The RESTART project aims at designing and developing a new human-robot interactive paradigm, in which the robot is humanized thanks to empowered AI-based social and cognitive abilities based on the concept of theory of mind and mutual-understanding in order to improve the acceptability of robots especially in assistance scenarios, where higher legibility and conformity to cognitive and emotional aspects of the social interaction are required.

Project Hypothesis

The possibility to model and adapt to users' mental models coupled with the identity of the robot will help to align the mismatch between users’ expectation and robots’ capabilities by increasing in turn robot behavior predictability and acceptance 

Project Proposal

Robots should be able to manage different forms of reasoning, according to the knowledge they have of the world, planning their interaction as a set of activities over time, adapting them based on the contextual information that dynamically emerges from the interaction with the users, while pursuing the objectives to have a realistic and natural interaction.

Proof of Concept

Our proposal is to employ an AI-powered humanized social robot for providing alternatives to the traditional CT treatment through an adaptive cognitive and social stimulation of PD patients based on the comprehension and the alignment of the mental models of the human users and on a proper balance between robot adaptivity and understandability.