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 reidentify 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 i...

• Type: Conference
• Year: 2008
• Where: ATAL
• Authors: Daniel Schulman, Mayur Sharma, Timothy W. Bickmore
• Keywords: ATAL 2008, Biometric Identification, Intelligent Agents, Relational Agents, User