An obstacle position determination method and system, an electronic device, and a storage medium

Abstract

The application provides an obstacle position determination method and system, electronic equipment and a storage medium. The method comprises the following steps: extracting lane line coordinate points; constructing an S-axis sequence of a Frenet road coordinate system based on a road center line; projecting left and right boundary lines of the road to the Frenet coordinate system to construct a road boundary constraint condition of the S-axis sequence; sequentially projecting obstacle coordinate points to the Frenet coordinate system; obtaining road boundary constraints of the obstacle at a Frenet longitudinal coordinate through linear interpolation; determining whether the Frenet transverse coordinate of the obstacle is within the road boundary constraint range to determine the road where the obstacle is located; projecting all lane lines of the road where the obstacle is located to the Frenet coordinate system to construct a lane line constraint condition; obtaining lane line constraints of the obstacle at the Frenet longitudinal coordinate through linear interpolation; determining whether the Frenet transverse coordinate of the obstacle is within the lane line constraint range to determine the lane where the obstacle is located. The scheme does not depend on lane line perception, is not limited by the scene, and has better applicability and stability.

Description

Technical Field

[0001] The present invention belongs to the field of autonomous driving, and in particular relates to a method, system, electronic device and storage medium for determining the position of an obstacle. Background Art

[0002] Perceiving obstacles ahead of the vehicle is a key function of autonomous driving systems. After identifying an obstacle through perception sensors, the system must quickly determine the road and lane the obstacle is located in based on its location and plan a path to avoid it. The obstacle location information provided by perception sensors is typically given in the form of latitude and longitude geodetic coordinates, Cartesian coordinates, or relative coordinates relative to the vehicle. None of these coordinate formats can intuitively determine the obstacle's location on the map, including its lane. Therefore, it is necessary to combine sensor data with map data to determine the specific road and lane the obstacle is located.

[0003] At present, the more common method is to combine the lane line equation provided by perception and the distance of the obstacle relative to the vehicle for judgment. For example, the Chinese patent "A method for screening key obstacles on structured roads" (application number 202011220296.X) proposes a method for determining the lane distribution of obstacles in the vehicle body coordinate system. The four lane line equations in front of the vehicle are obtained through perception, and the longitudinal coordinates of the obstacle relative to the vehicle are substituted into the equations of each lane line. The lateral displacement of each lane line at the longitudinal coordinate is calculated, and then compared with the actual lateral displacement of the obstacle to determine which lane the obstacle is in. For example, the Chinese patent "Method, device, electronic device and storage medium for determining the lane where the obstacle is located" (patent application number 201911272583.2) projects the map data of the front range to be measured into the image data, and finds the two lane lines with the smallest distance from the obstacle bounding box in the image domain, thereby obtaining the lane where the obstacle is located.

[0004] Both of the above methods require the use of lane line equations or image information provided by perception. They will encounter difficulties when the lane lines in the scene are blurred or invisible, and lane line recognition will be unreliable in curved scenes. For obstacles that are not visible in the field of view, such as the obstacle information at a long distance ahead broadcast by V2X (Vehicle-to-Everyting) communication, it is impossible to process them in advance for route avoidance planning. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a method, system, electronic device, and storage medium for determining an obstacle position, which are used to solve the problem that existing methods for determining an obstacle position are limited in applicable scenarios.

[0006] In a first aspect of an embodiment of the present invention, a method for determining an obstacle position is provided, comprising:

[0007] Extract high-precision map lane line coordinate points within a certain range around the obstacle;

[0008] Based on the centerline of each road, construct the corresponding Frenet road coordinate system S-axis sequence;

[0009] Project the left and right lines of each road into the Frenet coordinate system to construct the road boundary constraints of the S-axis sequence;

[0010] Project the obstacle coordinate points to the Frenet coordinate system of each road in turn to obtain the Frenet coordinates of the obstacle on each road;

[0011] Obtain the road boundary constraint corresponding to the obstacle at the Frenet ordinate through linear interpolation, determine whether the obstacle's Frenet abscissa is within the road boundary constraint range, and determine the road where the obstacle is located;

[0012] If the current road is determined to be the road where the obstacle is located, all lane lines of the current road are projected into the Frenet coordinate system to construct the lane line constraint conditions of the S-axis sequence;

[0013] The lane line constraint corresponding to the obstacle at the Frenet ordinate is obtained through linear interpolation. It is determined whether the obstacle's Frenet abscissa is within the constraint range of the adjacent lane line. If the constraint range of the adjacent lane line is satisfied, the lane where the obstacle is located is obtained.

[0014] In a second aspect of an embodiment of the present invention, a system for determining an obstacle position is provided, comprising:

[0015] Coordinate point extraction module, used to extract high-precision map lane line coordinate points within a certain range around the obstacle;

[0016] Point set sequence construction module, used to construct the corresponding Frenet road coordinate system S-axis sequence based on the center line of each road;

[0017] Boundary constraint construction module, used to project the left and right lines of each road into the Frenet coordinate system to construct the road boundary constraint conditions of the S-axis sequence;

[0018] The first projection module is used to project the obstacle coordinate points to the Frenet coordinate system of each road in sequence to obtain the Frenet coordinates of the obstacle on each road;

[0019] The road judgment module is used to obtain the road boundary constraint corresponding to the obstacle at the Frenet vertical coordinate through linear interpolation, determine whether the obstacle's Frenet horizontal coordinate is within the road boundary constraint range, and determine the road where the obstacle is located;

[0020] The second projection module is used to project all lane lines of the current road into the Frenet coordinate system if the current road is determined to be a road where an obstacle is located, and construct lane line constraint conditions of the S-axis sequence;

[0021] The lane determination module is used to obtain the lane line constraint corresponding to the obstacle at the Frenet vertical coordinate through linear interpolation, and determine whether the obstacle's Frenet horizontal coordinate is within the constraint range of the adjacent lane line. If the constraint range of the adjacent lane line is satisfied, the lane where the obstacle is located is determined.

[0022] In a third aspect of an embodiment of the present invention, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the steps of the method described in the first aspect of the embodiment of the present invention when executing the computer program.

[0023] In a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method provided in the first aspect of the embodiment of the present invention are implemented.

[0024] In this embodiment of the present invention, the boundary constraints of the Frenet coordinate system are obtained based on the projection of boundary points onto the road center. The obstacle's location is determined by separately determining the road and lane where the obstacle is located. This allows for precise obstacle location determination without relying on lane line perception or constructing lane line equations. Its applicability is not limited to straight or curved roads; it can be used even when the obstacle is out of view, significantly improving its adaptability to diverse scenarios and offering greater applicability and stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0026] Figure 1 A schematic flow chart of a method for determining the position of an obstacle provided by one embodiment of the present invention;

[0027] Figure 2A corresponding relationship between plane coordinates and Frenet road coordinates provided by an embodiment of the present application is shown in the schematic diagram;

[0028] Figure 3 A Frenet coordinate system road boundary constraint schematic diagram provided by an embodiment of the present application is shown in the schematic diagram;

[0029] Figure 4 An obstacle-located-road determination schematic diagram provided by an embodiment of the present application is shown in the schematic diagram;

[0030] Figure 5 An obstacle-located-lane determination schematic diagram provided by an embodiment of the present application is shown in the schematic diagram;

[0031] Figure 6 A structure schematic diagram of a system for obstacle position determination provided by an embodiment of the present application is shown in the schematic diagram;

[0032] Figure 7 A structure schematic diagram of an electronic device provided by an embodiment of the present application is shown in the schematic diagram. DETAILED DESCRIPTION

[0033] To make the purposes, features and advantages of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the embodiments described below are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0034] It should be understood that the terms “comprise” and other similar terms in the specification or claims of the present application and the above-described drawings mean covering non-exclusive inclusion, such as a process, method or system, device comprising a series of steps or units, which is not limited to the listed steps or units. In addition, “first” and “second” are used to distinguish different objects, and are not used to describe a specific order.

[0035] Please refer to Figure 1 A flow schematic diagram of an obstacle position determination method provided by an embodiment of the present application is shown in the schematic diagram, which comprises:

[0036] S101, extracting high-precision map lane line coordinate points within a certain range around the obstacle;

[0037] According to the obstacle coordinates (latitude and longitude coordinates or plane coordinates), high-precision map road lane line coordinate points within a certain range around the obstacle are extracted, each road contains a road center line, two road boundary lines and a plurality of lane lines, wherein the extraction range is determined according to the demand of automatic driving path planning, and the typical value is 50-200m.

[0038] S102. Based on the centerline of each road, construct the corresponding Frenet road coordinate system S-axis sequence;

[0039] According to the coordinate sequence of the center line coordinate points of each road {x base ,y base}, calculate its accumulated mileage {s base}, thus constructing the axis point set sequence {x base ,y base ,s base}.

[0040] Specifically, the plane point coordinates are projected vertically onto the road centerline, and the S coordinate and L (L stands for Lateral, representing the lateral distance) coordinate of the Frenet coordinate system corresponding to the plane point are calculated respectively:

[0041]

[0042]

[0043] Among them, the two endpoints of the road centerline segment where the projection point is located are (x base_i ,y base_i )、(x base_i+1 ,y base_i+1 ), the projection point coordinates are (x prj ,y prj ), the plane point is (x, y), sign is the sign of the L coordinate, s is the ordinate of the Frenet coordinate point, and l is the abscissa of the Frenet coordinate point.

[0044] like Figure 2 As shown in the figure, the correspondence between plane coordinates and the Frenet road coordinate system is shown. The road centerline 201 corresponds to the Frenet coordinate axis S axis 211, and the road centerline starting point 202 corresponds to the Frenet coordinate origin 212. The method for converting any plane point 203 (x, y) to a Frenet road coordinate point 213 (s, l) is to project the point coordinate perpendicularly to the road centerline. The two endpoints of the road centerline segment where the projection point is located are the left point 204 (x, y) and the left point 205 (x, y). base_i ,y base_i ) and right point 205(x base_i+1 ,y base_i+1 ), and their corresponding Frenet coordinate points in the S-axis sequence are point 214 (s base_i ,0) and point 215(s base_i+1 ,0), the plane projection point is 206(x prj ,y prj), and the corresponding Frenet projection point is 216(s, 0). Wherein, the calculation method of s value is: s is the longitudinal coordinate of the Frenet coordinate point 213, the absolute value of the transverse coordinate is the projection distance, and the transverse coordinate direction is left positive and right negative along the road center line direction. The specific calculation method of l value is:

[0045]

[0046] S103, project the left and right lines of each road to the Frenet coordinate system, and construct the road boundary constraint condition of S-axis sequence;

[0047] Specifically, the road left line coordinate point sequence and the right line point sequence of each road are projected and converted to the road center line to obtain the point sequence in the Frenet coordinate system;

[0048] The accumulated mileage s of the road center line point set is substituted into the point sequence in the two Frenet coordinate systems to perform linear interpolation to obtain the corresponding left boundary constraint and right boundary constraint at each s base point, and the S-axis point sequence containing the road boundary constraint is constructed. base

[0049] As shown in Figure 3 , the road center line coordinate point sequence 301{x base ,y base} corresponds to the point sequence 311{s base ,0} on the S-axis of the Frenet coordinate. The road left line coordinate point sequence 302{x side_left ,y side_left} and the road right line point sequence 303{x side_right ,y side_right} of each road are projected and converted to the road center line to obtain the point sequence 312{s side_left ,l side_left} and 313{s side_right ,l side_right} in the Frenet coordinate system respectively. The{s base} in the center line point set is substituted into the above two point sets to perform linear interpolation to obtain the corresponding left boundary constraint 314{s base, l base_leftside} and right boundary constraint 315{s base, l base_rightside} at each s base point, so as to obtain the S-axis point sequence{x base ,y base ,s base, l base_leftside, l base_rightside} containing the road boundary constraint.​

[0050] S104. Project the obstacle coordinate points sequentially to the Frenet coordinate system of each road to obtain the Frenet coordinates of the obstacle on each road;

[0051] The obstacle coordinates are converted into Frenet coordinates. Specifically, the obstacle plane coordinates (x obs ,y obs ) points are projected onto the Frenet coordinate system of each road in turn to obtain their Frenet coordinates (s obs ,l obs ).

[0052] S105. Obtain the road boundary constraint corresponding to the obstacle at the Frenet ordinate by linear interpolation, determine whether the obstacle's Frenet abscissa is within the road boundary constraint range, and determine the road where the obstacle is located;

[0053] If the obstacle Frenet coordinates are (s obs ,l obs ), obtain the obstacle Frenet ordinate s by linear interpolation obs The corresponding road boundary constraint is used to determine the horizontal coordinate of the obstacle l obs Whether it is within the road boundary constraint range, the road that meets this condition is the road where the obstacle is located.

[0054] like Figure 4 As shown, 401 and 402 are the road left boundary constraints {s base, l base_leftside} and the road right boundary constraint {s base, l base_rightside}, the vertical coordinate s of the obstacle Frenet coordinate point 403 obs , by respectively {s base, l base_leftside} and {s base, l base_rightside} perform linear interpolation to obtain s obs The corresponding road boundary left constraint point 404 (s obs ,l obs_leftside ) and right boundary constraint point 405(s obs ,l obs_rightside ), determine the horizontal coordinate of the obstacle l obs Whether the road boundary constraint conditions are met obs_leftside ≤l obs ≤l obs_rightside , the road that meets this condition is the road where the obstacle is located;

[0055] S106. If the current road is determined to be a road where an obstacle is located, all lane lines of the current road are projected into the Frenet coordinate system to construct lane line constraint conditions of the S-axis sequence;

[0056] After obtaining the road where the obstacle is located, all lane lines of the road are projected into the Frenet coordinate system to construct the constraints corresponding to the lane lines.

[0057] For all lane line coordinate sequences {x lane ,y lane}, converted to the Frenet coordinate system, each lane line i corresponds to a boundary constraint sequence {l base_lane_i}, and finally obtain the S-axis point sequence {x base ,y base ,s base, l base_lane_1, l base_lane_2, … , l base_lane_n}, n is the total number of lane lines;

[0058] S107. Obtain the lane line constraint corresponding to the obstacle at the Frenet ordinate through linear interpolation, and determine whether the Frenet abscissa of the obstacle is within the constraint range of the adjacent lane line. If the constraint range of the adjacent lane line is satisfied, the lane where the obstacle is located is determined.

[0059] The lane where the obstacle is located can be determined based on the lane line constraint range made by the obstacle's Frenet horizontal coordinate.

[0060] like Figure 5 As shown in the figure, 501, 502 and 503 are lane line 1 constraints {s base, l base_lane_1}、Lane 2 constraint {s base, l base_lane_2}、Lane line n constraint {s base, l base_lane_n}. The vertical coordinate s of the obstacle Frenet coordinate point obs , by respectively {s base, l base_lane_1}、{s base, l base_lane_2}…{s base, l base_lane_n} perform linear interpolation to obtain s obs All lane boundary constraint points corresponding to the lane line 1 boundary constraint point (s obs, l obs_lane_1 ), lane line 2 boundary constraint point (s obs, l obs_lane_2), lane line n boundary constraint point (s obs, l obs_lane_2 ), if the boundary constraint points corresponding to the lane line i and the lane line i+1 satisfy: obs_lane_i ≤l obs ≤l obs_lane_i+1 , the lane corresponding to the lane line i and the lane line i+1 is the lane where the obstacle is located, thereby completing the obstacle lane distribution determination.

[0061] In the embodiment, the high-precision map lane line information in the automatic driving system is used, the lane line data is not relied on, and the lane line equation does not need to be constructed, the applicable scene is not limited to a straight road or a curved road, the obstacle can be determined even if the obstacle is not in the field of view, the adaptability to different scenes is greatly enhanced, and better applicability and stability are achieved.

[0062] It should be understood that the sequence numbers of the steps in the above embodiments do not mean the order of execution, the execution order of the processes should be determined according to the functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0063] Figure 6 A structural schematic diagram of a system for obstacle position determination provided by the embodiment of the present application is shown in the figure, and the system comprises:

[0064] The coordinate point extraction module 610 is configured to extract high-precision map lane line coordinate points within a certain range around the obstacle.

[0065] The point set sequence construction module 620 is configured to construct a corresponding Frenet road coordinate system S axis sequence based on the center line of each road.

[0066] Specifically, the planar point coordinates are vertically projected on the road center line, and the Frenet coordinate system S coordinates and L coordinates corresponding to the planar point are calculated respectively:

[0067]

[0068]

[0069] wherein the two end points of the road center line segment where the projection point is located are (x base_i , y base_i ) and (x base_i+1 , y base_i+1 ), the projection point coordinates are (x prj , y prj ), the planar point is (x, y), sign is the sign of the L coordinate, s is the longitudinal coordinate of the Frenet coordinate point, and l is the horizontal coordinate of the Frenet coordinate point.

[0070] A boundary constraint construction module 630 is used to project the left and right sides of each road into the Frenet coordinate system to construct the road boundary constraint conditions of the S-axis sequence;

[0071] The boundary constraint building module 630 includes:

[0072] A projection conversion unit is used to project the left sideline coordinate point sequence and the right sideline point sequence of each road onto the road centerline to obtain a point sequence in the Frenet coordinate system;

[0073] Linear interpolation unit, the accumulated mileage s of the road centerline points base Substitute the set into the point sequence under two Frenet coordinate systems for linear interpolation to obtain each s base The left boundary constraint and the right boundary constraint corresponding to the point are constructed to obtain the S-axis point sequence containing the road boundary constraint.

[0074] A first projection module 640 is used to project the coordinate points of the obstacle onto the Frenet coordinate system of each road in sequence to obtain the Frenet coordinates of the obstacle on each road;

[0075] A road determination module 650 is configured to obtain the road boundary constraint corresponding to the obstacle at the Frenet ordinate through linear interpolation and determine whether the obstacle's Frenet abscissa is within the road boundary constraint range;

[0076] Specifically, the vertical coordinates of the obstacle's Frenet coordinate point are linearly interpolated with the left boundary constraint and the right boundary constraint to obtain the boundary constraint point; and it is determined whether the horizontal coordinate of the obstacle is within the range of the two boundary constraint points.

[0077] The second projection module 660 is configured to project all lane lines of the current road into the Frenet coordinate system to construct lane line constraint conditions of the S-axis sequence if the current road is determined to be a road where obstacles are located;

[0078] Lane determination module 670 is used to obtain the lane line constraint corresponding to the obstacle at the Frenet vertical coordinate through linear interpolation, and determine whether the obstacle's Frenet horizontal coordinate is within the adjacent lane line constraint range. If the adjacent lane line constraint range is satisfied, the lane where the obstacle is located is determined.

[0079] Specifically, the lane line constraint is linearly interpolated based on the vertical coordinates of the obstacle Frenet coordinate points to obtain the lane line boundary constraint points, and it is determined whether the horizontal coordinates of the obstacle meet the range of adjacent boundary constraint points.

[0080] Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0081] Figure 7 FIG. 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device is used to determine the location of obstacles on the road. Figure 7 As shown, the electronic device 7 of this embodiment includes: a memory 710, a processor 720 and a system bus 730, wherein the memory 710 includes an executable program 7101 stored thereon. It can be understood by those skilled in the art that Figure 7 The electronic device structure shown in the figure does not constitute a limitation to the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0082] The following combination Figure 7 A detailed introduction to the various components of electronic equipment:

[0083] The memory 710 can be used to store software programs and modules. The processor 720 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 710. The memory 710 may mainly include a program storage area and a data storage area. The program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device (such as cached data), etc. In addition, the memory 710 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0084] Memory 710 contains an executable program 7101 for a sign extraction method. This executable program 7101 can be divided into one or more modules / units. These modules / units are stored in memory 710 and executed by processor 720 to implement obstacle location determination, etc. These modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program 7101 in the electronic device 7. For example, the computer program 7101 can be divided into a data acquisition module, a distance calculation module, a stop line acquisition module, a determination module, etc.

[0085] The processor 720 is the control center of the electronic device, connecting the various parts of the entire electronic device using various interfaces and lines. By running or executing software programs and / or modules stored in the memory 710 and accessing data stored in the memory 710, it performs various functions of the electronic device and processes data, thereby monitoring the overall status of the electronic device. Optionally, the processor 720 may include one or more processing units; preferably, the processor 720 may integrate an application processor and a modem processor, wherein the application processor primarily processes the operating system, application programs, etc., and the modem processor primarily handles wireless communications. It is understood that the modem processor described above may not be integrated into the processor 720.

[0086] The system bus 730 connects the various functional components within the computer and can transmit data, address information, and control information. It can be a PCI bus, ISA bus, VESA bus, or other bus types. Instructions from the processor 720 are transmitted to the memory 710 via the bus, and the memory 710 feeds data back to the processor 720. The system bus 730 is responsible for the exchange of data and instructions between the processor 720 and the memory 710. Of course, the system bus 730 can also connect to other devices, such as network interfaces and display devices.

[0087] In an embodiment of the present invention, the executable program executed by the processing 720 included in the electronic device includes:

[0088] Extract high-precision map lane line coordinate points within a certain range around the obstacle;

[0089] Based on the centerline of each road, construct the corresponding Frenet road coordinate system S-axis sequence;

[0090] Project the left and right lines of each road into the Frenet coordinate system to construct the road boundary constraints of the S-axis sequence;

[0091] Project the obstacle coordinate points to the Frenet coordinate system of each road in turn to obtain the Frenet coordinates of the obstacle on each road;

[0092] Obtain the road boundary constraint corresponding to the obstacle at the Frenet ordinate through linear interpolation, determine whether the obstacle's Frenet abscissa is within the road boundary constraint range, and determine the road where the obstacle is located;

[0093] If the current road is determined to be the road where the obstacle is located, all lane lines of the current road are projected into the Frenet coordinate system to construct the lane line constraint conditions of the S-axis sequence;

[0094] The lane line constraint corresponding to the obstacle at the Frenet ordinate is obtained through linear interpolation. It is determined whether the obstacle's Frenet abscissa is within the constraint range of the adjacent lane line. If the constraint range of the adjacent lane line is satisfied, the lane where the obstacle is located is obtained.

[0095] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0096] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0097] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining the position of an obstacle, characterized in that: include: Extract high-precision map lane line coordinate points within a certain range around the obstacle; Based on the centerline of each road, construct the corresponding Frenet road coordinate system S-axis sequence; Project the left and right lines of each road into the Frenet coordinate system to construct the road boundary constraints of the S-axis sequence; Project the obstacle coordinate points to the Frenet coordinate system of each road in turn to obtain the Frenet coordinates of the obstacle on each road; Obtain the road boundary constraint corresponding to the obstacle at the Frenet ordinate through linear interpolation, determine whether the obstacle's Frenet abscissa is within the road boundary constraint range, and determine the road where the obstacle is located; Among them, the vertical coordinates of the obstacle Frenet coordinate point are linearly interpolated for the left boundary constraint and the right boundary constraint to obtain the boundary constraint point; Determine whether the horizontal coordinate of the obstacle is within the range of the two boundary constraint points; If the current road is determined to be the road where the obstacle is located, all lane lines of the current road are projected into the Frenet coordinate system to construct the lane line constraint conditions of the S-axis sequence; The lane line constraint corresponding to the obstacle at the Frenet ordinate is obtained through linear interpolation. It is determined whether the obstacle's Frenet abscissa is within the constraint range of the adjacent lane line. If the constraint range of the adjacent lane line is satisfied, the lane where the obstacle is located is obtained.

2. The method according to claim 1, characterized in that The construction of the corresponding Frenet road coordinate system S-axis sequence based on the center line of each road includes: Project the plane point coordinates perpendicularly to the road centerline, and calculate the S and L coordinates of the Frenet coordinate system corresponding to the plane point: Among them, the two endpoints of the road centerline segment where the projection point is located are (x base_i ,y base_i )、(x base_i+1 ,y base_i+1 ), s base_i Represents the endpoint (x base_i ,y base_i ) is the vertical coordinate of the Frenet coordinate point corresponding to the S-axis sequence, and the projection point coordinate is (x prj ,y prj ), the plane point is (x, y), sign is the sign of the L coordinate, s is the ordinate of the Frenet coordinate point, and l is the abscissa of the Frenet coordinate point.

3. The method according to claim 1, characterized in that The road boundary constraint conditions for projecting the left and right lines of each road into the Frenet coordinate system to construct the S-axis sequence include: Project the left sideline coordinate point sequence and the right sideline point sequence of each road onto the road centerline to obtain a point sequence in the Frenet coordinate system; The accumulated mileage s of the road centerline points base Substitute the set into the point sequence under two Frenet coordinate systems for linear interpolation to obtain each s base The left boundary constraint and the right boundary constraint corresponding to the point are constructed to obtain the S-axis point sequence containing the road boundary constraint.

4. The method according to claim 1, wherein The lane line constraint corresponding to the obstacle at the Frenet ordinate is obtained by linear interpolation, and whether the obstacle's Frenet abscissa is within the adjacent lane line constraint range is determined. If the adjacent lane line constraint range is satisfied, the lane where the obstacle is located is obtained, including: Based on the vertical coordinates of the obstacle's Frenet coordinate points, the lane line constraint is linearly interpolated to obtain the lane line boundary constraint point, and then determine whether the obstacle's horizontal coordinates meet the range of adjacent boundary constraint points.

5. A system for determining the position of an obstacle, characterized in that: include: Coordinate point extraction module, used to extract high-precision map lane line coordinate points within a certain range around the obstacle; Point set sequence construction module, used to construct the corresponding Frenet road coordinate system S-axis sequence based on the center line of each road; Boundary constraint construction module, used to project the left and right lines of each road into the Frenet coordinate system to construct the road boundary constraint conditions of the S-axis sequence; The first projection module is used to project the obstacle coordinate points to the Frenet coordinate system of each road in sequence to obtain the Frenet coordinates of the obstacle on each road; The road judgment module is used to obtain the road boundary constraint corresponding to the obstacle at the Frenet vertical coordinate through linear interpolation, determine whether the obstacle's Frenet horizontal coordinate is within the road boundary constraint range, and determine the road where the obstacle is located; Among them, the vertical coordinates of the obstacle Frenet coordinate point are linearly interpolated for the left boundary constraint and the right boundary constraint to obtain the boundary constraint point; Determine whether the horizontal coordinate of the obstacle is within the range of the two boundary constraint points; The second projection module is used to project all lane lines of the current road into the Frenet coordinate system if the current road is determined to be a road where an obstacle is located, and construct lane line constraint conditions of the S-axis sequence; The lane determination module is used to obtain the lane line constraint corresponding to the obstacle at the Frenet vertical coordinate through linear interpolation, and determine whether the obstacle's Frenet horizontal coordinate is within the constraint range of the adjacent lane line. If the constraint range of the adjacent lane line is satisfied, the lane where the obstacle is located is determined.

6. The system according to claim 5, characterized in that The construction of the corresponding Frenet road coordinate system S-axis sequence based on the center line of each road includes: Project the plane point coordinates perpendicularly to the road centerline, and calculate the S and L coordinates of the Frenet coordinate system corresponding to the plane point: Among them, the two endpoints of the road centerline segment where the projection point is located are (x base_i ,y base_i )、(x base_i+1 ,y base_i+1 ), s base_i Represents the endpoint (x base_i ,y base_i ) is the vertical coordinate of the Frenet coordinate point corresponding to the S-axis sequence, and the projection point coordinate is (x prj ,y prj ), the plane point is (x, y), sign is the sign of the L coordinate, s is the ordinate of the Frenet coordinate point, and l is the abscissa of the Frenet coordinate point.

7. The system according to claim 5, characterized in that The boundary constraint building module includes: A projection conversion unit is used to project the left sideline coordinate point sequence and the right sideline point sequence of each road onto the road centerline to obtain a point sequence in the Frenet coordinate system; Linear interpolation unit, the accumulated mileage s of the road centerline points base Substitute the set into the point sequence under two Frenet coordinate systems for linear interpolation to obtain each s base The left boundary constraint and the right boundary constraint corresponding to the point are constructed to obtain the S-axis point sequence containing the road boundary constraint.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the obstacle position determination method according to any one of claims 1 to 4 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed, the steps of the obstacle position determination method according to any one of claims 1 to 4 are implemented.

Images