CN112435573B - Map drawing method and device for automatic driving simulation test - Google Patents

Map drawing method and device for automatic driving simulation test Download PDF

Info

Publication number
CN112435573B
CN112435573B CN202011328186.5A CN202011328186A CN112435573B CN 112435573 B CN112435573 B CN 112435573B CN 202011328186 A CN202011328186 A CN 202011328186A CN 112435573 B CN112435573 B CN 112435573B
Authority
CN
China
Prior art keywords
road
control point
lane
vertex
midpoint
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011328186.5A
Other languages
Chinese (zh)
Other versions
CN112435573A (en
Inventor
何丰
王铁锋
白晋德
陈贞
薛晓卿
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Saimu Technology Co ltd
Zhejiang Saimu Technology Co ltd
Original Assignee
Zhejiang Saimu Technology Co ltd
Beijing Saimu Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhejiang Saimu Technology Co ltd, Beijing Saimu Technology Co ltd filed Critical Zhejiang Saimu Technology Co ltd
Priority to CN202011328186.5A priority Critical patent/CN112435573B/en
Publication of CN112435573A publication Critical patent/CN112435573A/en
Application granted granted Critical
Publication of CN112435573B publication Critical patent/CN112435573B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G09EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09BEDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B29/00Maps; Plans; Charts; Diagrams, e.g. route diagram
    • G09B29/003Maps
    • G09B29/005Map projections or methods associated specifically therewith

Abstract

The embodiment of the invention discloses a map drawing method and a map drawing device for an automatic driving simulation test. The method comprises the following steps: acquiring a road description file, and extracting the position information of the contour point of each lane line in the road description file; extracting lane attributes of each road from the road description file; the lane attributes include: lane marks, lane types, lane front-back connection relations, lane widths and lane heights; extracting the geometric attributes of each road from the road description file; the geometric attributes include: the distance between the geometric starting point and the road starting position, the coordinate information of the geometric starting point, the course of the geometric starting point, the length of the geometric track and the curvature of each curve geometry; drawing the contour points of each lane line to obtain each closed lane section; and generating the status bar information of each road section according to the geometric attributes of each road. By applying the scheme provided by the embodiment of the invention, the map drawing precision can be realized, and the automatic driving simulation test can be ensured to be normally carried out.

Description

Map drawing method and device for automatic driving simulation test
Technical Field
The invention relates to the technical field of automatic driving simulation tests, in particular to a map drawing method and a map drawing device for the automatic driving simulation tests.
Background
In the field of automatic driving simulation testing, part of simulation testing scenes are created by actually acquiring running environment images of an automatic driving vehicle. In addition, in order to accurately test the performance parameters of the vehicle to be tested, the acquired position data of the vehicle, the surrounding markers and the obstacles are required to be very accurate.
However, the existing high-precision mapping technology is developed for navigation, and the precision of the mapping technology cannot be directly used for simulation test of automatic driving. Therefore, a mapping technique that can be applied to an automated driving simulation test is highly desirable.
Disclosure of Invention
The invention provides a map drawing method and a map drawing device for an automatic driving simulation test, which are used for improving the map drawing precision and ensuring the normal running of the automatic driving simulation test. The specific technical scheme is as follows.
In a first aspect, an embodiment of the present invention provides a mapping method for an automatic driving simulation test, where the method includes:
acquiring a road description file, and extracting the position information of the contour point of each lane line in the road description file;
extracting lane attributes of each road from the road description file; the lane attributes include: lane marks, lane types, lane front-back connection relations, lane widths and lane heights;
extracting the geometric attributes of each road from the road description file; the geometric properties include: the distance between the geometric starting point and the road starting position, the coordinate information of the geometric starting point, the course of the geometric starting point, the length of the geometric track and the curvature of each curve geometry;
drawing the contour points of each lane line according to the contour point position information of each lane line and the lane attributes of each lane to obtain each closed road section;
and generating the status bar information of each road section according to the geometric attributes of each road.
Optionally, the step of drawing the contour points of each lane line according to the contour point position information of each lane line and the lane attributes of each lane to obtain each closed road section includes:
placing the position information of the contour points of the lane lines according to the lane section levels;
and drawing the contour points of the adjacent lanes according to lane sections according to the lane attributes of the roads to obtain the closed lane sections.
Optionally, the method further includes:
detecting a road notch existing in a current map, selecting a first vertex in a first side of the road notch, and selecting a second vertex in a second side of the road notch; wherein the distance from the first vertex to the road edge is less than a first threshold, the distance from the second vertex to the road edge is less than a second threshold, and the first threshold and the second threshold are equal or different;
determining the position of an auxiliary control point according to the positions of the first vertex and the second vertex; connecting the first vertex and the auxiliary control point to obtain a first connecting line, connecting the second vertex and the auxiliary control point to obtain a second connecting line, determining a first middle point of the first connecting line and a second middle point of the second connecting line, and determining the position of a candidate control point according to the positions of the first vertex, the second vertex, the auxiliary control point, the first middle point and the second middle point; the candidate control point is positioned on a midpoint connecting line of the first midpoint and the second midpoint, and the length ratio of the first connecting line to the second connecting line is equal to the ratio of the first midpoint to the connecting line of the candidate control point and the ratio of the second midpoint to the connecting line of the candidate control point;
determining positions of a first target control point and a second target control point respectively corresponding to the first midpoint and the second midpoint based on the positions of the candidate control point, the auxiliary control point, the first midpoint and the second midpoint;
generating a road edge curve according to the first vertex or the second vertex, the auxiliary control point, the first target control point and the second target control point;
and generating a connecting line corresponding to the road notch according to the road edge curve.
Optionally, the step of determining a position of an auxiliary control point according to the positions of the first vertex and the second vertex includes:
connecting the first vertex and the second vertex to obtain a connecting line of the first vertex and the second vertex;
constructing a central line of the connecting line, and determining a preset distance;
and determining a point which faces the direction of the road edge on the midline and is away from the connecting line by the preset distance as an auxiliary control point.
Optionally, the step of determining, based on the positions of the candidate control point, the auxiliary control point, the first midpoint, and the second midpoint, the positions of the first target control point and the second target control point corresponding to the first midpoint and the second midpoint, respectively, includes:
determining a vector line from the candidate control point to the auxiliary control point;
and translating the midpoint connecting line according to the vector line direction, determining the current position of the first midpoint as the position of a first target control point and determining the current position of the second midpoint as the position of a second target control point when the candidate control point is superposed with the auxiliary control point.
Optionally, the step of generating a road edge curve according to the first vertex or the second vertex, the auxiliary control point, the first target control point, and the second target control point includes:
a third order bezier curve b (t) is generated as the road-edge curve according to the following formula:
B(t)=P0(1-t)3+3P1t(1-t)2+3P2t2(1-t)+P3t3,t∈[0,1]
p0 is the coordinates of the first vertex or the second vertex, P1 is the coordinates of the first target control point, P2 is the coordinates of the second target control point, P3 is the coordinates of the auxiliary control point.
In a second aspect, an embodiment of the present invention provides a mapping apparatus for an automated driving simulation test, the apparatus including:
the system comprises a file acquisition module, a data processing module and a data processing module, wherein the file acquisition module is used for acquiring a road description file and extracting the position information of the contour point of each lane line in the road description file;
the lane attribute extraction module is used for extracting lane attributes of all roads from the road description file; the lane attributes include: lane marks, lane types, lane front-back connection relations, lane widths and lane heights;
the geometric attribute extraction module is used for extracting the geometric attributes of all roads from the road description file; the geometric properties include: the distance between the geometric starting point and the road starting position, the coordinate information of the geometric starting point, the course of the geometric starting point, the length of the geometric track and the curvature of each curve geometry;
the road drawing module is used for drawing the contour points of each lane line according to the contour point position information of each lane line and the lane attributes of each lane to obtain each closed road section;
and the status bar generating module is used for generating status bar information of each road section according to the geometric attributes of each road.
Optionally, the road drawing module includes:
the data placement submodule is used for placing the position information of the contour points of all the lane lines according to the level of the lane sections;
and the road drawing submodule is used for drawing the contour points of each adjacent lane according to lane sections according to the lane attributes of each road to obtain each closed lane section.
Optionally, the apparatus further comprises:
the device comprises a vertex selection module, a first vertex selection module and a second vertex selection module, wherein the vertex selection module is used for detecting a road notch existing in a current map, selecting a first vertex in a first side of the road notch and selecting a second vertex in a second side of the road notch; wherein the distance from the first vertex to the road edge is less than a first threshold, the distance from the second vertex to the road edge is less than a second threshold, and the first threshold and the second threshold are equal or different;
the candidate control point determining module is used for determining the position of an auxiliary control point according to the positions of the first vertex and the second vertex; connecting the first vertex and the auxiliary control point to obtain a first connecting line, connecting the second vertex and the auxiliary control point to obtain a second connecting line, determining a first middle point of the first connecting line and a second middle point of the second connecting line, and determining the position of a candidate control point according to the positions of the first vertex, the second vertex, the auxiliary control point, the first middle point and the second middle point; the candidate control point is positioned on a midpoint connecting line of the first midpoint and the second midpoint, and the length ratio of the first connecting line to the second connecting line is equal to the ratio of the first midpoint to the connecting line of the candidate control point and the ratio of the second midpoint to the connecting line of the candidate control point;
a target control point determining module, configured to determine positions of a first target control point and a second target control point corresponding to the first midpoint and the second midpoint, respectively, based on the positions of the candidate control point, the auxiliary control point, the first midpoint, and the second midpoint;
a road edge curve generating module, configured to generate a road edge curve according to the first vertex or the second vertex, the auxiliary control point, the first target control point, and the second target control point;
and the connecting line generating module is used for generating the connecting line corresponding to the road notch according to the road edge curve.
Optionally, the candidate control point determining module includes:
the connecting line generation submodule is used for connecting the first vertex and the second vertex to obtain a connecting line of the first vertex and the second vertex;
the preset distance determining submodule is used for constructing a central line of the connecting line and determining a preset distance;
and the auxiliary control point determining submodule is used for determining a point which faces the direction of the road edge on the midline and is away from the connecting line by the preset distance as an auxiliary control point.
Optionally, the target control point determining module includes:
a vector line determination submodule for determining a vector line from the candidate control point to the auxiliary control point;
and the target control point determining submodule is used for translating the midpoint connecting line according to the vector line direction, determining the current position of the first midpoint as the position of a first target control point and determining the current position of the second midpoint as the position of a second target control point when the candidate control point is overlapped with the auxiliary control point.
Optionally, the road edge curve generating module is specifically configured to:
a third order bezier curve b (t) is generated as the road-edge curve according to the following formula:
B(t)=P0(1-t)3+3P1t(1-t)2+3P2t2(1-t)+P3t3,t∈[0,1]
p0 is the coordinates of the first vertex or the second vertex, P1 is the coordinates of the first target control point, P2 is the coordinates of the second target control point, P3 is the coordinates of the auxiliary control point.
As can be seen from the above, the map drawing method and apparatus for the automatic driving simulation test provided in the embodiments of the present invention can draw the contour points of each lane line based on the lane attributes in the road description file to obtain each closed road segment, thereby accurately obtaining the position of each lane line and improving the map drawing precision. And moreover, the status bar information of each road section is generated according to the geometric attributes of each road, so that the road condition of the position of the vehicle can be obtained by positioning the automatic driving vehicle in the automatic driving test process, and the automatic driving algorithm can be further optimized. Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.
The innovation points of the embodiment of the invention comprise:
1. and drawing the contour points of each lane line based on the lane attributes in the road description file to obtain each closed road section, thereby accurately obtaining the position of each lane line and improving the drawing precision of the map. And moreover, the status bar information of each road section is generated according to the geometric attributes of each road, so that the road condition of the position of the vehicle can be obtained by positioning the automatic driving vehicle in the automatic driving test process, and the automatic driving algorithm can be further optimized.
2. Compared with the method using the geometric level contour points, the method using the lane section level contour points to map can still avoid generating road gaps when various geometric shapes exist in the road, and improve the accuracy of mapping, thereby improving the accuracy of the automatic driving simulation test.
3. When a road notch is detected, a connecting line corresponding to the road notch is generated, specifically, two vertexes can be selected from two edges forming the road notch, then an auxiliary control point, a candidate control point and a target control point are determined based on the two vertexes, and finally a road edge curve is generated based on any vertex, the auxiliary control point and the target control point, so that the connecting line corresponding to the road notch can be generated according to the road edge curve, that is, the road notch can be supplemented by the curve, compared with the situation that the notch is directly supplemented by a straight line, the notch is supplemented by the curve, a new road notch cannot be formed, and therefore, the test work of the automatic driving vehicle can be normally performed after the road is supplemented.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is to be understood that the drawings in the following description are merely exemplary of some embodiments of the invention. For a person skilled in the art, without inventive effort, further figures can be obtained from these figures.
Fig. 1 is a schematic flow chart of a mapping method for an automatic driving simulation test according to an embodiment of the present invention;
FIG. 2 is a schematic view of a road gap occurring in a road in an embodiment of the present invention;
FIG. 3 is a schematic flow chart of a mapping method for an automatic driving simulation test according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating a process for determining control points according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a mapping apparatus for an automatic driving simulation test according to an embodiment of the present invention.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It is to be understood that the described embodiments are merely a few embodiments of the invention, and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.
It is to be noted that the terms "comprises" and "comprising" and any variations thereof in the embodiments and drawings of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
The embodiment of the invention discloses a map drawing method and a map drawing device for an automatic driving simulation test, which can improve the map drawing precision and ensure the normal running of the automatic driving simulation test. The following provides a detailed description of embodiments of the invention.
Fig. 1 is a schematic flow chart of a mapping method for an automatic driving simulation test according to an embodiment of the present invention. The method is applied to the electronic equipment. The method specifically comprises the following steps.
S110: and acquiring a road description file, and extracting the position information of the contour point of each lane line in the road description file.
The road description file may include an Opendrive description file of a road, and all lane line contour points may be obtained according to the Opendrive description file of the road.
S120: extracting lane attributes of each road from the road description file; the lane attributes include: lane marks, lane types, lane front-back connection relations, lane widths and lane heights.
Lane attributes are some parameters inherent to the lane itself, such as may include a lane identification id; a lane type; the front and rear connection relation link of the lane; lane width; lane height, etc.
The lane marker may be used to distinguish lanes, and may be composed of characters, numbers, and the like, which is not limited in this embodiment of the present invention.
S130: extracting the geometric attributes of each road from the road description file; the geometric attributes include: the distance between the geometric starting point and the road starting position, the coordinate information of the geometric starting point, the heading at the geometric starting point, the length of the geometric track and the curvature of each curve geometry.
The geometric attribute of the road is related parameters for describing the road track, such as the distance s between a geometric starting point and the starting position of the road; x, y coordinates of the geometric starting point; heading hdg at the geometric starting point; length of the geometric locus; and curvature, which some curvilinear geometries may have, etc.
The geometric starting point may be set according to actual conditions, for example, a starting point of the autonomous vehicle, an origin of a coordinate system, or the like.
S140: and drawing the contour points of each lane line according to the position information of the contour points of each lane line and the lane attributes of each lane to obtain each closed road section.
In one implementation, the contour point position information of each lane line may be first placed according to the lane segment hierarchy; and then drawing the contour points of the adjacent lanes according to the lane attributes of the roads to obtain the closed road sections.
Compared with the method using the geometric level contour points, the method using the lane section level contour points to map can still avoid generating road gaps when various geometric shapes exist in the road, and improve the accuracy of mapping, thereby improving the accuracy of the automatic driving simulation test.
S150: and generating the status bar information of each road section according to the geometric attributes of each road.
After the status bar information of each road segment is generated in the map, when the cursor points at a certain point, information such as a road ID (Identity document) where the point is located, a lane ID, a distance between the point and a road starting point, a distance from a road reference line, a lane width and the like can be displayed.
As can be seen from the above, in the embodiment, the contour points of each lane line can be drawn to obtain each closed road segment based on the lane attributes in the road description file, so that the position of each lane line can be accurately obtained, and the map drawing precision is improved. And moreover, the status bar information of each road section is generated according to the geometric attributes of each road, so that the road condition of the position of the vehicle can be obtained by positioning the automatic driving vehicle in the automatic driving test process, and the automatic driving algorithm can be further optimized.
It is understood that in practical applications, due to the situation that roads intersect and the like, discontinuous gaps may exist in the drawn map, that is, the situation that the roads are discontinuous may occur. As shown in fig. 2, the area 210 is a gap in the road. As can be seen in fig. 2, the gap in the road may be composed of two edges 211 and 212. For the automatic driving vehicle, when a gap appears on the road in front, the front road is considered to be not available, and the automatic driving vehicle stops running, so that the test of the automatic driving vehicle cannot be normally carried out.
As an implementation manner of the embodiment of the present invention, after the map is drawn, the electronic device may also fill up gaps appearing in the road. Specifically, as shown in fig. 3, the process includes the following steps.
S310: detecting a road notch existing in a current map, selecting a first vertex in a first side of the road notch, and selecting a second vertex in a second side of the road notch; the distance between the first vertex and the road edge is smaller than a first threshold, the distance between the second vertex and the road edge is smaller than a second threshold, and the first threshold and the second threshold are equal or different.
For example, any known image detection method may be used to detect in the current map, and when a road region with a discontinuity is detected, it may be determined that a road gap exists in the current road.
The first threshold and the second threshold may be set according to actual situations, for example, may be set to 1 cm, 2 cm, 3 cm, and the like, which is not limited in this embodiment of the present invention.
S320: determining the position of an auxiliary control point according to the positions of the first vertex and the second vertex; connecting the first vertex and the auxiliary control point to obtain a first connecting line, connecting the second vertex and the auxiliary control point to obtain a second connecting line, determining a first middle point of the first connecting line and a second middle point of the second connecting line, and determining the position of the candidate control point according to the positions of the first vertex, the second vertex, the auxiliary control point, the first middle point and the second middle point; the candidate control points are positioned on a midpoint connecting line of the first midpoint and the second midpoint, and the length ratio of the first connecting line to the second connecting line is equal to the ratio of the first midpoint to the connecting line of the candidate control points and the ratio of the second midpoint to the connecting line of the candidate control points.
In the embodiment of the present invention, in order to complement the road gap, after the first vertex and the second vertex are determined, a plurality of control points for constructing the road edge curve may be sequentially determined based on the first vertex and the second vertex.
For example, as shown in FIG. 4, a schematic diagram of a process for determining control points is shown. After determining the first vertex a and the second vertex C, the auxiliary control point B may be first determined based on the first vertex a and the second vertex C, followed by connecting AB, BC, and determining the midpoint E of AB, and the midpoint F of BC, and then determining the candidate control point D on EF. Here, when B is selected, it is sufficient to ensure that point F is the midpoint of BC, point E is the midpoint of AB, and BC/AB is FD/ED.
In one implementation, the first vertex and the second vertex may be connected first, so as to obtain a connection line between the first vertex and the second vertex; then, constructing a central line of the connecting line, and determining a preset distance; and then, determining a point which is on the middle line and faces to the direction of the road edge and is at a preset distance from the connecting line as an auxiliary control point.
That is, the B point may be selected on the angular bisector, i.e., the midline, of the AC. Therefore, the road connecting lines generated subsequently are symmetrical about the road notch and accord with the actual road condition, and the test precision can be improved when the automatic driving vehicle test is carried out.
When the preset distance is determined, a pre-stored target distance can be acquired as the preset distance; or the length of the connecting line can be calculated, and the preset distance can be calculated according to the length of the connecting line and the proportional relation between the preset length of the connecting line and the preset distance.
The preset distance is determined according to the length of the connecting line, the determined auxiliary control point can be closer to the edge of the road, the road edge curve generated according to the auxiliary control point is closer to the edge of the actual road, and the test precision can be improved when the automatic driving vehicle is tested.
S330: and determining the positions of a first target control point and a second target control point respectively corresponding to the first midpoint and the second midpoint based on the positions of the candidate control point, the auxiliary control point, the first midpoint and the second midpoint.
In one implementation, a vector line from a candidate control point to an auxiliary control point may be first determined; and then, translating the midpoint connecting line according to the vector line direction, determining the position of the current first midpoint as the position of a first target control point and determining the position of the current second midpoint as the position of a second target control point when the candidate control point is superposed with the auxiliary control point.
As shown in fig. 4, that is, the line segment EF can be moved along the vector line DB, and when the points D and B coincide, the current point E is the first target control point E ', and the current point F is the second target control point F'.
Optionally, in the embodiment of the present invention, after the positions of the first target control point and the second target control point are determined, a straight line where the first target control point and the second target control point are located may also be constructed; and then moving the first target control point and the second target control point on a straight line by a preset length to obtain the updated first target control point and second target control point, wherein the preset length is related to the lengths of the first connecting line and the second connecting line.
That is, the target control point E 'F' can be moved on the straight line on which it is located, so that the state of the interpolation curve can be changed. Specifically, a coefficient K related to the initial distance between the auxiliary control point and the vertex can be used to move the target control point along a straight line. In practical applications, the farther away the target control point is from the vertex, the sharper the graphic appears.
S340: and generating a road edge curve according to the first vertex or the second vertex, the auxiliary control point, the first target control point and the second target control point.
There is a very common type of curve in computer graphics, commonly known as a bezier curve. Specifically, a first order bezier curve, a second order bezier curve, and a third order bezier curve may be included.
First order bezier curve: the vertices are two points, and the generated bezier curve is a line segment formed by connecting the two points. Second order bezier curve: the vertex is two points, and a control point is introduced, so that a second-order Bezier curve can be generated, wherein the second-order Bezier curve is a curve described by a quadratic function and has at most one vertex.
In the simulation, a cubic function is used to describe a curve road, so a third-order bezier curve needs to be generated, and then according to the drawing of the third-order bezier curve, two control points, namely the first target control point and the second target control point, need to be introduced.
To ensure that the curves are continuous at the vertices, it is desirable that the tangent to the left curve at the vertex coincide with the tangent to the right curve at the vertex. I.e. the left derivative of the function is equal to the right derivative.
In one implementation, when the road edge curve is generated according to the first vertex or the second vertex, the auxiliary control point, the first target control point, and the second target control point, a third-order bezier curve b (t) may be generated as the road edge curve according to the following formula:
B(t)=P0(1-t)3+3P1t(1-t)2+3P2t2(1-t)+P3t3,t∈[0,1]
p0 is the coordinates of the first vertex or the second vertex, P1 is the coordinates of the first target control point, P2 is the coordinates of the second target control point, and P3 is the coordinates of the auxiliary control point.
S350: and generating a connecting line corresponding to the road notch according to the road edge curve.
The above curve equation can also be modified as:
Figure BDA0002794985160000111
wherein n is 3.
In the embodiment of the present invention, the connecting line may be generated by the following Opendrive poly3 road type formula:
V=a+b*du+c*du2+d*du3
wherein, the coefficients in the Bezier curve formula and the openrive road type formula have a one-to-one correspondence relationship: the former 0-order coefficient corresponds to the latter a, the former 1-order coefficient corresponds to the latter b, the former 2-order coefficient corresponds to the latter c, and the former 3-order coefficient corresponds to the latter d.
This embodiment can generate the connecting wire that the road breach corresponds when detecting the road breach, and is concrete, can select two summits in two edges of constituteing the road breach, and then confirm auxiliary control point, candidate control point and target control point based on these two summits, finally generate road edge curve based on arbitrary summit, auxiliary control point and target control point, thereby can generate the connecting wire that the road breach corresponds according to road edge curve, that is to say, can mend the road breach with the curve, compare with directly mending the breach with the straight line, mend the breach with the curve and can not form new road breach, thereby can guarantee to mend the back to the road, the test work of autopilot vehicle normally goes on.
As shown in fig. 5, it shows a schematic structural diagram of a mapping apparatus for an automatic driving simulation test according to an embodiment of the present invention, the apparatus includes:
a file obtaining module 510, configured to obtain a road description file, and extract contour point position information of each lane line from the road description file;
a lane attribute extraction module 520, configured to extract lane attributes of each road from the road description file; the lane attributes include: lane marks, lane types, lane front-back connection relations, lane widths and lane heights;
a geometric attribute extraction module 530, configured to extract geometric attributes of each road from the road description file; the geometric properties include: the distance between the geometric starting point and the road starting position, the coordinate information of the geometric starting point, the course of the geometric starting point, the length of the geometric track and the curvature of each curve geometry;
the road drawing module 540 is configured to draw the contour points of each lane line according to the contour point position information of each lane line and the lane attributes of each lane, so as to obtain each closed road segment;
and a status bar generating module 550, configured to generate status bar information of each road segment according to the geometric attribute of each road.
Optionally, the road drawing module 540 includes:
the data placement submodule is used for placing the position information of the contour points of all the lane lines according to the level of the lane sections;
and the road drawing submodule is used for drawing the contour points of each adjacent lane according to lane sections according to the lane attributes of each road to obtain each closed lane section.
Optionally, the apparatus further comprises:
the device comprises a vertex selection module, a first vertex selection module and a second vertex selection module, wherein the vertex selection module is used for detecting a road notch existing in a current map, selecting a first vertex in a first side of the road notch and selecting a second vertex in a second side of the road notch; wherein the distance from the first vertex to the road edge is less than a first threshold, the distance from the second vertex to the road edge is less than a second threshold, and the first threshold and the second threshold are equal or different;
the candidate control point determining module is used for determining the position of an auxiliary control point according to the positions of the first vertex and the second vertex; connecting the first vertex and the auxiliary control point to obtain a first connecting line, connecting the second vertex and the auxiliary control point to obtain a second connecting line, determining a first middle point of the first connecting line and a second middle point of the second connecting line, and determining the position of a candidate control point according to the positions of the first vertex, the second vertex, the auxiliary control point, the first middle point and the second middle point; the candidate control point is positioned on a midpoint connecting line of the first midpoint and the second midpoint, and the length ratio of the first connecting line to the second connecting line is equal to the ratio of the first midpoint to the connecting line of the candidate control point and the ratio of the second midpoint to the connecting line of the candidate control point;
a target control point determining module, configured to determine positions of a first target control point and a second target control point corresponding to the first midpoint and the second midpoint, respectively, based on the positions of the candidate control point, the auxiliary control point, the first midpoint, and the second midpoint;
a road edge curve generating module, configured to generate a road edge curve according to the first vertex or the second vertex, the auxiliary control point, the first target control point, and the second target control point;
and the connecting line generating module is used for generating the connecting line corresponding to the road notch according to the road edge curve.
Optionally, the candidate control point determining module includes:
the connecting line generation submodule is used for connecting the first vertex and the second vertex to obtain a connecting line of the first vertex and the second vertex;
the preset distance determining submodule is used for constructing a central line of the connecting line and determining a preset distance;
and the auxiliary control point determining submodule is used for determining a point which faces the direction of the road edge on the midline and is away from the connecting line by the preset distance as an auxiliary control point.
Optionally, the target control point determining module includes:
a vector line determination submodule for determining a vector line from the candidate control point to the auxiliary control point;
and the target control point determining submodule is used for translating the midpoint connecting line according to the vector line direction, determining the current position of the first midpoint as the position of a first target control point and determining the current position of the second midpoint as the position of a second target control point when the candidate control point is overlapped with the auxiliary control point.
Optionally, the road edge curve generating module is specifically configured to:
a third order bezier curve b (t) is generated as the road-edge curve according to the following formula:
B(t)=P0(1-t)3+3P1t(1-t)2+3P2t2(1-t)+P3t3,t∈[0,1]
p0 is the coordinates of the first vertex or the second vertex, P1 is the coordinates of the first target control point, P2 is the coordinates of the second target control point, P3 is the coordinates of the auxiliary control point.
As can be seen from the above, the map drawing method and apparatus for the automatic driving simulation test provided in the embodiments of the present invention can draw the contour points of each lane line based on the lane attributes in the road description file to obtain each closed road segment, thereby accurately obtaining the position of each lane line and improving the map drawing precision. And moreover, the status bar information of each road section is generated according to the geometric attributes of each road, so that the road condition of the position of the vehicle can be obtained by positioning the automatic driving vehicle in the automatic driving test process, and the automatic driving algorithm can be further optimized.
The above device embodiment corresponds to the method embodiment, and has the same technical effect as the method embodiment, and for the specific description, refer to the method embodiment. The device embodiment is obtained based on the method embodiment, and for specific description, reference may be made to the method embodiment section, which is not described herein again.
Those of ordinary skill in the art will understand that: the figures are merely schematic representations of one embodiment, and the blocks or flow diagrams in the figures are not necessarily required to practice the present invention.
Those of ordinary skill in the art will understand that: modules in the devices in the embodiments may be distributed in the devices in the embodiments according to the description of the embodiments, or may be located in one or more devices different from the embodiments with corresponding changes. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (6)

1. A mapping method for automated driving simulation testing, the method comprising:
acquiring a road description file, and extracting the position information of the contour point of each lane line in the road description file;
extracting lane attributes of each road from the road description file; the lane attributes include: lane marks, lane types, lane front-back connection relations, lane widths and lane heights;
extracting the geometric attributes of each road from the road description file; the geometric properties include: the distance between the geometric starting point and the road starting position, the coordinate information of the geometric starting point, the course of the geometric starting point, the length of the geometric track and the curvature of each curve geometry;
drawing the contour points of each lane line according to the contour point position information of each lane line and the lane attributes of each lane to obtain each closed road section;
generating status bar information of each road section according to the geometric attributes of each road;
the step of drawing the contour points of each lane line according to the contour point position information of each lane line and the lane attributes of each lane to obtain each closed road section comprises the following steps:
placing the position information of the contour points of the lane lines according to the lane section levels;
drawing the contour points of each adjacent lane according to lane sections according to the lane attributes of each road to obtain each closed lane section;
the method further comprises the following steps:
detecting a road notch existing in a current map, selecting a first vertex in a first side of the road notch, and selecting a second vertex in a second side of the road notch; wherein the distance from the first vertex to the road edge is less than a first threshold, the distance from the second vertex to the road edge is less than a second threshold, and the first threshold and the second threshold are equal or different;
determining the position of an auxiliary control point according to the positions of the first vertex and the second vertex; connecting the first vertex and the auxiliary control point to obtain a first connecting line, connecting the second vertex and the auxiliary control point to obtain a second connecting line, determining a first middle point of the first connecting line and a second middle point of the second connecting line, and determining the position of a candidate control point according to the positions of the first vertex, the second vertex, the auxiliary control point, the first middle point and the second middle point; the candidate control point is positioned on a midpoint connecting line of the first midpoint and the second midpoint, and the length ratio of the first connecting line to the second connecting line is equal to the ratio of the first midpoint to the connecting line of the candidate control point and the ratio of the second midpoint to the connecting line of the candidate control point;
determining positions of a first target control point and a second target control point respectively corresponding to the first midpoint and the second midpoint based on the positions of the candidate control point, the auxiliary control point, the first midpoint and the second midpoint;
generating a road edge curve according to the first vertex or the second vertex, the auxiliary control point, the first target control point and the second target control point;
and generating a connecting line corresponding to the road notch according to the road edge curve.
2. The method of claim 1, wherein determining the location of an auxiliary control point based on the locations of the first vertex and the second vertex comprises:
connecting the first vertex and the second vertex to obtain a connecting line of the first vertex and the second vertex;
constructing a central line of the connecting line, and determining a preset distance;
and determining a point which faces the direction of the road edge on the midline and is away from the connecting line by the preset distance as an auxiliary control point.
3. The method of claim 1, wherein determining the locations of a first target control point and a second target control point corresponding to the first midpoint and the second midpoint, respectively, based on the locations of the candidate control point, the auxiliary control point, the first midpoint, and the second midpoint comprises:
determining a vector line from the candidate control point to the auxiliary control point;
and translating the midpoint connecting line according to the vector line direction, determining the current position of the first midpoint as the position of a first target control point and determining the current position of the second midpoint as the position of a second target control point when the candidate control point is superposed with the auxiliary control point.
4. A method according to any of claims 1-3, wherein the step of generating a road-edge curve from the first vertex or the second vertex, the auxiliary control point, the first target control point and the second target control point comprises:
a third order bezier curve b (t) is generated as the road-edge curve according to the following formula:
B(t)=P0(1-t)3+3P1t(1-t)2+3P2t2(1-t)+P3t3,t∈[0,1]
p0 is the coordinates of the first vertex or the second vertex, P1 is the coordinates of the first target control point, P2 is the coordinates of the second target control point, P3 is the coordinates of the auxiliary control point.
5. A mapping apparatus for automated driving simulation testing, the apparatus comprising:
the system comprises a file acquisition module, a data processing module and a data processing module, wherein the file acquisition module is used for acquiring a road description file and extracting the position information of the contour point of each lane line in the road description file;
the lane attribute extraction module is used for extracting lane attributes of all roads from the road description file; the lane attributes include: lane marks, lane types, lane front-back connection relations, lane widths and lane heights;
the geometric attribute extraction module is used for extracting the geometric attributes of all roads from the road description file; the geometric properties include: the distance between the geometric starting point and the road starting position, the coordinate information of the geometric starting point, the course of the geometric starting point, the length of the geometric track and the curvature of each curve geometry;
the road drawing module is used for drawing the contour points of each lane line according to the contour point position information of each lane line and the lane attributes of each lane to obtain each closed road section;
the status bar generating module is used for generating status bar information of each road section according to the geometric attributes of each road;
the road drawing module includes:
the data placement submodule is used for placing the position information of the contour points of all the lane lines according to the level of the lane sections;
the road drawing submodule is used for drawing the contour points of each adjacent lane according to lane sections according to the lane attributes of each road to obtain each closed lane section;
the device further comprises:
the device comprises a vertex selection module, a first vertex selection module and a second vertex selection module, wherein the vertex selection module is used for detecting a road notch existing in a current map, selecting a first vertex in a first side of the road notch and selecting a second vertex in a second side of the road notch; wherein the distance from the first vertex to the road edge is less than a first threshold, the distance from the second vertex to the road edge is less than a second threshold, and the first threshold and the second threshold are equal or different;
the candidate control point determining module is used for determining the position of an auxiliary control point according to the positions of the first vertex and the second vertex; connecting the first vertex and the auxiliary control point to obtain a first connecting line, connecting the second vertex and the auxiliary control point to obtain a second connecting line, determining a first middle point of the first connecting line and a second middle point of the second connecting line, and determining the position of a candidate control point according to the positions of the first vertex, the second vertex, the auxiliary control point, the first middle point and the second middle point; the candidate control point is positioned on a midpoint connecting line of the first midpoint and the second midpoint, and the length ratio of the first connecting line to the second connecting line is equal to the ratio of the first midpoint to the connecting line of the candidate control point and the ratio of the second midpoint to the connecting line of the candidate control point;
a target control point determining module, configured to determine positions of a first target control point and a second target control point corresponding to the first midpoint and the second midpoint, respectively, based on the positions of the candidate control point, the auxiliary control point, the first midpoint, and the second midpoint;
a road edge curve generating module, configured to generate a road edge curve according to the first vertex or the second vertex, the auxiliary control point, the first target control point, and the second target control point;
and the connecting line generating module is used for generating the connecting line corresponding to the road notch according to the road edge curve.
6. The apparatus of claim 5, wherein the candidate control point determining module comprises:
the connecting line generation submodule is used for connecting the first vertex and the second vertex to obtain a connecting line of the first vertex and the second vertex;
the preset distance determining submodule is used for constructing a central line of the connecting line and determining a preset distance;
and the auxiliary control point determining submodule is used for determining a point which faces the direction of the road edge on the midline and is away from the connecting line by the preset distance as an auxiliary control point.
CN202011328186.5A 2020-11-24 2020-11-24 Map drawing method and device for automatic driving simulation test Active CN112435573B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011328186.5A CN112435573B (en) 2020-11-24 2020-11-24 Map drawing method and device for automatic driving simulation test

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011328186.5A CN112435573B (en) 2020-11-24 2020-11-24 Map drawing method and device for automatic driving simulation test

Publications (2)

Publication Number Publication Date
CN112435573A CN112435573A (en) 2021-03-02
CN112435573B true CN112435573B (en) 2022-03-08

Family

ID=74692933

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011328186.5A Active CN112435573B (en) 2020-11-24 2020-11-24 Map drawing method and device for automatic driving simulation test

Country Status (1)

Country Link
CN (1) CN112435573B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113074744A (en) * 2021-03-18 2021-07-06 重庆数字城市科技有限公司 Method for generating topological connection line of map for intelligent network vehicle connection
CN113495562B (en) * 2021-06-07 2024-03-29 深圳市塞防科技有限公司 Simulation path generation method, device, equipment and computer storage medium
CN113602285B (en) * 2021-08-05 2022-08-26 北京赛目科技有限公司 Control method, device, equipment and medium for automatic driving of vehicle
CN114440929A (en) * 2022-01-28 2022-05-06 中国第一汽车股份有限公司 Test evaluation method and device for high-precision map, vehicle and medium
CN115797506B (en) * 2022-12-16 2023-11-17 江苏泽景汽车电子股份有限公司 Method, device, terminal equipment and storage medium for drawing lane line object

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102007035821A1 (en) * 2007-07-31 2009-02-05 Robert Bosch Gmbh Traffic route section representing method for e.g. motor vehicle navigation system, involves representing route section as Bezier curve from start point to end point, and representing determined control points as control points of curve
CN102157001A (en) * 2011-04-14 2011-08-17 中国测绘科学研究院 Method and system for drawing electronic map
CN102998684A (en) * 2012-11-21 2013-03-27 厦门雅迅网络股份有限公司 Terminal positioning track fitting method based on Bezier curve
CN105844013A (en) * 2016-03-23 2016-08-10 苏州数字地图信息科技股份有限公司 Method and system for generating road mark
CN106409129A (en) * 2016-11-29 2017-02-15 北京掌行通信息技术有限公司 Road condition drawing method and road condition drawing device
CN106646518A (en) * 2016-11-18 2017-05-10 北京创业公社征信服务有限公司 GPS trajectory data complementing method based on third-order Bezier curve and interpolation
CN108022273A (en) * 2016-10-28 2018-05-11 中国测绘科学研究院 A kind of figure number Detachable drafting method and system
US10380769B1 (en) * 2018-03-14 2019-08-13 Adobe Inc. Arrangement of drawing objects along arbitrary paths
CN110196056A (en) * 2018-03-29 2019-09-03 文远知行有限公司 For generating the method and navigation device that are used for the road-map of automatic driving vehicle navigation and decision
CN111426330A (en) * 2020-03-24 2020-07-17 江苏徐工工程机械研究院有限公司 Path generation method and device, unmanned transportation system and storage medium
CN111563412A (en) * 2020-03-31 2020-08-21 武汉大学 Rapid lane line detection method based on parameter space voting and Bessel fitting
CN111696170A (en) * 2020-06-05 2020-09-22 百度在线网络技术(北京)有限公司 Map drawing method, map drawing device, map drawing equipment and map drawing medium

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102007035821A1 (en) * 2007-07-31 2009-02-05 Robert Bosch Gmbh Traffic route section representing method for e.g. motor vehicle navigation system, involves representing route section as Bezier curve from start point to end point, and representing determined control points as control points of curve
CN102157001A (en) * 2011-04-14 2011-08-17 中国测绘科学研究院 Method and system for drawing electronic map
CN102998684A (en) * 2012-11-21 2013-03-27 厦门雅迅网络股份有限公司 Terminal positioning track fitting method based on Bezier curve
CN105844013A (en) * 2016-03-23 2016-08-10 苏州数字地图信息科技股份有限公司 Method and system for generating road mark
CN108022273A (en) * 2016-10-28 2018-05-11 中国测绘科学研究院 A kind of figure number Detachable drafting method and system
CN106646518A (en) * 2016-11-18 2017-05-10 北京创业公社征信服务有限公司 GPS trajectory data complementing method based on third-order Bezier curve and interpolation
CN106409129A (en) * 2016-11-29 2017-02-15 北京掌行通信息技术有限公司 Road condition drawing method and road condition drawing device
US10380769B1 (en) * 2018-03-14 2019-08-13 Adobe Inc. Arrangement of drawing objects along arbitrary paths
CN110196056A (en) * 2018-03-29 2019-09-03 文远知行有限公司 For generating the method and navigation device that are used for the road-map of automatic driving vehicle navigation and decision
CN111426330A (en) * 2020-03-24 2020-07-17 江苏徐工工程机械研究院有限公司 Path generation method and device, unmanned transportation system and storage medium
CN111563412A (en) * 2020-03-31 2020-08-21 武汉大学 Rapid lane line detection method based on parameter space voting and Bessel fitting
CN111696170A (en) * 2020-06-05 2020-09-22 百度在线网络技术(北京)有限公司 Map drawing method, map drawing device, map drawing equipment and map drawing medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
周知红.面向无人驾驶的车道级道路电子地图制作.《测绘与空间地理信息》.2018, *
面向无人驾驶的车道级道路电子地图制作;周知红;《测绘与空间地理信息》;20180228;第164-170页 *

Also Published As

Publication number Publication date
CN112435573A (en) 2021-03-02

Similar Documents

Publication Publication Date Title
CN112435573B (en) Map drawing method and device for automatic driving simulation test
CN112562484B (en) Road consistency processing method and device
CN111238504B (en) Road segment modeling data generation method and device of road map and related system
US6449557B2 (en) Device and method for changing map information
CN112154446B (en) Stereo lane line determining method and device and electronic equipment
Gikas et al. A novel geodetic engineering method for accurate and automated road/railway centerline geometry extraction based on the bearing diagram and fractal behavior
CN111238502B (en) Road map generation method, device and related system
JP7233575B2 (en) MAP GENERATION SYSTEM, MAP GENERATION METHOD AND MAP GENERATION PROGRAM
CN105205841A (en) Map generation method and system of geographic information system
CN111238498B (en) Road map generation method, device and related system for lane-level display
CN109937342B (en) Method, device and system for locating moving object
JP6716480B2 (en) Road network change detecting device, road network change detecting method, computer program, and recording medium recording computer program
JP2019100924A (en) Vehicle trajectory correction device
CN111238503B (en) Map generation method, device and related system for road segments
CN111238500B (en) Map generation method, device and system for road segments of road map area
US11733174B2 (en) Information processing apparatus, information processing method, and storage medium
CN109511165B (en) Indoor positioning method based on iBeacon Bluetooth module, terminal equipment and storage medium
JP4850161B2 (en) Road map data creation device
CN111238499B (en) Road map generation method and device and related system
CN114663545A (en) Map generation method, map generation system, electronic device, and storage medium
CN112949358A (en) Road description file generation method and equipment
JP6745112B2 (en) Road surface property evaluation method and road surface property evaluation device
JPH0786349A (en) Inspection device using electron beam
WO2012101915A1 (en) Tunnel entrance specification device and method thereof, computer program for specifiying tunnel entrance, and recording medium on which computer program is recorded
CN111238505B (en) Road line segment drawing method, device and related system of road map

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CP01 Change in the name or title of a patent holder

Address after: 100070 401, 4th floor, 66 Zizhuyuan Road, Haidian District, Beijing

Patentee after: Beijing Saimu Technology Co.,Ltd.

Patentee after: Zhejiang saimu Technology Co.,Ltd.

Address before: 100070 401, 4th floor, 66 Zizhuyuan Road, Haidian District, Beijing

Patentee before: Beijing saimu Technology Co.,Ltd.

Patentee before: Zhejiang saimu Technology Co.,Ltd.

CP01 Change in the name or title of a patent holder