Sven Behnke is professor for Autonomous Intelligent Systems at the University of Bonn and director of the Institute of Computer Science VI. He received his MS degree in Computer Science (Dipl.-Inform.) in 1997 from Martin-Luther-Universität Halle-Wittenberg. In 2002, he obtained a PhD in Computer Science (Dr. rer. nat.) from Freie Universität Berlin. He spent the year 2003 as postdoctoral researcher at the International Computer Science Institute, Berkeley, CA. From 2004 to 2008, Professor Behnke headed the Humanoid Robots Group at Albert-Ludwigs-Universität Freiburg. His research interests include cognitive robotics, computer vision, and machine learning.
Talk # 1
Perception and Planning for Mobile Manipulation in Complex Environments
Robots need to perceive their environment to act in a goal-directed way. While mapping the environment geometry is a necessary prerequisite for many mobile robot applications, understanding the semantics of the environment will enable novel applications, which require more advanced cognitive abilities. In the talk, I will report on methods that we developed for learning tasks like the categorization of surfaces, the detection, recognition, and pose estimation of objects, and the transfer of manipulation skills to novel objects. By combining dense geometric modelling – which is based on registration of measurements and graph optimization – and semantic categorization – which is based on deep learning and transfer learning – 3D semantic maps of the environment are built. We demonstrated the utility of semantic environment perception with cognitive robots in multiple challenging application domains, including domestic service, space exploration, search and rescue, and bin picking.
Talk # 2
Learning Semantic Perception for Cluttered Bin Picking
Picking objects from cluttered piles is a challenging task with great application potential, e.g. in warehouses or domestic service applications. A key prerequisite for cluttered bin picking is the understanding of complex manipulation scenes. In the talk, I will report on efficient methods that we developed for learning tasks like semantic segmentation, object detection, pose estimation of objects, and the transfer of manipulation skills to novel objects. Our team demonstrated the utility of semantic environment perception in multiple challenging bin picking demonstrations, including the Amazon Picking Challenge, the European Robotics Challenges 1 and 2, and the FP7 project STAMINA.