Metraipolis › archive › dc_35ea0230632a

ActGaze: Learning Action-Grounded Gaze through Counterfactual Visual Interventions for High-Precision Manipulation — arXiv:2609.28955

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.28955
License (as archived): CC0-1.0
Archived: 2026-10-08T07:16:33.837Z
SHA-256 of the archived text: d4a969fdcece18d626344c319e136cecc25120d122e70735d707cce81c4aec62
Stable URL of this page: https://metraipolis.com/documento/dc_35ea0230632a

How to cite

ActGaze: Learning Action-Grounded Gaze through Counterfactual Visual Interventions for High-Precision Manipulation — arXiv:2609.28955 — arXiv (en), https://arxiv.org/abs/2609.28955 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_35ea0230632a (Metraipolis archive dc_35ea0230632a, sha256 d4a969fdcece18d626344c319e136cecc25120d122e70735d707cce81c4aec62)

BibTeX

@misc{dc35ea0230632a,
  title = {ActGaze: Learning Action-Grounded Gaze through Counterfactual Visual Interventions for High-Precision Manipulation — arXiv:2609.28955},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28955},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_35ea0230632a; sha256 d4a969fdcece18d626344c319e136cecc25120d122e70735d707cce81c4aec62},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28955. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Current Vision-Language-Action (VLA) models often struggle with high-precision robotic manipulation. We attribute this limitation primarily to their visual attention being dispersed across task-irrelevant regions. To address this issue, we propose ActGaze, a training approach that guides VLA policies to gaze on task-relevant regions, much like humans gaze on critical visual cues while executing precise movements. Unlike prior methods that rely on external labels for gaze supervision, ActGaze derives spatial supervision directly from the VLA's own action objective by using counterfactual visual interventions to identify regions that are critical for action prediction. Extensive real-robot experiments on four high-precision robotic manipulation tasks demonstrate that ActGaze induces more focused visual attention on task-relevant regions and consistently outperforms the base VLA policy and other visual-grounding approaches.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.28955 — 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 2026-10-08T06:38:53.756Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).