Intelligent vehicle man-machine cooperative steering control parallel computing method based on risk assessment

Abstract

The invention relates to an intelligent vehicle man-machine cooperative steering control parallel computing method based on risk assessment. The method comprises the following steps: constructing a lateral kinetic equation model of a vehicle; establishing a target function by taking the minimum offset distance between the vehicle driving track and the lane center line and the minimum change of the front wheel turning angle and the longitudinal acceleration in the driving process as targets; establishing a parallel computing architecture of the prediction model and the target function, wherein the parallel computing architecture synchronously computes the prediction model and the target function by adopting a trigger type parallel computing method; solving and calculating a gradient by adopting a back propagation mode, and obtaining an optimal front wheel steering angle control quantity and a longitudinal acceleration control quantity by utilizing a gradient descent method; calculating the driving weight based on fuzzy logic to obtain an expected front wheel steering angle, and completing real-time control. Compared with the prior art, the method has the advantages that the model predictive control solving time is shortened, the expected front wheel steering angle solving time is shortened, and the man-machine cooperative steering control real-time performance of the intelligent vehicle is improved.

Description

Technical field [0001] The present invention relates to the field of parallel calculation, in particular, to a risk-based control parallel calculation method based on risk assessment. Background technique [0002] With the continuous development of the car, although it gives people a great convenience. However, as the number of car ownership increases year by year, the traffic environment of the vehicle is getting more complex. Complex traffic environments increase the driver's psychological burden and driving difficulty, so that the driver is prone to fatigue during driving, eventually leading to traffic accidents. Therefore, it is one of the most effective ways to reduce traffic accidents by reducing the driver's driving burden. [0003] With the development of sensors, communication technologies and perceived fusion technology, smart cars also flourish. And the human machine in the smart vehicle can effectively assist the driver's safe driving, and the specific manifestation i...

AI Technical Summary

Problems solved by technology

Although the human-machine collaborative system for intelligent vehicles is an effective means to reduce traffic accidents, it is a big challenge to quickly solve the optimal front wheel angle based on risk assessment according to the current driver behavior and traffic conditions.

It hinders the mass production of intelligent vehicle human-machine collaboration system

Images