The identification of users by relational agents

Virtual agents designed to establish relationships with more than one user must be able to identify and distinguish among those users with high reliability. We describe an approach for relational agents in public spaces to identify repeat users based on two strategies: a biometric identification system based on hand geometry, and an identification dialogue that references previous conversations. The ability to re-identify visitors enables the use of persistent dialogue and relationship models, with which the agent can perform a range of behaviors to establish social bonds with users and enhance user engagement. The agent's dialogue encourages users towards repeat visits, and provides mechanisms of recovery from identification errors, as well as contextual information which may be used to improve the accuracy of the biometric identification. We have implemented and evaluated this identification system in a virtual guide agent for a science museum that is designed to conduct repeated and continuing interactions with visitors. We also present the results of a preliminary evaluation of the system, including user opinions of this technology, and of the effect of identification, both successful and unsuccessful, on acceptance and engagement of the agent.

[1]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[2]  Stefan Kopp,et al.  A Conversational Agent as Museum Guide - Design and Evaluation of a Real-World Application , 2005, IVA.

[3]  E. Goffman.  On face-work; an analysis of ritual elements in social interaction. , 1955, Psychiatry.

[4]  Mircea Nicolescu,et al.  Peg-Free Hand Shape Verification Using High Order Zernike Moments , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[5]  Herbert H. Clark,et al.  Grounding in communication , 1991, Perspectives on socially shared cognition.

[6]  Jonathan Klein,et al.  This computer responds to user frustration: Theory, design, and results , 2002, Interact. Comput..

[7]  Pengcheng Shi,et al.  Peg-Free Hand Geometry Recognition Using Hierarchical Geomrtry and Shape Matching , 2002, MVA.

[8]  Geri Gay,et al.  Beyond just the facts: transforming the museum learning experience , 2006, CHI EA '06.

[9]  Alexander J. Smola,et al.  Advances in Large Margin Classifiers , 2000 .

[10]  Takayuki Kanda,et al.  Interactive Humanoid Robots for a Science Museum , 2006, IEEE Intelligent Systems.

[11]  Sharath Pankanti,et al.  A Prototype Hand Geometry-based Verication System , 1999 .

[12]  Kate S. Hone,et al.  Empathic agents to reduce user frustration: The effects of varying agent characteristics , 2006, Interact. Comput..

[13]  Youngme Moon,et al.  This Computer Responds to User Frustration Theory, Design, Results, and Implications , 2002 .

[14]  Stephanie D. Teasley,et al.  Perspectives on socially shared cognition , 1991 .

[15]  E. Goffman.  Interaction Ritual: Essays on Face-To-Face Behavior , 1967 .

[16]  Justine Cassell,et al.  BEAT: the Behavior Expression Animation Toolkit , 2001, Life-like characters.

[17]  Timothy W. Bickmore,et al.  Establishing and maintaining long-term human-computer relationships , 2005, TCHI.

[18]  Jon Hindmarsh,et al.  Engaging constable: revealing art with new technology , 2007, CHI.

[19]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[20]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[21]  Arun Ross,et al.  An introduction to biometric recognition , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[22]  Stephanie Rosenthal,et al.  Designing robots for long-term social interaction , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[23]  Yukiko I. Nakano,et al.  MACK: Media lab Autonomous Conversational Kiosk , 2002 .