CN115790632A

CN115790632A - Track determination method and device, electronic equipment and medium

Info

Publication number: CN115790632A
Application number: CN202211514571.8A
Authority: CN
Inventors: 程周; 谭业辉; 彭伟
Original assignee: Apollo Zhilian Beijing Technology Co Ltd; Apollo Zhixing Technology Guangzhou Co Ltd
Current assignee: Apollo Zhilian Beijing Technology Co Ltd; Apollo Zhixing Technology Guangzhou Co Ltd
Priority date: 2022-11-29
Filing date: 2022-11-29
Publication date: 2023-03-14

Abstract

The disclosure provides a track determination method, a track determination device, electronic equipment and a medium, and relates to the field of artificial intelligence, in particular to the technical field of automatic driving and intelligent traffic. The specific implementation scheme is as follows: the method comprises the steps of obtaining a plurality of track points generated in the running process of a vehicle, and screening concise path points from the plurality of track points, wherein the track error between a connecting line between adjacent concise path points and an initial running track is less than or equal to an error threshold value, and the initial running track is the running track represented by each track point between the adjacent concise path points. And then obtaining the driving track of the vehicle based on each concise waypoint. Therefore, on the basis of ensuring the accuracy of the track analysis, the calculation amount of the track analysis is reduced.

Description

Track determination method and device, electronic equipment and medium

Technical Field

The present disclosure relates to the field of artificial intelligence, and more particularly to the technical field of automatic driving and intelligent transportation.

Background

During the driving process of the vehicle, a series of track points can be generated periodically, for example, the current position of the vehicle is acquired every 1 second, and one track point is obtained. Each track point can truly reflect the driving state of the vehicle, and reflects the road and traffic environment where the vehicle is located from the side.

Disclosure of Invention

The disclosure provides a track determination method, a track determination device, an electronic device and a medium.

In a first aspect of the embodiments of the present disclosure, a method for determining a trajectory is provided, including:

acquiring a plurality of track points generated in the driving process of a vehicle;

screening concise path points from the plurality of track points; the track error between a connecting line between adjacent concise waypoints and the initial driving track is less than or equal to an error threshold value, and the initial driving track is the driving track represented by each track point between the adjacent concise waypoints;

and obtaining the driving track of the vehicle based on each concise path point.

In a second aspect of the embodiments of the present disclosure, there is provided a trajectory determination device, including:

the acquisition module is used for acquiring a plurality of track points generated in the running process of the vehicle;

the screening module is used for screening compact path points from the plurality of track points acquired by the acquisition module; the track error between a connecting line between adjacent concise path points and an initial running track is less than or equal to an error threshold value, and the initial running track is a running track represented by each track point between the adjacent concise path points;

and the determining module is used for obtaining the driving track of the vehicle based on each concise path point screened by the screening module.

In a third aspect of the embodiments of the present disclosure, an electronic device is provided, including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the trajectory determination method of any one of the first aspects.

In a fourth aspect of the disclosed embodiments, there is provided a non-transitory computer-readable storage medium having stored thereon computer instructions for causing the computer to execute the trajectory determination method of any one of the first aspects.

In a fifth aspect of the embodiments of the present disclosure, a computer program product is provided, which comprises a computer program, and the computer program realizes the trajectory determination method of any one of the first aspect when executed by a processor.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

fig. 1 is a flowchart of a trajectory determination method provided by an embodiment of the present disclosure;

FIG. 2 is a first exemplary diagram of trace points provided by embodiments of the present disclosure;

FIG. 3 is a flowchart of a method for filtering compact waypoints according to an embodiment of the disclosure;

FIG. 4 is a second exemplary diagram of trace points provided by embodiments of the present disclosure;

FIG. 5 is a flow chart of a method of determining a trajectory error provided by an embodiment of the present disclosure;

FIG. 6 is a third exemplary diagram of trace points provided by embodiments of the present disclosure;

FIG. 7 is a fourth exemplary diagram of trace points provided by embodiments of the present disclosure;

fig. 8 is a fifth exemplary diagram of trace points provided by embodiments of the present disclosure;

FIG. 9 is a flow chart of a method of managing a buffer set provided by an embodiment of the present disclosure;

FIG. 10 is a schematic structural diagram of a trajectory determination device provided in an embodiment of the present disclosure;

FIG. 11 is a block diagram of an electronic device for implementing a trajectory determination method of an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of embodiments of the present disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the driving process of the automatic driving vehicle, the automatic driving vehicle can perform track analysis according to the track points of the automatic driving vehicle. Moreover, the autonomous vehicle can also periodically send its own track points to other vehicles or devices, so that the other vehicles or devices can analyze the running track of the autonomous vehicle according to the received track points, and further can use the running track as a basis for predicting the road geometry and classifying the position of the autonomous vehicle.

However, the cycle of the vehicle for acquiring the track points is 1 Hertz (Hertz, hz), so that the data volume of the track points is huge, and the calculation amount of track analysis is large.

In order to reduce the calculation amount of trajectory analysis, the embodiments of the present disclosure provide a trajectory determination method, which may be applied to an electronic device having a trajectory data processing function in a vehicle. Referring to fig. 1, the method comprises the steps of:

s101, acquiring a plurality of track points generated in the driving process of the vehicle.

In the embodiment of the disclosure, in the driving process of the vehicle, the current position point of the vehicle can be periodically collected to obtain a plurality of track points. For example, the current position of the vehicle is acquired every 1 second, and a track point is obtained.

S102, screening concise path points from the plurality of track points.

That is, the nature of compact path points is a sampled subset of the trace points.

And the track error between the connecting line between the adjacent concise path points and the initial running track is less than or equal to an error threshold, and the initial running track is the running track represented by each track point between the adjacent concise path points.

For example, as shown in fig. 2, the vehicle starts at the lowermost point and moves to the rightmost point. Each open circle in fig. 2 represents a track point and each filled circle represents a terse waypoint, for example, terse waypoint 1 through terse waypoint 4 are shown in fig. 2. As can be seen from fig. 2, the connection line between the adjacent compact path points has high similarity with the driving track represented by the track points between the adjacent compact path points, so that the precision of track analysis is not affected too much by using each compact path point to replace all track points.

Referring to fig. 2, a connection line between compact waypoint 2 and compact waypoint 3 may be referred to as a compact data description. The trajectory error between the trajectory point between the two compact waypoints and the compact data description may be referred to as a data description error, and the data description error may be determined based on the distance between the trajectory point between the two compact waypoints and the compact data description.

And S103, obtaining the driving track of the vehicle based on each concise path point.

Alternatively, the total driving distance of the vehicle can be obtained by sequentially connecting adjacent concise route points. And/or sequentially connecting adjacent concise path points in the map, so as to draw and display the driving track of the vehicle.

Alternatively, the concise waypoints may also be subjected to trajectory analysis in other manners, which is not specifically limited in this embodiment of the disclosure.

Because the concise path points are screened from all track points, the track point data volume is reduced, and the calculation amount of track analysis is reduced. And the track error between the connecting line between the adjacent concise path points and the initial running track is less than or equal to the error threshold, so that the running track represented by the concise path points has smaller error with the running track represented by the original track points, and the calculation amount of track analysis can be reduced on the basis of ensuring the accuracy of track analysis.

In addition, the concise path points can express the driving track of the vehicle, so that the driving state of the vehicle is truly reflected, and the road and the traffic environment where the vehicle is located can be reflected from the side.

The following describes the trajectory determination method provided by the embodiment of the present disclosure in detail:

referring to fig. 3, the method for selecting concise path points from multiple track points in S102 includes the following steps:

and S301, taking a starting point of the plurality of track points as a target starting point, and taking a second track point after the target starting point as a target end point.

Wherein the target starting point can be marked as P _starting Let the target end point be P _next 。

The starting point in the track point can be used as a compact path point.

S302, determining a track error between the target chord and the initial running track. Wherein the target chord is a connecting line between the target starting point and the target ending point.

Referring to fig. 2, assuming that the concise path point 2 is a target starting point, the concise path point 3 is a target ending point, a connecting line between the target starting point and the target ending point, i.e. a target chord, is a straight line, and an initial travel track between the target starting point and the target ending point may be an arc line, so that an error between the straight line and the arc line is taken as a track error.

S303, judging whether the determined track error is larger than an error threshold value. If the determined track error is larger than the error threshold, executing S304; if the determined track error is less than or equal to the error threshold, S308 is executed.

And S304, determining the previous track point of the target end point as a concise path point.

It can be understood that when the determined track error is greater than the error threshold, it indicates that the track error of the vehicle running track represented by the current target starting point and target end point is large, and the target end point is not suitable for being used as a concise waypoint, so that the track point before the target end point is used as the concise waypoint.

S305, judging whether at least two track points exist after the concise path point. Executing S306 under the condition that at least two track points exist after the concise path point; if the number of trace points after the concise path point is less than two, S307 is executed.

S306, updating the concise path point as a target starting point, updating a second track point after the updated target starting point as a target end point, and returning to the step of determining the track error between the target chord and the initial running track in the S302.

Wherein, the previous track point of the target end point can be recorded as P _previous 。

Since there are at least two track points after the concise path point, the concise path point may be updated to the target start point, and the second track point after the updated target start point is updated to the target end point, and the process returns to S302, so that the next concise path point is continuously found from the concise path point.

S307, stopping screening.

It can be understood that when the number of trace points after the concise path point is less than two, it indicates that no trace point exists after the concise path point, or only one trace point exists after the concise path point. When no track point exists after the concise path point, the concise path point is indicated as the last track point, so that the concise path point does not need to be screened backwards continuously. When only one track point exists behind the concise path point, because the distance between the adjacent track points is short, namely the distance between the concise path point and the next track point is short, the corresponding track error is generally small, and the track point behind the concise path point can not be used as the concise path point. Or, in order to ensure the integrity of the vehicle driving track, when only one track point exists after the concise path point, one track point after the concise path point can be used as the concise path point.

And S308, judging whether at least one track point exists after the target end point. In the case where there is at least one trace point after the target end point, S309 is executed; in the case where there is no track point after the target end point, S310 is performed.

And S309, updating the next track point of the target end point to be the target end point, and returning to the step of determining the track error between the target chord and the initial running track in the step S302.

It can be understood that when the determined error is less than or equal to the error threshold, it indicates that the error of the vehicle running track represented by the current target starting point and target ending point is small, and at least one track point exists after the current target ending point, so that the concise path point can be continuously searched backwards. Therefore, the next trace point of the target end point is updated to the target end point, and the process returns to S302 to continue to search for the concise path point.

And S310, stopping screening.

It can be understood that, in the case that no trace point exists after the target end point, the judgment on whether each trace point is a concise path point is currently completed, and therefore, the screening process is stopped.

Optionally, in order to ensure the integrity of the vehicle driving track, the target end point may be used as a concise path point under the condition that no track point exists after the target end point.

By the method, the embodiment of the disclosure can judge whether each path point is a concise path point one by one, and can screen the concise path points from the path points and filter out the path points as many as possible under the condition that the track error between adjacent concise path points is less than the error threshold, so that the data volume of the concise path points is greatly lower than the total data volume of all the path points, and the subsequent calculation amount for analyzing the track of the concise path points is reduced.

In some embodiments of the present disclosure, since the distance between adjacent compact waypoints is too long, a connection line between the compact waypoints may deviate from a real driving trajectory, and thus the embodiments of the present disclosure may also control the distance between the adjacent compact waypoints. Based on this, the method for determining the trajectory error between the target chord and the initial travel trajectory in S302 includes the following steps:

step one, judging whether the chord length of the target chord is larger than a chord length threshold value. If yes, executing the step two; if not, executing the third step.

Each track point can be represented by longitude and latitude, so that the target chord length between the track points can be determined according to the longitude and latitude distance between the track points.

For example, the trajectory point P can be determined by the formula (1) ₁ And P ₂ Chord length of target chord between:

PH_ActuralChordLength＝RearthMeridian*arcos[cos(lat ₁ )cos(lat ₂ )cos(long ₁ -long ₂ )+sin(lat ₁ )sin(lat ₂ )] (1)

wherein, P ₁ And P ₂ The chord length of the target chord in between, rearthMeridian is the length of the earth's radius at the meridian, lat ₁ Is P ₁ Latitude of (3, long) ₁ Is P ₁ Longitude, lat of ₂ Is P ₂ Latitude of (3, long) ₂ Is P ₂ Longitude of (c).

The chord length threshold may be represented as K _ PH _ chord _ length _ chord, and the specific value may be set according to actual requirements, for example, the chord length threshold may be 10 meters.

And step two, determining the track error between the target chord and the initial running track as a specified error. Wherein the specified error is greater than the error threshold. For example, the error is specified as (error threshold + 1).

It is understood that when the chord length of the target chord is greater than the chord length threshold, it means that the error representing the vehicle travel track using the current target start point and target end point is large, and it is not appropriate to take the target end point as a compact waypoint, so the track error between the target chord and the initial travel track is set to a specified error, so that the track point immediately preceding the target end point can be taken as a compact waypoint when S303 is executed.

And step three, sequentially connecting all track points between the target starting point and the target end point to obtain a section of arc line, and taking the vertical distance from the specified point on the arc line to the target chord as the track error between the target chord and the initial running track.

For example, referring to FIG. 4, each circle in FIG. 4 represents a trace point, where each trace point is represented by P _i (lat _i ,long _i ) I is the serial number of the trace point, lat _i Latitude of the locus point i, long _i The longitude of the track point i is shown, and the unit of the latitude and the longitude is radian. For track point P ₁ 、P ₂ And P ₃ The indicated initial driving track is formed from the appointed point on the initial driving track to the track point P ₁ And P ₃ Distance of connecting line between them, as P ₁ And P ₃ The target chord and the initial travel trajectory.

Through the method, the vertical distance from the appointed point on the arc line between the target starting point and the target end point to the target chord can be used as the track error between the target chord and the initial running track, so that the error between the adjacent concise path point and the initial running track is quantized, and the error is compared with the error threshold value in the subsequent process.

In the embodiment of the present disclosure, in the third step, the vertical distance from the designated point on the arc line to the target chord is taken as a way of the trajectory error between the target chord and the initial travel trajectory, and the following two ways are included:

in a first mode of taking the vertical distance from the designated point on the arc line to the target chord as the trajectory error between the target chord and the initial travel trajectory, the designated point is the point on the arc line having the largest distance from the target chord. Referring to fig. 5, the first method specifically includes the following steps:

s501, fitting the arc line into a circular arc, and determining an included angle between the first connecting line and the second connecting line. The first connecting line is a connecting line of the target starting point and the circle center corresponding to the circular arc, and the second connecting line is a connecting line of the target ending point and the circle center.

In the embodiment of the present disclosure, a Global Navigation Satellite System (GNSS) direction angle (Heading) corresponding to the target endpoint and a GNSS direction angle difference corresponding to the target starting point may be used as an included angle between the first connection line and the second connection line.

For example, referring to FIG. 6, the target starting point is P ₁ Target end point is P ₂ The circles in FIG. 6 are based on P ₁ And P ₂ A fitted circle. P ₁ Has a GNSS direction angle of H ₁ ，P ₂ Has a GNSS direction angle of H ₂ Is prepared from H ₂ -H ₁ = Δ θ as the angle between the first and second links.

And S502, determining the curvature radius of the circular arc based on the included angle and the chord length of the target chord.

It can be understood that if the included angle determined at S501 is very small or even close to 0, the radius of curvature calculated based on the included angle is very large. To avoid this, it can be determined whether the included angle is smaller than a preset minimum included angle. If yes, the curvature radius of the circular arc is set to be the maximum value of the preset radius, namely K _ PH _ MAXESTIMADIRADIUS, and the track error is set to be 0. If not, the radius of curvature of the arc is determined based on the description below.

S503, determining the vertical distance from the circle center to the target chord according to the included angle and the curvature radius.

In the embodiment of the present disclosure, the vertical distance from the center of the circle to the target chord may be calculated according to formula (2):

wherein d is the vertical distance from the center of the circle to the target chord, PH _ EstimatedR is the curvature radius of the circular arc,

is the angle between the first line and the second line.

For example, referring to FIG. 4, the center of the circle and the locus point P ₁ And P ₃ Perpendicular to the target chordThe distance is d.

And S504, taking the difference between the curvature radius and the determined vertical distance as the track error between the target chord and the initial running track.

That is, the trajectory error is determined using equation (3):

PH_ActualError ＝ PH_EstimatedR–d (3)

and PH _ is a track error between the target chord and the initial running track, PH _ is a curvature radius, and d is a vertical distance from the center of the circle to the target chord.

It will be understood that the distance between each point on the arc and the center of the circle is the same and is the radius of the circle, and thus (radius-the vertical distance from the center of the circle to the target chord) is the maximum distance between the arc and the target chord, and thus the designated points on the arc are: the point at which the distance from the target chord is greatest.

By the method, the difference value between the curvature radius and the vertical distance from the circle center to the target chord can be used as the track error, so that the farthest distance between the point on the initial running track and the target chord is determined, and if the farthest distance does not exceed the error threshold, the distance between any point on the initial running track and the target chord does not exceed the error threshold. The trajectory error determined by the above method is more accurate.

In the embodiment of the present disclosure, in S504, the manner of determining the radius of curvature of the circular arc includes the following two manners:

mode 1 for determining the radius of curvature of the circular arc: and determining the sine value of half of the included angle, and taking the ratio of the chord length of the target chord to the double sine value as the curvature radius of the circular arc.

That is, the radius of curvature can be obtained by equation (4):

wherein PH _ is the curvature radius of the circular arc, PH _ hh is the chord length of the target chord,

is the included angle between the first connecting line and the second connecting line.

By the method, the curvature radius can be obtained according to the included angle and the chord length corresponding to the circular arc, so that the track error can be calculated based on the curvature radius in the subsequent process.

Mode 2 for determining the radius of curvature of the circular arc includes the steps of:

step 1, determining a sine value of half of an included angle, determining a ratio of a chord length to a double sine value, and obtaining an approximate curvature radius of the circular arc.

That is, the radius of curvature obtained in the first mode is taken as the approximate radius of curvature, and the approximate radius of curvature is denoted as PH _ EstimatedR ₁ 。

And 2, determining the curvature radius of each track point between the target starting point and the target end point according to the corresponding vehicle speed and yaw angular speed of the track point.

The radius of curvature of each trace point can be calculated using equation (5).

R _2i ＝ v _i /w _i (5)

Wherein R is ₂ Is a track point P _i Radius of curvature of b _i Is P _i Corresponding vehicle speed, w _i Is P _i Corresponding yaw rate.

For example, referring to fig. 7, assuming that each trace point in fig. 7 is another trace point between the target start point and the target end point, P can be obtained according to formula (5) ₁ Has a radius of curvature of R ₂₁ ＝ ₁ / ₁ ，P ₂ Has a radius of curvature of R ₂₂ ＝ ₂ / ₂ ，P ₃ Has a radius of curvature of R ₂₃ ＝ ₃ / ₃ ，P ₄ Has a radius of curvature of R ₂₄ ＝ ₄ / ₄ ，P _n Has a radius of curvature of R ₂ ＝ _n / _n . The radius of curvature of a track point is the distance between the track point and the center of the corresponding arc, for example, R in FIG. 7 ₂₃ Is P ₃ Distance from the centre of the circle, R ₂ Is P _n The distance from the center of the circle.

Referring to FIG. 7, assume P in FIG. 7 ₁ Is the target starting point, P ₃ Is the target end point, then P is calculated ₂ The radius of curvature of (a).

And step 3, determining the curvature radius average value of each track point to obtain the average curvature radius.

The average radius of curvature can be calculated using equation (6):

wherein, PH _ ₂ Is the mean radius of curvature, R _2i Is a track point P _i N is the number of other track points between the target starting point and the target end point.

And 4, taking the weighted sum of the approximate curvature radius and the average curvature radius as the curvature radius of the circular arc.

The radius of curvature of the circular arc can be calculated using equation (7):

PH_ ＝K_PH_×PH_EstimatedR ₁ +K_PH_USWEIGHTTWO×PH_ ₂ (7)

wherein K _ PH _ RADIUSSWEIGHTONE is the weight of approximate radius of curvature, PH _ ₁ To approximate the radius of curvature, K _ PH _ is the weight of the mean radius of curvature, PH _ ₂ Is the average radius of curvature.

The sum of K _ PH _ radiusweigtone and K _ PH _ is 1, and the specific value can be set according to the actual situation.

Since the arc between the target starting point and the target end point is not necessarily a circular arc of a perfect circle, for example, it may also be a circular arc of an ellipse, the average curvature radius of other locus points between the target starting point and the target end point is considered, and the curvature radius of the arc is determined, so that the determined curvature radius can be more accurate.

In the embodiment of the present disclosure, after the curvature radius of the track point is calculated in step 2, it may be further determined whether the curvature radius of each track point exceeds a curvature radius threshold. If the curvature radius exceeds the preset maximum value, the curvature radius of the track point is set to be K _ PH _ MAXESTIAMATEDRADIUS. If not, the curvature radius is added into the radius buffer area, so that the calculation of the average curvature radius is carried out based on the curvature radius of the radius buffer area in the step 3.

If all the curvature radiuses calculated in the step 2 exceed the curvature radius threshold, the radius buffer area is made to have no curvature radius, and the average curvature radius calculated in the step 3 is 0. When step 4 is used directly to calculate the weighted sum at this point, the resulting calculated weighted sum is smaller.

To avoid this, in the embodiment of the present disclosure, if the curvature radius of each of the other track points between the target start point and the target end point exceeds the radius threshold, the weight of the approximate curvature radius may be set to 1, and the weight of the average curvature radius may be set to 0. That is, K _ PH _ RADIUSSWEIGHTONE is 1 and K _PH _ is 0.

When the curvature radius of each other track point between the target starting point and the target end point exceeds the radius threshold, when the weighted sum is calculated, the weight of the approximate curvature radius is 1, and the weight of the average curvature radius is 0, so that the approximate curvature radius is used as the curvature radius of the circular arc, the influence on the calculation of the curvature radius of the circular arc when the average curvature radius is 0 is avoided, and the accuracy of determining the curvature radius of the circular arc is improved.

In the third step, in the second mode of taking the vertical distance from one point on the arc line to the target chord as the track error between the target chord and the initial running track, the specified point is the track point with the maximum distance from the target chord between the target starting point and the target ending point.

The second mode can be specifically realized as follows: and respectively determining every other track point between the target starting point and the target end point, and the vertical distance from the other track point to the target chord, and then screening the longest vertical distance from the determined vertical distances to be used as the track error between the target chord and the initial driving track.

Referring to fig. 8, the target start point is denoted as a (x 1, y 1), the target end point is denoted as C (x 2, y 2), each of the other track points between the target start point and the target end point is denoted as D (x 3, y 3), and the foot of the line segment AC from D is denoted as B (x, y).

Since B is within line segment AC, equation (8) can be derived:

B＝A+u(C-A) (8)

wherein the value range of u is [0,1].

Since the line segment DB is perpendicular to the line segment AC, it is possible to obtain:

(D-B)dot(C-A)＝0 (9)

where dot represents a vector dot product.

Substituting equation (8) into equation (9) yields:

[D-A-u(C-A)]dot(C-A)＝0 (10)

solving for u by equation (10) yields:

u＝((x3-x1)(x2-x1)+(y3-y1)(y2-y1))/||C–A|| ² (11) Substituting u in equation (11) into the following equation of a straight line, B (x, y) can be obtained:

x＝x1+u(x2-x1) (12)

y＝y1+u(y2-y1) (13)

after the coordinates of B, i.e., (x, y), are found, the distance d from B to the line segment AC can be calculated by equation (14) _i ：

d _i ＝sqrt((x3-x) ² +(y3-y) ² ) (14)

d _i Namely the vertical distance from one other track point between the target starting point and the target end point to the target chord.

Then, the trajectory error between the target chord and the initial running trajectory is determined by equation (15):

PH_ActualError＝MAX(d _i ) (15)

where PH _ is the trajectory error, d _i For other track points P between the target starting point and the target end point _i The vertical distance to the target chord, i, is in the range of [1, n ]]And n is the number of other track points between the target starting point and the target end point.

Through the method, the embodiment of the disclosure can select the longest vertical distance from the vertical distances from other track points between the target starting point and the target ending point to the target chord as the track error. The curvature radius and the included angle corresponding to the circular arc between the target starting point and the target end point are not required to be calculated, so that the calculation efficiency is higher.

In the embodiment of the present disclosure, a buffer set may be set to store a plurality of compact waypoints determined most recently. Therefore, the electronic equipment can send the concise waypoints in the buffer set to other vehicles or equipment, so that the other vehicles or equipment can analyze the driving track of the vehicle where the electronic equipment is located according to the received concise waypoints.

Therefore, after the starting point in the track point is taken as the concise path point, the concise path point can be added into the buffer set.

Furthermore, referring to fig. 9, after determining that the track point before the target end point is the concise path point in S303, the following steps may be further performed:

and S901, adding the determined concise path points into a buffer set.

S902, if the length of the driving track represented by each concise path point in the buffer set is greater than the length threshold, deleting the first designated number of concise path points from the buffer set according to the sequence from morning to evening when the concise path points are added into the buffer set.

And the length of the running track represented by each concise path point in the deleted buffer set is less than or equal to a length threshold value.

Alternatively, the length threshold may be set according to the storage capacity or actual requirement of the electronic device, for example, the length threshold is 100 meters.

The first designated number may be a preset number, or may be determined based on a distance between adjacent concise waypoints in the buffer set and a length threshold, so that the length of the travel track represented by each concise waypoint in the buffer set after deletion is less than or equal to the length threshold.

And S903, if the number of the concise path points in the buffer set is greater than the number threshold, deleting the second specified number of concise path points from the buffer set according to the sequence from morning to evening of adding the concise path points into the buffer set.

And the number of concise path points in the deleted buffer set is less than or equal to the number threshold.

Alternatively, the quantity threshold may be set according to the storage capacity or actual demand of the electronic device, for example, the quantity threshold is 15.

The second specified number may be a preset number, or may be determined based on the number of adjacent concise waypoints in the buffer set and a number threshold, so that the number of concise waypoints in the buffer set after deletion is less than or equal to the number threshold.

Through the method, the embodiment of the disclosure can limit the length of the driving track represented by the concise waypoints included in the buffer set and the number of the concise waypoints, thereby reducing the number of the concise waypoints sent to other devices. Since the situation that other devices cannot completely receive the data may be caused by sending too much data at one time, the embodiments of the present disclosure limit the number of concise waypoints included in the cache set, and can improve data transmission efficiency.

Based on the same inventive concept, corresponding to the above method embodiments, the disclosed embodiments provide a trajectory determination device, as shown in fig. 10, the device includes: an acquisition module 1001, a screening module 1002 and a determination module 1003;

the acquiring module 1001 is used for acquiring a plurality of track points generated in the driving process of a vehicle;

a screening module 1002, configured to screen concise path points from the multiple trace points acquired by the acquisition module 1001; the track error between a connecting line between the adjacent concise waypoints and the initial driving track is less than or equal to an error threshold value, and the initial driving track is the driving track represented by each track point between the adjacent concise waypoints;

the determining module 1003 is configured to obtain a driving track of the vehicle based on each concise waypoint screened by the screening module 1002.

In some embodiments of the present disclosure, the screening module 1002 is specifically configured to:

taking a starting point of the plurality of track points as a target starting point, and taking a second track point behind the target starting point as a target end point;

determining a track error between a target chord and an initial running track, wherein the target chord is a connecting line between a target starting point and a target end point;

if the determined track error is larger than the error threshold, determining that a track point before the target end point is a concise path point; under the condition that at least two track points exist behind the concise path point, updating the concise path point as a target starting point, updating a second track point behind the updated target starting point as a target end point, and returning to the step of determining the track error between the target string and the initial driving track; stopping screening under the condition that the number of the track points behind the concise path point is less than two;

if the determined track error is less than or equal to the error threshold, updating the track point behind the target end point to the target end point under the condition that at least one track point exists behind the target end point, and returning to the step of determining the track error between the target chord and the initial running track; or stopping screening under the condition that no track point exists after the target end point.

judging whether the chord length of the target chord is larger than a chord length threshold value or not;

if so, determining the track error between the target chord and the initial running track as a specified error, wherein the specified error is greater than an error threshold value;

if not, connecting the track points between the target starting point and the target end point in sequence to obtain an arc line, and taking the vertical distance from the specified point on the arc line to the target chord as the track error between the target chord and the initial running track.

fitting the arc line into a circular arc, and determining an included angle between the first connecting line and the second connecting line; the first connecting line is a connecting line between the target starting point and the circle center corresponding to the circular arc, and the second connecting line is a connecting line between the target ending point and the circle center;

determining the curvature radius of the circular arc based on the included angle and the chord length of the target chord;

determining the vertical distance from the circle center to the target chord according to the included angle and the curvature radius;

and taking the difference between the curvature radius and the determined vertical distance as the track error between the target chord and the initial running track.

determining the sine value of half of the included angle;

and taking the ratio of the chord length to the double sine value as the curvature radius of the circular arc.

determining the sine value of half of the included angle;

determining the ratio of the chord length to the double sine value to obtain the approximate curvature radius of the circular arc;

determining the curvature radius of each track point between the target starting point and the target end point according to the corresponding vehicle speed and yaw velocity of the track point;

determining the average value of the curvature radius of each track point to obtain the average curvature radius;

the weighted sum of the approximate radius of curvature and the average radius of curvature is taken as the radius of curvature of the arc.

In some embodiments of the disclosure, the apparatus further comprises:

and the setting module is used for setting the weight of the approximate curvature radius to be 1 and the weight of the average curvature radius to be 0 if the curvature radius of each other track point between the target starting point and the target end point exceeds a radius threshold before the weighted sum of the approximate curvature radius and the average curvature radius is used as the curvature radius of the circular arc.

respectively determining the vertical distance from each other track point between the target starting point and the target end point to the target chord;

and screening the longest vertical distance from the determined vertical distances to be used as the track error between the target chord and the initial running track.

In some embodiments of the present disclosure, the apparatus may further include:

the adding module is used for adding the determined concise path point into the buffer set after determining that the track point in front of the target end point is the concise path point;

the deleting module is used for deleting a first specified number of compact path points from the buffer set according to the sequence from morning to evening when the compact path points are added into the buffer set if the length of the driving track represented by each compact path point in the buffer set is greater than a length threshold; the length of the running track represented by each concise path point in the deleted buffer set is less than or equal to a length threshold value;

the deleting module is further used for deleting a second specified number of concise path points from the buffer set according to the sequence from morning to evening when the number of concise path points in the buffer set is greater than the number threshold; and the number of concise path points in the deleted buffer set is less than or equal to the number threshold.

In the technical scheme of the disclosure, the processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the related track information all accord with the regulations of related laws and regulations, and do not violate the common customs of public order.

It should be noted that the track information in this embodiment is not a head model for a specific user, and cannot reflect personal information of a specific user.

It should be noted that the track information in the present embodiment may be from a public data set.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

FIG. 11 shows a schematic block diagram of an example electronic device 1100 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 11, the electronic device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a Random Access Memory (RAM) 1103. In the RAM 1103, various programs and data necessary for the operation of the electronic device 1100 may also be stored. The calculation unit 1101, the ROM1102, and the RAM 1103 are connected to each other by a bus 1104. An input/output (I/O) interface 1105 is also connected to bus 1104.

A number of components in electronic device 1100 connect to I/O interface 1105, including: an input unit 1106 such as a keyboard, mouse, or the like; an output unit 1107 such as various types of displays, speakers, and the like; a storage unit 1108 such as a magnetic disk, optical disk, or the like; and a communication unit 1109 such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 1109 allows the electronic device 1100 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

The computing unit 1101 can be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and the like. The calculation unit 1101 performs the respective methods and processes described above, such as the trajectory determination method. For example, in some embodiments, the trajectory determination method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 1108. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 1100 via the ROM1102 and/or the communication unit 1109. When the computer program is loaded into RAM 1103 and executed by the computing unit 1101, one or more steps of the trajectory determination method described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to perform the trajectory determination method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user may provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server combining a blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel or sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A trajectory determination method, comprising:

2. The method of claim 1, wherein said screening compact path points from said plurality of trajectory points comprises:

taking a starting point in the plurality of track points as a target starting point, and taking a second track point behind the target starting point as a target end point;

determining a track error between a target chord and an initial running track, wherein the target chord is a connecting line between the target starting point and the target ending point;

if the determined track error is larger than the error threshold, determining that a track point before the target end point is a concise path point; under the condition that at least two track points exist after the concise path point, updating the concise path point as a target starting point, updating a second track point after the updated target starting point as a target end point, and returning to the step of determining the track error between the target string and the initial running track; stopping screening under the condition that the number of the track points behind the concise path point is less than two;

if the determined track error is smaller than or equal to the error threshold value, updating a track point behind the target end point to be the target end point under the condition that at least one track point exists behind the target end point, and returning to the step of determining the track error between the target string and the initial driving track; or stopping screening under the condition that no track point exists after the target end point.

3. The method of claim 2, wherein the determining a trajectory error between the target chord and the initial travel trajectory comprises:

if so, determining the track error between the target chord and the initial running track as a specified error, wherein the specified error is greater than the error threshold;

if not, sequentially connecting all track points between the target starting point and the target end point to obtain an arc line, and taking the vertical distance from the specified point on the arc line to the target string as the track error between the target string and the initial running track.

4. The method of claim 3, wherein said determining a vertical distance from a specified point on said arc to said target chord as a trajectory error between said target chord and an initial travel trajectory comprises:

fitting the arc line into a circular arc, and determining an included angle between a first connecting line and a second connecting line; the first connecting line is a connecting line between the target starting point and the circle center corresponding to the circular arc, and the second connecting line is a connecting line between the target ending point and the circle center;

5. The method of claim 4, wherein said determining a radius of curvature of the circular arc based on the included angle and a chord length of the target chord comprises:

determining the sine value of half of the included angle;

6. The method of claim 4, wherein the determining a radius of curvature of the circular arc based on the included angle and a chord length of the target chord comprises:

determining the sine value of half of the included angle;

determining the curvature radius of each other track point between the target starting point and the target end point according to the corresponding vehicle speed and yaw angular speed of the track point;

and taking the weighted sum of the approximate curvature radius and the average curvature radius as the curvature radius of the circular arc.

7. The method of claim 6, further comprising, prior to said taking the weighted sum of the approximate radius of curvature and the average radius of curvature as the radius of curvature of the arc:

and if the curvature radius of each other track point between the target starting point and the target end point exceeds a radius threshold, setting the weight of the approximate curvature radius to be 1, and setting the weight of the average curvature radius to be 0.

8. The method of claim 3, wherein said taking a vertical distance of a specified point on said arc to said target chord as a trajectory error between said target chord and an initial travel trajectory comprises:

and screening the longest vertical distance from the determined vertical distances to serve as the track error between the target chord and the initial running track.

9. The method of any of claims 2-8, further comprising, after said determining that a previous trajectory point of the target endpoint is a compact path point:

adding the determined concise path points into a buffer set;

if the length of the driving track represented by each concise waypoint in the buffer set is greater than a length threshold, deleting a first designated number of concise waypoints from the buffer set according to the sequence from morning to evening when the concise waypoints are added into the buffer set; after the deletion, the length of the driving track represented by each concise waypoint in the buffer set is less than or equal to the length threshold;

if the number of compact path points in the buffer set is greater than a number threshold, deleting a second specified number of compact path points from the buffer set according to the sequence from morning to evening when the compact path points are added into the buffer set; and after deletion, the number of compact path points in the buffer set is less than or equal to the number threshold.

10. A trajectory determination device comprising:

11. The apparatus according to claim 10, wherein the screening module is specifically configured to:

if the determined track error is smaller than or equal to the error threshold, updating the track point behind the target end point to be the target end point under the condition that at least one track point exists behind the target end point, and returning to the step of determining the track error between the target string and the initial running track; or stopping screening under the condition that no track point exists after the target end point.

12. The apparatus according to claim 11, wherein the screening module is specifically configured to:

if not, sequentially connecting all track points between the target starting point and the target end point to obtain an arc line, and taking the vertical distance between the specified point on the arc line and the target chord as the track error between the target chord and the initial running track.

13. The apparatus according to claim 12, wherein the screening module is specifically configured to:

14. The apparatus according to claim 13, wherein the screening module is specifically configured to:

determining the sine value of half of the included angle;

15. The apparatus of claim 13, wherein the screening module is specifically configured to:

determining the sine value of half of the included angle;

16. The apparatus of claim 15, the apparatus further comprising:

a setting module, configured to set a weight of the approximate curvature radius to 1 and a weight of the average curvature radius to 0 if a curvature radius of each other track point between the target start point and the target end point exceeds a radius threshold before the weighted sum of the approximate curvature radius and the average curvature radius is taken as the curvature radius of the arc.

17. The apparatus according to claim 12, wherein the screening module is specifically configured to:

18. The apparatus of any of claims 11-17, further comprising:

the adding module is used for adding the determined concise path point into the buffer set after the track point before the target end point is determined to be the concise path point;

a deleting module, configured to delete a first specified number of compact waypoints from the buffer set according to a sequence from morning to evening when the compact waypoints are added to the buffer set if the length of the driving track represented by each compact waypoint in the buffer set is greater than a length threshold; after the deletion, the length of the driving track represented by each concise waypoint in the buffer set is less than or equal to the length threshold;

the deleting module is further configured to delete a second specified number of compact waypoints from the buffer set according to the order from morning to evening when the compact waypoints are added to the buffer set if the number of compact waypoints in the buffer set is greater than a number threshold; and after deletion, the number of compact path points in the buffer set is less than or equal to the number threshold.

19. An electronic device, comprising:

at least one processor; and

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.

20. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-9.

21. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-9.