Embodied contextual agent in information delivering application

Abstract

We aim at building a new human-computer interface for Information Delivering applications: the conversational agent that we have developed is a multimodal believable agent able to converse with the User by exhibiting a synchronized and coherent verbal and nonverbal behavior. The agent is provided with a personality and a social role, that allows her to show her emotion or to refrain from showing it, depending on the context in which the conversation takes place. The agent is provided with a face and a mind. The mind is designed according to a BDI structure that depends on the agent's personality; it evolves dynamically during the conversation, according to the User's dialog moves and to emotions triggered as a consequence of the Interlocutor's move; such cognitive features are then translated into facial behaviors. In this paper, we describe the overall architecture of our system and its various components; in particular, we present our dynamic model of emotions. We illustrate our results with an example of dialog all along the paper. We pay particular attention to the generation of verbal and nonverbal behaviors and to the way they are synchronized and combined with each other. We also discuss how these acts are translated into facial expressions.

Psychological responses to simulated displays of mismatched emotional expressions

“…A wide variety of embodied agents that exhibit human-like emotion have been developed over recent years including Cosmo (Lester et al, 1997) and Herman the Bug (Lester et al, 1999), Gandalf (Thorisson, 1999), Steve Johnson, 1999), PPP Persona (Van Mulken et al, 1998), MACK (Cassell et al, 2002), REA (Bickmore and Cassell, 2001), Olga (Beskow and Mcglashan, 1997) and Laura (Bickmore, 2003). Such agents are used in a wide range of domains including educational applications (Maldonado et al, 2005;Johnson et al, 2000), military simulations (Marsella et al, 2004), behaviour change systems (De Rosis et al, 2004;Ruttkay et al, 2006), computer games (Isbister, 2006), presenting (Prendinger et al, 2004;Bos et al, 2006), as companions whilst browsing the web (Hook, 2004), and as information providers (Pelachaud et al, 2002).…”

Social signal processing: Survey of an emerging domain

“…doi:10.1016/j.imavis.2008. 11.007 begin to do the same by employing tools that can accurately sense and interpret social signals and social context of the pupil, learn successful context-dependent social behaviour, and use a proper socially adept presentation language (see, e.g., [141]) to drive the animation of the agent. The research area of machine analysis and employment of human social signals to build more natural, flexible computing technology goes by the general name of socially aware computing as introduced by Pentland [142,143].…”

“She is just stupid”—Analyzing user–agent interactions in emotional game situations

“…To realize the game, the Greta agent system (Pelachaud et al, 2002) was employed. It features a full body agent which is MPEG-4 compliant and thus allows for realistic facial expressions and gesture animation.…”

“…Thus, embodied conversational agents offer great promise to more natural interaction in social settings like tutoring or gaming. Prominent examples of such agent systems include the Steve Agent (Rickel and Johnson, 1999), the real estate agent REA (Cassell et al, 2000), the GRETA Medical Advisor (Pelachaud et al, 2002), the agent MAX (Kopp et al, 2003), the virtual patient (Hubal and Day, 2006) or the tactical language training agent (Core et al, 2006).…”