Time-delay feedback neural network-based vehicle dynamics prediction model, training data acquisition method and training method

Abstract

The invention discloses a time-delay feedback neural network-based vehicle dynamics prediction model, a training data acquisition method and a training method, provides a vehicle dynamics virtual and actual data set acquisition method under a multi-road condition, and lays a data foundation for vehicle dynamics model establishment. The method comprises the following steps: firstly, selectively adding different fidelity models based on vehicle nonlinear dynamics to obtain a low-fidelity interpretable vehicle nonlinear dynamics model multi-time-step virtual data set with different complexity degrees; secondly, obtaining multi-time-step virtual data of the high-fidelity dynamics model through high-fidelity vehicle dynamics software CarSim; and finally, arranging an actual unmanned vehicle dynamics data acquisition device to obtain a vehicle dynamics real data set. The freedom degree selection range of the vehicle dynamics virtual data set is wide, the obtaining cost is low, the demand quantity of real vehicle data is reduced, the weight parameters of the model are optimized again through the vehicle dynamics real data set, and the accuracy of actual vehicle dynamics prediction response is improved.

Description

technical field [0001] The invention relates to the field of unmanned vehicle dynamics modeling, in particular to a vehicle dynamics prediction model based on a time-delay feedback neural network, a training data acquisition method and a training method. Background technique [0002] With the continuous improvement of drivers' requirements for vehicle safety, mobility and ride comfort and the increasing maturity of control theory, the research on vehicle intelligent technology has attracted extensive attention. The development of dynamic model-based control technology for unmanned vehicles can achieve better road utilization and higher safety, but it also needs to adapt to various complex driving environments, such as roads with different adhesion coefficients and curvature changes driving, or to achieve safe and stable emergency obstacle avoidance operation in emergency conditions. [0003] The mathematical model of vehicle dynamics based on physical derivation usually mak...

AI Technical Summary

Problems solved by technology

However, an unmanned vehicle is a complex dynamical system. Especially under extreme conditions, the vehicle system and related subsystems will exhibit highly nonlinear and strong coupling characteristics. Although expanding the model dimension can improve the model accuracy, it will also reduce the Increasing the difficulty of modeling also brings challenges to the fast solution of the algorithm

Images