Virtual Human Interfaces
Marve: A Prototype Virtual Human Interface Framework for Studying Human-Virtual Human Interaction
Human to virtual human interaction is the next frontier in interface design, particularly for tasks that are social or collaborative in nature. Several embodied interface agents have been developed for specific social, place-related tasks, but empirical evaluations of these systems have been rare. In this work, we present Marve (Messaging And Recognition Virtual Entity), our general purpose Virtual Human Interface Framework, which integrates cutting-edge interface technologies into a seamless real-time system, to study human to virtual human interaction. Marve is a prototype of a real-time embodied, interactive, autonomous, virtual human interface agent framework. Marve “lives?next to the primary entrance of the Future Computing Lab. His primary tasks are to greet everyone who enters or leaves the lab, and to take and deliver messages to the students and faculty who work there. Marve uses computer vision techniques for passer-by detection, gaze tracking, and face recognition, and communicates via natural language. We present a preliminary empirical study of the basic elements of Marve, including interaction response times, recognition of friends, and ability to learn to recognize new people.
Screenshots of Marve greeting a user, and interacting with a user.
Babu, S., Schmugge, S., Inugala, R., Rao, S., Barnes, T., Hodges, L.F. (2005). Marve: a prototype virtual human interface framework for studying human-virtual human interaction. in Springer Lecture Notes on Aritifical Intelligence LNAI, (T. Panayiotopoulos et al.(Eds.) Springer-Verlag). [PDF]
"What Would You Like to Talk About?" An Evaluation of Social Conversations with a Virtual Receptionist
We describe an empirical study of Marve, a virtual receptionist located at the entrance of our research laboratory. Marve engages with lab members and visitors in natural face-to-face communication, takes and delivers messages, tells knock-knock jokes, conducts natural small talk on movies, and discusses the weather. In this research, we investigate the relative popularity of Marve’s social conversational capabilities and his role-specific messaging tasks, as well as his perceived social characteristics. Results indicate that users are interested in interacting with Marve, use social conversational conventions with Marve, and perceive and describe him as a social entity.
Screenshot of Marve showing the menu of topics of conversation to a user.
Screenshot of Marve telling a knock-knock joke and gesturing a knock to the user.
Video Link: http://suntel01.uncc.edu/sbabu/webstuff/finalMarve.mp4 (Please use QuickTime from http://www.apple.com/quicktime/win.html)
Babu, S., Schmugge, S., Barnes, T., Hodges, L.F. (2006). "What Would You Like to Talk About?" An Evaluation of Social Conversations with a Virtual Receptionist. in Springer Lecture Notes on Aritifical Intelligence LNAI, (T. Gratch et al.(Eds.) Springer-Verlag). [PDF]
Virtual Human Physiotherapist Framework for Personalized Training and Rehabilitation
We present a framework that employs a Virtual Human Physiotherapist (VHP) towards personalized training and rehabilitation. The VHP is an inexpensive alternative to training with a real person. Using a virtual human for training allows the user to train on their own schedule and in the privacy of their own homes. In addition, the gender, race and age of the virtual human can be altered to match the needs of the user, making the user more comfortable in interacting with the VHP. Finally, the VHP provides a uniform and accurate training experience. Unlike real people, virtual humans are not affected by having a bad day or being tired. The VHP is always happy and ready to assist the user in training for a particular exercise. There is also no limit on the amount times the user can repeat an exercise.
S. Babu, C. Zanbaka, J. Jackson, T-O. Chung, B. Lok, M. C. Shin, and L. F. Hodges (2005). "Virtual Human Physiotherapist Framework for Personalized Training and Rehabilitation," Short Paper Graphics Interface 2005, Victoria, British Columbia, Canada, May 9 - 11, 2005. [PDF]
Officer Garcia: A Virtual Human for Mediating Eyewitness Identification
An analysis of court cases has revealed that the mistaken identification of the wrong person by victims and witnesses of a crime is the single most common error leading to the arrest and conviction of innocent people. Recognizing the role of mistaken identification in erroneous conviction, a growing number of states and police departments have reformed their eyewitness identification procedures. We investigate a new procedural reform: the use of a virtual officer who does not know the identity of the suspect in the lineup and therefore cannot bias the witness toward false identification.
Daugherty, B., Babu, S., Cutler, B., and Hodges, L. F. (2008). “Comparison of Virtual Human versus Human Administration of Police Lineups”, in the IEEE Journal on Computer Graphics and Applications (IEEE CG&A), selected based on top 5 best papers of ACM Symposium on Virtual Reality Software and Technology 2007. [PDF]
Daugherty, B., Babu, S., Cutler, B., and Hodges, L. F. (2007). “Officer Garcia: A Virtual Human for Mediating Eyewitness Identification”, in the Proceedings of ACM Symposium on Virtual Reality Software and Technology, p. 117 – 120, Newport Beach, CA, Nov 5-7, 2007. [PDF]