The population of the world is rapidly aging and there is presently an increasing demand for residential care facilities to provide care for older adults. Understimulation can be a major concern in such facilities due to high resident-to-staff ratios and a decreasing number of healthcare staff to facilitate cognitive, social, and physical activities for older adults. Currently, socially assistive robots are being developed to assist in providing such stimulation. However, the existing robots are limited to only facilitating a set of activities that have been pre-programmed on the robot and cannot be customized to the needs of a facility. Furthermore, the majority consider only one-on-one activities, rather than providing stimulation to groups of users at the same time. This thesis focused on developing a learning based interaction system for socially assistive robots to:​ 1) autonomously facilitate multi-user activities while providing individualized assistance;​ 2) learn new customized activities from caregivers;​ and 3) personalize robot assistive behaviours to obtain user compliance.

Numerous human-robot interaction experiments were conducted with the system integrated into the socially assistive robot Tangy for the multi-user activity of Bingo. The participants for the experiments consisting of caregivers and older adults. The results showed that:​ 1) participants had positive attitudes towards interacting with the robot and found it easy to use, 2) older adults were engaged during the activity and complied with the robotâ s behaviours, and 3) caregivers were able to successfully teach a new activity to the robot with moderately low perceived workload.