The challenge of constructing psychologically believable agents

Embodied conversational agents (ECAs) are designed to provide a natural and intuitive communication with a human user. One current major topic in agent design consequently is to enhance their believability, often by means of incorporating internal models of emotions or motivations. As psychological theories often lack the necessary details for a direct implementation, many Agent modelers currently rely on models that are rather marginal in current psychological research, or models that are created ad hoc with little theoretical and empirical foundations. The goal of this article is both to raise psychologists’ awareness about central challenges in the process of creating psychologically believable agents, and to recommend existing psychological frameworks to the virtual agents community that seem particularly useful for an implementation in ECAs. Special attention is paid to a computationally detailed model of basic social motives that seems particularly useful for an implementation: the Zurich model of social motivation.

Emotional Memory and Adaptive Personalities

Believable agents designed for long-term interaction with human users need to adapt to them in a way which appears emotionally plausible while maintaining a consistent personality. For short-term interactions in restricted environments, scripting and state machine techniques can create agents with emotion and personality, but these methods are labor intensive, hard to extend, and brittle in new environments. Fortunately, research in memory, emotion and personality in humans and animals points to a solution to this problem. Emotions focus an animal’s attention on things it needs to care about, and strong emotions trigger enhanced formation of memory, enabling the animal to adapt its emotional response to the objects and situations in its environment. In humans this process becomes reflective: emotional stress or frustration can trigger re-evaluating past behavior with respect to personal standards, which in turn can lead to setting new strategies or goals. To aid the authoring of adaptive agents, we present an artificial intelligence model inspired by these psychological results in which an emotion model triggers case-based emotional preference learning and behavioral adaptation guided by personality models. Our tests of this model on robot pets and embodied characters show that emotional adaptation can extend the range and increase the behavioral sophistication of an agent without the need for authoring additional hand-crafted behaviors.

The Challenge of Constructing Psychologically Believable Agents

Embodied conversational agents (ECAs) are designed to provide natural and intuitive communication with a human user. One major current topic in agent design consequently is to enhance their believability, often by incorporating internal models of emotions or motivations. As psychological theories often lack the necessary details for direct implementation, many agent modelers currently rely on models that are rather marginal in current psychological research, or models that are created ad hoc with little theoretical and empirical foundation. The goal of this article is both to raise psychologists’ awareness of the central challenges in the process of creating psychologically believable agents, and to recommend existing psychological frameworks to the virtual agents community that seem particularly useful for implementation in ECAs. Special attention is paid to a computationally detailed model of basic social motives that seems particularly useful for implementation: the Zurich model of social motivation.