I research in the area of Artificial Intelligence. My long-term research goal is the effective construction of autonomous agents where cognition, perception, and action are combined to address planning, execution, and learning tasks.
I am interested in the continuous integration of reactive, deliberative planning and control learning for teams of multiple agents acting in dynamic and uncertain environments.
I am interested in adversarial modeling, reuse, and abstraction in control learning for multiple agents. I also continue to investigate effective planning, execution, and learning algorithms for deterministic and nondeterministic multiagent domains within the research projects CORAL (Collaborate, Observe, Resaon, Act, and Learn), MAPEL (Multi-Agent Planning, Execution, and Learning), and the MultiRobot Lab.
With my students, I have used robot soccer as a concrete testbed for research. We have developed teams of robot soccer agents in three different leagues that have been RoboCup world champions several times: simulation (1998,1999), CMU-built small-wheeled robots (1997,1998), and Sony four-legged robots (1998).
I also research on the integration of planning and information retrieval, and the application of evolutionary computation and machine learning to the performance prediction of signal processing algorithms.