T05 - An Introduction to the Distributed Kalman Filter (DKF)

The increasing trend towards connected sensors („internet of things“ and „ubiquitous computing“) derive a demand for powerful distributed estimation methodologies. In tracking scenarios, the „Distributed Kalman Filter“ (DKF) provides an optimal solution under certain conditions. The optimal solution in terms of the estimation accuracy is also achieved by a centralized fusion algorithm which receives either all associated measurements or so-called „tracklets“. However, the centralized scheme needs the result of each update step for the optimal solution whereas the DKF works at arbitrary communication rates since the calculation is completely distributed. In this tutorial an introduction to the DKF is given with a focus on communication and information aspects. The limiting conditions are discussed in detail and extensions to the DKF for a multi-radar scenario including clutter and non-detections are presented. 

Instructor biography

Felix Govaers received his Diploma in Mathematics at the University of Bonn, Germany, in 2007. He earned a PhD degree at the Fraunhofer Institute FKIE, Department for Sensor Data and Information Fusion in Wachtberg in 2012. Since 2009 he is working at the FKIE where he now is leading the team „Distributed Systems“. His research interests are topics in multi sensor fusion such as the Distributed Kalman Filter (DKF), Out-of-Sequece (OoS) processing, and contextual information fusion. He introduced a closed form solution to the DKF in [1], which was extended to more general applications by several other groups.