BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Vrije Universiteit Amsterdam//NONSGML v1.0//EN NAME:PhD defence C.L. Cheng METHOD:PUBLISH BEGIN:VEVENT DTSTART:20261019T114500 DTEND:20261019T131500 DTSTAMP:20261019T114500 UID:phd-defense-c-l-cheng@8F96275E-9F55-4B3F-A143-836282E12573 CREATED:20261015T082852 LOCATION:Main building VU, 1105, Auditorium, De Boelelaan, 1081 HV, Amsterdam SUMMARY:PhD defence C.L. Cheng X-ALT-DESC;FMTTYPE=text/html:

Gaze estimation for social robotics: Bridging the gap: Appearance-based gaze estimation m odels for human-robot interaction

Robots Can Reco gnize Human Eye Contact Using a Standard Camera

Socia l robots can estimate the direction of a person’s gaze fairly accur ately using only a standard camera. This does not require expensive, specialized eye-tracking equipment. This is according to research by robotics researcher Linlin Cheng on appearance-based gaze estimat ion for human-robot interaction.

The technology can determ ine whether someone is looking at a robot, for example, or at a task in front of them. This works particularly well at a distance of about one to two meters. The research also shows that a robot equipped wit h inexpensive cameras can recognize when someone has completed a task —for example, when the person shifts their gaze away from the task.

The technology still has limitations. Quick glances and sudden shifts in attention are more difficult to detect. As a result, the m ethod is primarily suited for observing general attention patterns an d less so for precisely tracking every eye movement.

The result s could make the use of social robots in everyday life more accessibl e. Since only a standard camera is required, the costs and technical complexity can be lower than with systems using specialized eye track ers. This is relevant, for example, for care robots in hospitals, rob ots in education, and assistive robots in the workplace.

For ex ample, a care robot could recognize whether an elderly person is look ing at a pill organizer or is distracted, and adjust its behavior acc ordingly. In a work environment, a robot could detect from a shift in gaze that someone has completed a task.

This research thus bri ngs robots one step closer to natural interaction in environments whe re people and robots work and live together. At the same time, furthe r research is needed to ensure the technology works reliably during r apid movements and in a wide range of real-world situations.

Mo re information about the d issertation

DESCRIPTION: Gaze estimation for social robotics: Bridging the gap: Ap pearance-based gaze estimation models for human-robot interaction

Robots Can Recognize Human Eye Contact Using a Standard Came ra

Social robots can estimate the direction of a person� ��s gaze fairly accurately using only a standard camera. This does no t require expensive, specialized eye-tracking equipment. This is acco rding to research by robotics researcher Linlin Cheng on appearan ce-based gaze estimation for human-robot interaction.The technol ogy can determine whether someone is looking at a robot, for example, or at a task in front of them. This works particularly well at a dis tance of about one to two meters. The research also shows that a robo t equipped with inexpensive cameras can recognize when someone has co mpleted a task—for example, when the person shifts their gaze away from the task.The technology still has limitations. Quick glances and sudden shifts in attention are more difficult to detect. As a result , the method is primarily suited for observing general attention patt erns and less so for precisely tracking every eye movement.The result s could make the use of social robots in everyday life more accessibl e. Since only a standard camera is required, the costs and technical complexity can be lower than with systems using specialized eye track ers. This is relevant, for example, for care robots in hospitals, rob ots in education, and assistive robots in the workplace.For example, a care robot could recognize whether an elderly person is looking at a pill organizer or is distracted, and adjust its behavior accordingl y. In a work environment, a robot could detect from a shift in gaze t hat someone has completed a task.This research thus brings robots one step closer to natural interaction in environments where people and robots work and live together. At the same time, further research is needed to ensure the technology works reliably during rapid movements and in a wide range of real-world situations.More information about the dissertation END:VEVENT END:VCALENDAR