Nonverbal Action Selection for Explanations Using an Enhanced Behavior Net

In this paper we present a novel approach to the nonverbal action selection problem for an agent in an intelligent tutoring system. We use a variation of the original Maes' Behavior Net that has several improvements that allow modeling action selection using the content of the utterance, communicative goals, and the discourse history. This Enhanced Behavior Net can perform action selection dynamically, reprioritize actions based on all these elements, and resolve conflict situations without the use of sophisticated predefined rules.

[1]  P. Maes.  How to Do the Right Thing , 1989 .

[2]  Hans-Peter Seidel,et al.  Annotated New Text Engine Animation Animation Lexicon Animation Gesture Profiles MR : . . . JL : . . . Gesture Generation Video Annotated Gesture Script , 2007 .

[3]  Toby Tyrrell,et al.  Computational mechanisms for action selection , 1993 .

[4]  Betsy Williams Sanders,et al.  Examining the Role of Gestures in Expert Tutoring , 2010, Intelligent Tutoring Systems.

[5]  Jacques Ferber,et al.  Action selection in an autonomous agent with a hierarchical distributed reactive planning architecture , 1998, AGENTS '98.

[6]  Jacqueline Bourdeau,et al.  Advances in Intelligent Tutoring Systems , 2010 .

[7]  W. Lewis Johnson,et al.  Animated Agents for Procedural Training in Virtual Reality: Perception, Cognition, and Motor Control , 1999, Appl. Artif. Intell..

[8]  Stacy Marsella,et al.  Nonverbal Behavior Generator for Embodied Conversational Agents , 2006, IVA.

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

[10]  R. Atkinson.  Optimizing learning from examples using animated pedagogical agents. , 2002 .

[11]  Arthur C. Graesser,et al.  Tutorial Dialog in Natural Language , 2010, Advances in Intelligent Tutoring Systems.

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

[13]  K. VanLehn,et al.  Scaffolding Deep Comprehension Strategies Through Point&Query, AutoTutor, and iSTART , 2005 .

[14]  Punya Mishra,et al.  RUNNING HEAD: PEDAGOGICAL SOFTWARE AGENTS All or Nothing: Levels of Sociability of a Pedagogical Software Agent and its Impact on Student Perceptions and Learning , 2005 .

[15]  P. Maes.  Modeling adaptive autonomous agents , 1993 .

[16]  Stefan Kopp,et al.  GNetIc - Using Bayesian Decision Networks for Iconic Gesture Generation , 2009, IVA.

[17]  Stan Franklin,et al.  An action selection mechanism for "conscious" software agents , 2002 .

[18]  James C. Lester,et al.  Achieving Affective Impact: Visual Emotive Communication in Lifelike Pedagogical Agents , 1999 .