Integrated Navigation on Vehicle Based on Low Cost MEMS SINS/GNSS using LS-SVM

Abstract The high-precision initial alignment time for the MEMS SINS/GNSS combination system is too long, and it is difficult to ensure the flexible navigation of existing low-cost vehicles. A LS-SVM-assisted fast alignment method is proposed, which uses MEMS gyroscopes, accelerometers and dual-antenna satellite receivers to achieve fast alignment under MEMS SINS/GNSS. Based on the analysis of traditional coordinates and strapdown inertial navigation, the dynamic error model is given. The self-aligned frame of LS-SVM is proposed. At the same time, the EKF filter for training is designed and the motion characteristics of the car body are selected. The state equations and observations, using the EKF to train the LS-SVM model, ultimately achieve fast alignment. Finally, the proposed method is simulated and tested. The final attitude alignment accuracy is better than 0.2° and the alignment time is 10s. Compared with the EKF alignment method under the traditional direct transfer alignment, the alignment accuracy and the alignment time are significantly improved, which can meet the requirements of low-cost vehicle flexibility.