Control method and device of domain controller for automatic driving

Abstract

The present invention provides a control method and device for a domain controller for automatic driving, and relates to the technical field of power control, wherein the control method for a domain controller for automatic driving includes: first, receiving vehicle state information output by the perception layer and the target path information, secondly, judge whether the driver intervenes in the vehicle control, and then, if the judgment result is no, conduct stability detection according to the vehicle state information and target path information, and then, when the stability of the vehicle is in an unstable state, select Corresponding stability intervention mode, after that, when the stability of the vehicle is in a steady state, calculate the comprehensive drivability index, then calculate the target control instruction according to the stability intervention mode or the comprehensive drivability index, and finally, send the target control instruction to The underlying actuator, through the above processing process, realizes the consideration of vehicle stability, comfort and other aspects in the process of automatic driving, thereby improving the experience of the occupants.

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