Metraipolis › archive › dc_e574192e417e
Eye, Robot: Learning Expressive Gaze Dynamics via a VLM-Guided Transformer-VAE — arXiv:2610.19635
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19635
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T20:02:43.867Z
- SHA-256 of the archived text
d2c75f5af66605b71fda93ad4014b5314ad20cb25b52217a299486f608a1c00d- Stable URL of this page
https://metraipolis.com/documento/dc_e574192e417e
How to cite
Eye, Robot: Learning Expressive Gaze Dynamics via a VLM-Guided Transformer-VAE — arXiv:2610.19635 — arXiv (en), https://arxiv.org/abs/2610.19635 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e574192e417e (Metraipolis archive dc_e574192e417e, sha256 d2c75f5af66605b71fda93ad4014b5314ad20cb25b52217a299486f608a1c00d)
BibTeX
@misc{dce574192e417e,
title = {Eye, Robot: Learning Expressive Gaze Dynamics via a VLM-Guided Transformer-VAE — arXiv:2610.19635},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19635},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e574192e417e; sha256 d2c75f5af66605b71fda93ad4014b5314ad20cb25b52217a299486f608a1c00d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19635. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Gaze coordinates attention in human interaction through coupled eye, head, and eyelid motion. A humanoid robot must choose where to look while generating a suitable movement toward that target; fixed tracking rules alone do not model the temporal structure of human gaze. We separate these tasks with an asynchronous vision-language model that selects a scene referent, a reactive perception module that maintains fixation, and a Realistic Gaze Transformer (RGT) that generates target-conditioned motion. RGT is a Transformer-VAE trained on markerless human recordings retargeted to the robot's 11-DoF joint space: self-supervised pretraining encodes recent full-head history, and autoregressive fine-tuning exposes the model to its own predictions during rollout. At inference, a four-dimensional binocular-eye trajectory conditions coordinated neck and eye motion; an auxiliary blink predictor triggers eyelid templates during playback. On a two-second benchmark in which all controllers receive the same ground-truth target, RGT-Base obtains the lowest reported overall seven-joint MSE, and physical demonstrations show the integrated targeting and control pipeline. The evidence establishes robot-space kinematic fidelity and real-time RGT inference; perceived naturalness and open-vocabulary target-selection accuracy remain questions for controlled evaluation. 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/2610.19635 — 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 2026-10-15T19:35:48.353Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).