Vehicle state estimation based on PSO-RBF neural network

In the last few years, many closed-loop control systems have been introduced in the automotive field to increase the level of safety and driving automation. For the integration of such systems, it is critical to estimate motion states and parameters of the vehicle that are not exactly known or that change over time. In order to estimate the motion states and parameters, a method based on PSO-RBF neural network is presented to solve problem of vehicle state estimation in vehicle handling dynamics. The basic idea behind the work was to identify several key parameters which affected the performance of vehicle by experimental data. Then the test data was input to the simulation model for network training and verification. The results show that the method can estimate vehicle state successfully with small absolute error of side slip angle in vehicle handling dynamics. Results are included to demonstrate the effectiveness of the estimation approach and its potential benefit towards the implementation of adaptive driving assistance systems or to automatically adjust the parameters of onboard controllers as well as the effectiveness of the proposed scheme in the estimation of states and unknown inputs.