Modeling and Reasoning about Success, Failure, and Intent of Multi-Agent Activities
Adam Sadilek, Henry Kautz · 2010
Recent research has shown that surprisingly rich models of human activity can be learned from GPS (positional) data. However, most effort to date has concentrated on modeling single individuals or statistical properties of groups of individuals. We, in contrast, take on the task of understanding human interactions, attempted interactions, and intentions from noisy sensor data in a multi-agent setting. We use a real-world game of capture the flag to illustrate our approach in a well-defined domain. Our evaluation shows that given a model of successfully performed multi-agent activities, along with a set of examples of failed attempts at the same activities, our system can automatically learn an augmented model that is capable of recognizing success, failure, as well as goals of people’s actions with high accuracy. Finally, we demonstrate that explicitly modeling unsuccessful attempts boosts performance on other important recognition tasks. Author Keywords Multi-agent activity recognition, statistical relational learning, structure learning.