Estimation, filtering and fusion for networked systems with network-induced phenomena: New progress and prospects

• A timely review is provided on information fusion algorithms for networked systems.
• Network-induced phenomena are discussed for the information fusion problems.
• Analysis and synthesis results of the networked systems are surveyed.
• Latest advances for both linear and nonlinear networked systems are given.
• Information fusion results for complex networks and sensor networks are included.

In this paper, some recent advances on the estimation, filtering and fusion for networked systems are reviewed. Firstly, the network-induced phenomena under consideration are briefly recalled including missing/fading measurements, signal quantization, sensor saturations, communication delays, and randomly occurring incomplete information. Secondly, the developments of the estimation, filtering and fusion for networked systems from four aspects (linear networked systems, nonlinear networked systems, complex networks and sensor networks) are reviewed comprehensively. Subsequently, some recent results on the estimation, filtering and fusion for systems with the network-induced phenomena are reviewed in great detail. In particular, some latest results on the multi-objective filtering problems for time-varying nonlinear networked systems are summarized. Finally, conclusions are given and several possible research directions concerning the estimation, filtering, and fusion for networked systems are highlighted.