Vortragende(r): Dr.-Ing. Michael Suppa
Im Auftrag des Informatik-Kolloquiums möchten wir Sie auf folgende Veranstaltung aufmerksam machen:
Perception is the key technology allowing automatic adaption of a robotic system’s operation to the environment and its robust operation under presence of uncertainty. Fully or partially autonomous systems rely on perception results obtained from measurements of the World to understand their surroundings. Nowadays, main focus of perception research shifts towards deep learning as the universal tool, neglecting other core aspects of robust measurements such as error estimates, confidence values, and parameter variation. The talk focuses on methods for robust perception with supervisory systems for error detection and recovery as well as confidence-based decision making and shows examples of these approaches for industrial and service robots.
Dr. Michael Suppa is a leading expert in robot perception. Michael received his master’s degree (Dipl.-Ing.) in Electrical Engineering with focus on Automation/Mechatronics with magna cum laude in 2000 and his Doctoral Degree (Dr.-Ing.) in Mechanical Engineering with summa cum laude both from the University of Hannover. From 2000 until 2009, he worked as project manager and researcher at the Institute of Robotics and Mechatronics of the German Aerospace Center (DLR) in the research areas: robotic exploration, 3-D vision, and data fusion. From 2009 until 2015, he was the Head of the Department Perception and Cognition, a recognized World leader on key robotic research topics such as complex scene analysis, perception for resource-limited systems and robotic cognition. He was appointed deputy institute director of the Institute of Robotics and Mechatronics in August 2014. In March 2015 he co-founded Roboception, a DLR spin-off company devoted to advancing the State-of-the -Art in 3D sensors and vision.
Michael was PI in the EC project TAPAS and has taken part in several other European and national projects. Currently, he is PI of the H2020 Project THOMAS and BMBF Project RoPHa. He has published over 60 journal and conference papers and was nominated for and received several best paper awards. Since 2015, Michael is an associate member of the Institute of Artificial Intelligence.