Gaze Estimation for Human-Robot Interaction: Analysis Using the NICO Platform
This work addresses practical limitations of gaze estimation for human-robot interaction systems, but it is incremental as it focuses on evaluation and dataset introduction without proposing new methods.
The paper evaluated state-of-the-art gaze estimation methods in a human-robot interaction context, finding that while angular errors were comparable to benchmarks, the best median error in practical workspace distance was 16.48 cm, highlighting limitations.
This paper evaluates the current gaze estimation methods within an 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 16.48 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.