C S 391R C S 391R. Robot Learning. 3 Hours.
Survey a wide range of modern techniques in robotics that learn from data, largely focusing on robot perception and decision making. Explore 3D vision, representation learning, active perception, reinforcement learning, imitation learning, and applications in robot manipulation. Three lecture hours a week for one semester. Computer Science 391R and 395T (Topic: Robot Learning) may not both be counted. Prerequisite: Graduate standing, and experience in machine learning and computer vision.