Human-Centred Robotics and AI for Trustworthy Human-Robot Interaction

Angelo Cangelosi, Manith Adikari, Rahul Singh Maharjan, Luca Raggioli, Francesco Semeraro, Radu Stoican, Federico Tavella, Hongbo Zhu, Marta Romeo

Abstract: This chapter provides an overview of the potential applications of robotics and AI models in a diverse set of domains. These applications range from social assistive robots for health and social care, to manufacturing scenarios with human-robot collaboration, and in the field of education. The chapter also considers two important issues for the design of human-centred, ethical and trustworthy robots: the concepts of trust based on Theory of Mind, and the use of explainable AI (XAI) methods in human-robot interaction. Trust is a multifaceted and complex construct which concerns both performance-based trust, i.e., the trust in a robot’s ability to complete a task consistently, and relation-based trust, i.e., trust that the robot will comply with social norms. The studies presented show the importance of modelling Theory of Mind (ToM) when studying trust, analysing both people’s ToM of the social robots’ capabilities and goal, robot’s artificial ToM when reading the intention and goals of their human users. XAI methods allows the human user to have access to the robot’s decision-making mechanisms based on AI and ML algorithms.

External IDs:doi:10.1007/978-3-031-97673-5_9