Distributed Dimensionality Reduction Fusion Kalman Filtering With Quantized Innovations

This paper is concerned with the distributed fusion Kalman filtering problem for networked systems with communication constraints. A dimensionality reduction strategy and a uniform quantization strategy are introduced to reduce communication traffic. To overcome the unboundedness of estimates/measurements in unstable systems, it is proposed to quantize the innovations that are sent to the fusion center through limited bandwidth channels. Then, a recursively distributed dimensionality reduction fusion Kalman filtering algorithm is developed by using a model uncertainty method to process quantization noises. Finally, a target tracking system is employed to demonstrate the effectiveness of the proposed methods.