Publication
Adaptive Gaze Modulation in Social Robots: A Reinforcement Learning Approach to Attention Regulation
In this paper, we present a novel framework for robotic attention modulation that enables dynamic regulation between attention-seeking and attention-avoidance behaviours through gaze feedback. For this feedback, we incorporate SGE with gaze fixation counts to create a metric that evaluates not just the quantity but also the quality of visual attention. Our approach implements two complementary modules, a Gaze Avoidance Module (GAM) and a Gaze Garnering Module (GGM), both powered by reinforcement learning (RL) algorithms that respond to real-time human gaze patterns. Thus the system continuously adapts to each individual’s current gaze feedback level, dynamically calibrating the robot’s attention-modulating behaviours to match personal attention thresholds. This personalisation ensures that the robot can effectively engage with users when needed, while remaining unobtrusive when appropriate, all based on real-time analysis of human gaze patterns.

Nipuni Wijesinghe
CRL Administrative, Communications & Marketing Coordinator
Nipuni Wijesinghe is a PhD student in the Faculty of Science and Technology at the University of Canberra, with a background in computer science. My research interests are centred around the fields of embodied AI, social presence, and the modulating presence of embodied systems. Through my work, I aim to explore and enhance the interactions between humans and robotic systems, particularly in healthcare settings.
More
Maleen Jayasuriya
Staff
Maleen Jayasuriya is a Lecturer in Robotics at the University of Canberra’s Faculty of Science and Engineering with a research focus on human-robot interaction and explainable AI (XAI) in robotics. Maleen holds a Bachelor’s degree in Electrical and Electronic Engineering from Sri Lanka and a PhD from the University of Technology Sydney, where his research focused on robot perception, localisation, and deep learning. He later completed a postdoctoral fellowship at UTS, contributing to research on collaborative robotics for sustainable construction.
More
David Hinwood
Research Student
Dr David Hinwood is an award-winning multidisciplinary researcher specialising in robot design, human-robot interaction, and machine-learning applications. He is the first PhD graduate from the University of Canberra’s Collaborative Robotics Lab with seven years of development experience in research and robotics deployments. Areas of technical experience include ROS development (C++/Python), motion planning, and data-driven techniques for perception and control.
More
Janie Busby Grant
Psychology Research Lead
Associate Professor Janie Busby Grant is the Psychology Research Lead at CRL, where her work integrates human-robot interaction and artificial intelligence with a foundation in cognitive psychology and research design. With a strong emphasis on practical applications, Janie brings a reconciliatory approach to interdisciplinary research, particularly in exploring factors influencing human perception of, and engagement with robotic systems.
More
Damith Herath
Founder/Director Collaborative Robotics Lab
Professor Damith Herath is the Founder and director of the Collaborative Robotics Lab (CRL). His work explores how robots and humans can collaborate, with an emphasis on the intersection of engineering, psychology, and the arts. His interdisciplinary approach actively seeks insights across diverse fields, promoting innovation and collaboration that transcends traditional disciplinary boundaries.
More
N. H. Wijesinghe, M. Jayasuriya, D. Hinwood, J. B. Grant and D. Herath, “Adaptive Gaze Modulation in Social Robots: A Reinforcement Learning Approach to Attention Regulation,” 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hangzhou, China, 2025, pp. 9217-9222, doi: 10.1109/IROS60139.2025.11247106. keywords: {Measurement;Visualization;Social robots;Reinforcement learning;Regulation;Real-time systems;Trajectory;Indexes;Reliability;Intelligent robots},