Cognitive Systems Engineering
Researchers: Dr.-Ing. Sebastian Wrede (head), Dipl.-Ing. (FH) Christoph Dreyer, Dipl.-Inform. Raphael Golombek, Dipl.-Math. Michael Götting, Dipl.-Inform. Michael Johannfunke, Dipl.-Inform. Stefan Krüger, Dipl.-Ing. Arne Nordmann, Dipl.-Inform. Jan Moringen, Johannes Wienke M.Sc.
Cognitive robotics is an experimental research activity that combines research efforts in mechatronics, informatics and the cognitive sciences. Creating cognitive robots requires building systems that can adapt their behavior to environments that are complex, rapidly changing, and that cannot be completely modeled in preface. Nowadays, many of the resulting challenges can be successfully addressed on the level of individual algorithms or by advanced robotics hardware tuned for specific scenarios.
In order to provide an avenue for robotic systems to become useful in every-day human settings and as a prerequisite for entering the consumer market, these attributes must be ensured on a system level that encompasses the web of skills advanced robots must be capable of. The aim of the cognitive systems engineering group is to investigate software architectures and engineering principles that allow to efficiently integrate, implement and bring together this web of different skills in order to build complex cognitive robotic systems.
A fundamental prerequisite for mastering the (technical) integration of complex robotics systems is the availability and in-depth understanding of robotics middleware technology. For this reason and despite the availability of frameworks such as ROS, we decided to further develop a custom, but very light-weight and open robotics middleware termed RSB. This so called Robotics Service Bus (RSB) is an efficient message-oriented, event-driven middleware aiming at scalable integration of robotics systems in heterogeneous environments. It is fully open source and available for various operating system, featuring implementations for a number of popular programming languages. Due to our involvement in the HUMAVIPS EU project, specific platform support will be made available for the NAO humanoid robot at the HUMAVIPS Open Portal page. Please find more information and a comparison to ROS concepts at the corresponding project website.
A current example for architectural principles that are investigated in this group for the functional organization of robotics skils are so-called memory architectures. This type of architecture provides temporal buffers and further functionality useful across different tasks and scenarios to support learning processes in cognitive systems. Further ongoing activities are concerned with transfer of current concepts of event-driven architectures for efficient software integration or the exploitation of autonomic computing and anomaly detection concepts for building self-awareness models (this work was recognized at IROS2010 with the RoboCup Best Paper award) in order to increase the autonomy and dependability of robotic systems.
The group is involved in different projects within CITEC and CoR-Lab, BMBF and EU projects. At EU level we conduct research on software architectures and engineering methodology for cognitive robots in the AMARSi and HUMAVIPS EU FP7 projects. Since 2012 the CSE group also participates in the leading edge cluster it's OWL on intelligent technical systems in the FlexiMon innovation project and Human-Machine Interaction cross-section project. Further activities in 2009 included the organization of a scientific workshop on Event-based Systems for Robotics at IROS09 and the development of an initial cognitive robotics testbed based on the KUKA Light-Weight Robot to demonstrate learning technologies in SME scenarios.
Besides conducting research, the operation of these humanoid robots, the education about research environments (platforms + toolkits) and the maintenance of IT infrastructure relevant for an efficient software development process (such as CoR-Lab's Continuous Integration services) are additional responsibilities of this group within the CoR-Lab.