Vehicle speed estimation method and system based on neural network

Abstract

The invention discloses a vehicle speed estimation method and system based on a neural network; the vehicle speed estimation method comprises the following steps of acquiring a training sample and a training output quantity, and expanding a training input quantity in the training sample to be a 8 * 8 symmetric vehicle real-time data matrix, wherein both the training output quantity and the training input quantity are vector forms; and then, training the convolutional neural network according to the symmetric vehicle real-time data matrix and the training output quantity; and finally, obtainingthe real-time data of the current vehicle, inputting the real-time data of the current vehicle into the trained convolutional neural network model so as to estimate the transverse speed and the longitudinal speed of the current vehicle to the ground. According to the method and the system in the invention, the convolutional neural network is utilized, the symmetric vehicle real-time data matrix is used as input, the real-time longitudinal speed and transverse speed of the vehicle to the ground are output through convolution calculation and convergence, not only the method and the system can be applied to the limit working condition of vehicle slipping, but also the calculated amount is small, and the problem of accumulative error in the later integration process is effectively solved.

Description

technical field [0001] The invention relates to the technical field of vehicle speed estimation, in particular to a neural network-based vehicle speed estimation method and system. Background technique [0002] Based on the collected value of the acceleration sensor, the unscented Kalman method is used for filtering prediction, and the acceleration value is integrated to obtain the corresponding lateral velocity and longitudinal velocity. The disadvantage is that the unscented Kalman method has a large amount of calculation and cannot effectively solve the later integration process. The cumulative error problem in . [0003] Based on the collected four-wheel wheel speed signals, combined with the four-wheel model of the vehicle, the calculation of longitudinal speed and lateral speed has good real-time performance, but its disadvantage is that the model is established under the condition of no slippage of the vehicle, so it is not suitable for Extreme conditions of vehicle ...

AI Technical Summary

Problems solved by technology

[0002] Based on the collected value of the acceleration sensor, the unscented Kalman method is used for filtering prediction, and the acceleration value is integrated to obtain the corresponding lateral velocity and longitudinal velocity. The disadvantage is that the unscented Kalman method has a large amount of calculation and cannot effectively solve the later integration process. The cumulative error problem in

[0003] Based on the collected four-wheel wheel speed signals, combined with the four-wheel model of the vehicle, the calculation of longitudinal speed and lateral speed has good real-time performance, but its disadvantage is that the model is established under the condition of no slippage of the vehicle, so it is not suitable for Extreme condition of vehicle skidding

Images