Modeling an Adaptive Resident-System Interaction for Cognitive Assistance in Ambient Assisted Living

In the last decade, advances in the field of ambient assisted living (AAL) have changed the way services can be provided in smart homes. New possibilities are now offered for addressing complex interaction problems between the technology and users with special needs. Within this context, this study addresses human-computer interactions for cognitive assistance to people with Traumatic Brain Injury (TBI). Interdisciplinary research combining computer science and occupational therapy was conducted to model the interaction between an AAL system (AALS) and a person with cognitive impairments due to TBI residing in an AAL environment. Cognitive assistance is modelled as an interactive exchange where an AALS spreads assistance cues that should induce appropriate behaviours from an assisted person as responses. After an assistance cue is delivered, the AALS should evaluate the user reaction and, stop the interaction if the intended reaction is observed or resume by adapting the assistance. To do so, evidence-based cognitive rehabilitation and speech acts are used to model the interaction content i.e., assistive cues and user feedback, while an ontology formalizes the semantics of this knowledge in a computer readable format. A behavioural model based on behaviour trees informed by the ontological model is then used to enable the cognitive assistant to plan the sequence of cues to be delivered adaptively depending on the circumstances, the assistance goal and the user's behaviour. To show that the proposed interaction model can help an AALS to provide adaptive assistance to people with cognitive impairments, it is exemplified on a cooking safety assistant designed for people with TBI.