Quintic curve path planning method and lane center line maintenance method

Abstract

The invention relates to the technical field of automatic driving, in particular to a quintic curve path planning method and a lane center line maintenance method. The invention comprises the following steps of adopting a quadruple (x, y, r, k) in a vehicle body coordinate system of a vehicle to describe a state model of the vehicle, and position limitation, curvature limitation and attitude limitation conditions of a track starting point S are set; setting a position limit, a curvature limit and an attitude limit condition of a track end point T; and solving the n-order curve model meeting all the limiting conditions in the step a and the step b, wherein n is a positive integer greater than or equal to 5. The path obtained through the method not only meets the pose condition of the starting point, but also gives a limiting condition to the curvature of the track of the starting point, and the smoothness of steering control of the vehicle is guaranteed. The following performance is very good, step jump of steering wheel control is avoided, and a real vehicle test verification result also shows that when automatic driving control is carried out according to the method, the comfortof riding experience of people is not obviously different from the control effect of a human driver.

Description

technical field [0001] The invention relates to the technical field of automatic driving, in particular to a quintic curve path planning method and a lane centerline maintenance method. Background technique [0002] An important task in automatic driving is to enable the computer to replace the human to automatically control the steering wheel of the vehicle, so as to ensure that the vehicle can automatically drive on the road with a reasonable and safe position and posture. The most typical function in the L3 automatic driving application scenario is lane keeping. This function requires the vehicle to be in the middle of the lane and drive along the direction of the lane line. In most lane keeping application scenarios, the vehicle is required to It is necessary to configure an image sensor or other positioning sensors to detect the current position and attitude of the vehicle. For example, some image sensors can detect the shape model of the lane line of the vehicle's lane...

AI Technical Summary

Problems solved by technology

[0004] The difficulty of the path planning algorithm is to design a trajectory model so that the model can meet the conditions for the vehicle to change from the current attitude to the target attitude. Most automatic driving systems use the cubic curve model as the trajectory model, which is better than the automatic driving of Mingkoya University in Japan. The path planning curve hermit curve used in the open source project autoware simulator is this cubic curve model. The trajectory model of the cubic curve requires the trajectory curve to satisfy the position of the starting point and the end point trajectory and the first-order derivative of the trajectory to satisfy the position limit and orientation limit. There are four restriction equations. The disadvantage of this method is that when the path following the path obtained by the cubic curve path planning algorithm is followed by the path following algorithm, the angular velocity curve has a step at the starting point of the trajectory. This jump causes in the actual vehicle test, The steering wheel of the vehicle swings very much, and the vehicle cannot follow the preset trajectory, that is, the following performance of the cubic curve is very poor

Images