Multisensor data fusion for skill transfer systems

The paper describes the design of a data fusion module for skill transfer purposes. The data fusion paradigm is addressed. It consists of two independent modules for optimal fusion and filtering. A new interpretation of the Kalman filter equations is given to achieve a "model-free" equation capable of following arbitrary variables. A stochastic approach is used to tune the parameters of interest for a certain task. The fusion algorithm presented is global, and can easily be extended to any arbitrary system. It was successfully tested in The Institute of Robotics and System Dynamics at the DLR.