← Back to all news
arXiv Computer Vision By Matej Palider, Omar Eldardeer, Viktor Kocur

Gaze Estimation for Human-Robot Interaction: Analysis Using the NICO Platform

Read the original on arXiv Computer Vision →

This paper evaluates current gaze estimation methods in a human‑robot interaction setting using the NICO robotic platform. A new annotated dataset was collected, and four state‑of‑the‑art models were tested, showing angular errors comparable to general benchmarks. In the shared workspace, the best median error was 14.57 cm, highlighting practical limitations and prompting recommendations for integrating gaze estimation into HRI systems.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Aug 28

Gaze Authentication: Factors Influencing Authentication Performance

This paper investigates how key factors affect the performance of gaze-based authentication systems. Using a large in-house dataset of 8,849 subjects recorded with Meta Quest Pro–equivalent hardware and a 72 Hz video oculography pipeline, the study evaluates the impact of eye‑tracking signal quality, calibration settings, and simple filtering on neural‑network‑based authentication. The authors present performance results and an analysis of these influences.

By Dillon Lohr, Michael J Proulx, Mehedi Hasan Raju, Oleg V Komogortsev
benchmarks
More like this →