Metraipolis › archive › dc_a8dcf597c595
Physico-Geospatial Grounded Scene Interpretation for Mobile Robotics — arXiv:2609.06629
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06629
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:09:15.562Z
- SHA-256 of the archived text
0e48ecf24f9e2ab1755ad8ee93e0827c4c04bc727cc73ba3dcdf4a20e7f35665- Stable URL of this page
https://metraipolis.com/documento/dc_a8dcf597c595
How to cite
Physico-Geospatial Grounded Scene Interpretation for Mobile Robotics — arXiv:2609.06629 — arXiv (en), https://arxiv.org/abs/2609.06629 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a8dcf597c595 (Metraipolis archive dc_a8dcf597c595, sha256 0e48ecf24f9e2ab1755ad8ee93e0827c4c04bc727cc73ba3dcdf4a20e7f35665)
BibTeX
@misc{dca8dcf597c595,
title = {Physico-Geospatial Grounded Scene Interpretation for Mobile Robotics — arXiv:2609.06629},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06629},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a8dcf597c595; sha256 0e48ecf24f9e2ab1755ad8ee93e0827c4c04bc727cc73ba3dcdf4a20e7f35665},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06629. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent advancements in deep learning allow robotic agents to interact with dynamic and unstructured environments. Of special interest is the integration of physico-geospatial world knowledge into such systems, either by using physics-aware machine learning models, knowledge graphs to model relationships or spatio-temporal and logical reasoning. In the present work, we introduce an approach to augment the output of pre-trained, unmodified VLMs used for scene interpretation by integrating semantic descriptions, OpenStreetMap building data and street information with positional, temporal and metric information obtained from our sensory systems, fusing this information using LLMs. We apply this concept to an outdoor recording within a university campus, achieving an F1-Score of 0.83 in the task of grounding buildings and 0.64 for path surface grounding on our pilot evaluation set. The results demonstrate the conceptual capability of the proposed solution to deliver physico-geospatial grounded natural language descriptions. Code and results are available at this https URL Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.06629 — 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 2026-10-16T14:49:57.107Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).