Distributed Kalman filtering and Network Tracking Capacity

We propose and study a new distributed Kalman filter algorithm that can track unstable dynamics with bounded mean-squared error (MSE). The Network Tracking Capacity (NTC) of this algorithm depends only on the diffusion rate of the network and is independent of the local observation patterns, only requiring global observability. We analyze and compare the NTC for different network models.

[1]  José M. F. Moura,et al.  Distributed Kalman filtering , 2013, 21st European Signal Processing Conference (EUSIPCO 2013).

[2]  José M. F. Moura,et al.  Distributing the Kalman Filter for Large-Scale Systems , 2007, IEEE Transactions on Signal Processing.

[3]  Usman A. Khan,et al.  Networked estimation under information constraints , 2011, ArXiv.

[4]  R. Olfati-Saber,et al.  Distributed Kalman Filter with Embedded Consensus Filters , 2005, Proceedings of the 44th IEEE Conference on Decision and Control.

[5]  José M. F. Moura,et al.  Distributed linear estimation of dynamic random fields , 2013, 2013 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[6]  Soummya Kar,et al.  Convergence Rate Analysis of Distributed Gossip (Linear Parameter) Estimation: Fundamental Limits and Tradeoffs , 2010, IEEE Journal of Selected Topics in Signal Processing.

[7]  José M. F. Moura,et al.  Distributed state estimation in multi-agent networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[8]  Soummya Kar,et al.  Topology for Distributed Inference on Graphs , 2006, IEEE Transactions on Signal Processing.

[9]  Reza Olfati-Saber,et al.  Distributed Kalman filtering for sensor networks , 2007, 2007 46th IEEE Conference on Decision and Control.

[10]  Soummya Kar,et al.  On connectivity, observability, and stability in distributed estimation , 2010, 49th IEEE Conference on Decision and Control (CDC).