Interface Design for Learning from Demonstration with Older Adults

Abstract

Assistive in-home robots have the potential to enable older adults to age in place, by allowing older adults to offload mentally and physically demanding tasks to a robot. However, one challenge for in-home robots is that each individual will have differing needs, preferences, and home environments, which all change over time. Learning from Demonstration (LfD) is one solution to enable non-expert users to communicate their differing and changing needs and preferences to a robot, but LfD is underexplored with a population of older adults. We aim to develop a user interface that is intuitive for older adults and facilitates their ability to teach a robot via LfD. In this paper, we conduct a human-subjects experiment to evaluate the usability of a robot manipulation and recording interface with a target population of older adults. Additionally, we propose a full study with a robot to understand the feasibility of LfD for older adults.