A road recognition method and apparatus

Abstract

The application discloses a road recognition method and device, and belongs to the technical field of automatic driving. A specific embodiment of the method comprises the following steps: acquiring road point cloud data of a front road by using a vehicle-mounted radar of a vehicle; recognizing static objects indicating two-side road boundaries of the front road according to the road point cloud data; and calculating a road width of the front road according to point cloud data corresponding to the static objects; further, in the case that the road width of the front road is determined to increase and then returns to the road width before the increase after a set distance, it is determined that the front road has a branch road section, and prompt information indicating the branch road section is sent to the vehicle; the embodiment of the application improves the accuracy and reliability of recognizing the branch road section in the road.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a road recognition method and apparatus. Background Technology

[0002] During the autonomous driving process, it is necessary to identify the road conditions ahead (such as whether there are forks in the road) in real time so as to adjust the autonomous driving behavior of the vehicle according to the road conditions ahead.

[0003] In existing methods, the presence of road forks is usually determined by map data or by using road images captured by camera equipment. However, existing methods for determining road forks by map data suffer from low real-time performance and low accuracy due to their heavy reliance on map data. Furthermore, methods using road images suffer from low accuracy due to limitations imposed by external environments (such as poor visibility or nighttime). Summary of the Invention

[0004] In view of this, the present invention provides a road recognition method and apparatus, which can acquire road point cloud data of the road ahead using the vehicle's onboard radar; identify static objects indicating the road boundaries on both sides of the road ahead based on the road point cloud data; calculate the road width of the road ahead based on the point cloud data corresponding to the static objects; further, if it is determined that the road width of the road ahead has increased and then returns to its original width after a set distance, it determines that there is a fork in the road ahead and sends a prompt message indicating the fork to the vehicle; the embodiments of the present invention improve the accuracy and reliability of identifying fork in the road, overcome the accuracy and angle problems of existing methods for determining forks using map data, and overcome the low accuracy problem of existing methods for identifying forks using road images.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0006] In a first aspect, the present invention provides a road recognition method, comprising: acquiring road point cloud data of the road ahead using a vehicle's onboard radar; identifying static objects indicating the road boundaries on both sides of the road ahead based on the road point cloud data; calculating the road width of the road ahead based on the point cloud data corresponding to the static objects; determining that there is a fork in the road ahead when it is determined that the road width of the road ahead has increased and then returns to the road width before the increase after a set distance; and sending a prompt message indicating the fork in the road to the vehicle.

[0007] Optionally, the road width of the road ahead is calculated based on the point cloud data corresponding to the static object, including: calculating the road width of the road ahead based on the position of the static object contained in the point cloud data of the static object on both sides of the road ahead.

[0008] Optionally, the road recognition method further includes: constructing visualized road width data for multiple road widths based on multiple road widths ahead; to use the visualized road width data to show whether there are branching sections on the road ahead.

[0009] Optionally, based on multiple road widths of the road ahead, visualized road width data for multiple road widths is constructed, including: in a preset two-dimensional coordinate system, fitting the width data of the road ahead to generate a visualized width data curve, wherein the horizontal axis of the two-dimensional coordinate system is parallel to the vehicle's driving direction, and the vertical axis represents the road width.

[0010] Optionally, the road recognition method further includes: determining the changes in road width by visualizing the curve shape of the width data curve, so as to determine whether there is a fork in the road ahead based on the changes; wherein the changes include whether the road width increases, the magnitude of the increase within a set distance, and whether the road width returns to the road width before the increase after exceeding the set distance.

[0011] Optionally, based on the multiple road widths of the road ahead, visualized road width data for the multiple road widths is constructed, including: constructing visualized point cloud data of the road boundaries of the road ahead based on the point cloud data corresponding to the identified static objects indicating the road boundaries on both sides of the road ahead; and using the visualized point cloud data to visualize and display the information of the branching sections of the road ahead.

[0012] Optionally, determining the road width variation by visualizing the curve shape of the width data curve further includes: determining the starting position of the fork in the road segment based on the curve shape of the visualized width data curve; sending a prompt message indicating the fork in the road segment to the vehicle, including: sending information indicating the starting position of the fork in the road segment to the vehicle.

[0013] In a second aspect, embodiments of the present invention provide a road recognition device, comprising:

[0014] The width calculation module is used to acquire road point cloud data of the road ahead using the vehicle's onboard radar; based on the point cloud data, it identifies static objects that indicate the road boundaries on both sides of the road ahead; and based on the point cloud data corresponding to the static objects, it calculates the road width of the road ahead.

[0015] The road condition determination module is used to determine the presence of a fork in the road ahead when the road width ahead increases and then returns to its original width after a set distance.

[0016] The information sending module is used to send prompts indicating road forks to vehicles.

[0017] Optionally, the road recognition device is used to calculate the road width of the road ahead based on the point cloud data corresponding to the static objects, including: calculating the road width of the road ahead based on the position of the static objects contained in the point cloud data of the static objects on both sides of the road ahead.

[0018] Optionally, the road recognition device is further configured to construct visualized road width data for multiple road widths based on the multiple road widths of the road ahead; so as to use the visualized road width data to show whether there are branching sections of the road ahead.

[0019] Optionally, the road recognition device is used to construct visualized road width data for multiple road widths based on multiple road widths ahead, including: in a preset two-dimensional coordinate system, fitting the width data of the road ahead to generate a visualized width data curve, wherein the horizontal axis of the two-dimensional coordinate system is parallel to the vehicle's driving direction, and the vertical axis represents the road width.

[0020] Optionally, the road recognition device is further configured to determine the changes in road width by visualizing the curve shape of the width data curve, so as to determine whether there is a fork in the road ahead based on the changes; wherein the changes include whether the road width increases, the magnitude of the increase within a set distance, and whether the road width returns to the road width before the increase after exceeding the set distance.

[0021] Optionally, the road recognition device is used to construct visualized road width data for multiple road widths based on multiple road widths of the road ahead, including: constructing visualized point cloud data of the road boundaries of the road ahead based on the point cloud data corresponding to the identified static objects indicating the road boundaries on both sides of the road ahead; and visually displaying the information of the branching sections of the road ahead using the visualized point cloud data.

[0022] Optionally, the road recognition device, used to determine changes in road width by means of the curve shape of a visualized width data curve, further includes: determining the starting position of a fork in the road segment based on the curve shape of the visualized width data curve; and sending a prompt message indicating the fork in the road segment to the vehicle, including: sending information indicating the starting position of the fork in the road segment to the vehicle.

[0023] Thirdly, embodiments of the present invention provide an electronic device, comprising:

[0024] One or more processors;

[0025] Storage device, which is used to store one or more programs.

[0026] When the one or more programs are executed by the one or more processors, the one or more processors implement the road recognition method as described in the above embodiments of the present invention.

[0027] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program storing thereon that implements a road recognition method, wherein the computer program, when executed by an on-board processor, implements the road recognition method of the present invention.

[0028] Fifthly, embodiments of the present invention provide a vehicle capable of implementing the road recognition method described in the embodiments of the present invention above.

[0029] The technical solution of the above invention has the following advantages or beneficial effects: it can use the vehicle's onboard radar to acquire road point cloud data of the road ahead; identify static objects indicating the road boundaries on both sides of the road ahead based on the road point cloud data; calculate the road width of the road ahead based on the point cloud data corresponding to the static objects; further, if it is determined that the road width of the road ahead has increased and then returns to the road width before the increase after a set distance, it is determined that there is a fork in the road ahead, and a prompt message indicating the fork in the road is sent to the vehicle; the embodiments of the present invention improve the accuracy and reliability of identifying fork in the road, overcome the accuracy and angle problems of existing methods for determining fork in the road using map data, and overcome the low accuracy problem of existing methods for identifying fork in the road using road images. Attached Figure Description

[0030] Figure 1 This is a schematic flowchart of a road recognition method provided according to an embodiment of the present invention;

[0031] Figure 2A This is a schematic diagram of a branching road section according to an embodiment of the present invention;

[0032] Figure 2B This is a schematic diagram of a visualized road width data provided by an embodiment of the present invention;

[0033] Figure 2C This is a schematic diagram of visualized point cloud data of a road ahead, provided by an embodiment of the present invention;

[0034] Figure 3 This is a schematic flowchart of a road recognition method provided according to an embodiment of the present invention;

[0035] Figure 4 This is a schematic diagram of the structure of a road recognition device according to an embodiment of the present invention;

[0036] Figure 5 This is a schematic diagram of the structure of a computer system suitable for implementing embodiments of the present invention. Detailed Implementation

[0037] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0038] It should be noted that, unless otherwise specified, the embodiments of the present invention and the technical features thereof can be combined with each other.

[0039] Furthermore, the terms "first," "second," and "third," etc., included in the terminology of this invention are used to distinguish similar objects and are not necessarily used to describe a specific number or order. It should be understood that such terms can be used interchangeably where appropriate; this is merely a distinguishing method used in the embodiments of this invention when describing objects with the same attributes.

[0040] Furthermore, the vehicles involved in the embodiments of the present invention may be internal combustion engine vehicles that use an engine as a power source, hybrid vehicles that use an engine and an electric motor as power sources, electric vehicles that use an electric motor as a power source, etc.

[0041] Figure 1 The following diagram illustrates the main steps of the road recognition method provided in the embodiments of the present invention:

[0042] Step S101: Use the vehicle's onboard radar to acquire road point cloud data of the road ahead; based on the road point cloud data, identify static objects that indicate the road boundaries on both sides of the road ahead.

[0043] Specifically, vehicle-mounted radar (such as millimeter-wave radar) is used to acquire road point cloud data of the road ahead, and static objects indicating the road boundaries on both sides of the road ahead are identified based on the road point cloud data.

[0044] By using vehicle-mounted radar to monitor the road ahead, the problem of low accuracy in road identification caused by cameras at night or in poor visibility conditions (rain, snow, or fog) is overcome. Furthermore, for static objects on both sides of the road that are metal guardrails, radar has a strong ability to detect metal targets and can penetrate obstructions (such as vehicles in the middle of the road). Therefore, using vehicle-mounted radar to detect static objects on both sides of the road improves the accuracy and reliability of road boundary detection.

[0045] Step S102: Calculate the road width of the road ahead based on the point cloud data corresponding to the static object.

[0046] Specifically, the road width of the road ahead is calculated based on the positions of the static objects indicating the road boundaries on both sides of the road identified in step S101. That is, the road width of the road ahead is calculated based on the positions of the static objects contained in the point cloud data of the static objects on both sides of the road ahead. Specifically, when calculating the road width based on the point cloud data of the static objects, multiple reference points indicated by the point cloud data of the static objects can be selected. By finding the point closest to the road centerline or by matching geometric features, multiple sets of corresponding reference points on the static objects on both sides of the road ahead can be determined. Furthermore, the distance between each set of reference points can be calculated using geometric methods to obtain multiple sets of road width data for the road ahead. Statistical analysis can also be performed on the road width data calculated from multiple sets of reference points (e.g., calculating the average, median, etc.), and multiple sets of road width data for the road ahead can be obtained based on the statistical results.

[0047] Step S103: If it is determined that the road width ahead has increased and then returns to the original road width after a set distance, determine that there is a fork in the road ahead; send a prompt message indicating the fork in the road to the vehicle.

[0048] Specifically, in this embodiment of the invention, the presence of a fork in the road ahead (such as a ramp, intersection, etc.) is determined based on changes in road width.

[0049] If it is determined that the road width ahead has increased, and then returns to the original road width after a set distance, it is determined that there is a fork in the road ahead.

[0050] The following is based on Figure 2A and Figure 2B The following diagram illustrates the process:

[0051] Figure 2A A schematic diagram of a branching road section is shown; as follows: Figure 2A As shown, vehicle V is traveling in the direction indicated by the arrow on the main road S1, and there is a fork in the road ahead of vehicle V, indicated by S2 (e.g., a ramp).

[0052] like Figure 2A As shown, the road width of the main road S1 is basically the same when there is no fork in the road. When a fork appears, the road width increases and then returns to the original width after a certain distance. This indicates that there is a fork in the road ahead of the vehicle, as shown in S2.

[0053] In an embodiment of the present invention, visualized road width data for multiple road widths can be constructed based on multiple road widths ahead; the visualized road width data can be used to show whether there are branching sections on the road ahead.

[0054] Figure 2B A schematic diagram illustrating road width data is shown.

[0055] like Figure 2B The two-dimensional coordinate system shown includes an abscissa X (representing the longitudinal distance of the vehicle in the direction of travel on the main road) and an ordinate Y (representing the road width). That is, the abscissa of the two-dimensional coordinate system is parallel to the vehicle's direction of travel, and the ordinate represents the road width. Curve C in this two-dimensional coordinate system is a visualized width data curve generated by fitting the width data of the road ahead; for example... Figure 2B The curve C shown is divided into two parts. The first part is a curve showing the increase in road width, and the second part is a straight line that restores the road width before the increase. That is, based on the multiple road widths of the road ahead, visualized road width data for multiple road widths is constructed, including: in a preset two-dimensional coordinate system, fitting the width data of the road ahead to generate a visualized width data curve.

[0056] Furthermore, according to such Figure 2B The shape of curve C shown indicates the variation in road width. Curve C shows an increase in road width starting from point B (marked with a triangle), continuing to increase within a set distance, and then returning to the pre-increase width after exceeding the set distance. Figure 2B The shape of curve C shown indicates that the road ahead may have features such as... Figure 2A The diagram illustrates a fork in the road. Specifically, the change in road width is determined by the shape of the visualized width data curve. This change includes whether the road width increases, the magnitude of the increase within a set distance, and whether the road width returns to its pre-increase state after exceeding the set distance. The set distance can be determined based on actual road measurement data. It is understood that road width increases may occur even on roads that do not contain fork in the road. This embodiment of the invention uses the analysis results obtained from analyzing the shape of the visualized width data curve to determine whether the road width increases, the magnitude of the increase within a set distance, and whether the road width returns to its pre-increase state after exceeding the set distance, thereby improving the accuracy and reliability of determining fork in the road.

[0057] More preferably, in this embodiment of the invention, based on the point cloud data corresponding to the identified static objects indicating the road boundaries on both sides of the road ahead, a visualized point cloud data of the road boundary ahead is constructed, and the information of the fork in the road ahead is visualized using the visualized point cloud data.

[0058] Figure 2C This diagram illustrates a visualization of point cloud data of a road ahead; for example... Figure 2CAs shown, vehicle V is traveling on the road, and multiple dots P represent point cloud data of static objects on both sides of the road; through Figure 2C The visualized point cloud data of the two side boundaries of the road ahead further improves the accuracy and visualization of road conditions detection. Specifically, based on multiple road widths of the road ahead, visualized road width data for multiple road widths is constructed, including: constructing visualized point cloud data of the road boundaries of the road ahead based on the point cloud data corresponding to the identified static objects indicating the two side boundaries of the road ahead; and using the visualized point cloud data to visualize the information of the branching sections of the road ahead.

[0059] Furthermore, if it is determined that there is a fork in the road ahead, a prompt message indicating the fork in the road is sent to the vehicle. The prompt message may include the existence of a fork in the road ahead and the positional relationship between the fork in road and the main road.

[0060] Furthermore, the information displayed for the fork in the road can also include the starting position of the fork; wherein, the starting position of the fork can be determined based on, for example... Figure 2B The shape of the visualized width data curve (e.g., point B in curve C) determines the starting position of the road branch. Alternatively, if the road width data shows a continuous increase, and this increase exceeds a set threshold, the point cloud data corresponding to the starting increase in road width data can be used to determine the starting position of the branch. The set threshold for the increase can be determined using actual road measurement data. In other words, determining the road width change through the shape of the visualized width data curve further includes: determining the starting position of the branch based on the shape of the visualized width data curve; and sending a prompt indicating the branch to the vehicle, including sending information indicating the starting position of the branch to the vehicle.

[0061] By sending prompts indicating road forks to the vehicle, the vehicle can obtain real-time road conditions ahead, thereby further determining the driving route to choose when there are road forks ahead, thus improving the passenger's driving experience.

[0062] Figure 3 The diagram illustrates the main process flow of the road recognition method provided in the embodiments of the present invention, as follows: Figure 3 As shown:

[0063] Step S301: Use the vehicle's onboard radar to acquire road point cloud data of the road ahead.

[0064] Step S302: Based on the road point cloud data, identify the static objects that indicate the road boundaries on both sides of the road ahead.

[0065] Step S303: Calculate the road width of the road ahead based on the location of the static objects contained in the point cloud data of the static objects.

[0066] Step S304: Fit the width data of the road ahead to generate a visual width data curve.

[0067] Step S305: Determine the changes in road width by visualizing the curve shape of the width data curve, and determine the presence of road forks ahead based on the changes.

[0068] Specifically, the descriptions of steps S301 to S305 are consistent with those of steps S101 to S103, and will not be repeated here.

[0069] Figure 4 A schematic diagram of the structure of a road recognition device 400 to which embodiments of the present invention can be applied is shown. It includes:

[0070] The width calculation module 401 is used to acquire road point cloud data of the road ahead using the vehicle's onboard radar; identify static objects indicating the road boundaries on both sides of the road ahead based on the point cloud data; and calculate the road width of the road ahead based on the point cloud data corresponding to the static objects.

[0071] The road condition determination module 402 is used to determine that there is a fork in the road ahead when the road width ahead has increased and the road width before the increase is restored after a set distance.

[0072] The information sending module 403 is used to send prompts indicating branch road sections to vehicles.

[0073] The following is for reference. Figure 5 It shows a schematic diagram of the structure of a computer system 500 suitable for implementing embodiments of the present invention. Figure 5 The computer system shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0074] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 502 or programs loaded from storage section 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the system 500. The CPU 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0075] The following components are connected to I / O interface 505: an input section 506; an output section 507 including devices such as cathode ray tubes (CRTs), liquid crystal displays (LCDs), and speakers; a storage section 508 including devices such as hard disks; and a communication section 509 including network interface cards such as LAN cards and modems. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to I / O interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 510 as needed so that computer programs read from it can be installed into storage section 508 as needed.

[0076] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by central processing unit (CPU) 501, it performs the functions defined above in the system of this invention.

[0077] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0078] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0079] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs that, when executed by the device, cause the device to: acquire road point cloud data of the road ahead using the vehicle's onboard radar; identify static objects indicating the road boundaries on both sides of the road ahead based on the road point cloud data; calculate the road width of the road ahead based on the point cloud data corresponding to the static objects; determine that there is a fork in the road ahead if the road width increases and then returns to its original width after a set distance; and send a prompt message indicating the fork in the road to the vehicle.

[0080] Those skilled in the art will understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A road recognition method, characterized in that, include: Use the vehicle's onboard radar to acquire road point cloud data of the road ahead; Based on the road point cloud data, identify static objects that indicate the road boundaries on both sides of the road ahead; Calculate the road width of the road ahead based on the point cloud data corresponding to the static object; If it is determined that the road width ahead has increased, and then returns to the original road width after a set distance, it is determined that there is a fork in the road ahead; Send a prompt message indicating the branching section to the vehicle.

2. The road recognition method according to claim 1, characterized in that, The step of calculating the road width of the road ahead based on the point cloud data corresponding to the static object includes: The road width of the road ahead is calculated based on the position of the static objects contained in the point cloud data of the static objects on both sides of the road boundary ahead.

3. The road recognition method according to claim 1, characterized in that, Further includes: Based on the multiple road widths of the road ahead, construct visualized road width data for the multiple road widths; The visualized road width data can be used to show whether there are branching sections on the road ahead.

4. The road recognition method according to claim 3, characterized in that, The step of constructing visualized road width data for multiple road widths based on the multiple road widths of the road ahead includes: In a preset two-dimensional coordinate system, the width data of the road ahead is fitted to generate a visual width data curve, wherein the horizontal coordinate of the two-dimensional coordinate system is parallel to the vehicle's driving direction, and the vertical coordinate represents the road width.

5. The road recognition method according to claim 4, characterized in that, Further includes: The changes in road width are determined by the shape of the visualized width data curve, so as to determine whether there is a fork in the road ahead based on the changes; wherein, the changes include whether the road width increases, the increase within a set distance, and whether the road width returns to the road width before the increase after exceeding the set distance.

6. The road recognition method according to claim 3, characterized in that, The step of constructing visualized road width data for multiple road widths based on the multiple road widths of the road ahead includes: Based on the point cloud data corresponding to the identified static objects indicating the road boundaries on both sides of the road ahead, a visual point cloud data of the road boundary of the road ahead is constructed. The visualization point cloud data is used to visualize and display the information of the forked road sections ahead.

7. The road recognition method according to claim 5, characterized in that, The step of determining the road width variation through the curve shape of the visualized width data curve further includes: The starting position of the branching segment is determined based on the curve shape of the visualized width data curve; Sending the prompt message indicating the branch road segment to the vehicle includes: Send information indicating the starting position of the branch road segment to the vehicle.

8. A road recognition device, characterized in that, include: The width calculation module is used to acquire road point cloud data of the road ahead using the vehicle's onboard radar; identify static objects indicating the road boundaries on both sides of the road ahead based on the point cloud data; and calculate the road width of the road ahead based on the point cloud data corresponding to the static objects. The road condition determination module is used to determine that there is a fork in the road ahead when it is determined that the road width of the road ahead has increased and then returns to the original road width after a set distance. The information sending module is used to send a prompt message indicating the branch road section to the vehicle.

9. A road recognition electronic device, characterized in that, The electronic device includes: One or more processors; Storage device, which is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program thereon storing a road recognition implementation, characterized in that, include: When the computer program is executed by a processor, it implements the method as described in any one of claims 1-7.

Images