CN116360455A

CN116360455A - Method and device for compensating dynamic deviation of automatic driving vehicle, electronic equipment and medium

Info

Publication number: CN116360455A
Application number: CN202310439919.XA
Authority: CN
Inventors: 王发平; 韦文; 胡仁强
Original assignee: Shenzhen Haixing Zhijia Technology Co Ltd
Current assignee: Shenzhen Haixing Zhijia Technology Co Ltd
Priority date: 2023-04-12
Filing date: 2023-04-12
Publication date: 2023-06-30

Abstract

The invention relates to the technical field of automatic driving, in particular to a dynamic deviation compensation method, a device, electronic equipment and a medium for an automatic driving vehicle, which comprise the following steps: acquiring a plurality of historical track points included in a driven track corresponding to a target vehicle, and determining positions, curvatures, lateral errors and course angle errors corresponding to the historical track points; according to the positions and curvatures corresponding to the historical track points, determining target track points corresponding to the linear track in the historical track; calculating the dynamic compensation quantity of the linear track corresponding to each target track point according to the transverse error and the course angle error corresponding to each target track point; and controlling the corresponding wheel angle of the target vehicle according to the dynamic compensation quantity so as to compensate the dynamic offset in the running process of the target vehicle. Therefore, the transverse error and the course angle error of the target vehicle in the tracking process are smaller, and the target vehicle is prevented from deviating from the central line of the lane seriously. Thereby improving the control accuracy of the target vehicle.

Description

Method and device for compensating dynamic deviation of automatic driving vehicle, electronic equipment and medium

Technical Field

The invention relates to the field of automatic driving, in particular to a dynamic deviation compensation method, a device, electronic equipment and a medium for an automatic driving vehicle.

Background

With the development of unmanned technologies, unmanned technologies for on-site transportation vehicles are also rapidly developing. The traditional unmanned transport vehicle in the field is generally formed by modifying a collector card, the collector card is composed of a towing head and a trailer, the length of the collector card is long, turning, lane changing and reversing driving control are not flexible enough, the track of the trailer is difficult to accurately predict, and the trafficability of the collector card on a narrow road is poor. Based on the above drawbacks, unmanned vehicles in the field have a trend to replace the collector card with intelligent flatcars (also called IGVs) gradually.

Compared with the traditional collection card, the intelligent flat car structure has no towing head part, the driving system is arranged on a trailer, the car length is short, the steering system is jointly completed by a front axle and a rear axle, and the intelligent flat car structure has all-splayed steering, half-splayed steering, crab walking and other motion driving modes. The full splayed steering and the half splayed steering make the turning and lane changing more flexible; the vehicle is symmetrical from front to back, so that the reversing running and the forward running are as convenient, and the crab running can realize the translation lane change of the vehicle on a narrow road. Based on these advantages, the use of intelligent flat cars in an in-field scenario (e.g., port) will be a trend.

Although the intelligent flat car has a plurality of advantages, the intelligent flat car has more steering wheels and complicated steering synchronous control, meanwhile, the load of the intelligent flat car directly acts on each wheel, the steering can be influenced by different load weights and different distribution conditions, and the influence can be reflected in the condition of zero rotation angle input, and the phenomenon that the vehicle deviates from the center line of a lane can be obviously observed when the vehicle runs in a straight line tracking way. This affects not only the lateral error at the time of tracking control but also the heading angle error, and even causes the vehicle to run away at high speed tracking when the lane center line deviation phenomenon is serious.

Disclosure of Invention

In view of the above, the embodiments of the present invention provide a method, an apparatus, an electronic device, and a medium for compensating dynamic deviation of an autonomous vehicle, which aim to solve the problem that a target vehicle deviates from a lane center line in tracking control.

According to a first aspect, an embodiment of the present invention provides a dynamic deviation compensation method for an autonomous vehicle, including:

acquiring a plurality of historical track points included in a driven track corresponding to a target vehicle, and determining positions, curvatures, lateral errors and course angle errors corresponding to the historical track points;

According to the positions and curvatures corresponding to the historical track points, determining target track points corresponding to the linear track in the historical track;

calculating the dynamic compensation quantity of the linear track corresponding to each target track point according to the transverse error and the course angle error corresponding to each target track point;

and controlling the corresponding wheel angle of the target vehicle according to the dynamic compensation quantity so as to compensate the dynamic offset in the running process of the target vehicle.

According to the method for compensating the dynamic deviation of the automatic driving vehicle, provided by the embodiment of the invention, a plurality of historical track points included in the running track corresponding to the target vehicle are obtained, and the position, curvature, transverse error and course angle error corresponding to each historical track point are determined. Then, according to the positions and curvatures corresponding to the historical track points, the target track points corresponding to the linear track in the historical track are determined, and the accuracy of the determined target track points is ensured. According to the transverse error and the course angle error corresponding to each target track point, calculating the dynamic compensation quantity of the linear track corresponding to each target track point, and ensuring the accuracy of the calculated dynamic compensation quantity of the linear track corresponding to the target track point. And then, controlling the corresponding wheel corner of the target vehicle according to the dynamic compensation quantity to compensate the dynamic offset in the running process of the target vehicle, thereby ensuring that the transverse error and the course angle error of the target vehicle are smaller in the tracking process and ensuring that the target vehicle does not deviate from the central line of the lane seriously. Thereby improving the control accuracy of the target vehicle.

With reference to the first aspect, in a first implementation manner of the first aspect, determining each target track point corresponding to a straight track in the historical track according to a position and a curvature corresponding to each historical track point includes:

determining a historical track starting point from the historical track points according to the positions of the historical track points;

starting from the historical track starting point, comparing the curvature of each historical track point with a preset curvature threshold value according to the sequence of driving each historical track point;

when the curvatures of at least two continuous historical track points are smaller than the preset curvature threshold, determining the at least two continuous historical track points as candidate track points;

and determining target track points from the candidate track points according to the positions of the candidate track points.

According to the dynamic deviation compensation method for the automatic driving vehicle, provided by the embodiment of the invention, the historical track starting point is determined from the historical track points according to the positions of the historical track points, so that the accuracy of the determined historical track starting point is ensured. Starting from the historical track starting point, comparing the curvature of each historical track point with a preset curvature threshold value according to the sequence of driving each historical track point, and ensuring the accuracy of the obtained comparison result. When the curvatures of at least two continuous historical track points are smaller than the preset curvature threshold, determining the at least two continuous historical track points as candidate track points, and ensuring that the determined candidate track points are on a straight track. And then, determining target track points from the candidate track points according to the positions of the candidate track points, so that the accuracy of the result that the determined candidate track points are the target track points is ensured.

With reference to the first implementation manner of the first aspect, in a second implementation manner of the first aspect, determining, according to a position of each candidate track point, a target track point from each candidate track point includes:

calculating a candidate distance from the first candidate track point to the last candidate track point according to the positions of the candidate track points;

comparing the candidate distance with a preset distance threshold;

when the candidate distance is greater than a preset distance threshold value, determining the candidate track point as a standby track point;

and determining the standby track point as the target track point according to the corresponding transverse error of the standby track point.

According to the dynamic deviation compensation method for the automatic driving vehicle, provided by the embodiment of the invention, the candidate distance from the first candidate track point to the last candidate track point is calculated according to the positions of the candidate track points, so that the accuracy of the calculated candidate distance is ensured. And comparing the candidate distance with a preset distance threshold value, so that the accuracy of the obtained comparison result is ensured. When the candidate distance is larger than the preset distance threshold value, the candidate track point is determined to be the standby track point, and the accuracy of the result that the determined candidate track point is the standby track point is ensured. And according to the corresponding transverse error of the standby track point, determining the standby track point as the target track point, and ensuring the accuracy of the determined target track point. And further, the accuracy of controlling the corresponding wheel angle of the target vehicle according to the target track point can be ensured.

With reference to the second embodiment of the first aspect, in a third embodiment of the first aspect, determining, according to a lateral error corresponding to the spare track point, the spare track point as the target track point includes:

comparing the absolute values of the transverse errors corresponding to the standby track points, and selecting the maximum absolute transverse error from the absolute values of the transverse errors;

comparing the maximum absolute transverse error with a preset transverse error threshold;

and when the maximum absolute transverse error is greater than a preset transverse error threshold, determining the standby track point as a target track point.

According to the dynamic deviation compensation method for the automatic driving vehicle, provided by the embodiment of the invention, the absolute values of the transverse errors corresponding to the standby track points are compared, the maximum absolute transverse error is selected from the absolute values of the transverse errors, and the accuracy of the determined maximum absolute transverse error is ensured. Comparing the maximum absolute transverse error with a preset transverse error threshold; and when the maximum absolute transverse error is greater than a preset transverse error threshold, determining the standby track point as the target track point, and ensuring the accuracy of the determined standby track point as the target track point.

With reference to the first aspect, in a fourth implementation manner of the first aspect, calculating, according to a lateral error and a heading angle error corresponding to each target track point, a dynamic compensation amount of a straight track corresponding to each target track point includes:

According to the corresponding transverse errors of each target track point, calculating the corresponding average transverse error of each target track point;

calculating the average course angle error corresponding to each target track point according to the course angle error corresponding to each target track point;

and calculating the dynamic compensation quantity according to the relation between the average transverse error and the average course angle error.

According to the dynamic deviation compensation method for the automatic driving vehicle, which is provided by the embodiment of the invention, the average transverse error corresponding to each target track point is calculated according to the transverse error corresponding to each target track point, so that the accuracy of the average transverse error corresponding to the calculated target track point is ensured. According to the course angle errors corresponding to the target track points, the average course angle errors corresponding to the target track points are calculated, and the accuracy of the calculated average course angle errors corresponding to the target track points is ensured. According to the relation between the average transverse error and the average course angle error, the dynamic compensation quantity is calculated, and the accuracy of the calculated dynamic compensation quantity is ensured.

With reference to the first aspect, in a fifth implementation manner of the first aspect, according to the dynamic compensation amount, the controlling the wheel angle corresponding to the target vehicle to compensate the dynamic offset during the driving of the target vehicle includes:

Acquiring a feedforward corner and a current corner of the next step corresponding to the target vehicle;

determining a wheel target corner of the next step corresponding to the target vehicle according to the relation among the dynamic compensation quantity, the feedforward corner and the current corner;

and controlling the corresponding wheel angle of the target vehicle according to the wheel target angle so as to compensate the dynamic offset in the running process of the target vehicle.

According to the dynamic deviation compensation method for the automatic driving vehicle, provided by the embodiment of the invention, the feedforward corner and the current corner of the next step corresponding to the target vehicle are obtained, then the wheel target corner of the next step corresponding to the target vehicle is determined according to the relation among the dynamic compensation quantity, the feedforward corner and the current corner, and the accuracy of the determined wheel target corner of the next step corresponding to the target vehicle is ensured. And then, controlling the corresponding wheel corner of the target vehicle according to the wheel target corner to compensate the dynamic offset in the running process of the target vehicle, thereby ensuring that the transverse error and the course angle error of the target vehicle are smaller in the tracking process and ensuring that the target vehicle does not deviate from the central line of the lane seriously. Thereby improving the control accuracy of the target vehicle.

With reference to the fifth implementation manner of the first aspect, in a sixth implementation manner of the first aspect, acquiring a feed-forward rotation angle of a next step corresponding to the target vehicle includes:

acquiring a current speed and a pre-aiming coefficient corresponding to a target vehicle;

calculating to obtain a pretightening distance by utilizing the relation between the current speed and the pretightening coefficient;

determining a pretightening trajectory point according to the pretightening distance, and determining a pretightening curvature of the pretightening trajectory point;

acquiring a vehicle equivalent wheelbase corresponding to a target vehicle;

and determining a feed-forward corner of the next step corresponding to the target vehicle according to the relation between the pre-aiming curvature and the equivalent wheelbase of the vehicle.

According to the dynamic deviation compensation method for the automatic driving vehicle, which is provided by the embodiment of the invention, the current speed and the pretightening coefficient corresponding to the target vehicle are obtained, and the pretightening distance is calculated by utilizing the relation between the current speed and the pretightening coefficient, so that the accuracy of the calculated pretightening distance is ensured. And determining a pretightening trajectory point according to the pretightening distance, and determining the pretightening curvature of the pretightening trajectory point, thereby ensuring the accuracy of the determined pretightening curvature. Acquiring a vehicle equivalent wheelbase corresponding to a target vehicle; and according to the relation between the pre-aiming curvature and the equivalent wheelbase of the vehicle, determining the feedforward corner of the next step corresponding to the target vehicle, and ensuring the accuracy of the determined feedforward corner. And further, the accuracy of the calculated wheel target rotation angle can be ensured.

According to a second aspect, an embodiment of the present invention further provides a dynamic deviation compensation apparatus for an autonomous vehicle, including:

the acquisition module is used for acquiring a plurality of historical track points included in the driven track corresponding to the target vehicle and determining positions, curvatures, transverse errors and course angle errors corresponding to the historical track points;

the determining module is used for determining each target track point corresponding to the linear track in the history track according to the position and the curvature corresponding to each history track point;

the calculation module is used for calculating the dynamic compensation quantity of the linear track corresponding to each target track point according to the transverse error and the course angle error corresponding to each target track point;

and the control module is used for controlling the corresponding wheel angle of the target vehicle according to the dynamic compensation quantity so as to compensate the dynamic offset in the running process of the target vehicle.

The dynamic deviation compensation device for the automatic driving vehicle acquires a plurality of historical track points included in a driven track corresponding to a target vehicle, and determines positions, curvatures, lateral errors and course angle errors corresponding to the historical track points. Then, according to the positions and curvatures corresponding to the historical track points, the target track points corresponding to the linear track in the historical track are determined, and the accuracy of the determined target track points is ensured. According to the transverse error and the course angle error corresponding to each target track point, calculating the dynamic compensation quantity of the linear track corresponding to each target track point, and ensuring the accuracy of the calculated dynamic compensation quantity of the linear track corresponding to the target track point. And then, controlling the corresponding wheel corner of the target vehicle according to the dynamic compensation quantity to compensate the dynamic offset in the running process of the target vehicle, thereby ensuring that the transverse error and the course angle error of the target vehicle are smaller in the tracking process and ensuring that the target vehicle does not deviate from the central line of the lane seriously. Thereby improving the control accuracy of the target vehicle.

According to a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, where the memory and the processor are communicatively connected to each other, and the memory stores computer instructions, and the processor executes the computer instructions, thereby executing the method for compensating for dynamic deviation of an autonomous vehicle according to the first aspect or any implementation manner of the first aspect.

According to a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the method of dynamic deviation compensation of an autonomous vehicle of the first aspect or any of the embodiments of the first aspect.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method for dynamic bias compensation for an autonomous vehicle using an embodiment of the present invention;

FIG. 2 is a flow chart of a method for compensating for dynamic deviation of an autonomous vehicle according to another embodiment of the present invention;

FIG. 3 is a flow chart of a method for compensating for dynamic deviation of an autonomous vehicle using a further embodiment of the present invention;

FIG. 4 is a functional block diagram of a dynamic deviation compensation apparatus for an autonomous vehicle according to an embodiment of the present invention;

fig. 5 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

It should be noted that, in the method for compensating dynamic deviation of an autopilot vehicle provided in the embodiment of the present application, the execution subject may be a device for compensating dynamic deviation of an autopilot vehicle, where the device for compensating dynamic deviation of an autopilot vehicle may be implemented as part or all of an electronic device by software, hardware, or a combination of software and hardware, where the electronic device may be part or all of a computing platform carried in a target vehicle, and the electronic device may also be a server or a terminal independent of the target vehicle, where the server in the embodiment of the present application may be a server or a server cluster formed by multiple servers, and the terminal in the embodiment of the present application may be other intelligent hardware devices such as a smart phone, a personal computer, a tablet computer, a wearable device, and an intelligent robot. In the following method embodiments, the execution subject is an electronic device.

In one embodiment of the present application, as shown in fig. 1, a method for compensating dynamic deviation of an automatic driving vehicle is provided, and the method is applied to an electronic device for illustration, and includes the following steps:

s11, acquiring a plurality of historical track points included in the driven track corresponding to the target vehicle, and determining positions, curvatures, lateral errors and course angle errors corresponding to the historical track points.

Optionally, the electronic device may receive a preset track sent by other devices, or may receive a preset track input by a user, or may plan, according to a target start point and a target end point, a preset track from the target start point to the target end point by using a path planning method.

Specifically, the electronic device may control the target vehicle to automatically drive according to the received preset track, record the traveled track, obtain a plurality of historical track points included in the traveled track corresponding to the target vehicle, and determine positions corresponding to the historical track points by using the positioning system. The electronic device may further determine a curvature corresponding to each historical track point according to the information of the preset track, and determine a lateral error and a heading angle error corresponding to each historical track point according to a positional relationship between each historical track point and a preset track point corresponding to each historical track point in the preset track.

In an optional embodiment of the present application, the electronic device may further determine an accumulated length corresponding to the target vehicle reaching each historical track point according to the position corresponding to each historical track point.

For example, the electronic device may obtain track point information (X, Y, k, s, e, h) corresponding to each historical track point, where X and Y are coordinate points of the historical track point in the X axis and the Y axis, k is a curvature corresponding to the historical track point, s is an accumulated length from the current historical track point to the track start point, e is a lateral error corresponding to the historical track point, and h is a heading angle error corresponding to the historical track point.

S12, determining each target track point corresponding to the straight track in the history track according to the position and curvature corresponding to each history track point.

Specifically, after the electronic device obtains the curvatures corresponding to the historical track points, the curvature corresponding to the historical track points can be compared with a preset curvature threshold, and each target track point corresponding to the linear track in the historical track can be determined according to the comparison result and the positions of the historical track points.

This step will be described in detail below.

S13, calculating the dynamic compensation quantity of the linear track corresponding to each target track point according to the transverse error and the course angle error corresponding to each target track point.

Specifically, after determining each target track point corresponding to the linear track in the historical track, the electronic device may calculate the dynamic compensation amount of the linear track corresponding to each target track point according to the relationship between the lateral error and the heading angle error corresponding to each target track point.

This step will be described in detail below.

And S14, controlling the corresponding wheel angle of the target vehicle according to the dynamic compensation quantity so as to compensate the dynamic offset in the running process of the target vehicle.

In an optional embodiment of the present application, the electronic device may control a wheel angle of the target vehicle according to the dynamic compensation amount, and dynamically compensate the wheel angle corresponding to the target vehicle, so as to compensate the dynamic offset in the driving process of the target vehicle.

In one embodiment of the present application, as shown in fig. 2, a method for compensating dynamic deviation of an automatic driving vehicle is provided, and the method is applied to an electronic device for illustration, and includes the following steps:

s21, acquiring a plurality of historical track points included in the driven track corresponding to the target vehicle, and determining positions, curvatures, lateral errors and course angle errors corresponding to the historical track points.

For this step, please refer to the description of S11 in fig. 1, and a detailed description is omitted here.

S22, determining each target track point corresponding to the straight track in the history track according to the position and curvature corresponding to each history track point.

In an optional embodiment of the present application, the step S22 "determining each target track point corresponding to the straight track in the history track according to the position and the curvature corresponding to each history track point" may include the following steps:

s221, determining a historical track starting point from the historical track points according to the positions of the historical track points.

Specifically, the electronic device may determine a history track start point from the history track points according to the positions of the respective history track points.

S222, starting from the historical track start point, and comparing the curvature of each historical track point with a preset curvature threshold value according to the sequence of driving each historical track point.

Specifically, the electronic device may receive a preset curvature threshold value input by a user, may also receive preset curvature threshold values sent by other devices, and may set the preset curvature threshold value according to the curvature of the historical track point.

After determining the historical track start point, the electronic device compares the curvature of each historical track point with a preset curvature threshold value according to the sequence of each historical track point of the target vehicle running from the historical track start point.

S223, when the curvatures of at least two continuous historical track points are smaller than a preset curvature threshold value, determining the at least two continuous historical track points as candidate track points.

Specifically, after the electronic device compares the curvature of each history track point with the preset curvature threshold, when there are at least two continuous history track points whose curvatures are smaller than the preset curvature threshold, the electronic device determines that the at least two continuous history track points are candidate track points.

When the curvature of at least one history track point is larger than or equal to a preset curvature threshold, the electronic equipment continuously compares the curvature of the next history track point with the preset curvature threshold until at least two continuous history track points are found to be smaller than the preset curvature threshold, and the at least two continuous history track points are determined to be candidate track points.

S224, determining target track points from the candidate track points according to the positions of the candidate track points.

In an optional implementation manner of the application, the electronic device determines each candidate track point as each target track point corresponding to the straight track in the history track according to the position of each candidate track point.

In an optional embodiment of the present application, the step S224 "determining the target track point from the candidate track points according to the positions of the candidate track points" may include the following steps:

(1) And calculating the candidate distance from the first candidate track point to the last candidate track point according to the positions of the candidate track points.

Specifically, after determining each candidate track point, the electronic device may calculate a candidate distance from the first candidate track point to the last candidate track point according to the position of each candidate track point.

(2) And comparing the candidate distance with a preset distance threshold.

Specifically, after the candidate distance is determined, the electronic device may receive a preset distance threshold value input by a user, or may receive a preset distance threshold value sent by other devices, or may set the preset distance threshold value according to the length of an actual running track.

After the preset distance threshold is obtained, the electronic device may compare the candidate distance to the preset distance threshold.

(3) And when the candidate distance is greater than a preset distance threshold value, determining the candidate track point as a standby track point.

Specifically, when the candidate distance is greater than a preset distance threshold, the candidate track point is determined to be a standby track point.

When the candidate distance is smaller than or equal to the preset distance threshold, the electronic device can compare the curvature of the historical track points after the last candidate track point with the preset curvature threshold, determine candidate track points with the curvature of at least two continuous historical track points smaller than the preset curvature threshold again, and the candidate distance between the first candidate track point and the last candidate track point is larger than the preset distance threshold, and the candidate track points are used as standby track points.

(4) And determining the standby track point as the target track point according to the corresponding transverse error of the standby track point.

In an alternative embodiment of the present application, the electronic device may determine the standby track point as the target track point.

In another optional embodiment of the present application, the step (4) "determining the standby track point as the target track point according to the lateral error corresponding to the standby track point" may include the following steps:

(41) Comparing the absolute values of the lateral errors corresponding to the standby track points, and selecting the maximum absolute lateral error from the absolute values of the lateral errors.

(42) And comparing the maximum absolute transverse error with a preset transverse error threshold.

(43) And when the maximum absolute transverse error is greater than a preset transverse error threshold, determining the standby track point as a target track point.

Specifically, the electronic device may receive a preset lateral error threshold input by a user, may also receive preset lateral error thresholds sent by other devices, and may also set the preset lateral error threshold according to lateral errors corresponding to each historical track point.

After the preset transverse error threshold is obtained, the electronic device can compare the absolute values of the transverse errors corresponding to the standby track points, and the maximum absolute transverse error is selected from the absolute values of the transverse errors. And comparing the maximum absolute transverse error with a preset transverse error threshold, and determining the standby track point as the target track point when the maximum absolute transverse error is larger than the preset transverse error threshold. When the maximum absolute lateral error is smaller than or equal to the preset lateral error threshold, the electronic device determines that the lateral errors corresponding to the standby track points are smaller, so that dynamic deviation compensation is not needed.

And then, the electronic equipment continuously compares the curvature of the historical track point after the last standby track point with a preset curvature threshold value, determines candidate track points of which the curvature of at least two continuous historical track points is smaller than the preset curvature threshold value again, and determines each candidate track point as the standby track point when the candidate distance between the first candidate track point and the last candidate track point is larger than the preset distance threshold value. And then, when the maximum absolute transverse error corresponding to each standby track point is larger than a preset transverse error threshold value, determining the standby track point as a target track point.

In order to better describe the method for compensating the dynamic deviation of the automatic driving vehicle provided by the embodiment of the application, the following is exemplary:

(1) The electronic device can start point-by-point detection from the starting point of the historical track;

(2) Judging the ith history trace point (x _i ,y _i ,k _i ,s _i ,e _i ,h _i ) Curvature k of (2) _i Whether or not to satisfy k _i <k (wherein a curved trajectory having a curvature smaller than k is considered as a straight trajectory):

a) If not satisfy k _i <k, let i=i+1, repeat step (2);

b) If satisfy k _i <k, the point (x _i ,y _i ,k _i ,s _i ,e _i ,h _i ) As a start point (x) _{_} s,y _{_} s,k _{_} s,s _{_} s,e _{_} s,h _{_} s)；

(3) Judging whether the curvature of the (i+1) th point meets k _i+1 <k：

a) If not satisfy k _i+1 <k, making the i=i+2, and repeating the step (2);

b) If it meetsk _i+1 <k, calculate d=s _i+1 -s _{_} s；

(4) Judging whether d > L is satisfied:

a) If d > L is not satisfied, letting i=i+1, repeating step (3);

b) If d > L is met, acquiring transverse error data from the starting point of the linear track to the i+1 point, and finding out the absolute value of the maximum transverse error, and the maximum absolute transverse error e_max;

(5) Judging whether or not e is satisfied _max >α：

a) If not meet e _max >Alpha, making the (i+2) th point be the track starting point of the next linear track, and repeating the step (2);

b) If satisfy e _max >Alpha, the history trace point (x _i+1 ,y _i+1 ,k _i+1 ,s _i+1 ,e _i+1 ,h _i+1 ) As the linear track end point (x _{_t} ,y _{_t} ,k _{_t} ,s _{_t} ,e _{_t} ,h _{_t} ) And (x) _i ,y _i ,k _i ,s _i ,e _i ,h _i ) And (x) _i+1 ,y _i+1 ,k _i+1 ,s _i+1 ,e _i+1 ,h _i+1 ) And determining the target track point.

S23, calculating the dynamic compensation quantity of the linear track corresponding to each target track point according to the transverse error and the course angle error corresponding to each target track point.

For this step, please refer to the description of S13 in fig. 1, and a detailed description is omitted here.

And S24, controlling the corresponding wheel angle of the target vehicle according to the dynamic compensation quantity so as to compensate the dynamic offset in the running process of the target vehicle.

For this step, please refer to the description of S14 in fig. 1, and a detailed description is omitted here.

According to the dynamic deviation compensation method for the automatic driving vehicle, provided by the embodiment of the invention, the historical track starting point is determined from the historical track points according to the positions of the historical track points, so that the accuracy of the determined historical track starting point is ensured. Starting from the historical track starting point, comparing the curvature of each historical track point with a preset curvature threshold value according to the sequence of driving each historical track point, and ensuring the accuracy of the obtained comparison result. When the curvatures of at least two continuous historical track points are smaller than the preset curvature threshold, determining the at least two continuous historical track points as candidate track points, and ensuring that the determined candidate track points are on a straight track. Then, according to the positions of the candidate track points, the candidate distance from the first candidate track point to the last candidate track point is calculated, and the accuracy of the calculated candidate distance is ensured. And comparing the candidate distance with a preset distance threshold value, so that the accuracy of the obtained comparison result is ensured. When the candidate distance is larger than the preset distance threshold value, the candidate track point is determined to be the standby track point, and the accuracy of the result that the determined candidate track point is the standby track point is ensured. And then comparing the absolute values of the transverse errors corresponding to the standby track points, and selecting the maximum absolute transverse error from the absolute values of the transverse errors, so that the accuracy of the determined maximum absolute transverse error is ensured. Comparing the maximum absolute transverse error with a preset transverse error threshold; and when the maximum absolute transverse error is greater than a preset transverse error threshold, determining the standby track point as the target track point, and ensuring the accuracy of the determined standby track point as the target track point.

In one embodiment of the present application, as shown in fig. 3, a method for compensating dynamic deviation of an automatic driving vehicle is provided, and the method is applied to an electronic device for illustration, and includes the following steps:

s31, acquiring a plurality of historical track points included in the driven track corresponding to the target vehicle, and determining positions, curvatures, lateral errors and course angle errors corresponding to the historical track points.

For this step, please refer to the description of S21 in fig. 2, and a detailed description is omitted here.

S32, determining each target track point corresponding to the straight track in the history track according to the position and curvature corresponding to each history track point.

For this step, please refer to fig. 2 for description of S22, and detailed description thereof is omitted herein.

S33, calculating the dynamic compensation quantity of the linear track corresponding to each target track point according to the transverse error and the course angle error corresponding to each target track point.

In an optional embodiment of the present application, the step S33 "calculating the dynamic compensation amount of the linear track corresponding to each target track point according to the lateral error and the heading angle error corresponding to each target track point" may include the following steps:

s331, calculating the average transverse error corresponding to each target track point according to the transverse error corresponding to each target track point.

Specifically, the electronic device may calculate, according to the lateral errors corresponding to the target track points, an average lateral error corresponding to the target track points.

For example, the electronic device may calculate the average lateral error using the following formula:

wherein, the liquid crystal display device comprises a liquid crystal display device,

for average lateral error +.>

And n is the number of target track points for the corresponding transverse error of each target track point.

S332, calculating the average course angle error corresponding to each target track point according to the course angle error corresponding to each target track point.

Specifically, the electronic device may calculate, according to the course angle errors corresponding to the target track points, an average course angle error corresponding to the target track points

For example, the electronic device may calculate the average heading angle error using the following formula:

for average heading angle error, +.>

And n is the number of target track points for the course angle error corresponding to each target track point.

S333, calculating the dynamic compensation quantity according to the relation between the average transverse error and the average course angle error.

Specifically, after calculating the average lateral error and the average heading angle error, the electronic device may calculate the dynamic compensation amount according to a relationship between the average lateral error and the average heading angle error.

For example, the electronic device may calculate the dynamic compensation amount using the following formula:

wherein delta _d In order to dynamically compensate for the amount of compensation,

for average lateral error +.>

For the average heading angle error, L is the length of the straight line track between the first target track point and the last target track point.

And S34, controlling the corresponding wheel angle of the target vehicle according to the dynamic compensation quantity so as to compensate the dynamic offset in the running process of the target vehicle.

In an optional embodiment of the present application, the step S34 "controlling the wheel angle corresponding to the target vehicle according to the dynamic compensation amount to compensate the dynamic offset during the driving process of the target vehicle" may include the following steps:

s341, acquiring a feedforward corner and a current corner of the next step corresponding to the target vehicle.

In an optional embodiment of the present application, the electronic device may receive a feed-forward corner and a current corner of a next step corresponding to the target vehicle input by the user, and may also obtain the feed-forward corner and the current corner of the next step corresponding to the target vehicle sent by other devices.

In an optional embodiment of the present application, the step S341 "of obtaining the feed-forward rotation angle of the next step corresponding to the target vehicle" may include the following steps:

(1) And acquiring the current speed and the pre-aiming coefficient corresponding to the target vehicle.

Specifically, the electronic device may measure, using the speed sensor, a current vehicle speed corresponding to the target vehicle, and obtain a pretightening coefficient input by a user, or a pretightening coefficient sent by other devices.

(2) And calculating to obtain the pretightening distance by utilizing the relation between the current speed and the pretightening coefficient.

Specifically, after the electronic device obtains the current speed and the pretightening coefficient corresponding to the target vehicle, the pretightening distance can be calculated by multiplying the current speed by the pretightening coefficient.

For example, the electronic device may calculate the pretighted distance using the following formula:

d＝kv (4)

wherein d is the pretightening distance, k is the pretightening coefficient, and v is the current speed.

(3) And determining a pretightening trajectory point according to the pretightening distance, and determining the pretightening curvature of the pretightening trajectory point.

Specifically, after the electronic device calculates the pretightening distance, pretightening track points included in the pretightening distance can be determined according to the pretightening distance, and pretightening curvature of the pretightening track points can be determined according to the position of the pretightening track points in the preset track.

(4) And obtaining the equivalent wheelbase of the vehicle corresponding to the target vehicle.

Specifically, the electronic device may receive a vehicle equivalent wheelbase corresponding to the target vehicle input by the user, and may also receive a vehicle equivalent wheelbase corresponding to the target vehicle sent by other devices.

(5) And determining a feed-forward corner of the next step corresponding to the target vehicle according to the relation between the pre-aiming curvature and the equivalent wheelbase of the vehicle.

In an optional embodiment of the present application, after obtaining the equivalent wheelbase of the vehicle and the pretightening curvature of the pretightening trajectory point, the electronic device may perform an arctangent function solution on the product of the pretightening curvature multiplied by the equivalent wheelbase of the vehicle, to determine the feedforward corner of the next step corresponding to the target vehicle.

In an optional implementation manner of the present application, after obtaining the equivalent wheelbase of the vehicle and the pre-aiming curvature of the pre-aiming track point, the electronic device may further obtain a feedforward corner coefficient corresponding to the target vehicle, then perform an arctangent function solution on the product of the pre-aiming curvature multiplied by the equivalent wheelbase of the vehicle, then multiply the feedforward corner coefficient, and determine a feedforward corner of the next step corresponding to the target vehicle.

For example, the electronic device may calculate the feed-forward rotation angle according to the following formula:

δ _f ＝arctan(l _b *κ)*k _f (5)

wherein, kappa is pretightening curvature, l _b For equivalent wheelbase of vehicle, k _f Is a feed-forward rotation angle coefficient.

S342, determining a wheel target rotation angle of the next step corresponding to the target vehicle according to the relation among the dynamic compensation quantity, the feedforward rotation angle and the current rotation angle.

In an optional embodiment of the present application, after the electronic device obtains the dynamic compensation amount, the feedforward corner and the current corner, the electronic device may add the dynamic compensation amount, the feedforward corner and the current corner, and calculate to obtain the wheel target corner of the next step corresponding to the target vehicle.

In another optional implementation manner of the present application, the electronic device may further obtain weight coefficients corresponding to the dynamic compensation amount, the feedforward corner and the current corner, and then multiply the dynamic compensation amount, the feedforward corner and the current corner by the corresponding weight coefficients respectively, and then add the weight coefficients, so as to calculate a wheel target corner of the next step corresponding to the target vehicle.

And S343, controlling the corresponding wheel rotation angle of the target vehicle according to the wheel target rotation angle so as to compensate the dynamic offset in the running process of the target vehicle.

Specifically, after the electronic device calculates the wheel target rotation angle, the electronic device controls the wheel rotation angle corresponding to the target vehicle according to the wheel target rotation angle so as to compensate the dynamic offset in the running process of the target vehicle.

In addition, the dynamic deviation compensation method for the automatic driving vehicle obtains the current speed and the pretightening coefficient corresponding to the target vehicle, calculates the pretightening distance by utilizing the relation between the current speed and the pretightening coefficient, and ensures the accuracy of the calculated pretightening distance. And determining a pretightening trajectory point according to the pretightening distance, and determining the pretightening curvature of the pretightening trajectory point, thereby ensuring the accuracy of the determined pretightening curvature. Acquiring a vehicle equivalent wheelbase corresponding to a target vehicle; and according to the relation between the pre-aiming curvature and the equivalent wheelbase of the vehicle, determining the feedforward corner of the next step corresponding to the target vehicle, and ensuring the accuracy of the determined feedforward corner. And further, the accuracy of the calculated wheel target rotation angle can be ensured. Then, the current rotation angle of the target vehicle is obtained, and the wheel target rotation angle of the next step corresponding to the target vehicle is determined according to the relation among the dynamic compensation quantity, the feedforward rotation angle and the current rotation angle, so that the accuracy of the wheel target rotation angle of the next step corresponding to the determined target vehicle is ensured. And then, controlling the corresponding wheel corner of the target vehicle according to the wheel target corner to compensate the dynamic offset in the running process of the target vehicle, thereby ensuring that the transverse error and the course angle error of the target vehicle are smaller in the tracking process and ensuring that the target vehicle does not deviate from the central line of the lane seriously. Thereby improving the control accuracy of the target vehicle.

It should be understood that, although the steps in the flowcharts of fig. 1-3 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 1-3 may include multiple steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the steps or stages in other steps or other steps.

As shown in fig. 4, the present embodiment provides a dynamic deviation compensation device for an autonomous vehicle, including:

the acquiring module 41 is configured to acquire a plurality of historical track points included in a traveled track corresponding to the target vehicle, and determine a position, a curvature, a lateral error, and a heading angle error corresponding to each historical track point.

And the determining module 42 is configured to determine each target track point corresponding to the straight track in the history track according to the position and the curvature corresponding to each history track point.

The calculating module 43 is configured to calculate a dynamic compensation amount of the linear track corresponding to each target track point according to the lateral error and the heading angle error corresponding to each target track point.

The control module 44 is configured to control a wheel angle corresponding to the target vehicle according to the dynamic compensation amount, so as to compensate the dynamic offset during the driving process of the target vehicle.

In one embodiment of the present application, the determining module 42 is specifically configured to determine, from the historical track points, a historical track start point according to the positions of the historical track points; starting from the historical track starting point, comparing the curvature of each historical track point with a preset curvature threshold value according to the sequence of driving each historical track point; when the curvatures of at least two continuous historical track points are smaller than the preset curvature threshold, determining the at least two continuous historical track points as candidate track points; and determining target track points from the candidate track points according to the positions of the candidate track points.

In one embodiment of the present application, the determining module 42 is specifically configured to calculate, according to the positions of the candidate track points, a candidate distance from the first candidate track point to the last candidate track point; comparing the candidate distance with a preset distance threshold; when the candidate distance is greater than a preset distance threshold value, determining the candidate track point as a standby track point; and determining the standby track point as the target track point according to the corresponding transverse error of the standby track point.

In one embodiment of the present application, the determining module 42 is specifically configured to compare absolute values of lateral errors corresponding to each standby track point, and select a maximum absolute lateral error from the absolute values of the lateral errors; comparing the maximum absolute transverse error with a preset transverse error threshold; and when the maximum absolute transverse error is greater than a preset transverse error threshold, determining the standby track point as a target track point.

In one embodiment of the present application, the calculating module 43 is specifically configured to calculate an average lateral error corresponding to each target track point according to the lateral error corresponding to each target track point; calculating the average course angle error corresponding to each target track point according to the course angle error corresponding to each target track point; and calculating the dynamic compensation quantity according to the relation between the average transverse error and the average course angle error.

In one embodiment of the present application, the control module 44 is specifically configured to obtain a feed-forward rotation angle and a current rotation angle of a next step corresponding to the target vehicle; determining a wheel target corner of the next step corresponding to the target vehicle according to the relation among the dynamic compensation quantity, the feedforward corner and the current corner; and controlling the corresponding wheel angle of the target vehicle according to the wheel target angle so as to compensate the dynamic offset in the running process of the target vehicle.

In one embodiment of the present application, the control module 44 is specifically configured to obtain a current speed and a pre-aiming coefficient corresponding to the target vehicle; calculating to obtain a pretightening distance by utilizing the relation between the current speed and the pretightening coefficient; determining a pretightening trajectory point according to the pretightening distance, and determining a pretightening curvature of the pretightening trajectory point; acquiring a vehicle equivalent wheelbase corresponding to a target vehicle; and determining a feed-forward corner of the next step corresponding to the target vehicle according to the relation between the pre-aiming curvature and the equivalent wheelbase of the vehicle.

The specific limitations and advantages of the dynamic deviation compensation device for an autonomous vehicle can be found in the above limitations of the dynamic deviation compensation method, and will not be described in detail herein. The respective modules in the above-described dynamic deviation compensation apparatus for an autonomous vehicle may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or independent of a processor in the electronic device, or may be stored in software in a memory in the electronic device, so that the processor may call and execute operations corresponding to the above modules.

The embodiment of the invention also provides electronic equipment, which is provided with the dynamic deviation compensation device shown in the figure 4.

Fig. 5 is a schematic structural diagram of an electronic device according to an alternative embodiment of the present invention, as shown in fig. 5, where the electronic device may include: at least one processor 51, such as a CPU (Central Processing Unit ), at least one communication interface 53, a memory 54, at least one communication bus 52. Wherein the communication bus 52 is used to enable connected communication between these components. The communication interface 53 may include a Display screen (Display) and a Keyboard (Keyboard), and the selectable communication interface 53 may further include a standard wired interface and a wireless interface. The memory 54 may be a high-speed RAM memory (Random Access Memory, volatile random access memory) or a non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 54 may alternatively be at least one memory device located remotely from the aforementioned processor 51. Wherein the processor 51 may be as described in connection with fig. 4, the memory 54 stores an application program, and the processor 51 invokes the program code stored in the memory 54 for performing any of the method steps described above.

The communication bus 52 may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The communication bus 52 may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, only one thick line is shown in fig. 5, but not only one bus or one type of bus.

Wherein the memory 54 may include volatile memory (english) such as random-access memory (RAM); the memory may also include a nonvolatile memory (english: non-volatile memory), such as a flash memory (english: flash memory), a hard disk (english: hard disk drive, abbreviated as HDD) or a solid state disk (english: solid-state drive, abbreviated as SSD); memory 54 may also include a combination of the types of memory described above.

The processor 51 may be a central processor (English: central processing unit, abbreviated: CPU), a network processor (English: network processor, abbreviated: NP) or a combination of CPU and NP.

The processor 51 may further include a hardware chip, among others. The hardware chip may be an application-specific integrated circuit (ASIC), a Programmable Logic Device (PLD), or a combination thereof (English: programmable logic device). The PLD may be a complex programmable logic device (English: complex programmable logic device, abbreviated: CPLD), a field programmable gate array (English: field-programmable gate array, abbreviated: FPGA), a general-purpose array logic (English: generic array logic, abbreviated: GAL), or any combination thereof.

Optionally, the memory 54 is also used for storing program instructions. The processor 51 may invoke program instructions to implement the method of dynamic bias compensation for an autonomous vehicle as shown in the embodiments of fig. 1-3 of the present application.

Embodiments of the present invention also provide a non-transitory computer storage medium storing computer executable instructions that are capable of performing the method for compensating for dynamic deviation of an autonomous vehicle in any of the above-described method embodiments. Wherein the storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a Flash Memory (Flash Memory), a Hard Disk (HDD), or a Solid State Drive (SSD); the storage medium may also comprise a combination of memories of the kind described above.

Although embodiments of the present invention have been described in connection with the accompanying drawings, various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope of the invention as defined by the appended claims.

Claims

1. A method of compensating for dynamic deviations in an autonomous vehicle, comprising:

determining each target track point corresponding to a straight track in the history track according to the position and the curvature corresponding to each history track point;

2. The method of claim 1, wherein said determining each target track point corresponding to a straight track in said historical track based on said location and said curvature corresponding to each said historical track point comprises:

determining a history track starting point from the history track points according to the positions of the history track points;

and determining the target track point from the candidate track points according to the positions of the candidate track points.

3. The method of claim 2, wherein said determining the target track point from each of the candidate track points based on the location of each of the candidate track points comprises:

comparing the candidate distance with a preset distance threshold;

when the candidate distance is greater than the preset distance threshold, determining the candidate track point as a standby track point;

and determining the standby track point as the target track point according to the transverse error corresponding to the standby track point.

4. A method according to claim 3, wherein said determining the spare track point as the target track point according to the lateral error corresponding to the spare track point comprises:

Comparing the absolute values of the lateral errors corresponding to the standby track points, and selecting the maximum absolute lateral error from the absolute values of the lateral errors;

comparing the maximum absolute lateral error with a preset lateral error threshold;

and when the maximum absolute transverse error is larger than the preset transverse error threshold, determining the standby track point as the target track point.

5. The method according to claim 1, wherein the calculating the dynamic compensation amount of the linear track corresponding to each target track point according to the lateral error and the heading angle error corresponding to each target track point includes:

according to the transverse errors corresponding to the target track points, calculating average transverse errors corresponding to the target track points;

and calculating the dynamic compensation amount according to the relation between the average transverse error and the average course angle error.

6. The method according to claim 1, wherein controlling the corresponding wheel angle of the target vehicle according to the dynamic compensation amount to compensate the dynamic offset during the driving of the target vehicle includes:

determining a wheel target turning angle of the next step corresponding to the target vehicle according to the relation among the dynamic compensation quantity, the feedforward turning angle and the current turning angle;

7. The method of claim 6, wherein the obtaining the corresponding feed-forward rotation angle of the target vehicle for the next step comprises:

acquiring a current speed and a pre-aiming coefficient corresponding to the target vehicle;

acquiring a vehicle equivalent wheelbase corresponding to the target vehicle;

and determining the feed-forward rotation angle of the next step corresponding to the target vehicle according to the relation between the pre-aiming curvature and the equivalent wheelbase of the vehicle.

8. A dynamic deviation compensation device for an autonomous vehicle, comprising:

and the control module is used for controlling the wheel angle corresponding to the target vehicle according to the dynamic compensation quantity so as to compensate the dynamic offset in the running process of the target vehicle.

9. An electronic device comprising a memory and a processor, the memory having stored therein computer instructions that, when executed, perform the method of dynamically compensating for deviation of an autonomous vehicle of any of claims 1-7.

10. A computer-readable storage medium storing computer instructions for causing a computer to perform the method of dynamic deviation compensation of an autonomous vehicle according to any one of claims 1-7.