Affective Multimodal Control of Virtual Characters

Lecture Notes in Computer Science, 2006

Virtual assistants, also called Avatars, are virtual characters making the communication between the user and the machine more natural and interactive. In this research we have given avatars the capacity of having and expressing emotions by means of a computational emotional model based on the cognitive perspective. Once the system knows the emotional expressiveness that the virtual character will show to the user, we also have worked in how to express it through facial animation techniques.

International Journal of Intelligent Games & Simulation, 2003

The paper outlines an emotionally intelligent agent design for use in computer games. The agent is designed to provide users with a rationally unpredictable adversary or companion in virtual environments. An overview of the agent's emotional assessment mechanism are given followed by an assessment of the agent when used to model a computerized pet dog.

2011

A key factor for the playing experience in modern video games is the behavior of the agents in the game. Recently, several mechanisms have been put forward, with the objective to define synthetic emotional models, so as to make the player believe that the responses of the software agents are motivated, in some way, by emotions. However, there is currently no virtual agent model that satisfies the restrictions imposed by the software development of a commercial video game, namely limited design time and computational complexity but offering flexible mechanisms to define emotional reactions. In this paper, we present the Emotional Elicitation Process (EEP), a lightweight emotional model suitable for use in real-time video game environments. EEP includes: (1) a parametric definition for the character emotional profile, (2) a mechanism to translate events into emotions, (3) a method to update mood state by these emotions, and (4) a mechanism to map mood state into different behavior controllers. We illustrate this model by an example from a commercial role-playing game (RPG) scenario, in which a relatively simple setup of EEP can produce realistic emotional behaviors consuming few computational resources.

2010

ABSTRACT In this paper we present a system which allows embodied conversational agent to display multimodal sequential expressions. Recent studies show that several emotions are expressed by a set of different nonverbal behaviors which include different modalities: facial expressions, head and gaze movements, gestures, torso movements and posture.

International Journal of Computer-supported Collaborative Learning, 2003

In this paper, we present our approach to modelling perceptive 3D virtual characters with emotion and personality. The characters are powered by a di- alogue system that consists of a large set of ba- sic interactions between the user and the computer. These interactions are encoded in finite state ma- chines. The system is integrated with an expres- sion recognition

2011 IEEE Conference on Computational Intelligence and Games (CIG'11), 2011

A key factor for the playing experience in modern video games is the behavior of the agents in the game. Recently, several mechanisms have been put forward, with the objective to define synthetic emotional models, so as to make the player believe that the responses of the software agents are motivated, in some way, by emotions. However, there is currently no virtual agent model that satisfies the restrictions imposed by the software development of a commercial video game, namely limited design time and computational complexity but offering flexible mechanisms to define emotional reactions. In this paper, we present the Emotional Elicitation Process (EEP), a lightweight emotional model suitable for use in real-time video game environments. EEP includes: (1) a parametric definition for the character emotional profile, (2) a mechanism to translate events into emotions, (3) a method to update mood state by these emotions, and (4) a mechanism to map mood state into different behavior controllers. We illustrate this model by an example from a commercial role-playing game (RPG) scenario, in which a relatively simple set-up of EEP can produce realistic emotional behaviors consuming few computational resources.

While human emotions have been researched for decades, designing authentic emotional behavior for non-human characters has received less attention. However, virtual behavior not only affects game design, but also allows creating authentic avatars or robotic companions. After a discussion of methods to model and recognize emotions, we present three characters with a decreasing level of human features and describe how established design techniques can be adapted for such characters. In a study, 220 participants assess these characters' emotional behavior, focusing on the emotion " anger ". We want to determine how reliable users can recognize emotional behavior, if characters increasingly do not look and behave like humans. A secondary aim is determining if gender has an impact on the competence in emotion recognition. The findings indicate that there is an area of insecure attribution of virtual affective behavior not distant but close to human behavior. We also found that at least for anger, men and women assess emotional behavior equally well.

2001

Abstract: A person s behavior provides significant information about their emotional state, attitudes, and attention. Our goal is to create virtual humans that convey such information to people while interacting with them in virtual worlds. The virtual humans must respond dynamically to the events surrounding them, which are fundamentally influenced by users actions, while providing an illusion of human-like behavior.

2005

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.

Lecture Notes in Computer Science, 2009

Psychology suggests highly synchronized expressions of emotion across different modalities. Few experiments jointly studied the relative contribution of facial expression and body posture to the overall perception of emotion. Computational models for expressive virtual characters have to consider how such combinations will be perceived by users. This paper reports on two studies exploring how subjects perceived a virtual agent. The first study evaluates the contribution of the facial and postural expressions to the overall perception of basic emotion categories, as well as the valence and activation dimensions. The second study explores the impact of incongruent expressions on the perception of superposed emotions which are known to be frequent in everyday life. Our results suggest that the congruence of facial and bodily expression facilitates the recognition of emotion categories. Yet, judgments were mainly based on the emotion expressed in the face but were nevertheless affected by postures for the perception of the activation dimension.