The objective of the CORBYS project is to design and implement a robot control architecture that allows the integration of high-level cognitive control modules, such as a semantically-driven self-awareness module and a cognitive framework for anticipation of, and synergy with, human behaviour based on biologically-inspired information-theoretic principles. CORBYS aims to provide a generic control architecture to benefit a wide range of applications where robots work in synergy with humans, ranging from mobile robots such as robotic followers to gait rehabilitation robots. The behaviour of the two demonstrators, used for validating this architecture, will each be driven by a combination of task specific algorithms and generic cognitive algorithms. In this paper we focus on the generic algorithms based on information theory.
Categories and Subject Descriptors
ROBOTIC DEMONSTRATORSAs the first practical application of the CORBYS control architecture, a novel cognitive mobile gait rehabilitation system is being developed during the project's lifetime. The system comprises a mobile platform and a powered orthosis attached to the platform.The mobile platform will provide mobility for the patient while the powered orthosis will assist in completing his/her leg movements. CORBYS cognitive modules create appropriate commands for low-level robot control derived from the patient's intentions. The cognitive modules are supported by an advanced multi-sensor system consisting of physiological wearable sensors and EEG sensors for perception of the physical and psychological state of the patient. Through cognitive robot control, the CORBYS gait rehabilitation system will be a situationally-aware system capable of learning and reasoning to optimally match the requirements of the patient at different stages of rehabilitation in a range of gait disorders.The second CORBYS demonstrator is an existing mobile robot that follows a human co-worker during investigation of the environment. The robot is equipped with sensors to perceive and reconstruct the dynamic environment, including the location of the human co-worker. Supported by sensor measurements, the cognitive modules provide a trajectory to the low-level control which realizes a following behavior, whilst maintaining controllability and mobility of the robot.
GENERIC COGNITIVE ABILITIESOne question being addressed in the CORBYS project is: Which generic cognitive abilities could benefit both demonstrators, and possibly, an even wider range of robots? Interacting with humans, as both demonstrators do, increases the need for generality, because human behavior is highly unpredictable, and therefore hard to account for in advance. In summary, we are looking for algorithms that can both deal with generic robot architectures and generic situations.One approach being realized in the CORBYS project is to use information-theoretic measurements to define and work towards certain desirable system properties, which can then be combined with task-dependent robot behavior. Informati...