Robot Learning

Robot learning consists of a multitude of machine learning approaches, particularly reinforcement learning, inverse reinforcement learning, and regression methods, that have been adapted su ciently to domain so that they allow learning in complex robot systems such as helicopters, apping-wing ight, legged robots, anthropomorphic arms and humanoid robots. While classical arti cial intelligence-based robotics approaches have often attempted to manually generate a set of rules and models that allows the robot systems to sense and act in the real-world, robot learning centers around the idea that it is unlikely that we can foresee all interesting real-world situations su ciently accurate. Hence, the eld of robot learning assumes that future robots need to be able to adapt to the real-world, and domain-appropriate machine learning might o er the most approach in this direction.