Incorporating Transformer and LSTM to Kalman Filter with EM algorithm for state estimation

TL;DR

This paper introduces a novel state estimation method that combines Transformer, LSTM, and EM algorithm within a seq2seq framework, demonstrating improved accuracy in simulations of a mobile robot model.

Contribution

It presents a new approach integrating deep learning models with EM-KF for enhanced parameter estimation and state accuracy.

Findings

The method achieves higher accuracy than traditional EM-KF.

Simulation results validate the effectiveness of the combined models.

Source code is publicly available for reproducibility.

Abstract

Kalman Filter requires the true parameters of the model and solves optimal state estimation recursively. Expectation Maximization (EM) algorithm is applicable for estimating the parameters of the model that are not available before Kalman filtering, which is EM-KF algorithm. To improve the preciseness of EM-KF algorithm, the author presents a state estimation method by combining the Long-Short Term Memory network (LSTM), Transformer and EM-KF algorithm in the framework of Encoder-Decoder in Sequence to Sequence (seq2seq). Simulation on a linear mobile robot model demonstrates that the new method is more accurate. Source code of this paper is available at https://github.com/zshicode/Deep-Learning-Based-State-Estimation.