Control method and device of domain controller used for automatic driving

Abstract

The invention provides the control method and the device of a domain controller used for automatic driving and relates to the power control technology field. The control method of the domain controller used for automatic driving comprises the following steps of firstly, receiving vehicle state information and target path information output by a perception layer; secondly, determining whether a driving end intervenes in vehicle control; then, when a determination result is negate, according to the vehicle state information and the target path information, carrying out stability detection; then,when the vehicle stability is an instability state, selecting a corresponding stability intervention mode; then, when the vehicle stability is a stable state, calculating an integration driving performance index; and then, according to the stability intervention mode or the integration driving performance index, calculating a target control instruction; and finally, sending the target control instruction to a bottom layer actuator. Through the above processing process, multiple aspects of vehicle stability, comfortableness and the like during an automatic driving process are considered and then a passenger experience is increased.

Description

technical field [0001] The invention relates to the technical field of power control, in particular to a control method and device for a domain controller used for automatic driving. Background technique [0002] In the process of automatic driving, after the upper-level processor obtains the surrounding environment information of the vehicle and gives the planned target path, it needs to solve the target control signal required by the vehicle's underlying actuators according to the target path and the current state of the vehicle. Most of the existing calculation methods only consider the path tracking accuracy, but less consideration is given to vehicle dynamics stability, occupant comfort, and vehicle fuel economy. Specifically, the existing solutions mainly have the following shortcomings: [0003] 1) Existing automatic driving control algorithms do not fully consider vehicle stability. When the vehicle is driving on a low-adhesion road surface or other harsh working co...

AI Technical Summary

Problems solved by technology

When the vehicle is driving on low-adhesion roads or other harsh working conditions, it is prone to instability and brings danger to the occupants in the vehicle

[0004] 2) The existing automatic driving control algorithm does not consider the comfort of the whole vehicle enough, resulting in poor comfort for the occupants, and the vehicle is prone to frequent braking and acceleration, which makes the occupants poor acceptance of autonomous vehicles

[0005] 3) The existing self-driving vehicle control algorithms often can only make the performance of a certain aspect reach the optimum or local optimum, and the comprehensive performance of the vehicle cannot be guaranteed

[0006] 4) Existing multi-objective optimization algorithms often have a large amount of calculation and are not suitable for real-time calculation

[0007] To sum up, there is currently no effective solution to the problem that it is difficult to guarantee the comprehensive experience of the occupants during the autonomous driving process.

Images