Learning to Grasp Using More or Less Vision
The more information is available about the object (and the gripper), the easier it is, presumably, to form grasps that satisfy desired properties. In practice, object information is often difficult to acquire, and even if available, it can be difficult to exploit. In this tutorial, I will discuss a diverse set of learning-based approaches to grasping that differ in the amount and treatment of object information, primarily obtained by RGB-D sensing. Examples include almost blind sampling, part-based approaches, deep learning. The tutorial will include compact introductions to the most relevant machine-learning methods.
Justus Piater is a professor of computer science at the University of Innsbruck, Austria, where he leads the Intelligent and Interactive Systems group. He holds a M.Sc. degree from the University of Magdeburg, Germany, and M.Sc. and Ph.D. degrees from the University of Massachusetts Amherst, USA, all in computer science. Before joining the University of Innsbruck in 2010, he was a visiting researcher at the Max Planck Institute for Biological Cybernetics in Tübingen, Germany, a professor of computer science at the University of Liège, Belgium, and a Marie-Curie research fellow at GRAVIR-IMAG, INRIA Rhône-Alpes, France. His research interests focus on visual perception, learning and inference in sensorimotor systems. He has published more than 160 papers in international journals and conferences, several of which have received best-paper awards, and currently serves as Associate Editor of the IEEE Transactions on Robotics.
University of Innsbruck
Department of Computer Science