aiqbench analysis
This study provides a critical evaluation of gaze estimation models specifically within human-robot interaction scenarios, revealing significant practical limitations when converting angular errors into physical distance metrics in shared workspaces. By introducing a new annotated dataset from the NICO robotic platform, the paper offers concrete benchmarks and recommendations for integrating this modality effectively into future HRI systems.
Gaze Estimation for Human-Robot Interaction: Analysis Using the NICO Platform
arXiv:2509.24001v3 Announce Type: replace-cross Abstract: This paper evaluates the current gaze estimation methods within a human-robot interaction (HRI) context of a shared workspace scenario. We introduce a new, annotated dataset collected with the NICO robotic platform. We evaluate four state-of-the-art gaze estimation models. The evaluation shows that the angular errors are close to those reported on general-purpose benchmarks. However, when expressed in terms of distance in the shared workspace the best median error is 14.57~cm, quantifying the practical limitations of current methods. We conclude by discussing these limitations and offering recommendations on how to best integrate gaze estimation as a modality in HRI systems.
Abstract:This paper evaluates the current gaze estimation methods within a human-robot interaction (HRI) context of a shared workspace scenario. We introduce a new, annotated dataset collected with the NICO robotic platform. We evaluate four state-of-the-art gaze estimation models. The evaluation shows that the angular errors are close to those reported on general-purpose benchmarks. However, when expressed in terms of distance in the shared workspace the best median error is 14.57~cm, quantifying the practical limitations of current methods. We conclude by discussing these limitations and offering recommendations on how to best integrate gaze estimation as a modality in HRI systems.
Code available at this http URL data available at: this https URL. Accepted to appear in the proceedings of ICETA 2026
Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
arXiv:2509.24001 [cs.CV]
(or arXiv:2509.24001v3 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2509.24001 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 217 words
