: avoiding visible obstacles. Given a proximal radiation or thermal source, PG-VP performs a physics-guided risk assessment to determine the avoidance direction and overlays a corresponding virtual obstacle that moves across consecutive frames (Dynamic Visual Prompting). The navigation policy then naturally detours around this invisible hazard. The identical virtual obstacle is used regardless of hazard type, so the visual prompting pattern remains fixed as sensors are added. When no hazard is detected, nothing is rendered, and the policy behaves exactly as it would without PG-VP. We evaluate PG-VP on OmniNav using the val-unseen splits of R2R-CE and RxR-CE, where it guides the policy toward intended low-risk actions in 84.9% and 83.2% of cases, at a cost of 6.8 and 7.9 percentage points in navigation success rate. We further test it with distinct scenarios on a real robot in the presence of actual thermal and radiation sources, all without any retraining. The real test shows that PG-VP effectively avoids these invisible hazards, improving worst-10% average trajectory safety by 63.45% and 32.59% against thermal and radiation sources, respectively.

作者：Hojoon Son, Fan Zhang
:::

## 原始参考来源 (Sources)

- [arXiv 2610.07558：Seeing the Invisible: Physics-Guided Visual Prompting for Temperature- and Radiation-Aware VLA Navigation](https://arxiv.org/abs/2610.07558)