Sticky-Glance: Robust Intent Recognition for Human Robot Collaboration via Single-Glance
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915839275433984 |
|---|---|
| author | Lai, Yuzhi Yuan, Shenghai Li, Peizheng Zell, Andreas |
| author_facet | Lai, Yuzhi Yuan, Shenghai Li, Peizheng Zell, Andreas |
| contents | Gaze is a valuable means of communication for impaired people with extremely limited motor capabilities. However, robust gaze-based intent recognition in multi-object environments is challenging due to gaze noise, micro-saccades, viewpoint changes, and dynamic objects. To address this, we propose an object-centric gaze grounding framework that stabilizes intent through a sticky-glance algorithm, jointly modeling geometric distance and direction trends. The inferred intent remains anchored to the object even under short glances with minimal 3 gaze samples, achieving a tracking rate of 0.94 for dynamic targets and selection accuracy of 0.98 for static targets. We further introduce a continuous shared control and multi-modal interaction paradigm, enabling high-readiness control and human-in-loop feedback, thereby reducing task duration for nearly 10 \%. Experiments across dynamic tracking, multi-perspective alignment, a baseline comparison, user studies, and ablation studies demonstrate improved robustness, efficiency, and reduced workload compared to representative baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_06121 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Sticky-Glance: Robust Intent Recognition for Human Robot Collaboration via Single-Glance Lai, Yuzhi Yuan, Shenghai Li, Peizheng Zell, Andreas Robotics Gaze is a valuable means of communication for impaired people with extremely limited motor capabilities. However, robust gaze-based intent recognition in multi-object environments is challenging due to gaze noise, micro-saccades, viewpoint changes, and dynamic objects. To address this, we propose an object-centric gaze grounding framework that stabilizes intent through a sticky-glance algorithm, jointly modeling geometric distance and direction trends. The inferred intent remains anchored to the object even under short glances with minimal 3 gaze samples, achieving a tracking rate of 0.94 for dynamic targets and selection accuracy of 0.98 for static targets. We further introduce a continuous shared control and multi-modal interaction paradigm, enabling high-readiness control and human-in-loop feedback, thereby reducing task duration for nearly 10 \%. Experiments across dynamic tracking, multi-perspective alignment, a baseline comparison, user studies, and ablation studies demonstrate improved robustness, efficiency, and reduced workload compared to representative baselines. |
| title | Sticky-Glance: Robust Intent Recognition for Human Robot Collaboration via Single-Glance |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.06121 |