ABSTRACT
Affective interaction between a user and a virtual agent must be believable. The virtual actor has to behave properly, to have the capacity to talk in natural language and to express some affectivity. For achieving this goal, it is basic to provide the agent with intelligence to let him make all kind of real-time decisions in complex situations. In this paper, an architecture for the user interaction with intelligent affective multimodal virtual agents in uncertain environments is proposed. It is based on the integration of Maxine, a powerful multimodal animation engine for managing virtual agents and 3D scenarios, and PROPHET, a cognitive intelligent system based on Fuzzy Logic. The outstanding features of the proposed architecture are its affective and intelligence capabilities that make the system able to cope with decisions based on the analysis and learning of information and perceptions coming from uncertain environments.
- Cassell, J., Sullivan, J., Prevost, S. and Churchill E. 2000. Embodied conversational agents. Cambridge, MIT Press.Google Scholar
- Canny, J. 2006. The future of human-computer interaction. ACM Queue, Vol. 4, No. 6 (Jul./Aug. 2006). Google ScholarDigital Library
- Pantic, M. and Bartlett, M. S. 2007. Machine Analysis of Facial Expressions. Face Recognition. K. Delac and M. Grgic, Eds. I-Tech Education and Publishing, Vienna, Austria, 377--416.Google Scholar
- Jaume-i-Capó, A., Varona, J. and Perales, F. J. 2006. Interactive applications driven by human gestures. Ibero-American Symposium on Computer Graphics (Santiago de Compostela, Spain, Jul. 2006).Google Scholar
- Cowie, R., Douglas-Cowie, E. and Schroeder, M. 2000. ICSA Workshop on Speech and Emotion: a Conceptual Framework for Research (Belfast).Google Scholar
- Egges, A., Kshirsagar, S. and Magnenat-Thalmann, N. 2004. Generic personality and emotion simulation for conversational agents. Computer Animation and Virtual Worlds, Vol. 15, No. 1, 1--13. Google ScholarDigital Library
- Magnenat-Thalmann, N. 2003. Creating a Smart Virtual Personality. Knowledge-Based Intelligent Information and Engineering Systems 2003, LNCS, Springer, Heidelberg, 15--16.Google Scholar
- Zadeh, L. A. 2003. Computing with Words and Perceptions - A Paradigm. Computing and Decision Analysis and Machine Intelligence, Proceedings of the 2003 International Conference on Machine Learning and Applications, 3--5.Google Scholar
- Baldassarri, S., Cerezo, E. and Seron, F. J. 2008. Maxine: a platform for embodied Animated Agents. Computers&Graphics, Vol. 32, No. 4, 430--437. Google ScholarDigital Library
- Hupont, I., Baldassari, S., Cerezo, E. and Del Hoyo, R. 2008. Effective emotional classification combining facial classifiers and user assessment. V Conference on Articulated Motion and Deformable Objects, LNCS, Springer, No. 5098, 431--440. Google ScholarDigital Library
- Del Hoyo, R., Ciprés, D., Prieto, J., Del Barrio, M., Polo, L. and Calahorra, R. 2007. PROPHET: Herramienta para la Toma de Decisiones en Sistemas Complejos. II Simposio de Inteligencia Computacional 2007 (Zaragoza, Spain).Google Scholar
- Del-Hoyo, R., Martín-del-Brío, B., Medrano, N. and Fernández-Navajas, J. Computational Intelligence Tools for Next Generation Quality of Service Management. Neurocomputing, 2009, in press. Google ScholarDigital Library
- https://www.hibernate.org/Google Scholar
- Lin, C. T., and Lee, C. S. G. 1996. Neural Fuzzy Systems: A Neuro-Fuzzy Synergism to Intelligent Systems. Upper Saddle River, NJ: Prentice Hall. Google ScholarDigital Library
Index Terms
- Towards an intelligent affective multimodal virtual agent for uncertain environments
Recommendations
Introduction to the special issue on affective interaction in natural environments
Special Issue on Affective Interaction in Natural EnvironmentsAffect-sensitive systems such as social robots and virtual agents are increasingly being investigated in real-world settings. In order to work effectively in natural environments, these systems require the ability to infer the affective and mental ...
Developing Intelligent Agent Applications with JADE and JESS
KES '08: Proceedings of the 12th international conference on Knowledge-Based Intelligent Information and Engineering Systems, Part IIIAgent systems differ from more traditional software systems because agents are intended to be independent autonomous, reactive, pro-active and sociable software entities. Due to these unique characteristics developing agent systems has been a very ...
An agent-based intelligent tutoring systems review
This paper presents the current state of research in the fields of intelligent tutoring systems and intelligent agents. The architecture of intelligent tutoring systems typically consists of four major components: the domain knowledge module, the learner ...
Comments