Distributed Estimation of Sensor Networks Based on LSTM-Kalman Filter
Si-peng Kuang, Ya Zhang · 2022 17th International Conference on Control, Automation, Robotics and Vision (ICARCV) · 2022
This paper studies the distributed estimation problem of sensor networks where the noise parameters are unknown and some sensors cannot obtain the measurements. The expectation maximization (EM) algorithm integrating Kalman filtering algorithm, which is called the EM-KF algorithm, is adopted to sensor networks. Simulation examples are given to illustrate the effectiveness of the algorithm. By using LSTM network, and LSTM-KF algorithm is further proposed to improve the accuracy of EM-KF algorithm.