Improving and Extending Behavioral Animation Through Machine Learning

• Main Author: Dinerstein, Jonathan J.
• Format: Others
• Published: BYU ScholarsArchive 2005
• Subjects: computer animation; behavioral animation; character animation; synthetic characters; behavioral modeling; cognitive modeling; machine learning; reinforcement learning; programming by demonstration; autonomous agents; AI-based animation; computer games; training simulators; Computer Sciences
• Online Access: https://scholarsarchive.byu.edu/etd/310; https://scholarsarchive.byu.edu/cgi/viewcontent.cgi?article=1309&context=etd

Behavioral animation has become popular for creating virtual characters that are autonomous agents and thus self-animating. This is useful for lessening the workload of human animators, populating virtual environments with interactive agents, etc. Unfortunately, current behavioral animation techniques suffer from three key problems: (1) deliberative behavioral models (i.e., cognitive models) are slow to execute; (2) interactive virtual characters cannot adapt online due to interaction with a human user; (3) programming of behavioral models is a difficult and time-intensive process. This dissertation presents a collection of papers that seek to overcome each of these problems. Specifically, these issues are alleviated through novel machine learning schemes. Problem 1 is addressed by using fast regression techniques to quickly approximate a cognitive model. Problem 2 is addressed by a novel multi-level technique composed of custom machine learning methods to gather salient knowledge with which to guide decision making. Finally, Problem 3 is addressed through programming-by-demonstration, allowing a non technical user to quickly and intuitively specify agent behavior.