Towards a logic-based approach for multi-modal fusion and decision making during motor rehabilitation sessions

We introduce a general approach which aims at combining machine learning and logic-based techniques in order to model its user’s cognitive and motor abilities. In the context of motor rehabilitation, hybrid systems are a convenient option as they allow both for the representation of formal constraints needed to implement a clinically valid exercise, and for the statistical modelling of intrinsically noisy data sources. Moreover, logic-based systems offer a transparent way to look at the decisions taken by an automated system. This is particularly useful when an AI system needs to interact with a therapist in order to assist therapeutic intervention, e.g. by explaining why a given decision is sound. This methodology is currently being developed within the context of the AVATEA project.