CN115447584A

CN115447584A - Method, device and equipment for determining lane center line and storage medium

Info

Publication number: CN115447584A
Application number: CN202211150264.6A
Authority: CN
Inventors: 杨再甫; 李正宁; 鲁荣荣; 傅文标; 姜伟
Original assignee: Ecarx Hubei Tech Co Ltd
Current assignee: Ecarx Hubei Tech Co Ltd
Priority date: 2022-09-21
Filing date: 2022-09-21
Publication date: 2022-12-09

Abstract

The invention discloses a method, a device and equipment for determining lane center lines and a storage medium. The method comprises the following steps: acquiring a road boundary line of a target road and vehicle motion trail information generated by driving of a vehicle in the target road, wherein the vehicle motion trail information comprises: the vehicle trajectory line and the pose information corresponding to the trajectory points on the vehicle trajectory line; determining to form a lane center reference line according to track points on a vehicle track line and boundary points of the track points mapped on a road boundary line; determining the total error of the vehicle track line according to the vehicle motion track information and the lane center reference line; and performing position optimization on track points on the vehicle track line according to the total error to obtain the lane center line of the target road. The method and the device can realize no influence of the missing of the road boundary line, determine the accurate, complete and smooth lane center line and improve the comfort level of the vehicle in driving or parking along the lane center line.

Description

Method, device and equipment for determining lane center line and storage medium

Technical Field

The invention relates to the technical field of path planning, in particular to a method, a device, equipment and a storage medium for determining lane center lines.

Background

When planning a vehicle path or parking a vehicle, the lane center line is often used. At present, the lane center line is determined mainly based on the road boundary line.

The method for determining the lane center line based on the road boundary line (or lane boundary line) has the following problems: the first is that when the road boundary line is missing, especially for the road turning position, the longer distance road boundary line may be missing, and the lane central line cannot be accurately determined. Secondly, the lane central line determined according to the road boundary line is not smooth enough, and especially for the road steering position, the deviation between the determined lane central line and the actual driving path of the vehicle is large, so that the driving experience of the vehicle when the vehicle drives or parks along the lane central line is not good.

Disclosure of Invention

The invention provides a method, a device, equipment and a storage medium for determining a lane center line, which are used for determining the lane center line according to vehicle motion track information and a road boundary line, so that the problems that the existing method for determining the lane center line based on the road boundary line is limited by the integrity of the road boundary line and the determined lane center line is not smooth enough are solved, the lane center line is not influenced by the missing of the road boundary line, the accurate, integral and smooth lane center line is determined, and the comfort level of driving or parking of a vehicle along the lane center line is improved.

According to an aspect of the present invention, there is provided a lane center line determining method, including:

acquiring a road boundary line of a target road and vehicle motion trail information generated by driving of a vehicle in the target road, wherein the vehicle motion trail information comprises: vehicle trajectory line and pose information corresponding to trajectory points on the vehicle trajectory line;

determining to form a lane center reference line according to the track points on the vehicle track line and the boundary points of the track points mapped on the road boundary line;

determining the total error of the vehicle track line according to the vehicle motion track information and the lane center reference line;

and performing position optimization on track points on the vehicle track line according to the total error to obtain a lane center line of the target road.

According to another aspect of the present invention, there is provided a lane center line determining apparatus, including:

the vehicle motion track information acquisition module is used for acquiring a road boundary line of a target road and vehicle motion track information generated by driving of a vehicle in the target road, and the vehicle motion track information comprises: vehicle trajectory line and pose information corresponding to trajectory points on the vehicle trajectory line;

the reference line determining module is used for determining and forming a lane center reference line according to the track points on the vehicle track line and the boundary points of the track points mapped on the road boundary line;

the error determination module is used for determining the total error of the vehicle track line according to the vehicle motion track information and the lane center reference line;

and the optimization module is used for carrying out position optimization on track points on the vehicle track line according to the total error to obtain the lane center line of the target road.

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the method of determining a lane centerline according to any embodiment of the invention.

According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the method for determining a lane centerline according to any one of the embodiments of the present invention when executed.

According to the technical scheme of the embodiment of the invention, the road boundary line of the target road and the vehicle motion trail information generated by the running of the vehicle in the target road are obtained, and the vehicle motion trail information comprises the following components: the vehicle trajectory line and the pose information corresponding to the trajectory points on the vehicle trajectory line; determining to form a lane center reference line according to track points on a vehicle track line and boundary points of the track points mapped on a road boundary line; determining the total error of the vehicle track line according to the vehicle motion track information and the lane center reference line; performing position optimization on track points on the vehicle track line according to the total error to obtain a lane center line of the target road; the basic line of the lane center line is determined according to the vehicle track line, so that the lane center line is smoother and is close to the running track of the vehicle, and the comfort level of the vehicle in running or parking along the lane center line is improved. Meanwhile, the position of the vehicle track line is optimized according to the error between the vehicle track line and the lane center reference line, so that the vehicle track line and the lane center reference line are approximately superposed to determine the lane center line; the method solves the problems that the existing method for determining the lane center line based on the road boundary line is limited by the integrity of the lane center line and the determined lane center line is not smooth enough, realizes the purpose of not being influenced by the missing of the road boundary line, determines the accurate, complete and smooth lane center line, and improves the comfort level of the vehicle in driving or parking along the lane center line.

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

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a flowchart of a lane center line determining method according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a method of determining a center reference point;

FIG. 3 is a flowchart of a lane center line determining method according to a second embodiment of the present invention;

FIG. 4 is a schematic illustration of a second error in determining the first error;

fig. 5 is a schematic structural diagram of a lane center line determining apparatus according to a third embodiment of the present invention;

fig. 6 is a schematic structural diagram of an electronic device implementing the method for determining a lane center line according to the embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," "object," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example one

Fig. 1 is a flowchart of a lane centerline determining method according to an embodiment of the present invention, which may be implemented by a lane centerline determining device, and the lane centerline determining device may be implemented in hardware and/or software. As shown in fig. 1, the method includes:

s110, acquiring a road boundary line of a target road and vehicle motion trail information generated by driving of a vehicle in the target road, wherein the vehicle motion trail information comprises: and (4) position and attitude information corresponding to the vehicle trajectory line and the trajectory point on the vehicle trajectory line.

Wherein the target road is a road needing to determine the center line of the lane. The method for determining the lane center line provided by the embodiment of the invention can be suitable for a single lane or multiple lanes, namely, the target road can comprise one lane or two or more lanes; it can also be applied to lanes in various road scenarios, such as lanes in garages or lanes on highways. The road boundary line is a line formed by a plurality of road boundary points, and may include a left boundary line and a right boundary line.

The vehicle motion trajectory information is trajectory information generated by the vehicle during the motion of the target road. The vehicle motion trajectory information may include pose information of the vehicle trajectory line and the trajectory point on the vehicle trajectory line. The vehicle track line is a route formed by a plurality of vehicle track points; the vehicle has pose information at each track point, which may include position coordinates of the track point and a body pose angle at the track point. The body attitude angle can be understood as the angle of the body orientation with respect to the boundary line of the road.

Specifically, the road boundary line may be obtained by scanning with an on-board camera during the driving of the vehicle, or may be obtained from a semantic map constructed in advance. The embodiment of the invention does not limit the acquisition mode of the road boundary line.

The acquisition mode of the vehicle motion track information can be that in the running process of the vehicle in the target road, the motion track information generated by the vehicle and the pose information at each track point are acquired by a sensor in a vehicle navigation module arranged on the vehicle.

And S120, determining to form a lane center reference line according to the track points on the vehicle track line and the boundary points of the track points mapped on the road boundary line.

The lane center reference line is understood to be a route which is referred to when determining the lane center line.

Specifically, a mapping relationship between a track point on a vehicle track line and a boundary point on a road boundary line is constructed in advance. For example, a boundary point where a track point makes a perpendicular line to the boundary line may be used as a boundary point where the track point is mapped on the road boundary line, or a closest point of the track point to the road boundary line may be used as a boundary point where the track point is mapped on the road boundary line. And determining central reference points on connecting lines of the track points and the mapped boundary points according to information such as the number of lanes contained in the target road, and connecting the central reference points to determine lane central reference lines.

In the embodiment of the invention, the lane central line determined by the vehicle track line and the road boundary line is not directly used as the lane central line but used as a reference line for determining the lane central line, so that the determination of the lane central line is not completely dependent on the road boundary line, and the determination of the lane central line is not greatly influenced even if part of the road boundary line is blurred or lost.

And S130, determining the total error of the vehicle track line according to the vehicle motion track information and the lane center reference line.

The total error of the vehicle trajectory line can be an error between trajectory points in the vehicle trajectory line, or an error between the vehicle trajectory line and a lane center reference line, or a sum of the two types of errors.

Specifically, the position information of each track point is determined according to the vehicle motion track information, and the position information of each central reference point is determined according to the lane central reference line; according to the position information of each track point and the position information of the corresponding central reference point; and determining the total error of the vehicle track line according to the position deviation between the central reference points and/or the track points or the posture deviation of the vehicle between the track points.

The method comprises the step of determining the total error of the vehicle track line according to the vehicle motion track information and the lane center reference line, so that when the problems of boundary line loss or boundary line blurring and the like occur on the road boundary line, the lane center line can be determined according to the vehicle motion track information and the error of the complete part of the road boundary line, the influence of the road boundary line loss is avoided, and the accurate and complete lane center line is determined.

And S140, carrying out position optimization on track points on the vehicle track line according to the total error to obtain a lane center line of the target road.

Specifically, optimizing the position of the trace point on the vehicle trace line based on the total error is to adjust the vehicle trace line toward a direction close to the center reference line to reduce the total error. And determining the vehicle track line with the minimum total error as the lane central line of the target road.

According to the embodiment of the invention, the road boundary line of the target road and the vehicle motion trail information generated by the running of the vehicle in the target road are obtained, and the vehicle motion trail information comprises: the vehicle trajectory line and the pose information corresponding to the trajectory points on the vehicle trajectory line; determining to form a lane center reference line according to track points on a vehicle track line and boundary points of the track points mapped on a road boundary line; determining the total error of the vehicle track line according to the vehicle motion track information and the lane center reference line; and performing position optimization on track points on the vehicle track line according to the total error to obtain the lane center line of the target road. The basic line of the lane center line is determined according to the vehicle track line, so that the lane center line is smoother and is close to the running track of the vehicle, and the comfort level of the vehicle in running or parking along the lane center line is improved. Meanwhile, the position of the vehicle track line is optimized according to the error between the vehicle track line and the lane center reference line, so that the vehicle track line is adjusted towards the direction close to the center reference line to determine the lane center line; when the problems of boundary line missing or boundary line blurring and the like occur on the road boundary line, the accurate and complete lane center line can be determined according to the vehicle motion track information and the complete part of the road boundary line without being influenced by the road boundary line missing.

Optionally, determining a lane center reference line according to a track point on a vehicle track line and a boundary point of the track point mapped on a road boundary line, including:

for each track point on the vehicle track line, determining the closest boundary point of the mapping of the track point on the road boundary line;

determining a central reference point meeting preset conditions on a connecting line of the track point and the nearest boundary point;

and determining a lane center reference line formed by the center reference points.

Wherein the preset condition is a preset condition for determining the center reference point. The preset condition may be set by default when determining the target road, or may be set by the user.

Specifically, the boundary point closest to the track point is determined as the boundary point of the track point mapped on the road boundary line, the center reference point meeting the preset condition is determined on the connecting line of the track point and the mapped boundary point, and the center reference points are connected to determine the lane center reference line.

For example, fig. 2 is a schematic diagram of a method for determining the center reference point. As shown in fig. 2, for a track point P1 on the vehicle track line, a closest point P2 of the track point P1 on the left-side road boundary line (or a closest point P3 on the right-side road boundary line) is determined; determining a central reference point P4 meeting a preset condition on a connecting line P1P2 between the track point P1 and a closest point P2 on a left road boundary line, wherein the distance d between the central reference point P4 and the closest point P2 (or the closest point P3) meets the preset condition; and determining a central reference point corresponding to each track point by analogy, and determining a connecting line of the central reference points as a lane central reference line. The distance d between the center reference point P4 and the closest point P2 (or the closest point P3) may be determined according to the number of lanes included in the target road, which is not limited in this embodiment.

In the embodiment, the boundary points which are closest to the track points are determined as the boundary points of the track points mapped on the road boundary line, so that the boundary points of the track points mapped on the road boundary line can be simply and quickly determined; meanwhile, a complete and smooth central reference line can be determined according to the track points and the mapping boundary points.

Optionally, the preset conditions include:

the distance from the central reference point to the boundary line of the road is a preset value;

and the vehicle body attitude angle of the track point corresponding to the vehicle at the central reference point is smaller than a preset angle.

Specifically, the preset value of the distance from the central reference point to the road boundary line may be determined according to the number of lanes included in the target road. The preset angle is the maximum angle which meets the selection condition of the vehicle track point, if the attitude angle at the vehicle track point is larger than the preset angle, the track point is indicated to have larger attitude change, and a central reference point determined by the track point has larger error, so the track point cannot be used for determining the central reference point. For example, the preset angle is 30 degrees, i.e. the preset conditions include: it is necessary that the angle between the vehicle heading and the direction of the left and right boundary lines is within 30 degrees.

For example, if the target road includes a single lane, the target road only includes a lane center reference line, and the preset value should be set to be half of the road width; that is, as shown in fig. 2, the distance d from the center reference point P4 to the closest point P3 on the right-side road boundary line should be 1/2P 3, and it is understood that the distance from the center reference point P4 to the closest point P2 on the left-side road boundary line should also be 1/2P 3.

If the target road includes two lanes, the preset value of the distance from the center reference point on the right lane center reference line to the right side road side boundary line should be set to one fourth of the road width, i.e., the distance d1 from the center reference point P4 on the right lane center reference line to the closest point P3 on the right side road side boundary line should be 1/4P2P3, and it is understood that the distance d2 from the center reference point P4 to the closest point P2 on the left side road side boundary line should be 3/4P2P3 at this time. Similarly, the preset value of the distance from the center reference point on the left lane center reference line to the left side road boundary line should be set to be one fourth of the road width, i.e., the distance d2 from the center reference point P4 on the left lane center reference line to the closest point P2 on the left side road boundary line should be 1/4P2P3, and it can be understood that the distance d1 from the center reference point P4 on the left lane center reference line to the closest point P3 on the right side road boundary line should be 3/4P2P3.

In the embodiment, the distance condition from the central reference point to the road boundary line and the angle condition of the vehicle body attitude angle of the track point can be preset, so that the influence on the accuracy of the lane center line due to the overlarge attitude angle of part of the track point caused by the shaking of the vehicle in the driving process and the influence on the accuracy of the lane center line can be avoided, and the effect of improving the accuracy of the lane center line is achieved.

Example two

Fig. 3 is a flowchart of a method for determining a lane center line according to a second embodiment of the present invention, which is detailed based on step S130 in the foregoing embodiment. Step S130, determining a vehicle track line according to the vehicle motion track information and the lane center reference line, wherein the step S comprises the following steps: determining a first error of the vehicle trajectory line according to pose information corresponding to two adjacent trajectory points in the vehicle trajectory line; determining a second error of the vehicle track line and the lane center reference line according to the coordinates of the track points on the vehicle track line and the coordinates of the center reference point of the track points mapped on the lane center reference line; a total error of the vehicle trajectory is determined based on the first error and the second error. As shown in fig. 3, the method includes:

s210, acquiring a road boundary line of a target road and vehicle motion trail information generated by the running of a vehicle in the target road, wherein the vehicle motion trail information comprises: and (4) position and attitude information corresponding to the vehicle trajectory line and the trajectory point on the vehicle trajectory line.

And S220, determining to form a lane center reference line according to the track points on the vehicle track line and the boundary points of the track points mapped on the road boundary line.

And S230, determining a first error of the vehicle trajectory line according to the pose information corresponding to two adjacent trajectory points in the vehicle trajectory line.

Wherein the first error is an error between two adjacent trajectory points in the vehicle trajectory line.

Specifically, the vehicle body attitude angles of two adjacent track points in the vehicle track line can be determined through the position and attitude information of the two adjacent track points, the position and attitude error between the adjacent track points is determined according to the vehicle body attitude angle corresponding to each track point, and the first error of the vehicle track line is determined according to the position and attitude error between every two adjacent track points.

And S240, determining a second error of the vehicle track line and the lane center reference line according to the coordinates of the track points on the vehicle track line and the coordinates of the center reference points of the track points mapped on the lane center reference line.

Wherein the second error is an error of the vehicle trajectory line and the lane center reference line.

Specifically, the position information of the track point is determined according to the coordinate of the track point on the vehicle track line, and the position information of the central reference point is determined according to the coordinate of the central reference point mapped by the track point on the lane central reference line; determining the position error according to the position information of the track point and the position information of the central reference point; and determining a second error of the vehicle track line and the lane center reference line according to the position error between each track point and the corresponding center reference point.

And S250, determining the total error of the vehicle track line according to the first error and the second error.

Specifically, determining the total error of the vehicle trajectory line according to the first error and the second error may obtain the total error by summing the first error and the second error, or may obtain the total error by weighted summing the first error and the second error.

And S260, carrying out position optimization on track points on the vehicle track line according to the total error to obtain the lane center line of the target road.

According to the technical scheme of the embodiment, the road boundary line of the target road and the vehicle motion trail information generated by the running of the vehicle in the target road are obtained, and the vehicle motion trail information comprises: the vehicle trajectory line and the pose information corresponding to the trajectory points on the vehicle trajectory line; determining to form a lane center reference line according to track points on a vehicle track line and boundary points of the track points mapped on a road boundary line; determining a first error of the vehicle trajectory line according to pose information corresponding to two adjacent trajectory points in the vehicle trajectory line; determining a second error of the vehicle track line and the lane center reference line according to the coordinates of the track points on the vehicle track line and the coordinates of the center reference point mapped on the lane center reference line by the track points; determining a total error of the vehicle trajectory line according to the first error and the second error; and performing position optimization on track points on the vehicle track line according to the total error to obtain the lane center line of the target road. According to the method, the total error of the vehicle track line is determined through the first error of the vehicle track line and the second error of the vehicle track line and the lane center reference line, the position of the track point on the vehicle track line is optimized according to the total error to obtain the lane center line of the target road, and the accuracy of the lane center line can be improved.

Optionally, determining a first error of the vehicle trajectory line according to pose information corresponding to two adjacent trajectory points in the vehicle trajectory line includes:

determining an adjacent track point group according to a vehicle track line in the vehicle motion track information; the adjacent track point group comprises two adjacent track points;

determining the relative pose of the adjacent track point groups according to the pose information corresponding to the adjacent track point groups contained in the vehicle motion track information;

determining the pose error of the adjacent track point groups according to the pose information and the relative pose corresponding to the adjacent track point groups;

and determining the weighted sum of the pose error corresponding to each adjacent track point group in the vehicle motion track information and the first weight as the first error of the vehicle track line.

The adjacent track point groups are the combination formed by two adjacent track point groups on the vehicle track line. The relative pose of the adjacent track point groups is the relative pose angle between any two adjacent track points. The first weight is a degree of significance of the pose error with respect to the first error.

Specifically, a vehicle track line is determined according to vehicle motion track information, and an adjacent track point group formed by two adjacent track points is determined according to the positions of the track points on the vehicle track line. And determining the relative pose of the adjacent track point groups according to the pose information between two adjacent track points in the adjacent track point groups. And determining the pose error of the adjacent track point groups according to the pose information and the relative pose corresponding to the adjacent track point groups. And determining the weighted sum of the pose error corresponding to each adjacent track point group in the vehicle motion track information and the first weight as the first error of the vehicle track line.

Determining the pose error of the adjacent track point groups according to the pose information and the relative pose corresponding to the adjacent track point groups can be realized by the following formula:

wherein e is _ij Pose errors for sets of adjacent track points, M _ij Is the relative position and posture T of two adjacent track points i and j _i Is a sum of T _j Respectively representing the poses of a track point i and a track point j; the V operator is to implement the conversion of an antisymmetric matrix to a column vector,

is a three-dimensional column vector representing the rotation amount, p _e Is a three-dimensional column vector representing the amount of translation.

Illustratively, as shown in FIG. 4, the pose T of the track point i is determined _i Coordinate T of adjacent track point j _j Relative pose therebetween is e _ij Determining the weighted sum of the pose error corresponding to each adjacent track point group in the vehicle motion track information and the first weight as a first error of the vehicle track line, namely:

wherein e is ₁ First error of vehicle trajectory, W ₁ The weight matrix of the first error is the number of track points in the N vehicle track lines.

For example, the first error may be calculated by: setting the first error with respect to xi, respectively _i ，ξ _j The corresponding matrix is also called the jacobian matrix, i.e.:

wherein:

i represents a 6 × 6 unit array;

an inverse matrix representing the attitude matrix;

3 rows and 3 columns of antisymmetric matrixes corresponding to the three-dimensional attitude vectors are represented;

representing a 3 row 3 column antisymmetric matrix for the three-dimensional position vector.

And Λ is used for converting the three-dimensional column vector into an anti-symmetric array, and if the three-dimensional column vector is p, the method comprises the following steps:

illustratively, the weight matrix W of the first error ₁ May be a 6 x 6 matrix, for example:

in the embodiment, the pose errors of the adjacent track point groups are determined according to the pose information and the relative pose corresponding to the adjacent track point groups, and the weighted sum of the pose error corresponding to each adjacent track point group in the vehicle motion track information and the first weight is determined as the first error of the vehicle track line; the problem that the accuracy of the lane center reference line is reduced due to the fact that track points with large vehicle track changes are selected can be solved, and the effect of accurately determining the lane center line is achieved. Optionally, determining a second error between the vehicle trajectory line and the lane center reference line according to the coordinates of the trajectory point on the vehicle trajectory line and the coordinates of the center reference point mapped by the trajectory point on the lane center reference line, including:

determining the difference value of the coordinates of the track points and the coordinates of the center reference point mapped by the track points on the lane center reference line as the offset error of the track points and the center reference point;

and determining the weighted sum of the offset error corresponding to each track point on the vehicle track line and the second weight as the second error of the vehicle track line and the lane center reference line.

The coordinates of the track points can be longitude and latitude coordinates of the track points and can also be coordinates of the track points in a self-defined coordinate system. The offset error is the position offset error of the track point and the mapped center reference point. The second weight is the degree of importance of the position error relative to the second error.

Specifically, the position information of the track point and the central reference point is determined according to the coordinate of the track point and the coordinate of the central reference point mapped on the lane central reference line of the track point, and the position offset error is determined according to the offset error of the coordinate of the track point and the central reference point; and determining the weighted sum of the offset error corresponding to each track point on the vehicle track line and the second weight as a second error of the vehicle track line and the lane center reference line.

The offset error between the trajectory point and the central reference point can be determined by the following equation:

e _ii ＝t _i -p _i ；

wherein e is _ii As deviation error of the track point from the central reference point, t _i As coordinates of the locus point i, p _i And coordinates of a center reference point mapped on the lane center reference line by the track point.

Illustratively, as shown in FIG. 4, the coordinates t of a trace point i are determined _i Coordinates p from a central reference point k _i Offset error between is e _ii And then the second error of the vehicle trajectory line and the lane center reference line is:

wherein e is ₂ A second error, W, of the vehicle trajectory line and the lane center reference line ₂ And M is the weight matrix of the second error, and M is the number of lane center reference points contained in the lane center line.

For example, the second error may be calculated by:

setting a second error with respect to ξ _i The corresponding matrix is also called the jacobian matrix, i.e.:

weight matrix W of second error ₂ May be a 3 × 3 array, for example:

in the embodiment, determining an offset error according to the coordinates of the track points and the coordinates of the central reference point, and determining a weighted sum of the offset error corresponding to each track point on the vehicle track line and the second weight as a second error of the vehicle track line and the lane central reference line; the problem that errors exist between the vehicle track line and the lane center line can be solved, and the accuracy of the lane center line is further improved.

Optionally, performing position optimization on the track point on the vehicle track line according to the total error to obtain a lane center line of the target road, including:

adjusting the coordinates of the track points on the vehicle track line according to the total error;

and determining the corresponding vehicle track line when the total error is minimum as the lane central line of the target road.

Specifically, the adjustment of the coordinates of the trajectory points on the vehicle trajectory line according to the total error is to adjust the vehicle trajectory points in a direction close to the central reference line to reduce the total error. And determining the vehicle track line with the minimum total error as the lane central line of the target road.

The total error in the vehicle trajectory can be determined by the following equation:

wherein e is the total error, e _ij Pose errors for sets of adjacent track points, e _ii As an offset error of the track point and the central reference point, W ₁ Is a weight matrix of the first error, W ₂ And the weight matrix is a weight matrix of the second error, N is the number of track points contained in the vehicle track line, and M is the number of lane center reference points contained in the lane center reference line.

In the embodiment, the coordinates of the track points on the vehicle track line are adjusted through the total error, and the corresponding vehicle track line when the total error is minimum is determined as the lane center line of the target road; the method can ensure that the error between the vehicle track line and the lane center reference line is minimum, and improve the accuracy of the lane center line of the target road.

EXAMPLE III

Fig. 4 is a schematic structural diagram of a device for determining a lane center line according to a third embodiment of the present invention. As shown in fig. 5, the apparatus includes: an acquisition module 510, a reference line determination module 520, an error determination module 530, and an optimization module 540;

the obtaining module 510 is configured to obtain a road boundary line of a target road and vehicle motion trail information generated when a vehicle runs in the target road, where the vehicle motion trail information includes: vehicle trajectory line and pose information corresponding to trajectory points on the vehicle trajectory line;

a reference line determining module 520, configured to determine a lane center reference line according to the track point on the vehicle track line and the boundary point of the track point mapped on the road boundary line;

an error determination module 530, configured to determine a total error of the vehicle trajectory line according to the vehicle motion trajectory information and the lane center reference line;

and the optimizing module 540 is configured to perform position optimization on the track points on the vehicle track line according to the total error to obtain a lane center line of the target road.

Optionally, the reference line determining module 520 includes:

the boundary point determining unit is used for determining the closest boundary point of each track point on the vehicle track line, wherein the track point is mapped on the road boundary line;

a central reference point determining unit, configured to determine a central reference point that meets a preset condition on a connection line between the track point and the closest boundary point;

and the reference line determining unit is used for determining a lane center reference line formed by the center reference point.

Optionally, the preset conditions include:

the distance from the central reference point to the road boundary line is a preset value;

and the vehicle body attitude angle of the vehicle at the track point corresponding to the central reference point is smaller than a preset angle.

Optionally, the error determining module 530 includes:

the first error determining unit is used for determining a first error of the vehicle track line according to pose information corresponding to two adjacent track points in the vehicle track line;

the second error determination unit is used for determining a second error of the vehicle track line and the lane center reference line according to the coordinates of the track point on the vehicle track line and the coordinates of the center reference point of the track point mapped on the lane center reference line;

a total error determination unit to determine a total error of the vehicle trajectory line from the first error and the second error.

Optionally, the first error determining unit includes:

the track point group determining subunit is used for determining an adjacent track point group according to the vehicle track line in the vehicle motion track information; the adjacent track point group comprises two adjacent track points;

the relative pose determining subunit is configured to determine, according to pose information corresponding to adjacent track point groups included in the vehicle motion trajectory information, relative poses of the adjacent track point groups;

the pose error determining subunit is used for determining the pose errors of the adjacent track point groups according to the pose information and the relative pose corresponding to the adjacent track point groups;

and the first error determining subunit is configured to determine, as the first error of the vehicle trajectory, a weighted sum of the pose error and the first weight that correspond to each adjacent trajectory point group in the vehicle motion trajectory information.

Optionally, the second error determining unit includes:

the offset error determining subunit is configured to determine a difference between the coordinates of the track point and the coordinates of a center reference point of the track point mapped on the lane center reference line as an offset error between the track point and the center reference point;

and the second error determining subunit is used for determining a weighted sum of the offset error corresponding to each track point on the vehicle track line and a second weight as a second error of the vehicle track line and the lane center reference line.

Optionally, the optimizing module 540 includes:

the adjusting unit is used for adjusting the coordinates of the track points on the vehicle track line according to the total error;

and the lane central line determining unit is used for determining the corresponding vehicle track line when the total error is minimum as the lane central line of the target road.

The device can execute the method for determining the lane center line provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the method for determining the lane center line.

Example four

Fig. 6 is a schematic structural diagram of an electronic device implementing the method for determining a lane center line according to the embodiment of the present invention. The electronic device 10 is 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 assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 6, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

Processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 11 performs the various methods and processes described above, such as the lane center line determination method.

In some embodiments, the lane centerline determination method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the lane center line determination method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the lane centreline 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), load 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.

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

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage 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. Alternatively, the computer readable storage medium may be a machine readable signal medium. 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 an electronic device 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 electronic device. 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), blockchain networks, and the internet.

The computing 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 can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.

It should be understood that various forms of the flows shown above, reordering, adding or deleting steps, may be used. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired result of the technical solution of the present invention can be achieved.

The above-described embodiments should not be construed as limiting the scope of the invention. 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 invention should be included in the protection scope of the present invention.

Claims

1. A method of determining a lane centerline, comprising:

the method comprises the steps of obtaining a road boundary line of a target road and vehicle motion trail information generated by driving of a vehicle in the target road, wherein the vehicle motion trail information comprises: vehicle trajectory lines and pose information corresponding to trajectory points on the vehicle trajectory lines;

and performing position optimization on track points on the vehicle track line according to the total error to obtain the lane center line of the target road.

2. The method of claim 1, wherein determining a lane center reference line from the track points on the vehicle track line and the boundary points on the road boundary line to which the track points map comprises:

for each track point on the vehicle track line, determining the closest boundary point of the track point mapped on the road boundary line;

determining a central reference point meeting a preset condition on a connecting line of the track point and the nearest boundary point;

3. The method according to claim 2, wherein the preset condition comprises:

4. The method of claim 1, wherein said determining the vehicle trajectory line from the vehicle motion trajectory information and the lane center reference line comprises:

determining a first error of the vehicle trajectory line according to pose information corresponding to two adjacent trajectory points in the vehicle trajectory line;

determining a second error of the vehicle track line and the lane center reference line according to the coordinates of the track points on the vehicle track line and the coordinates of the center reference point mapped on the lane center reference line by the track points;

determining a total error of the vehicle trajectory from the first error and the second error.

5. The method of claim 4, wherein determining the first error of the vehicle trajectory line from pose information corresponding to two adjacent trajectory points in the vehicle trajectory line comprises:

determining an adjacent track point group according to the vehicle track line in the vehicle motion track information; the adjacent track point group comprises two adjacent track points;

determining the relative pose of the adjacent track point groups according to pose information corresponding to the adjacent track point groups contained in the vehicle motion track information;

6. The method of claim 4, wherein determining a second error for the vehicle trajectory line and the lane center reference line based on coordinates of a trajectory point on the vehicle trajectory line and coordinates of a center reference point to which the trajectory point is mapped on the lane center reference line comprises:

determining the difference value between the coordinates of the track points and the coordinates of the center reference point mapped by the track points on the lane center reference line as the offset error of the track points and the center reference point;

7. The method of claim 1, wherein the optimizing the position of the trajectory point on the vehicle trajectory line according to the total error to obtain the lane centerline of the target road comprises:

8. A lane centerline determination apparatus, comprising:

the vehicle motion track information acquisition module is used for acquiring a road boundary line of a target road and vehicle motion track information generated by driving of a vehicle in the target road, and the vehicle motion track information comprises: vehicle trajectory lines and pose information corresponding to trajectory points on the vehicle trajectory lines;

9. An electronic device, characterized in that the electronic device comprises:

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 a computer program executable by the at least one processor to enable the at least one processor to perform the method of lane centerline determination of any one of claims 1-7.

10. A computer-readable storage medium storing computer instructions for causing a processor to perform the method of determining lane center line according to any one of claims 1-7 when executed.