Sensor networks, comprising numerous individual sensing nodes, possess the fundamental capabilities of information processing, including data collection, computation, and transmission. Nowadays sensor networks are increasingly prevalent in various fields such as intelligent transportation, environment monitoring, marine surveying, and industrial Internet of Things (IoTs). Consequently, extensive research has been developed on sensor networks from diverse perspectives, among which the distributed filtering issue has attracted particular interest. Typically, filtering algorithms in sensor networks can be categorized into centralized and distributed strategies. The centralized strategy requires a filtering center to collect observations from all sensing nodes and utilize these observations for estimation. Obviously, it imposes high demands on the storage capacity and processing speed of the filtering center, especially in large-scale sensor networks. In contrast, the distributed approach involves the deployment of local filters at each individual node, and utilizes messages propagated from neighboring nodes as well as local messages at each node to perform state estimation. This approach enhances the flexibility and robustness of the filtering algorithms. Therefore, over the last few years, significant research efforts have been devoted to studying distributed filtering issues.
