Metraipolis › archive › dc_0127c844271b

Explore, Map, Remember, Decide: Are Embodied VLMs Ready for Safety-Critical Scenarios? — arXiv:2608.08077

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.08077
License (as archived)
CC0-1.0
Archived
2026-10-19T06:49:31.961Z
SHA-256 of the archived text
4fcf52f9d4de15397f32c849758c10c640d6dae131f2712cf2d6e9034d98c61c
Stable URL of this page
https://metraipolis.com/documento/dc_0127c844271b

How to cite

Explore, Map, Remember, Decide: Are Embodied VLMs Ready for Safety-Critical Scenarios? — arXiv:2608.08077 — arXiv (en), https://arxiv.org/abs/2608.08077 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0127c844271b (Metraipolis archive dc_0127c844271b, sha256 4fcf52f9d4de15397f32c849758c10c640d6dae131f2712cf2d6e9034d98c61c)
BibTeX
@misc{dc0127c844271b,
  title = {Explore, Map, Remember, Decide: Are Embodied VLMs Ready for Safety-Critical Scenarios? — arXiv:2608.08077},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.08077},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0127c844271b; sha256 4fcf52f9d4de15397f32c849758c10c640d6dae131f2712cf2d6e9034d98c61c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08077. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Theory of Space framework (ToS) assesses the spatial understanding of curiosity-driven Vision-Language Models (VLMs) under partial observability. As AI techniques are increasingly applied to safety-critical scenarios, it is crucial to understand whether VLMs possess robust spatial memory and make reliable decisions. In this paper, we assess whether VLMs' decisions are based on physical evidence or are corrupted by visual-language biases, if their memory processes align with human cognitive patterns, and how they respond to environmental hazards. We extend the ToS framework into a safety-critical, goal-driven pipeline, named Explore, Map, Remember, and Decide (EMRD). We then quantify Exploration Competence (Explore) through metrics of environmental coverage and temporal efficiency, assess Spatial Fidelity (Map), evaluate, with a suite of psychological metrics, Memory Persistence (Remember), and measure, using focal-point metrics, Cognitive Decision-Making (Decide). Our results show that in terms of decision-making capabilities, VLMs frequently select evacuation points based on pre-trained textual priors while lacking the spatial grounding to justify their choices. We also show that spatial reasoning degrades in low-light conditions, but it is not affected by texture and colour tampering. Our findings suggest that VLM memory fundamentally diverges from human cognition, creating unpredictable risks of misalignment.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.MA).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.08077 — 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 2026-10-19T06:45:31.707Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).