This award, in the NSF/EPRI Initiative on Intelligent Control, supports research on the integration of machine learning and sensor-based control in intelligent robotic systems. The research is interdisciplinary in nature and combines techniques of explanation-based control with robust and adaptive nonlinear control, computer vision, and motion planning. The goal is to go beyond the strict hierarchical control architectures typically found in robotic systems by integrating modeling, dynamics, and control at all levels of intelligence. Ultimately, techniques of nonlinear dynamics and control will be combined with artificial intelligence into a single new paradigm in which symbolic reasoning holds an equal place with differential equation based modeling and control. Both theoretical and experimental investigations will be conducted.