Abstract
Advanced mobile robot systems need to accomplish increasingly complex task sets. However, to solve demanding problems, they are typically optimized to a very restricted set of tasks and environments. This work will therefore propose a self-reconfigurable software and hardware architecture to allow the dynamic optimization of a robot system depending on the current situation, i. e. the current task, the robot inner state, and the environment. The proposed framework is based on organic computing principles and unsupervised machine learning techniques. It further uses dynamically reconfigurable Field Programmable Gate Arrays (FPGA) as hardware accelerators. Preliminary results will be presented, which demonstrate the feasibility of the self-reconfiguration approach.
Funding statement: This work was funded in part by the German Research Foundation (DFG) within priority program 1183 under grant reference MA 1412/8-2.
About the authors
Jan Frost studied Computer Science at the University of Lübeck (M.Sc. 2011). He is a research assistant of the robotics group of Prof. Dr.-Ing. Erik Maehle (2011-now) where he studies robust and scalable approaches to Visual Simultaneous Localization and Mapping.
Universität zu Lübeck, Institute for Computer Engineering, D-23562 Lübeck
Walter Stechele received the Dipl.-Ing. and Dr.-Ing. degrees in electrical engineering from the Technical University of Munich, Germany, in 1983 and 1988, respectively. In 1990 he joined Kontron Elektronik GmbH, a German electronic company, where he was responsible for the ASIC and PCB design department. Since 1993 he has been Academic Director at the Institute for Integrated Systems at the Technical University of Munich. His interests include visual computing and robotic vision, with focus on Multi Processor System-on-Chip (MPSoC) architectures and design methodology, low power optimization, dynamic reconfiguration of FPGA devices, and applications in automotive and robotics.
Technische Universität München, Institute for Integrated Systems, D-80290 München
Erik Maehle received his Diploma and Doctoral Degree in computer science from the University of Erlangen-Nuremberg, Germany, in 1977 and 1982 respectively. After subsequent positions as postdoc researcher at the IBM Zurich Research Laboratory and the University of Erlangen-Nuremberg he became a Professor at the Universities of Augsburg in 1987 and Paderborn in 1989, respectively. Since 1994 he is Professor and Director of the Institute of Computer Engineering at the University of Lübeck, Germany. His research interests include parallel and fault-tolerant computing, reconfigurable and organic computing as well as mobile robotics.
Universität zu Lübeck, Institute for Computer Engineering, D-23562 Lübeck
©2015 Walter de Gruyter Berlin/Boston
