Richard Cubek M.Sc., Dipl.-Ing.(FH)

Forschung:

KI/Robotik (Abstract Learning, Symbol Grounding)

Richard Cubek studierte Angewandte Informatik an der HS Ravensburg-Weingarten. Nach zweijähriger Tätigkeit als Diplom-Ingenieur in der Industrie kehrte er an die Hochschule zurück. Als Mitglied des früheren Robocup-Teams ist er nun vor allem in der Forschung aktiv, ein gleichzeitiges Masterstudium schloss er mit Auszeichnung ab. Neben seiner Forschung zum Lernen auf höherer Abstraktionsebene und Symbol Grounding sowie seiner Arbeit an der Fakultät ist er im Bereich Machine Learning für externe Unternehmen tätig und als Doktorand an der Universität Ulm angemeldet.

Publikationen

Richard Cubek, Wolfgang Ertel, Günther Palm. A Critical Review on the Symbol Grounding Problem as an Issue of Autonomous Agents. In Proceedings of the 38th German Conference on Artificial Intelligence (KI), Dresden, Germany, September, 21-25. 2015.

Vladimir Zakharov, Richard Cubek, Wolfgang Ertel. Transparent Integration of a Real-Time Collision Safety System to a Motor Control Chain of a Service Robot. In Proceedings of the 7th Annual International Conference on Technologies for Practical Robot Applications (TEPRA 2015), Boston, Massachusetts, USA, May 11-12, 2015.

Richard Cubek, Wolfgang Ertel, Günther Palm. High-Level Learning from Demonstration with Conceptual Spaces and Subspace Clustering. In Proceedings of the 2015 IEEE International Conference on Robotics and Automation (ICRA), Seattle, Washington, USA, May 26-30, 2015.

P. Ertle, M. Tokic, R. Cubek, H. Voos, and D. Söffker. Towards learning of safety knowledge from human demonstrations. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'12), Vilamoura, Algarve, Portugal. 2012.

R. Cubek and W. Ertel. Conceptual Similarity as a Key to High-Level Robot Programming by Demonstration. In ROBOTIK 2012, 7th German Conference on Robotics, Munich, Germany. 2012.

R. Cubek and W. Ertel. Learning and Execution of High-Level Concepts with Conceptual Spaces and PDDL. In 3rd Workshop on Learning and Planning, ICAPS (21st International Conference on Automated Planning and Scheduling). Freiburg, Germany. 2011.

M. Schneider and R. Cubek and T. Fromm and W. Ertel. Combining Gaussian Processes and Conventional Path Planning in a Learning from Demonstration Framework. In Proceedings of the Eurobot Conference 2010. Rapperswil-Jona (CH). 2010.

W. Ertel and M. Schneider and R. Cubek and M. Tokic. The Teaching-Box: A Universal Robot Learning Framework. In Proceedings of the 14th International Conference on Advanced Robotics (ICAR 2009). Munich. 2009.