Predavanje "Robot Learning"
Robot learning is a research field at the intersection of machine learning and robotics. It studies techniques allowing a robot to acquire novel skills or adapt to its environment through learning algorithms. In this presentation I will talk about the application of different learning algorithms for robot grasping as well as manipulating. I will discuss state-of-the-art algorithms such as deep learning and reinforcement learning and how can they be used to teach a robot complex skills such as pouring from a mug or throwing objects. Mia Kokić is a PhD student working at the Robotics, Perception and Learning (RPL) laboratory at KTH, Stockhom and her supervisor is Danica Kragić.