CN117698734A - Lane line information prediction method, device, equipment and computer readable storage medium - Google Patents

Abstract

A lane information prediction method, apparatus, device and computer readable storage medium. Determining a first mark point and a second mark point when the current moment meets the prediction condition of the lane line information and at least one track point exists before the track point corresponding to the current moment; calculating first track deviation information of the vehicle relative to the previous track point at the first mark point and second track deviation information of the vehicle relative to the previous track point at the second mark point; the lane line prediction information at the current moment is obtained based on the first track deviation information, the second track deviation information and the lane line information corresponding to the latest real lane line information updating moment at the current moment, the lane line information is predicted by utilizing the vehicle motion deviation, the time deviation problem between the perception information and the vehicle control is solved, and the technical problem that the lane line information is delayed from an actual scene when the vehicle is controlled, so that the control effect on the vehicle is poor in the related art is solved.

Description

Lane line information prediction method, device, equipment and computer-readable storage medium

Technical field

This application relates to the field of autonomous driving technology, and specifically to a lane line information prediction method, device, equipment and computer-readable storage medium.

Background technique

With the development of autonomous driving technology, the application of lane line recognition technology is becoming more and more widespread. For example, lane line positioning, lane keeping and other functions will use lane line information. Therefore, the requirements for lane line recognition accuracy are getting higher and higher.

In related technologies, vehicle intelligent driving assistance functions usually use lane lines detected by sensors as input to decision-making control algorithms. However, there is an inevitable time deviation between sensor detection and the execution of decision-making control algorithms. Therefore, the lane line when controlling the vehicle Line information lags behind the actual scene, resulting in poor vehicle control.

Contents of the invention

The present application provides a lane line information prediction method, device, equipment and computer-readable storage medium, which can solve the problem in the existing technology that the lane line information lags behind the actual scene when controlling the vehicle, resulting in poor control effect on the vehicle. Poor technical issues.

In a first aspect, embodiments of the present application provide a method for predicting lane line information. The method for predicting lane line information includes:

When the current moment satisfies the conditions for executing lane line information prediction and there is at least one track point before the trajectory point corresponding to the current moment, the vehicle driving trajectory point corresponding to the last time when lane line information was predicted is determined to be the first marking point, which is closest to the current moment. The vehicle driving trajectory point corresponding to the real lane line information update time is the second marking point;

Calculate first trajectory deviation information between the vehicle at the first marking point and the vehicle at a first trajectory point, where the first trajectory point is a trajectory point preceding the first marking point;

Calculate second trajectory deviation information between the vehicle at the second marking point and the vehicle at a second trajectory point, where the second trajectory point is a trajectory point preceding the second marking point;

The lane line prediction information at the current time is obtained based on the first trajectory deviation information, the second trajectory deviation information and the lane line information corresponding to the latest real lane line information update time at the current time.

In a second aspect, embodiments of the present application provide a device for predicting lane line information. The device for predicting lane line information includes:

A determination module configured to determine the vehicle driving trajectory point corresponding to the last time the lane line information was predicted as the first marking point when the current moment meets the conditions for executing lane line information prediction and there is at least one trajectory point before the trajectory point corresponding to the current moment. , the vehicle driving trajectory point corresponding to the latest real lane line information update time at the current moment is the second marking point;

The first calculation module is used to calculate the first trajectory deviation information between the vehicle at the first marking point and the vehicle at the first trajectory point, where the first trajectory point is the trajectory point preceding the first marking point. ;

The second calculation module is used to calculate the second trajectory deviation information between the vehicle at the second marking point and the vehicle at the second trajectory point, where the second trajectory point is the previous trajectory point of the second marking point. ;

The lane line information prediction module is configured to obtain the lane line prediction information at the current moment based on the first trajectory deviation information, the second trajectory deviation information and the lane line information corresponding to the latest real lane line information update time at the current time.

In a third aspect, embodiments of the present application provide a lane line information prediction device. The lane line information prediction device includes a processor, a memory, and lane line information stored on the memory and executable by the processor. Prediction program, wherein when the lane line information prediction program is executed by the processor, the steps of the lane line information prediction method as described above are implemented.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium. A lane line information prediction program is stored on the computer-readable storage medium. When the lane line information prediction program is executed by a processor, the above is implemented. The steps of the lane line information prediction method.

The beneficial effects brought by the technical solutions provided by the embodiments of this application include:

When the current time satisfies the conditions for executing lane line information prediction and there is at least one track point before the track point corresponding to the current time, it is determined that the vehicle driving track point corresponding to the last time the lane line information was predicted is the first marking point, which is the same as the current time. The vehicle driving trajectory point corresponding to the latest real lane line information update time is the second marking point; the first trajectory deviation information between the vehicle at the first marking point and the vehicle at the first trajectory point is calculated, where, One trajectory point is the previous trajectory point of the first marker point; calculate the second trajectory deviation information between the vehicle at the second marker point and the vehicle at the second trajectory point, where the second trajectory point is the second trajectory point. The previous trajectory point of the marker point; obtain the lane line prediction information at the current moment based on the first trajectory deviation information, the second trajectory deviation information and the lane line information corresponding to the latest real lane line information update time at the current time, The use of vehicle motion deviations to predict lane line information makes up for the time deviation problem between sensing information and vehicle control, and solves the problem in related technologies that the lane line information lags behind the actual scene when controlling the vehicle, resulting in poor control of the vehicle. Technical issues with poor results.

Description of the drawings

Figure 1 is a schematic flow chart of an embodiment of the lane line information prediction method of the present application;

Figure 2 is a schematic diagram of time and trajectory point matching of the lane line information prediction method of this application;

Figure 3 is a detailed flow chart of step S20 in Figure 1 of the present application;

Figure 4 is a functional module schematic diagram of an embodiment of the lane line information prediction device of the present application;

Figure 5 is a schematic diagram of the hardware structure of the lane line information prediction device involved in the embodiment of the present application.

Detailed ways

In order to enable those in the technical field to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only These are part of the embodiments of this application, but not all of them. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

In order to make the purpose, technical solutions, and advantages of the present application clearer, the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

In a first aspect, embodiments of the present application provide a method for predicting lane line information.

In one embodiment, refer to FIG. 1 , which is a schematic flow chart of an embodiment of the lane line information prediction method of the present application. As shown in Figure 1, lane line information prediction methods include:

Step S10, when the current moment meets the conditions for executing lane line information prediction and there is at least one trajectory point before the trajectory point corresponding to the current moment, determine the vehicle driving trajectory point corresponding to the last time the lane line information was predicted as the first marker point, and The vehicle driving trajectory point corresponding to the latest real lane line information update time at the current moment is the second marking point;

In this embodiment, when there is at least one trajectory point before the trajectory point corresponding to the current moment, it means that the vehicle has a historical trajectory point to avoid the situation where the vehicle has not started moving at the current moment and is at the starting point of movement. When the current moment satisfies the execution lane line information When predicting conditions, the lane line information prediction step is performed to ensure the rationality of the prediction results. Therefore, when the current moment satisfies the conditions for executing lane line information prediction and there is at least one trajectory point before the trajectory point corresponding to the current moment, refer to Figure 2, which is a schematic diagram of time and trajectory point matching of the lane line information prediction method of the present application. As shown in Figure 2, the vehicle driving trajectory point corresponding to the last predicted lane line information time T _end is determined as the first marking point, and the vehicle driving trajectory point corresponding to the latest real lane line information update time T _d at the current time is determined as The second marker point is easy to understand. When the current moment meets the conditions for executing lane line information prediction and there is at least one track point before the track point corresponding to the current moment, the last time the lane line information is predicted is the last time the virtual lane is obtained. At the time of line information, the latest real lane line information update time to the current time is the last time before the current time when new actual lane line information is input to update the real lane line information.

Further, in one embodiment, the lane line information prediction condition is:

a. The current time is after the last time when lane line information was predicted;

b. The difference between the current time and the time of the last predicted lane line information is less than the first preset duration;

c. The current time is greater than the sum of the time of the last predicted lane line information plus the second preset duration, and smaller than the sum of the last time of the last predicted lane line information plus the third preset duration, where the second preset time is The duration is set to be less than the third preset duration;

d. There is a real lane line information update time between the current time and the last time the lane line information was predicted.

In this embodiment, in order to ensure the continuity of prediction, the current time must be after the last time the lane line information was predicted, and the gap between the current time and the last time the lane line information was predicted cannot be too long, that is, the current time minus the last prediction The difference in time between the lane line information should be less than the first preset duration, and the current time should not be far or near the time when the lane line information was last predicted, that is, the current time is greater than the time when the lane line information was last predicted plus The sum of the second preset duration is smaller than the sum of the last predicted lane line information time plus the third preset duration, where the second preset duration is smaller than the third preset duration. Since the last predicted lane line information cannot always be used, there must be a real lane line information update time between the current moment and the last time the lane line information was predicted, so that the lane line information can be predicted again.

Step S20: Calculate the first trajectory deviation information between the vehicle at the first marking point and the vehicle at the first trajectory point, where the first trajectory point is the trajectory point preceding the first marking point;

In this embodiment, the first trajectory deviation information includes a first longitudinal distance deviation, a first lateral distance deviation and a first orientation angle deviation. Calculate the first longitudinal distance deviation, the first lateral distance deviation and the first orientation angle deviation of the vehicle at the first marking point relative to the vehicle at the first trajectory point, where the first trajectory point is the previous one of the first marking point Track point, heading angle is the angle between the vehicle and the lane centerline.

Step S30: Calculate the second trajectory deviation information between the vehicle at the second marker point and the vehicle at the second trajectory point, where the second trajectory point is the trajectory point preceding the second marker point;

In this embodiment, the second trajectory deviation information includes a second longitudinal distance deviation, a second lateral distance deviation, and a second orientation angle deviation. Calculate the second longitudinal distance deviation, the second lateral distance deviation and the second orientation angle deviation of the vehicle at the second marking point relative to the vehicle at the second trajectory point, where the second trajectory point is the previous one of the second marking point track points.

Specifically, a fourth trajectory point adjacent to the second marker point and behind the second marker point is obtained. Continuing to refer to Figure 2, the trajectory point corresponding to the moment t _end2 in Figure 2 is the fourth trajectory point adjacent to the second marking point and after the second marking point. Substituting the vehicle's speed at the second trajectory point, the vehicle's heading angle at the second trajectory point, and the time between the moment corresponding to the previous trajectory point of the trajectory point corresponding to the current moment and the current moment into the fourth preset formula, the calculation is obtained The fifth longitudinal distance deviation Δx _start2 between the vehicle at the second trajectory point and the vehicle at the previous trajectory point of the second trajectory point, the fourth preset formula is as follows:

Δx _start2 = (t _cur -t _E )*(V _xstart2 cosθ _start2 -V _ystart2 sinθ _start2 )

Among them, t _cur is used to represent the current moment, t _E is used to represent the moment corresponding to the previous trajectory point of the trajectory point corresponding to the current moment, V _xstart2 is used to represent the longitudinal speed of the vehicle at the second trajectory point, and V _ystart2 is used to represent The lateral speed of the vehicle at the second trajectory point, θ _start2, is used to represent the heading angle of the vehicle at the second trajectory point.

Substituting the vehicle's speed at the fourth trajectory point, the vehicle's heading angle at the fourth trajectory point, and the time between the moment corresponding to the previous trajectory point of the trajectory point corresponding to the current moment and the current moment into the fourth preset formula, the calculation is obtained The sixth longitudinal distance deviation Δx _end2 between the vehicle at the fourth trajectory point and the vehicle at the previous trajectory point of the fourth trajectory point, that is, Δx _end2 = (t _cur -t _E )*(V _xend2 cosθ _end2 -V _yend2 sinθ _end2 )

Among them, t _cur is used to represent the current moment, t _E is used to represent the moment corresponding to the previous trajectory point of the trajectory point corresponding to the current moment, V _xend2 is used to represent the longitudinal speed of the vehicle at the fourth trajectory point, and V _yend2 is used to represent The lateral speed of the vehicle at the fourth trajectory point, θ _end4, is used to represent the heading angle of the vehicle at the fourth trajectory point.

The fifth longitudinal distance deviation Δx _start2 , the sixth longitudinal distance deviation Δx _end2 , the latest real lane information update time t _d to the current time, the time t _end2 corresponding to the fourth trajectory point, and the time t _start1 corresponding to the first trajectory point And the time t _start2 corresponding to the second trajectory point is substituted into the preset formula

The second longitudinal distance deviation between the vehicle at the second marking point and the vehicle at the second trajectory point is calculated, where ΔX ₂ is used to represent the distance between the vehicle at the second marking point and the vehicle at the second trajectory point The second longitudinal distance deviation.

Substituting the speed of the vehicle at the second trajectory point, the heading angle of the vehicle at the second trajectory point, and the time between the moment corresponding to the previous trajectory point of the trajectory point corresponding to the current moment and the current moment into the fifth preset formula, the calculation is obtained The fifth lateral distance deviation Δy _start2 between the vehicle at the second trajectory point and the vehicle at the previous trajectory point of the second trajectory point, the fifth preset formula is as follows:

Δy _start2 = (t _cur -t _E )*(V _ystart2 sinθ _start2 +V _ystart2 cosθ _start2 )

Among them, t _cur is used to represent the current moment, t _E is used to represent the moment corresponding to the previous trajectory point of the trajectory point corresponding to the current moment, V _ystart2 is used to represent the lateral speed of the vehicle at the second trajectory point, and θ _start2 is used to represent The heading angle of the vehicle at the second trajectory point.

Substituting the speed of the vehicle at the fourth trajectory point, the heading angle of the vehicle at the fourth trajectory point, and the time between the moment corresponding to the previous trajectory point of the trajectory point corresponding to the current moment and the current moment into the fifth preset formula, the calculation is obtained The sixth lateral distance deviation Δy _end2 between the vehicle at the fourth trajectory point and the vehicle at the previous trajectory point of the fourth trajectory point, that is, Δy _end2 = (t _cur -t _E )*(V _yend2 sinθ _end2 +V _yend2 cosθ _end2 )

Among them, t _cur is used to represent the current moment, t _E is used to represent the moment corresponding to the previous trajectory point of the trajectory point corresponding to the current moment, V _yend2 is used to represent the lateral speed of the vehicle at the fourth trajectory point, and θ _end2 is used to represent The heading angle of the vehicle at the fourth trajectory point.

The fifth lateral distance deviation Δy _start2 , the sixth lateral distance deviation Δy _end2 , the latest real lane information update time t _d to the current time, the time t _end2 corresponding to the fourth trajectory point and the time t _start2 corresponding to the second trajectory point Substitute into the default formula The second lateral distance deviation between the vehicle at the second marking point and the vehicle at the second trajectory point is calculated, where ΔY ₂ is used to represent the distance between the vehicle at the second marking point and the vehicle at the second trajectory point second lateral distance deviation.

Calculate the product of the time between the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time and the current time multiplied by the angular velocity of the vehicle at the second trajectory point, and use the resulting product as the distance between the vehicle at the second trajectory point and the vehicle The sixth orientation angle deviation Δθ _start2 between the second trajectory point and the previous trajectory point, that is, Δθ _start2 = (t _cur -t _E )*ω _start2 , where t _cur is used to represent the current moment, and t _E is represented by At the time corresponding to the previous trajectory point representing the trajectory point corresponding to the current time, ω _start2 is used to represent the angular velocity of the vehicle at the second trajectory point.

Calculate the product of the time between the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time and the current time multiplied by the angular velocity of the vehicle at the fourth trajectory point, and use the resulting product as the distance between the vehicle at the fourth trajectory point and the vehicle The seventh orientation angle deviation Δθ _end2 between the second mark points is Δθ _end2 = (t _cur -t _E )*ω _end2 , where ω _end2 is used to represent the angular velocity of the vehicle at the fourth trajectory point.

The sixth heading angle deviation Δθ _start2 , the seventh heading angle deviation Δθ _end2 , the latest real lane information update time t _d to the current time, the time t _end2 corresponding to the fourth trajectory point, and the time t _start1 corresponding to the first trajectory point And the time t _start2 corresponding to the second trajectory point is substituted into the preset formula

That is, the second orientation angle deviation between the vehicle at the second marking point and the vehicle at the second trajectory point can be calculated, where Δθ ₂ is used to represent the vehicle at the second marking point and the vehicle at the second trajectory point. The second orientation angle deviation between

Step S40: Obtain lane line prediction information at the current time based on the first trajectory deviation information, the second trajectory deviation information and the lane line information corresponding to the latest real lane line information update time at the current time.

In this embodiment, the lane line information at the current moment is predicted based on the first trajectory deviation information, the second trajectory deviation information and the lane line information corresponding to the latest real lane line information update time at the current moment, and the lane line information at the current moment can be obtained. Lane prediction information.

In this embodiment, when the current time satisfies the conditions for executing lane line information prediction and there is at least one trajectory point before the trajectory point corresponding to the current time, it is determined that the vehicle driving trajectory point corresponding to the time when lane line information was last predicted is the first mark. point, the vehicle driving trajectory point corresponding to the latest real lane line information update time at the current moment is the second marking point; calculate the first trajectory deviation between the vehicle at the first marking point and the vehicle at the first trajectory point Information, wherein the first trajectory point is the previous trajectory point of the first marking point; calculate the second trajectory deviation information between the vehicle at the second marking point and the vehicle at the second trajectory point, wherein the second The trajectory point is the previous trajectory point of the second marker point; the current time is obtained based on the first trajectory deviation information, the second trajectory deviation information and the lane line information corresponding to the latest real lane line information update time at the current time. Lane line prediction information uses vehicle motion deviation to predict lane line information, which makes up for the time deviation problem between sensing information and vehicle control, and solves the problem in related technologies that the lane line information lags behind the actual scene when controlling the vehicle. Technical problems that result in less effective control of the vehicle.

Further, in one embodiment, the first trajectory deviation information includes a first longitudinal distance deviation, a first lateral distance deviation and a first orientation angle deviation. Refer to Figure 3. Figure 3 is the details of step S20 in Figure 1 of this application. chemical process diagram. As shown in Figure 3, the step of calculating the first trajectory deviation information between the vehicle at the first marker point and the vehicle at the first trajectory point includes:

Step S201, obtain a third trajectory point adjacent to the first marker point and after the first marker point;

Step S202: Calculate the third longitudinal distance deviation Δx _start1 between the vehicle at the first trajectory point and the vehicle at the previous trajectory point of the first trajectory point;

Step S203: Calculate the fourth longitudinal distance deviation Δx _end1 between the vehicle at the third trajectory point and the vehicle at the first mark point;

Step S204, based on the third longitudinal distance deviation Δx _start1 , the fourth longitudinal distance deviation Δx _end1 , the time t _end of the last predicted lane line information, the time t end1 corresponding to the third trajectory point, and the corresponding time t _end1 of the first trajectory point. At the time t _start1 , the first longitudinal distance deviation between the vehicle at the first marking point and the vehicle at the first trajectory point is calculated through the first preset formula. The first preset formula is as follows:

Wherein, ΔX ₁ is used to represent the first longitudinal distance deviation between the vehicle at the first mark point and the vehicle at the first trajectory point;

Step S205: Calculate the third lateral distance deviation Δy _start1 between the vehicle at the first trajectory point and the vehicle at the previous trajectory point of the first trajectory point;

Step S206: Calculate the fourth lateral distance deviation Δy _end1 between the vehicle at the third trajectory point and the vehicle at the first mark point;

Step S207, based on the third lateral distance deviation Δy _start1 , the fourth lateral distance deviation Δy _end1 , the time t _end of the last predicted lane line information, the time t _end1 corresponding to the third trajectory point and the corresponding first trajectory point At the time t _start1 , the first lateral distance deviation between the vehicle at the first marking point and the vehicle at the first trajectory point is calculated through the second preset formula. The second preset formula is as follows:

Wherein, ΔY ₁ is used to represent the first lateral distance deviation between the vehicle at the first mark point and the vehicle at the first trajectory point;

Step S208: Calculate the product of the time length between the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time and the current time multiplied by the angular velocity of the vehicle at the first trajectory point, and use the product as the vehicle's angular velocity at the first trajectory point. The third orientation angle deviation Δθ _start1 between the first trajectory point and the vehicle at the previous trajectory point of the first trajectory point;

Step S209: Calculate the product of the duration between the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time and the current time multiplied by the angular velocity of the vehicle at the third trajectory point, and use the product as the vehicle's angular velocity at the third trajectory point. The fourth orientation angle deviation Δθ _end1 between the third trajectory point and the vehicle at the first mark point;

Step S210, based on the third orientation angle deviation Δθ _start1 , the fourth orientation angle deviation Δθ _end1 , the time t _end of the last predicted lane line information, the time t end1 corresponding to the third trajectory point, and the corresponding time t _end1 of the first trajectory point. At the time t _start1 , the first orientation angle deviation between the vehicle at the first marking point and the vehicle at the first trajectory point is calculated through the third preset formula. The third preset formula is as follows:

Wherein, Δθ ₁ is used to represent the first orientation angle deviation between the vehicle at the first mark point and the vehicle at the first trajectory point, and the orientation angle is the angle between the vehicle and the lane centerline.

In this embodiment, continuing to refer to FIG. 2 , the trajectory point corresponding to the moment t _end1 in FIG. 2 is the third trajectory point adjacent to the first marking point and after the first marking point. A third longitudinal distance deviation of the vehicle relative to the previous trajectory point when the vehicle is at the first trajectory point is calculated, and a fourth longitudinal distance deviation of the vehicle relative to the previous trajectory point when the vehicle is at the third trajectory point is calculated.

Substitute the third longitudinal distance deviation Δx _start1 , the fourth longitudinal distance deviation Δx _end1 , the time t _end of the last predicted lane line information, the time t _end1 corresponding to the third trajectory point and the time t _start1 corresponding to the first trajectory point into the first A preset formula is used to calculate the first longitudinal distance deviation between the vehicle at the first marking point and the vehicle at the first trajectory point. The first preset formula is as follows:

Among them, ΔX ₁ is used to represent the first longitudinal distance deviation between the vehicle at the first mark point and the vehicle at the first trajectory point.

Calculate the third lateral distance deviation Δy _start1 of the vehicle at the first trajectory point relative to the vehicle at the previous trajectory point, and calculate the distance deviation Δy start1 of the vehicle at the third trajectory point relative to the vehicle at the previous trajectory point, that is, the first mark point. The fourth lateral distance deviation Δy _end1 .

Substitute the third lateral distance deviation Δy _start1 , the fourth lateral distance deviation Δy _end1 , the time t _end of the last predicted lane line information, the time t _end1 corresponding to the third trajectory point and the time t _start1 corresponding to the first trajectory point into the second The preset formula is used to calculate the first lateral distance deviation between the vehicle at the first marking point and the vehicle at the first trajectory point. The second preset formula is as follows:

Among them, ΔY ₁ is used to represent the first lateral distance deviation between the vehicle at the first mark point and the vehicle at the first trajectory point.

Calculate the product of the time between the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time and the current time multiplied by the angular velocity of the vehicle at the first trajectory point, and use the obtained product as the distance between the vehicle at the first trajectory point and the vehicle The third orientation angle deviation Δθ _start1 between the first trajectory point and the previous trajectory point, that is, Δθ _start1 = (t _cur -t _E )*ω _start1 , where t _cur is used to represent the current moment, and t _E is represented by At the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time, ω _start1 is used to represent the angular velocity of the vehicle at the first trajectory point.

Calculate the product of the time between the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time and the current time multiplied by the angular velocity of the vehicle at the third trajectory point, and use the resulting product as the distance between the vehicle at the third trajectory point and the vehicle The fourth orientation angle deviation Δθ _end1 between the first marking points is Δθ _end1 =(t _cur -t _E )*ω _end1 , where ω _end1 is used to represent the angular velocity of the vehicle at the third trajectory point.

Substitute the third heading angle deviation Δθ _start1 , the fourth heading angle deviation Δθ _end1 , the time t _end of the last predicted lane line information, the time t _end1 corresponding to the third trajectory point and the time t _start1 corresponding to the first trajectory point into the third The preset formula can be used to calculate the first orientation angle deviation between the vehicle at the first marking point and the vehicle at the first trajectory point. The third preset formula is as follows:

Among them, Δθ ₁ is used to represent the first orientation angle deviation between the vehicle at the first marking point and the vehicle at the first trajectory point, and the orientation angle is the angle between the vehicle and the lane centerline.

Further, in one embodiment, the step of calculating the third longitudinal distance deviation between the vehicle at the first trajectory point and the vehicle at a trajectory point preceding the first trajectory point includes:

Substituting the speed and heading angle of the vehicle at the first trajectory point and the time period between the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time and the current time into the fourth preset formula, the calculation result is that the vehicle is at the first trajectory point. The third longitudinal distance deviation Δx _start1 between a trajectory point and the vehicle at the previous trajectory point of the first trajectory point, the fourth preset formula is as follows:

Δx _start1 = (t _cur -t _E )*(V _xstart1 cosθ _start1 -V _ystart1 sinθ _start1 )

Among them, t _cur is used to represent the current moment, t _E is used to represent the moment corresponding to the previous trajectory point of the trajectory point corresponding to the current moment, V _xstart1 is used to represent the lateral speed of the vehicle at the first trajectory point, and V _ystart1 is used to represent The longitudinal velocity of the vehicle at the first trajectory point, θ _start1, is used to represent the heading angle of the vehicle at the first trajectory point.

In this embodiment, the speed of the vehicle at the first trajectory point, the heading angle of the vehicle at the first trajectory point, and the time between the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time and the current time are substituted into the fourth predetermined time. Set up a formula to calculate the third longitudinal distance deviation Δx _start1 between the vehicle at the first trajectory point and the vehicle at the previous trajectory point of the first trajectory point. The fourth preset formula is as follows:

Δx _start1 = (t _cur -t _E )*(V _xstart1 cosθ _start1 -V _ystart1 sinθ _start1 )

Among them, t _cur is used to represent the current moment, t _E is used to represent the moment corresponding to the previous trajectory point of the trajectory point corresponding to the current moment, V _xstart1 is used to represent the lateral speed of the vehicle at the first trajectory point, and V _ystart1 is used to represent The longitudinal velocity of the vehicle at the first trajectory point, θ _start1, is used to represent the heading angle of the vehicle at the first trajectory point. It is easy to think that the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time is the time corresponding to the last trajectory point in the historical trajectory points. It should be noted that among the historical track points, only a preset number of track points are saved on a first-in, first-out basis.

Further, in one embodiment, the speed of the vehicle at the third trajectory point, the heading angle of the vehicle at the third trajectory point, and the time period between the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time and the current time are substituted into The fourth preset formula calculates the fourth longitudinal distance deviation Δx _end1 between the vehicle at the third trajectory point and the vehicle at the previous trajectory point of the third trajectory point, that is

Δx _end1 = (t _cur -t _E )*(V _xend1 cosθ _end1 -V _yend1 sinθ _end1 )

Among them, t _cur is used to represent the current moment, t _E is used to represent the moment corresponding to the previous trajectory point of the trajectory point corresponding to the current moment, V _xend1 is used to represent the lateral speed of the vehicle at the third trajectory point, and V _yend1 is used to represent The longitudinal velocity of the vehicle at the third trajectory point, θ _end1, is used to represent the heading angle of the vehicle at the third trajectory point.

Further, in one embodiment, the step of calculating the third lateral distance deviation between the vehicle at the first trajectory point and the vehicle at the trajectory point preceding the first trajectory point includes:

Substituting the vehicle's speed and heading angle at the first trajectory point and the time period between the time corresponding to the previous trajectory point of the current time and the current time into the fifth preset formula, the vehicle's speed at the first trajectory is calculated. The third lateral distance deviation Δy _start1 between a trajectory point and the vehicle at the previous trajectory point of the first trajectory point, the fifth preset formula is as follows:

Δy _start1 = (t _cur -t _E )*(V _ystart1 sinθ _start1 +V _ystart1 cosθ _start1 )

Among them, t _cur is used to represent the current moment, t _E is used to represent the moment corresponding to the previous trajectory point of the trajectory point corresponding to the current moment, V _ystart1 is used to represent the longitudinal speed of the vehicle at the first trajectory point, and θ _start1 is used to represent The heading angle of the vehicle at the first trajectory point.

In this embodiment, the speed of the vehicle at the first trajectory point, the heading angle of the vehicle at the first trajectory point, and the time between the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time and the current time are substituted into the fifth predetermined time. Set up a formula to calculate the third lateral distance deviation Δy _start1 between the vehicle at the first trajectory point and the vehicle at the previous trajectory point of the first trajectory point. The fifth preset formula is as follows:

Δy _start1 = (t _cur -t _E )*(V _ystart1 sinθ _start1 +V _ystart1 cosθ _start1 )

Among them, t _cur is used to represent the current moment, t _E is used to represent the moment corresponding to the previous trajectory point of the trajectory point corresponding to the current moment, V _ystart1 is used to represent the longitudinal speed of the vehicle at the first trajectory point, and θ _start1 is used to represent The heading angle of the vehicle at the first trajectory point.

Further, in one embodiment, the speed of the vehicle at the third trajectory point, the heading angle of the vehicle at the third trajectory point, and the time period between the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time and the current time are substituted into The fifth preset formula calculates the fourth lateral distance deviation Δy _end1 between the vehicle at the third trajectory point and the vehicle at the previous trajectory point of the third trajectory point, that is

Δy _end1 = (t _cur -t _E )*(V _yend1 sinθ _end1 +V _yend1 cosθ _end1 )

Among them, t _cur is used to represent the current moment, t _E is used to represent the moment corresponding to the previous trajectory point of the trajectory point corresponding to the current moment, V _yend1 is used to represent the longitudinal speed of the vehicle at the third trajectory point, and θ _end1 is used to represent The heading angle of the vehicle at the third trajectory point.

Further, in one embodiment, the first trajectory deviation information includes a first longitudinal distance deviation, a first lateral distance deviation, and a first orientation angle deviation, and the second trajectory deviation information includes a second longitudinal distance deviation, a second longitudinal distance deviation, and a first orientation angle deviation. lateral distance deviation and second orientation angle deviation, the lane at the current moment is obtained based on the first trajectory deviation information, the second trajectory deviation information and the lane line information corresponding to the latest real lane line information update time at the current time The steps for line prediction information include:

Based on the first longitudinal distance deviation, the first lateral distance deviation, the second longitudinal distance deviation and the second lateral distance deviation, the distance calculation formula between two points is used to calculate the trajectory point of the vehicle at the current moment and the trajectory point of the vehicle at the current moment. The distance deviation between the previous trajectory points;

Calculate the difference of the second orientation angle deviation minus the first orientation angle deviation, and use the difference as the fifth orientation between the vehicle's trajectory point at the current moment and the vehicle's previous trajectory point at the current moment's trajectory point. Angular deviation;

The lane line prediction information at the current time is obtained based on the distance deviation, the fifth orientation angle deviation, and the lane line information corresponding to the latest real lane line information update time at the current time.

In this embodiment, the first trajectory deviation information includes a first longitudinal distance deviation, a first lateral distance deviation and a first orientation angle deviation, and the second trajectory deviation information includes a second longitudinal distance deviation, a second lateral distance deviation and a second orientation. Angular deviation. Based on the first longitudinal distance deviation ΔX ₁ , the first lateral distance deviation ΔY ₁ , the second longitudinal distance deviation ΔX ₂ and the second lateral distance deviation ΔY ₂ , the vehicle’s trajectory point at the current moment and The distance deviation between the vehicle at the previous trajectory point of the current trajectory point, that is, the distance deviation

The difference between the second orientation angle deviation minus the first orientation angle deviation is used as the fifth orientation angle deviation Δθ between the vehicle's trajectory point at the current time and the vehicle's previous trajectory point at the current time trajectory point, that is, Δθ =Δθ ₂ -Δθ ₁ .

The lane line prediction information at the current moment can be obtained based on the distance deviation Δd, the fifth orientation angle deviation Δθ, and the lane line information corresponding to the latest real lane line information update time at the current time.

Further, in one embodiment, the step of obtaining the lane line prediction information at the current time based on the distance deviation, the fifth orientation angle deviation and the lane line information corresponding to the latest real lane line information update time at the current time ,include:

The distance deviation, the fifth orientation angle deviation and the lane line information corresponding to the latest real lane line information update time at the current time are substituted into the sixth preset formula to calculate the lane line prediction information at the current time. The sixth preset formula Let the formula be as follows:

Among them, c ₀ , c ₁ , c ₂ and c ₃ are the lane line prediction information at the current moment, c ₀ is used to represent the lateral distance between the vehicle and the lane line at the current moment, and c ₁ is used to represent the heading angle of the vehicle at the current moment. , c ₂ is used to represent the curvature of the road at the current moment, c ₃ is used to represent the curvature change rate of the road at the current moment, and/> It is the lane line information corresponding to the latest real lane line information update time at the current time,/> Used to represent the lateral distance between the vehicle and the lane line corresponding to the latest real lane line information update time at the current moment,/> Used to represent the heading angle of the vehicle corresponding to the latest real lane line information update time at the current moment,/> Used to represent the curvature of the road corresponding to the latest real lane information update time at the current moment,/> Used to represent the curvature change rate of the road corresponding to the latest real lane line information update time at the current time.

In this embodiment, the distance deviation Δd, the fifth orientation angle deviation Δθ and the lane line information corresponding to the latest real lane line information update time at the current time are substituted into the sixth preset formula to calculate the lane line prediction at the current time. Information, the sixth default formula is as follows:

Among them, c ₀ , c ₁ , c ₂ and c ₃ are the lane line prediction information at the current moment, c ₀ is used to represent the lateral distance between the vehicle and the lane line at the current moment, and c ₁ is used to represent the heading angle of the vehicle at the current moment. , c ₂ is used to represent the curvature of the road at the current moment, c ₃ is used to represent the curvature change rate of the road at the current moment, and/> It is the lane line information corresponding to the latest real lane line information update time at the current time,/> Used to represent the lateral distance between the vehicle and the lane line corresponding to the latest real lane line information update time at the current moment,/> Used to represent the heading angle of the vehicle corresponding to the latest real lane line information update time at the current moment,/> Used to represent the curvature of the road corresponding to the latest real lane information update time at the current moment,/> Used to represent the curvature change rate of the road corresponding to the latest real lane line information update time at the current time.

Further, in one embodiment, after obtaining the lane line prediction information at the current moment, the relationship between the vehicle and the lane line at the current moment is obtained through the lane line information linear equation based on the longitudinal distance between the vehicle and the lane line and the lane line prediction information at the current moment. The lateral distance between the vehicle and the lane line is used to control the vehicle based on the lateral distance between the vehicle and the lane line at the current moment. The linear equation of lane line information is as follows:

f＝c ₃ s ³ +c ₂ s ² +c ₁ s+c ₀

Among them, f is used to represent the length change of the vertical line segment projected from the point on the lane line to the direction of the vehicle's longitudinal centerline, and s is used to represent the longitudinal distance between the vehicle's current position and each projected point.

In a second aspect, embodiments of the present application also provide a device for predicting lane line information.

In one embodiment, refer to FIG. 4 , which is a functional module schematic diagram of an embodiment of the lane line information prediction device of the present application. As shown in Figure 4, the lane line information prediction device includes:

The determination module 10 is configured to determine the vehicle driving trajectory point corresponding to the last time when lane line information was predicted as the first mark when the current moment meets the conditions for executing lane line information prediction and there is at least one trajectory point before the trajectory point corresponding to the current moment. point, the vehicle driving trajectory point corresponding to the latest real lane line information update time at the current moment is the second marking point;

The first calculation module 20 is used to calculate the first trajectory deviation information between the vehicle at the first marking point and the vehicle at the first trajectory point, where the first trajectory point is the previous trajectory of the first marking point. point;

The second calculation module 30 is used to calculate the second trajectory deviation information between the vehicle at the second marking point and the vehicle at the second trajectory point, where the second trajectory point is the previous trajectory of the second marking point. point;

The lane line information prediction module 40 is configured to obtain lane line prediction information at the current time based on the first trajectory deviation information, the second trajectory deviation information, and the lane line information corresponding to the latest real lane line information update time at the current time. .

Further, in one embodiment, the lane line information prediction condition is:

a. The current time is after the last time when lane line information was predicted;

b. The difference between the current time and the time of the last predicted lane line information is less than the first preset duration;

c. The current time is greater than the sum of the time of the last predicted lane line information plus the second preset duration, and smaller than the sum of the last time of the last predicted lane line information plus the third preset duration, where the second preset time is The duration is set to be less than the third preset duration;

d. There is a real lane line information update time between the current time and the last time the lane line information was predicted.

Further, in one embodiment, the first trajectory deviation information includes a first longitudinal distance deviation, a first lateral distance deviation and a first orientation angle deviation. The first calculation module 20 is used to:

Obtain a third trajectory point adjacent to the first marker point and after the first marker point;

Calculate the third longitudinal distance deviation Δx _start1 between the vehicle at the first trajectory point and the vehicle at a trajectory point preceding the first trajectory point;

Calculate the fourth longitudinal distance deviation Δx _end1 between the vehicle at the third trajectory point and the vehicle at the first mark point;

Based on the third longitudinal distance deviation Δx _start1 , the fourth longitudinal distance deviation Δx _end1 , the time t _end of the last predicted lane line information, the time t _end1 corresponding to the third trajectory point and the time t corresponding to the first trajectory point _start1 calculates the first longitudinal distance deviation between the vehicle at the first marking point and the vehicle at the first trajectory point through the first preset formula. The first preset formula is as follows:

Wherein, ΔX ₁ is used to represent the first longitudinal distance deviation between the vehicle at the first mark point and the vehicle at the first trajectory point;

Calculate a third lateral distance deviation Δy _start1 between the vehicle at the first trajectory point and the vehicle at a trajectory point preceding the first trajectory point;

Calculate the fourth lateral distance deviation Δy _end1 between the vehicle at the third trajectory point and the vehicle at the first mark point;

Based on the third lateral distance deviation Δy _start1 , the fourth lateral distance deviation Δy _end1 , the time t _end of the last predicted lane line information, the time t _end1 corresponding to the third trajectory point and the time t corresponding to the first trajectory point _start1 calculates the first lateral distance deviation between the vehicle at the first marking point and the vehicle at the first trajectory point through the second preset formula. The second preset formula is as follows:

Wherein, ΔY ₁ is used to represent the first lateral distance deviation between the vehicle at the first mark point and the vehicle at the first trajectory point;

Calculate the product of the time length between the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time and the current time multiplied by the angular velocity of the vehicle at the first trajectory point, and use the product as the vehicle's angular velocity at the first trajectory The third orientation angle deviation Δθ _start1 between the point and the vehicle at the previous trajectory point of the first trajectory point;

Calculate the product of the time length between the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time and the current time multiplied by the angular velocity of the vehicle at the third trajectory point, and use the product as the vehicle's angular velocity at the third trajectory The fourth orientation angle deviation Δθ _end1 between the point and the vehicle at the first mark point;

Based on the third orientation angle deviation Δθ _start1 , the fourth orientation angle deviation Δθ _end1 , the time t _end of the last predicted lane line information, the time t _end1 corresponding to the third trajectory point, and the time t corresponding to the first trajectory point _start1 calculates the first orientation angle deviation between the vehicle at the first marking point and the vehicle at the first trajectory point through the third preset formula. The third preset formula is as follows:

Wherein, Δθ ₁ is used to represent the first orientation angle deviation between the vehicle at the first mark point and the vehicle at the first trajectory point, and the orientation angle is the angle between the vehicle and the lane centerline.

Further, in one embodiment, the first calculation module 20 is used for:

Substituting the speed and heading angle of the vehicle at the first trajectory point and the time period between the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time and the current time into the fourth preset formula, the calculation result is that the vehicle is at the first trajectory point. The third longitudinal distance deviation Δx _start1 between a trajectory point and the vehicle at the previous trajectory point of the first trajectory point, the fourth preset formula is as follows:

Δx _start1 = (t _cur -t _E )*(V _xstart1 cosθ _start1 -V _ystart1 sinθ _start1 )

Among them, t _cur is used to represent the current moment, t _E is used to represent the moment corresponding to the previous trajectory point of the trajectory point corresponding to the current moment, V _xstart1 is used to represent the lateral speed of the vehicle at the first trajectory point, and V _ystart1 is used to represent The longitudinal velocity of the vehicle at the first trajectory point, θ _start1, is used to represent the heading angle of the vehicle at the first trajectory point.

Further, in one embodiment, the first calculation module 20 is used for:

Substituting the vehicle's speed and heading angle at the first trajectory point and the time period between the time corresponding to the previous trajectory point of the current time and the current time into the fifth preset formula, the vehicle's speed at the first trajectory is calculated. The third lateral distance deviation Δy _start1 between a trajectory point and the vehicle at the previous trajectory point of the first trajectory point, the fifth preset formula is as follows:

Δy _start1 = (t _cur -t _E )*(V _ystart1 sinθ _start1 +V _ystart1 cosθ _start1 )

Among them, t _cur is used to represent the current moment, t _E is used to represent the moment corresponding to the previous trajectory point of the trajectory point corresponding to the current moment, V _ystart1 is used to represent the longitudinal speed of the vehicle at the first trajectory point, and θ _start1 is used to represent The heading angle of the vehicle at the first trajectory point.

Further, in one embodiment, the first trajectory deviation information includes a first longitudinal distance deviation, a first lateral distance deviation, and a first orientation angle deviation, and the second trajectory deviation information includes a second longitudinal distance deviation, a second longitudinal distance deviation, and a first orientation angle deviation. The lateral distance deviation and the second orientation angle deviation, the lane line information prediction module 40 is used for:

Based on the first longitudinal distance deviation, the first lateral distance deviation, the second longitudinal distance deviation and the second lateral distance deviation, the distance calculation formula between two points is used to calculate the trajectory point of the vehicle at the current moment and the trajectory point of the vehicle at the current moment. The distance deviation between the previous trajectory points;

Calculate the difference of the second orientation angle deviation minus the first orientation angle deviation, and use the difference as the fifth orientation between the vehicle's trajectory point at the current moment and the vehicle's previous trajectory point at the current moment's trajectory point. Angular deviation;

The lane line prediction information at the current time is obtained based on the distance deviation, the fifth orientation angle deviation, and the lane line information corresponding to the latest real lane line information update time at the current time.

Further, in one embodiment, the lane line information prediction module 40 is used for:

The distance deviation, the fifth orientation angle deviation and the lane line information corresponding to the latest real lane line information update time at the current time are substituted into the sixth preset formula to calculate the lane line prediction information at the current time. The sixth preset formula Let the formula be as follows:

Among them, c ₀ , c ₁ , c ₂ and c ₃ are the lane line prediction information at the current moment, c ₀ is used to represent the lateral distance between the vehicle and the lane line at the current moment, and c ₁ is used to represent the heading angle of the vehicle at the current moment. , c ₂ is used to represent the curvature of the road at the current moment, c ₃ is used to represent the curvature change rate of the road at the current moment, and/> It is the lane line information corresponding to the latest real lane line information update time at the current time,/> Used to represent the lateral distance between the vehicle and the lane line corresponding to the latest real lane line information update time at the current moment,/> Used to represent the heading angle of the vehicle corresponding to the latest real lane line information update time at the current moment,/> Used to represent the curvature of the road corresponding to the latest real lane information update time at the current moment,/> Used to represent the curvature change rate of the road corresponding to the latest real lane line information update time at the current time.

The functional implementation of each module in the above-mentioned lane line information prediction device corresponds to each step in the embodiment of the above-mentioned lane line information prediction device method, and their functions and implementation processes will not be described in detail here.

In a third aspect, embodiments of the present application provide a lane line information prediction device. The lane line information prediction device may be a personal computer (PC), laptop, server, or other device with data processing functions.

Referring to Figure 5, Figure 5 is a schematic diagram of the hardware structure of the lane line information prediction device involved in the embodiment of the present application. In this embodiment of the present application, the lane line information prediction device may include a processor, a memory, a communication interface, and a communication bus.

The communication bus can be of any type and is used to interconnect processors, memories and communication interfaces.

The communication interface includes an input/output (I/O) interface, a physical interface, a logical interface, and other interfaces used to realize device interconnection within the lane line information prediction device, as well as interfaces used to realize the lane line information prediction device An interface that interconnects with other devices, such as other computing devices or user devices. The physical interface can be an Ethernet interface, an optical fiber interface, an ATM interface, etc.; the user equipment can be a display screen (Display), keyboard (Keyboard), etc.

Memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical memory , hard disk, programmable ROM (PROM), erasable PROM (erasable PROM, EPROM), electrically erasable PROM (electrically erasable PROM, EEPROM), etc.

The processor may be a general-purpose processor, and the general-purpose processor may call the lane line information prediction device program stored in the memory and execute the lane line information prediction device method provided by the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). For the method executed when the lane line information prediction device program is called, reference can be made to various embodiments of the lane line information prediction device method of this application, and will not be described again here.

Those skilled in the art can understand that the hardware structure shown in Figure 5 does not limit the present application, and may include more or fewer components than shown, or combine certain components, or arrange different components.

In a fourth aspect, embodiments of the present application further provide a computer-readable storage medium.

The computer-readable storage medium of the present application stores a lane line information prediction device program, wherein when the lane line information prediction device program is executed by a processor, the steps of the lane line information prediction device method as described above are implemented.

For the method implemented when the lane line information prediction device program is executed, reference can be made to various embodiments of the lane line information prediction device method of the present application, and will not be described again here.

It should be noted that the above serial numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

The terms "including" and "having" and any variations thereof in the description and claims of this application and the above-described drawings are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes Other steps or units inherent to such processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc. They do not represent a sequence, nor do they limit "first", "second" and "third" are different types.

In the description of the embodiments of this application, "exemplary", "such as" or "for example" are used to represent examples, illustrations or explanations. Any embodiment or design described as "exemplary," "such as," or "for example" in the embodiments of the present application is not to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the words "exemplary," "such as," or "for example" is intended to present the concepts in a concrete manner.

In the description of the embodiments of this application, unless otherwise stated, "/" means or, for example, A/B can mean A or B; "and/or" in the text is just a way to describe the association of associated objects. Relationship means that there can be three relationships. For example, A and/or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiment of this application, " "Plural" means two or more than two.

Some of the processes described in the embodiments of this application include multiple operations or steps that appear in a specific order. However, it should be understood that these operations or steps may be performed out of the order in which they appear in the embodiments of this application or in parallel. , the sequence number of the operation is only used to distinguish different operations, the sequence number itself does not represent any execution order. Additionally, these processes may include more or fewer operations, and these operations or steps may be performed sequentially or in parallel, and these operations or steps may be combined.

Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is better. implementation. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM/RAM) as mentioned above. , magnetic disk, optical disk), including several instructions to cause a terminal device to execute the methods described in various embodiments of the present application.

The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of the present application may be directly or indirectly used in other related technical fields. , are all equally included in the patent protection scope of this application.

Claims (10)

1. A lane line information prediction method, characterized in that the lane line information prediction method includes: When the current moment satisfies the conditions for executing lane line information prediction and there is at least one track point before the trajectory point corresponding to the current moment, the vehicle driving trajectory point corresponding to the last time when lane line information was predicted is determined to be the first marking point, which is closest to the current moment. The vehicle driving trajectory point corresponding to the real lane line information update time is the second marking point; Calculate first trajectory deviation information between the vehicle at the first marking point and the vehicle at a first trajectory point, where the first trajectory point is a trajectory point preceding the first marking point; Calculate second trajectory deviation information between the vehicle at the second marking point and the vehicle at a second trajectory point, where the second trajectory point is a trajectory point preceding the second marking point; The lane line prediction information at the current time is obtained based on the first trajectory deviation information, the second trajectory deviation information and the lane line information corresponding to the latest real lane line information update time at the current time. 2. The lane line information prediction method according to claim 1, characterized in that the lane line information prediction condition is: a. The current time is after the last time when lane line information was predicted; b. The difference between the current time and the time of the last predicted lane line information is less than the first preset duration; c. The current time is greater than the sum of the time of the last predicted lane line information plus the second preset duration, and smaller than the sum of the last time of the last predicted lane line information plus the third preset duration, where the second preset time is The duration is set to be less than the third preset duration; d. There is a real lane line information update time between the current time and the last time the lane line information was predicted. 3. The lane line information prediction method according to claim 1, wherein the first trajectory deviation information includes a first longitudinal distance deviation, a first lateral distance deviation and a first orientation angle deviation, and the calculated vehicle is in The step of obtaining first trajectory deviation information between the first marker point and the vehicle at the first trajectory point includes: Obtain a third trajectory point adjacent to the first marker point and after the first marker point; Calculate the third longitudinal distance deviation Δx _start1 between the vehicle at the first trajectory point and the vehicle at a trajectory point preceding the first trajectory point; Calculate the fourth longitudinal distance deviation Δx _end1 between the vehicle at the third trajectory point and the vehicle at the first mark point; Based on the third longitudinal distance deviation Δx _start1 , the fourth longitudinal distance deviation Δx _end1 , the time t _end of the last predicted lane line information, the time t _end1 corresponding to the third trajectory point and the time t corresponding to the first trajectory point _start1 calculates the first longitudinal distance deviation between the vehicle at the first marking point and the vehicle at the first trajectory point through the first preset formula. The first preset formula is as follows: Wherein, ΔX ₁ is used to represent the first longitudinal distance deviation between the vehicle at the first mark point and the vehicle at the first trajectory point; Calculate a third lateral distance deviation Δy _start1 between the vehicle at the first trajectory point and the vehicle at a trajectory point preceding the first trajectory point; Calculate the fourth lateral distance deviation Δy _end1 between the vehicle at the third trajectory point and the vehicle at the first mark point; Based on the third lateral distance deviation Δy _start1 , the fourth lateral distance deviation Δy _end1 , the time t _end of the last predicted lane line information, the time t _end1 corresponding to the third trajectory point and the time t corresponding to the first trajectory point _start1 calculates the first lateral distance deviation between the vehicle at the first marking point and the vehicle at the first trajectory point through the second preset formula. The second preset formula is as follows: Wherein, ΔY ₁ is used to represent the first lateral distance deviation between the vehicle at the first mark point and the vehicle at the first trajectory point; Calculate the product of the time length between the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time and the current time multiplied by the angular velocity of the vehicle at the first trajectory point, and use the product as the vehicle's angular velocity at the first trajectory The third orientation angle deviation Δθ _start1 between the point and the vehicle at the previous trajectory point of the first trajectory point; Calculate the product of the time length between the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time and the current time multiplied by the angular velocity of the vehicle at the third trajectory point, and use the product as the vehicle's angular velocity at the third trajectory The fourth orientation angle deviation Δθ _end1 between the point and the vehicle at the first mark point; Based on the third orientation angle deviation Δθ _start1 , the fourth orientation angle deviation Δθ _end1 , the time t _end of the last predicted lane line information, the time t _end1 corresponding to the third trajectory point, and the time t corresponding to the first trajectory point _start1 calculates the first orientation angle deviation between the vehicle at the first marking point and the vehicle at the first trajectory point through the third preset formula. The third preset formula is as follows: Wherein, Δθ ₁ is used to represent the first orientation angle deviation between the vehicle at the first mark point and the vehicle at the first trajectory point, and the orientation angle is the angle between the vehicle and the lane centerline. 4. The method for predicting lane line information according to claim 3, wherein the calculated distance between the vehicle at the first trajectory point and the vehicle at the previous trajectory point of the first trajectory point is calculated. Three longitudinal distance deviation steps include: Substituting the speed and heading angle of the vehicle at the first trajectory point and the time period between the time corresponding to the previous trajectory point of the trajectory point corresponding to the current time and the current time into the fourth preset formula, the calculation result is that the vehicle is at the first trajectory point. The third longitudinal distance deviation Δx _start1 between a trajectory point and the vehicle at the previous trajectory point of the first trajectory point, the fourth preset formula is as follows: Δx _start1 = (t _cur -t _E )*(V _xstart1 cosθ _start1 -V _ystart1 sinθ _start1 ) Among them, t _cur is used to represent the current moment, t _E is used to represent the moment corresponding to the previous trajectory point of the trajectory point corresponding to the current moment, V _xstart1 is used to represent the longitudinal speed of the vehicle at the first trajectory point, and V _ystart1 is used to represent The lateral speed of the vehicle at the first trajectory point, θ _start1, is used to represent the heading angle of the vehicle at the first trajectory point. 5. The method for predicting lane line information according to claim 3, wherein the calculated distance between the vehicle at the first trajectory point and the vehicle at the previous trajectory point of the first trajectory point is calculated. Three lateral distance deviation steps include: Substituting the vehicle's speed and heading angle at the first trajectory point and the time period between the time corresponding to the previous trajectory point of the current time and the current time into the fifth preset formula, the vehicle's speed at the first trajectory is calculated. The third lateral distance deviation Δy _start1 between a trajectory point and the vehicle at the previous trajectory point of the first trajectory point, the fifth preset formula is as follows: Δy _start1 = (t _cur -t _E )*(V _ystart1 sinθ _start1 +V _ystart1 cosθ _start1 ) Among them, t _cur is used to represent the current moment, t _E is used to represent the moment corresponding to the previous trajectory point of the trajectory point corresponding to the current moment, V _ystart1 is used to represent the longitudinal speed of the vehicle at the first trajectory point, and θ _start1 is used to represent The heading angle of the vehicle at the first trajectory point. 6. The lane line information prediction method according to claim 1, wherein the first trajectory deviation information includes a first longitudinal distance deviation, a first lateral distance deviation and a first orientation angle deviation, and the second trajectory The deviation information includes a second longitudinal distance deviation, a second lateral distance deviation and a second orientation angle deviation, which is updated based on the first trajectory deviation information, the second trajectory deviation information and the real lane line information closest to the current moment. The steps for obtaining the lane line prediction information at the current moment from the lane line information corresponding to the time include: Based on the first longitudinal distance deviation, the first lateral distance deviation, the second longitudinal distance deviation and the second lateral distance deviation, the distance calculation formula between two points is used to calculate the trajectory point of the vehicle at the current moment and the trajectory point of the vehicle at the current moment. The distance deviation between the previous trajectory points; Calculate the difference of the second orientation angle deviation minus the first orientation angle deviation, and use the difference as the fifth orientation between the vehicle's trajectory point at the current moment and the vehicle's previous trajectory point at the current moment's trajectory point. Angular deviation; The lane line prediction information at the current time is obtained based on the distance deviation, the fifth orientation angle deviation, and the lane line information corresponding to the latest real lane line information update time at the current time. 7. The lane line information prediction method according to claim 6, characterized in that the lane line is based on the distance deviation, the fifth orientation angle deviation and the lane line corresponding to the latest real lane line information update time at the current time. The steps to obtain lane line prediction information at the current moment include: The distance deviation, the fifth orientation angle deviation and the lane line information corresponding to the latest real lane line information update time at the current time are substituted into the sixth preset formula to calculate the lane line prediction information at the current time. The sixth preset formula Let the formula be as follows: Among them, c ₀ , c ₁ , c ₂ and c ₃ are the lane line prediction information at the current moment, c ₀ is used to represent the lateral distance between the vehicle and the lane line at the current moment, and c ₁ is used to represent the heading angle of the vehicle at the current moment. , c ₂ is used to represent the curvature of the road at the current moment, c ₃ is used to represent the curvature change rate of the road at the current moment, and/> It is the lane line information corresponding to the latest real lane line information update time at the current time,/> Used to represent the lateral distance between the vehicle and the lane line corresponding to the latest real lane line information update time at the current moment,/> Used to represent the heading angle of the vehicle corresponding to the latest real lane line information update time at the current moment,/> Used to represent the curvature of the road corresponding to the latest real lane information update time at the current moment,/> Used to represent the curvature change rate of the road corresponding to the latest real lane line information update time at the current time. 8. A lane line information prediction device, characterized in that the lane line information prediction device includes: A determination module configured to determine the vehicle driving trajectory point corresponding to the last time the lane line information was predicted as the first marker point when the current moment meets the conditions for executing lane line information prediction and there is at least one trajectory point before the trajectory point corresponding to the current moment. , the vehicle driving trajectory point corresponding to the latest real lane line information update time at the current moment is the second marking point; The first calculation module is used to calculate the first trajectory deviation information between the vehicle at the first marking point and the vehicle at the first trajectory point, where the first trajectory point is the trajectory point preceding the first marking point. ; The second calculation module is used to calculate the second trajectory deviation information between the vehicle at the second marking point and the vehicle at the second trajectory point, where the second trajectory point is the previous trajectory point of the second marking point. ; The lane line information prediction module is configured to obtain the lane line prediction information at the current moment based on the first trajectory deviation information, the second trajectory deviation information and the lane line information corresponding to the latest real lane line information update time at the current time. 9. A lane line information prediction device, characterized in that the lane line information prediction device includes a processor, a memory, and a lane line information prediction program stored on the memory and executable by the processor, wherein When the lane line information prediction program is executed by the processor, the steps of the lane line information prediction method according to any one of claims 1 to 7 are implemented. 10. A computer-readable storage medium, characterized in that a lane line information prediction program is stored on the computer-readable storage medium, wherein when the lane line information prediction program is executed by a processor, the steps of claims 1 to 1 are implemented The steps of the lane line information prediction method according to any one of 7.