Metraipolis › archive › dc_0f71c2997be2
Social Intuition vs. Machine Reasoning: Anticipating Human-Robot Interaction from multiple modalities — arXiv:2609.07394
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.07394
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:11:48.192Z
- SHA-256 of the archived text
052b16d2c8570739145521565c6baf8c4c2d98c0ec3ecb92eb300a4de963926c- Stable URL of this page
https://metraipolis.com/documento/dc_0f71c2997be2
How to cite
Social Intuition vs. Machine Reasoning: Anticipating Human-Robot Interaction from multiple modalities — arXiv:2609.07394 — arXiv (en), https://arxiv.org/abs/2609.07394 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0f71c2997be2 (Metraipolis archive dc_0f71c2997be2, sha256 052b16d2c8570739145521565c6baf8c4c2d98c0ec3ecb92eb300a4de963926c)
BibTeX
@misc{dc0f71c2997be2,
title = {Social Intuition vs. Machine Reasoning: Anticipating Human-Robot Interaction from multiple modalities — arXiv:2609.07394},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.07394},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0f71c2997be2; sha256 052b16d2c8570739145521565c6baf8c4c2d98c0ec3ecb92eb300a4de963926c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07394. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Anticipating whether a person will interact from one's own perspective is a highly intuitive task for humans, that relies on a combination of cues. We investigate how humans perform at predicting a person's intention to interact from a service robot's point of view, using pose-only or full video input, then benchmark different lightweight pose-based models and state-of-the-art vision-language models. We conducted our benchmark on the HUI360 dataset on a fixed pilot subset of 100 test tracks (25 positive, 75 negative). We found that with pose-only input, human annotators outperform lightweight trained pose models but not by large margins (+0.08 in F1-Score). But when given full egocentric video with a target bounding box, human annotators perform substantially better and largely outperform the Vision-Language Models (+0.2 in F1-Score). We also compared VLMs of different size and under different input conditions, and found that the best results do not correlate with model size. Our result confirms that predicting interactions is a challenging task for social robots and that reasoning-capable models are necessary but their actual reasoning capabilities alone do not suffice to match the social intuition of humans. 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). Pagina del lavoro: https://arxiv.org/abs/2609.07394 — 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 2026-10-16T14:49:57.214Z 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).