Behavior believability in virtual worlds: agents acting when they need to

Abstract

Believability has been a perennial goal for the intelligent virtual agent community. One important aspect of believability largely consists in demonstrating autonomous behavior, consistent with the agent’s personality and motivational state, as well as the world conditions. Autonomy, on behalf of the agent, implies the existence of an internal structure and mechanism that allows the agent to have its own needs and interests, based on which the agent will dynamically select and generate goals that will in turn lead to self-determined behavior. Intrinsic motivation allows the agent to function and demonstrate behavior, even when no external stimulus is present, due to the constant change of its internal emotional and physiological state. The concept of motivation has already been investigated by research works on intelligent agents, trying to achieve autonomy. The current work presents an architecture and model to represent and manage internal driving factors in intelligent virtual agents, using the concept of motivations. Based on Maslow and Alderfer’s bio-psychological needs theories, we present a motivational approach to represent human needs and produce emergent behavior through motivation synthesis. Particular attention is given to basic, physiological level needs, which are the basis of behavior and can produce tendency to action even when there is no other interaction with the environment.

Alzheimer's Disease Prevention Health Coaching

“…Increasing these skills is critical in low-income populations, who are at higher risks of health literacy challenges and may need support to synthesize health information effectively ( 61 ). Based on Maslow’s hierarchy, low-income populations are one of the most challenging groups in which to create lifestyle change, partly from competing basic needs and increased vulnerability ( 62 ). Employing the participant preference approach generates understanding between the health coach and the participant.…”

Needs Model for an Autonomous Agent during Long-term Simulations

“…Many approaches have been made to simulate needs for agents living in different places such as cities [3], [7], [11] or houses [2], [5], [8]. Some of them, like MAGE [2] are based on Maslow's Pyramid of needs [9].…”

“…Many approaches have been made to simulate needs for agents living in different places such as cities [3], [7], [11] or houses [2], [5], [8]. Some of them, like MAGE [2] are based on Maslow's Pyramid of needs [9]. In this theory, recognized by the psychological field, needs are ordered according to their urgency level (see Fig.…”

“…Simulating the behavior of virtual agents is a crucial part to have a believable virtual environment. Among the main parts of the human decision process, simulating needs is essential to reach this credibility since it lets the agents managing their goal in an autonomous way [2]. However, most agent behavior models, including needs model, do not really address the issue of long periods where time drift and unusual activities may happen.…”

“…Indeed, as an example, such data could replace or complete real data to train algorithms for detecting or predicting daily activities [4]. Here, the explanations given by Avradinis et al [2] are used to distinguish credibility over realism. In our case, credibility assessment is chosen over realism assessment, since our goal is not reaching a reproduction of the human brain regarding needs.…”