Abstracting Away Low-Level Details in Service Robotics with Fuzzy Fluents

ing Away Low-Level Details in Service Robotics with Fuzzy Fluents Stefan Schiffer, Alexander Ferrein, and Gerhard Lakemeyer 1 Knowledge Based Systems Group (KBSG) RWTH Aachen University, Aachen, Germany {schiffer,gerhard}@cs.rwth-aachen.de 2 Mobile Autonomous Systems & Cognitive Robotics Institute (MASCOR) FH Aachen University of Applied Sciences, Aachen, Germany ferrein@fh-aachen.de Abstract. In domestic service robotic applications, complex tasks have In domestic service robotic applications, complex tasks have to be fulfilled in close collaboration with humans. We try to integrate qualitative reasoning and human-robot interaction by bridging the gap in human and robot representations and by enabling the seamless integration of human notions in the robot’s high-level control. The developed methods can also be used to abstract away low-level details of specific robot platforms. These low-level details often pose a problem in re-using software components and applying the same programs and methods in different contexts. When combined with methods for self-maintenance developed earlier these abstractions also allow for seamlessly increasing the robustness and resilience of different robotic systems with only little effort.