Author: Massimiliano Cappuccio
Cappuccio, Massimiliano, 2025 The Role of Embodiment in Human-Robot Interaction: Modelling Attentional Behaviours through Cognitive Neuro-Robotics, Flinders University, College of Science and Engineering
Terms of Use: This electronic version is (or will be) made publicly available by Flinders University in accordance with its open access policy for student theses. Copyright in this thesis remains with the author. You may use this material for uses permitted under the Copyright Act 1968. If you are the owner of any included third party copyright material and/or you believe that any material has been made available without permission of the copyright owner please contact copyright@flinders.edu.au with the details.
Robot cognition is fundamentally embodied. I articulate this idea in three domains of skilful expertise: sensorimotor skills, concerning the preconditions for competent autonomous or team-based action; social skills, concerning robots’ ability to interact meaningfully with humans, gain trust, and build lasting relationships; and moral/pedagogical skills, concerning how robots can promote human self-improvement and learning. I focus on the embodiment of attentional behaviours (eye contact, gaze following, joint attention) in their action-guiding, communicative, and moralizing roles. Attention, I contend, is not an abstract intellectual stance but a concrete form of engagement strictly tied to physical presence, poise, and behaviour. My “bottom-up” approach is inspired by enactivist robotics. By combining computational models, literature review, and experimental data, I show that correctly understanding human and robotic attention is crucial to design successful human-robot interactions.
Keywords: social robotics, human-robot interaction, human-computer interaction, attention, autistic spectrum disorder, cognitive robotics, enactive cognition, embodied cognition, embodiment, trust, acceptance, technology resistance, developmental robotics, virtue ethics, synthetic methods, skill & expertise, action control
Subject: Computer Science thesis
Thesis type: Doctor of Philosophy
Completed: 2025
School: College of Science and Engineering
Supervisor: Richard Leibbrandt