Metraipolis › archive › dc_f69b8b5dbaee
GeoMind: A Benchmark for Spatial Understanding in Robotic Manipulation — arXiv:2611.12175
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.12175
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:43:57.661Z
- SHA-256 of the archived text
9110233205833531a2d3531a3bb31c43c904973b55c4df7297dd3d0626652b21- Stable URL of this page
https://metraipolis.com/documento/dc_f69b8b5dbaee
How to cite
GeoMind: A Benchmark for Spatial Understanding in Robotic Manipulation — arXiv:2611.12175 — arXiv (en), https://arxiv.org/abs/2611.12175 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f69b8b5dbaee (Metraipolis archive dc_f69b8b5dbaee, sha256 9110233205833531a2d3531a3bb31c43c904973b55c4df7297dd3d0626652b21)
BibTeX
@misc{dcf69b8b5dbaee,
title = {GeoMind: A Benchmark for Spatial Understanding in Robotic Manipulation — arXiv:2611.12175},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.12175},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f69b8b5dbaee; sha256 9110233205833531a2d3531a3bb31c43c904973b55c4df7297dd3d0626652b21},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12175. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Robotic manipulation has advanced rapidly in mapping visual observations and language instructions to actions. However, reliable manipulation in open-world environments requires robust spatial understanding: the ability to identify targets in complex layouts (spatial reasoning) and adapt to scenes that continuously evolve through interaction (spatial memory). Yet existing embodied benchmarks fall short in evaluating spatial understanding: they often introduce strong visual cues that bypass spatial reasoning, and focus on static scenes that offer little insight into an agent's capacity for spatial memory. To address this gap, we introduce GeoMind, a systematic benchmark for structured spatial understanding through tabletop manipulation. GeoMind comprises 54 evaluated task variants organized around spatial reasoning and spatial memory. It also incorporates a scalable pipeline that automates the generation and annotation of task instances with verified targets and executable interactions. Extensive evaluations across diverse embodied agents reveal their consistent weaknesses in spatial understanding. Our findings highlight that these agents struggle to track identities after spatial changes and convert relational or geometric constraints into executable actions. We release the GeoMind benchmark at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.12175 — 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 2026-11-10T18:37:37.682Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).