Institute for Creative Technologies

Emotions have a pervasive impact over our lives. They influence how we perceive the world, how we make decisions and how we communicate socially. In the context of virtual training environments, emotions also play a key role in the believability of the simulation and the extent to which a student will feel immersed in the experience. In the Emotion Project, we develop models that allow synthetic characters to derive an emotional response to events in the world and respond with behaviors consistent with that emotional state.

We study: * The information processing that underlies emotional behavior and how to use it in computational models. * How emotions are physically and mentally manifested * How emotions are interpreted by observers, and how those interpretations affect the behaviors of the observers

Based on these studies, the team develops computational systems that enable Virtual Human (VH) agents to respond to events in a training environment with human-like emotions and behaviors consistent with the emotional state. The project then uses the VH agents to investigate how people interpret emotional behavior and how these interpretations influence (directly or indirectly) memory and decision-making. Other research efforts include the development of machine learning techniques to characterize expressive behaviors, computation models of social attribution theory and social influence theory, and psychological studies that validate these models.

This project differs from others in the following ways:

• It models human behaviors that are less constrained and typical of real life (unlike work in "believable agents" for entertainment)
• It encompasses emotional modeling with more general qualities that can be applied to a wide range of training environments (other emotional models are restrained to domain-specific knowledge)

Tags: behavior, computational, emotion, human, immersion, model, simulation, virtual

View All Projects »