Design and Evaluation of a Nonverbal Communication Platform between Assistive Robots and their Users

Abstract

Assistive robotics will become integral to the everyday lives of a human population that is increasingly mobile, older, urban-centric and networked. The overwhelming demands on healthcare delivery alone will compel the adoption of assistive robotics. How will we communicate with such robots, and how will they communicate with us? This research makes the case for a relatively "artificial" mode of nonverbal human-robot communication that is non-disruptive, non-competitive, and non-invasive human-robot communication that we envision will be willingly invited into our private and working lives over time. This research proposes a nonverbal communication (NVC) platform be conveyed by familiar lights and sounds, and elaborated here are experiments with our NVC platform in a rehabilitation hospital. This NVC is embedded into the Assistive Robotic Table (ART), developed within our lab, that supports the well-being of an expanding population of older adults and those with limited mobility. The broader aim of this research is to afford people robot-assistants that exist and interact with them in the recesses, rather than in the foreground, of their intimate and social lives. With support from our larger research team, I designed and evaluated several alternative modes of nonverbal robot communication with the objective of establishing a nonverbal, human-robot communication loop that evolves with users and can be modified by users. The study was conducted with 10-13 clinicians-doctors and occupational, physical, and speech therapists-at a local rehabilitation This work would not have been made possible without Jessica Merino. Jessica is more than a colleague and friend-she has become family. Thank you for your efforts, your insights, your guidance, and your willingness to always push me and this work to its greatest possible conclusion.

An Interdisciplinary Capstone Project in Assistive Robotics

“…1 For unskilled or impaired users, as may be present in an aging population, models of nonverbal communication with intelligent assistive agents offer the promise of intuitive and adaptive interaction. 2 Command interfaces based on hand/arm gesture (static and dynamic), eye gaze, or voice, present options for nonverbal communication which would be easily adopted by this target population. Typically, Human-Robot Interaction (HRI), regardless of the command form, depends on a command language which is predefined by the system designers.…”