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.
Read the paper:
Emotional Memory and Adaptive Personalities
by Anthony Francis, Manish Mehta, Ashwin Ram
Handbook of Research on Synthetic Emotions and Sociable Robotics: New Applications in Affective Computing and Artificial Intelligence, IGI Global, 2009www.cc.gatech.edu/faculty/ashwin/papers/er-08-10.pdf
View my profile.svg){kind=logo}
Read my bio
Follow me
OpenStudy with me
Cognitive Computing 
Posted by Anthony Francis on October 13, 2009 at 8:47 pm
The most important takehomes of this paper is that developing complex agents becomes much easier if you put careful thought into the behavioral, emotional and learning elements of your agent and make them available to the agent author, rather than relying on a large library of handcrafted behaviors. We were able to make agents do very interesting things with relatively little effort by choosing the right building blocks.
Doing this work was a lot of fun, but it was a long slog getting from the idea to the implementations to the final publication. You can read a bit more about that process here:
http://googleresearch.blogspot.com/2009/01/maybe-your-computer-just-needs-hug.html
You can also follow the progress of this research on my blog:
http://www.dresan.com/2009/05/more-on-why-your-computer-needs-hug.html
We hope this work his helpful to you all…
-Anthony