|
Research Interests
My research is directed toward developing
human-like software agents for virtual training environments and to use
these computational methods to concretize psychological theories of human
behavior. Specifically, I investigate how algorithms can control the
behavior of characters in virtual worlds, endowing them with an ability to
think and engage in socio-emotional interactions with human users, using
both verbal and nonverbal communication. Such methods can deepen our
understanding of human behavior, by instantiating and systematically
manipulating psychological theories. They also have wide application to
such areas as training, entertainment and clinical diagnosis, assessment
and treatment.
|
|
Emotion Modeling
Emotions have a
pervasive impact over our lives. They influence how we perceive the
world, how we make decisions, and play a key role in social
communication. 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. Unlike work in
"believable agents" for entertainment, the focus is more
constrained (modeling typical human behavior); there is much greater need
for generality and much less tolerance for domain-specific knowledge.
|
|
|
|
|
Virtual
Humans
The Virtual
Human Project brings together research in intelligent tutoring,
natural language recognition and generation, interactive narrative,
emotional modeling, and immersive graphics and audio. The focus is on
creating a highly realistic and compelling training environment. The
system includes an 8'x30' wrap-around screen, 10.2 channels of immersive
audio, and interactive synthetic humans that can interact with the
trainee and respond emotionally to their decisions. Applications of this
technology include the Mission Rehearsal Exercise [MRE Movie Clip] and the
Stability and Support Operations [SASO Movie Clip]
training prototypes.
|
|
|
Rapport
When people interact their speech prosody, gesture, gaze, posture,
and facial expression contribute to establishment of a sense of rapport. Rapport is argued to
underlie success in negotiations, psychotherapeutic effectiveness,
classroom performance and even susceptibility to hypnosis. The rapport project uses machine vision
and prosody analysis to create virtual humans that can detect and respond
in real-time to human gestures, facial expressions and emotional cues and
create a sense of rapport. These techniques have a demonstrable beneficial
impact on human interaction. [Rapport
Movie Clip]
|
|
|
|
Social Cognition
This project addresses the challenge of
reasoning about social causality.
This refers to the rules of inference people apply when making sense of
social events, rules that differ dramatically from how people (or AI
methods) reason about “acts of nature.” Unlike physical processes, human
actors introspect on their actions, predict their consequence for other
social actors, and have developed social norms and moral codes that
inform judgments of social cause, blame and responsibility. Social causal
judgments involve inferences about mental state and social power. Social causality and
social judgment underlie how we act on and make sense of the
social world around us: they lead to emotional expressions of praise or rage;
they justify public applause or prison terms. In short, they lie at the heart of social
intelligence.
|
|
|
|
