Automatic driving vehicle longitudinal control method and system with environment self-adaptive capacity

Abstract

The invention discloses an automatic driving vehicle longitudinal control method with environment self-adaptive capacity. The method comprises the steps of acquiring vehicle track information, vehicleposition information and state information; collecting vehicle pitch angle information, establishing a clustering analysis model, performing clustering analysis on the collected data, and fitting gradient information in the road of the region of interest; acquiring load information of the vehicle; determining a switching mechanism of driving and braking; calculating a feedforward control quantityof longitudinal control according to the slope information and the load information; calculating feedback control quantity of longitudinal control according to the track information, the vehicle position and the state information; and calculating the total control output quantity through weighting of the feedforward control quantity and the feedback control quantity. According to the invention, road ramp information, vehicle load information and vehicle state information are comprehensively considered and are realized by weighting the feedforward control part and the feedback control part, sothat the longitudinal control precision is greatly improved.

Description

technical field [0001] The invention relates to a longitudinal control method of an automatic driving vehicle, in particular to a longitudinal control method and system of an automatic driving vehicle with environment adaptive capability. Background technique [0002] Autonomous driving technology has developed by leaps and bounds in the past ten years. Autonomous vehicles rely on the cooperation of artificial intelligence, visual computing, radar, and global positioning systems to allow vehicles to drive autonomously and safely on the road without the active operation of the driver. drive on. The automatic driving system is generally divided into three modules: perception module, decision planning module and control module. The perception module perceives the surrounding environment information of the vehicle in real time through sensors such as cameras and radars, and informs the vehicle of the area of ​​interest through the fusion algorithm. The decision-making planning...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the technical problem that the longitudinal control of the self-driving vehicle is affected by the vehicle load and the change of the road slope, resulting in a large longitudinal following error, the present invention provides a method and system for the longitudinal control of the self-driving vehicle with the ability to adapt to the environment. Considering the road slope information, vehicle load information and the vehicle's own state information comprehensively, it is realized by weighting the feedforward control part and the feedback control part, which greatly improves the longitudinal control accuracy

Images