DEI Distinguished Lecturer Series - Wolfram Burgard

Autonomous robots are faced with a series of state estimation and learning problems to optimize their behavior. In this presentation I will start from probabilistic approaches and then describe recent methods developed in my group based on deep learning architectures for different perception problems including object recognition and segmentation and using RGB(-D) images. In addition, I will present a terrain classification approaches that utilize sound and vision. Finally, I will discuss the applicability of deep learning methods to robot navigation. For all approaches I will describe extensive experiments quantifying in which way the corresponding approaches extend the state of the art. This talk is designed to stimulate the discussion about potential directions in robotics and if they should be model- or data-driven.