CORAL: A Cognitively Assistive Robot for Personalized Neurorehabilitation at Home

Cognitively assistive robots (CARs) have great potential to extend the reach of clinical interventions to the home. Due to the wide variety of cognitive abilities and rehabilitation goals, it is critical that these systems are flexible and adaptable in order to support rapid and accurate implementation of intervention content that is grounded in existing clinical practice. To this end, we detail the system architecture of CORAL (COgnitively assistive Robot for Adaptation and Learning), an adaptable robot system we developed in collaboration with our key stakeholders: clinicians and people with mild cognitive impairment (PwMCI). We implemented a well-validated compensatory cognitive training (CCT) intervention on CORAL, which it autonomously delivers to PwMCI. We deployed CORAL in the homes of these stakeholders in order to evaluate and gain initial feedback on the system. Our findings inform how HRI researchers can design more longitudinal and autonomous CARs for cognitive interventions. Furthermore, we will release elements of CORAL as open source to support flexible and adaptable home-deployed robots. Thus, CORAL will enable the HRI community to deploy quality interventions to robots, and ultimately increase the accessibility and extendability of these interventions.