|Emotional Expression in Virtual Characters through Body Language|
Emotional Expression in Virtual Characters through Body Language
Virtual agents are used to interact with humans in a myriad of applications. However, the agents often lack the believability necessary to maximize their effectiveness. These agents, or characters, lack personality and emotions, and therefore the capacity to emotionally connect and interact with the human. This deficiency prevents the viewer from identifying with the characters on a personal level. This research explores the possibility of automating the expression of a character’s mental state through its body language. Using a system that animates a character procedurally, we provide tools to modify the character's body movements in real-time, so that they reflect the character’s mood, personality, interest, bodily pain, and emotions, all of which make up the current mental state of the character.
Virtual agents should be able to interact and communicate effectively with a human. If virtual agents can connect with the user on a personal and emotional level, theywill be able to be maximally effective in their interaction with humans. This connection is especially important for applications that attempt to significantly affect the user, such as certain educational applications or games that aim to challenge the individual emotionally.
We believe that individuals will be able to better relate to virtual agents if these agents exhibit personality and emotions through affective behaviors. Their believability would increase, since the expression of personality and emotions causes the agents to seem more like living characters. The objective of this research is to translate the high-level qualitative concepts of personality and emotion into low-level communicative physical gestures. In other words, we have enabled the character to perform body language based on his/her current mental state, which may include personality, emotions, mood, interest, or even bodily pain.
Using the Perlin Emotive Actor Library, which is a procedural, 3-dimensional, character animation system, and using Playspace's Emotivation Model, we have implemented body language for seven main mental state characteristics: confidence, anxiety, interest, thought, anger, defensiveness, and physical pain in various body parts. We have implemented this body language by procedurally animating the character's body movements (body part adjustments as well as additional actions) and facial expressions.
Watch a brief video of some body language that we implemented.
June, 2005 - Thesis project paper