EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Active Vision for Visuomotor Policy Generalization Under Positional Variations

Yonghee Lee, Junheon Yoon, Woo-Jeong Baek, Haeseong Lee, Jaeheung Park

International Journal of Control, Automation, and Systems · 17.11.2026

DOI: 10.1007/s12555-026-00237-w ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Control, Automation, and Systems, online erschienen am 17.11.2026. Verfasst von Yonghee Lee und 4 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Seoul National University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, visuomotor policy learning has gained increased attention in the robotics domain. Ideally, such policies enable robots to generate actions directly from observations with high efficiency and accuracy. In reality, performance is significantly degraded when the robot encounters previously unseen environments (e.g., a novel position of an object to grasp, disturbances in the camera viewpoint). Several studies have attempted to deal with this problem by training the model on large-scale datasets, but constructing such datasets raises another challenge of data efficiency. To address these limitations, this work presents a data-efficient visuomotor policy framework via active vision. To be specific, the proposed framework employs an object detection algorithm and expresses the robot state and actions in terms of the camera coordinate frame. Provided that the camera viewpoint is properly adjusted by active vision, the visuomotor policy can manipulate objects at any position, even at positions not included in the training data. The experiments performed in both simulation and real-world environments with a humanoid robot and a dual manipulator system highlight that the proposed framework outperforms the state-of-the-art approaches significantly by enhancing the success rate for the pick-and-place task at unseen object positions from 45 to 91%.

Förderung

  • Seoul National University

Zitieren

APA

Lee, Y., Yoon, J., Baek, W., Lee, H., & Park, J. (2026). Active Vision for Visuomotor Policy Generalization Under Positional Variations. International Journal of Control, Automation, and Systems. https://doi.org/10.1007/s12555-026-00237-w

Vancouver

Lee Y, Yoon J, Baek W, Lee H, Park J. Active Vision for Visuomotor Policy Generalization Under Positional Variations. International Journal of Control, Automation, and Systems. 2026. doi:10.1007/s12555-026-00237-w

BibTeX
@article{Lee2026,
  author = {Lee, Yonghee and Yoon, Junheon and Baek, Woo-Jeong and Lee, Haeseong and Park, Jaeheung},
  title = {Active Vision for Visuomotor Policy Generalization Under Positional Variations},
  journal = {International Journal of Control, Automation, and Systems},
  year = {2026},
  doi = {10.1007/s12555-026-00237-w}
}
Kostenlos starten →