Metraipolis › archive › dc_f1b01a455e35
Seeing the Invisible: Physics-Guided Visual Prompting for Temperature- and Radiation-Aware VLA Navigation — arXiv:2610.07558
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07558
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:20:49.537Z
- SHA-256 of the archived text
046160ae96201f2892c9da2911786abac0b3bb817372b32c2844e23607438600- Stable URL of this page
https://metraipolis.com/documento/dc_f1b01a455e35
How to cite
Seeing the Invisible: Physics-Guided Visual Prompting for Temperature- and Radiation-Aware VLA Navigation — arXiv:2610.07558 — arXiv (en), https://arxiv.org/abs/2610.07558 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f1b01a455e35 (Metraipolis archive dc_f1b01a455e35, sha256 046160ae96201f2892c9da2911786abac0b3bb817372b32c2844e23607438600)
BibTeX
@misc{dcf1b01a455e35,
title = {Seeing the Invisible: Physics-Guided Visual Prompting for Temperature- and Radiation-Aware VLA Navigation — arXiv:2610.07558},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07558},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f1b01a455e35; sha256 046160ae96201f2892c9da2911786abac0b3bb817372b32c2844e23607438600},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07558. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.07558 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T11:15:24.730Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).