Research on fusion algorithm based on multimode sensor

In vehicle position monitoring, the GPS system provides high accuracy but has a low refresh rate and is susceptible to instability in environments with weakened signals. The IMU can provide high-frequency motion data in a short time, but its integration errors accumulate over time, leading to position estimation drift. Combining the two through data fusion can compensate for their respective drawbacks and achieve better monitoring results. This paper explores GPS/IMU data fusion based on the principles of Kalman filtering, linear regression, and random forest. The results show that the Kalman filtering algorithm achieves better data fusion performance, with the Mean Squared Error (MSE) controlled below 0.68, while the MSE values obtained from linear regression and random forest algorithms are more than 6 times higher, indicating inferior performance. This confirms the superiority of the Kalman filtering approach over simple machine learning algorithms in data fusion. Additionally, the study simulates different noise environments and reveals that GPS signals have a significant impact on the fusion algorithm's results, being more susceptible to noise interference. This insight provides a feasible direction for further optimization of the Kalman filter.