Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

On how the distributed Kalman filter is related to the federated Kalman filter

: Govaers, F.; Charlish, A.; Koch, W.


IEEE Aerospace and Electronic Systems Society -AESS-; American Institute of Aeronautics and Astronautics -AIAA-, Washington/D.C.:
IEEE Aerospace Conference 2014 : 1-8 March 2014, Big Sky, Montana, Conference digest
Piscataway, NJ: IEEE, 2014
ISBN: 978-1-4799-5582-4 (Print)
ISBN: 978-1-4799-1622-1
9 pp.
Aerospace Conference <2014, Big Sky/Mont.>
Conference Paper
Fraunhofer FKIE ()

In this paper, a direct connection between the covariance debiasing methodology for the distributed Kalman (DKF) filter in [1] and the federated Kalman filter is shown. In particular, it can be seen that for a unique choice of the information gain hypothesis of the DKF, the covariance debiasing becomes equivalent to the federated Kalman filter. As the complexity of the covariance calculation for the federated Kalman filter is rather low, a hybrid solution is proposed. A numerical evaluation presents two different scenarios where the state estimate of the distributed Kalman filter outperforms the federated Kalman filter in terms of accuracy. The first scenario is using linear Gaussian noise on position measurements whereas in the second scenario a distributed radar application is shown.