Context-Aware Assistive Interfaces for Persons with Severe Motor Disabilities

Abstract

Persons with severe motor disabilities have a great need for assistive robots, but also struggle to communicate these needs in ways that a robot can understand. I propose an interface that will make it possible to communicate with robots using limited movements. This will be done using contextual information from the robot's semantic model of the world. I also describe the state-of-the-art hardware and personal collaborations that equip our lab for this research. Assistive robotic interfaces also evoke concerns that a robot could violate personal privacy expectations, particularly if a remote operator can see the robot's video stream. This is especially important for persons with disabilities because it may be harder for them to monitor the robot's whereabouts. I describe ongoing work on two interfaces that help make it possible for robots to be privacy conscious. Answers for privacy concerns need to be developed alongside the new interface technologies prior to in-home deployment.