As a part of National Robotics Week, Dr. Cindy Bethel of Yale University will present her work on "Non-Facial and Non-Verbal Affective Expression for Appearance-Constrained Robots" at the UMass Lowell Computer Science Department Colloquium Series on Wednesday, April 14, from 3-4pm in Olsen Hall, Room 311. Please join us!

Faculty host: Prof. Holly Yanco

Abstract: Non-facial and non-verbal methods of affective expression are essential for naturalistic social interaction in robots that are designed to be functional and lack expressive faces (appearance-constrained) such as those used in search and rescue, military, industry, and law enforcement applications. This research identifies five main methods of non-facial and non-verbal affective expression (body movements, postures, orientation, color, and sound) and ranks their effectiveness for appearance-constrained robots operating within the intimate (contact through 0.46 m), personal (0.46 through 1.22 m), and social (1.22 through 3.66 m) proximity zones of a human corresponding to inter-agent distances of approximately three meters or less. This leads to design recommendations for retroactively adding affective expression through software to a robot with little or no physical modifications or the need for designing a new robot.

To confirm that humans respond more favorably to an affective appearance-constrained robot, a study was conducted with 128 participants and two robots (iRobot Packbot and an Inuktun Extreme) in a high fidelity simulated disaster site. Four methods of evaluation were utilized: (1) self-assessments, (2) psychophysiological measures (EKG, abdominal respiration, thoracic respiration, blood volume pulse, skin conductance response), (3) video recording from four different camera perspectives that will later be coded for behavioral responses, and (4) an audio recorded follow-up interview. This is the largest and most comprehensive controlled study performed in Human-Robot Interaction (HRI). Details of the study design, implications for HRI and robot design, results, and video will be presented.

Brief Bio: Dr. Bethel is an NSF/CRA/CCC Computing Innovation Postdoctoral Fellow and Postdoctoral Associate at Yale University. She is currently working with Dr. Brian Scassellati of Yale University as her fellowship mentor. She was a National Science Foundation Graduate Research Fellow and the recipient of the 2008 IEEE Robotics and Automation Society Fellowship.

She graduated in August 2009 with her Ph.D. in Computer Science and Engineering from the University of South Florida. Her research interests are in Human-Robot Interaction (HRI), affective computing, robotics, Human-Computer Interaction (HCI), artificial intelligence, and experimental design for HRI. She graduated with a B.S. in Computer Science Summa Cum Laude from the University of South Florida. She was awarded the King ONeal Scholar award, the Computer Science and Engineering Outstanding Graduate Award, and the Engineering Alumni Society Outstanding Senior of the Year Award.