Road edge recognition method and device, electronic equipment and storage medium

Abstract

The invention provides a road edge recognition method and device, electronic equipment and a storage medium, and relates to the technical field of automatic driving, and the method comprises the steps: collecting road data in a preset range of a vehicle through a road data collection device; based on road data in a preset range collected by a road data collection device, whether the sight of the vehicle in the first direction is shielded by an obstacle or not is judged; if the sight line of the vehicle in the first direction is shielded by an obstacle, searching a target high-precision map corresponding to a current area where the vehicle is located; under the condition that the target high-precision map corresponding to the current area is found, the road edge recognition result of the vehicle in the first direction is determined through the target high-precision map, the road edge recognition result is used for indicating whether the sight line of the vehicle in the first direction is the road edge or not, and therefore when the road data collection device is shielded by an obstacle, the vehicle can be conveniently collected. Therefore, the road edge recognition result can be obtained by using the high-precision map, so that the reliability of automatic driving can be improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a road edge recognition method, device, electronic equipment and storage medium. Background Art

[0002] With the rapid development of autonomous driving, how to improve the accuracy of autonomous driving decisions is becoming increasingly important. In related technologies, vehicles collect road data and then use the road data to make autonomous driving decisions.

[0003] However, during the driving process of the vehicle, the vehicle may be blocked by obstacles, which will make the road conditions in the blocked direction unable to be determined, thereby reducing the reliability of autonomous driving. Summary of the invention

[0004] In view of this, an object of the present invention is to provide a road edge recognition method, device, electronic device and storage medium to improve the reliability of autonomous driving.

[0005] In a first aspect, an embodiment of the present invention provides a method for identifying a road edge, which is applied to a vehicle, wherein the vehicle includes at least one road data acquisition device, and the method includes: during the driving of the vehicle, collecting road data within a preset range of the vehicle through the road data acquisition device; based on the road data within the preset range collected by the road data acquisition device, determining whether the vehicle's line of sight along a first direction is blocked by an obstacle; if the vehicle's line of sight along the first direction is blocked by an obstacle, searching for a target high-precision map corresponding to the current area where the vehicle is located; when the target high-precision map corresponding to the current area is found, determining a road edge recognition result of the vehicle along the first direction using the target high-precision map, and the road edge recognition result is used to indicate whether the vehicle's line of sight along the first direction is a road edge.

[0006] In one possible implementation, the road data acquisition device includes an image sensor and a laser radar, and determines whether the vehicle's line of sight along a first direction is blocked by an obstacle based on road data within a preset range collected by the road data acquisition device, including: determining whether the vehicle's line of sight along the first direction is blocked by an obstacle based on first road data within a preset range collected by one of the image sensor or the laser radar; if it is determined that the vehicle's line of sight along the first direction is blocked by an obstacle based on the first road data, then determining whether the vehicle's line of sight along the first direction is blocked by an obstacle based on second road data within a preset range collected by the other of the image sensor or the laser radar; if the vehicle's line of sight along the first direction is blocked by an obstacle, searching for a target high-precision map corresponding to the current area where the vehicle is located, including: if it is determined that the vehicle's line of sight along the first direction is blocked by an obstacle based on the second road data, then searching for a target high-precision map corresponding to the current area where the vehicle is located.

[0007] In one possible implementation, the image sensor is installed at a height lower than the height at which the laser radar is installed, and based on first road data within a preset range collected by one of the image sensor or the laser radar, it is determined whether the vehicle's line of sight along the first direction is blocked by an obstacle, including: based on image data within a preset range collected by the image sensor, it is determined whether the vehicle's line of sight along the first direction is blocked by an obstacle, and the first road data includes image data; if it is determined that the vehicle's line of sight along the first direction is blocked by an obstacle based on the first road data, then based on second road data within a preset range collected by the other of the image sensor or the laser radar, it is determined whether the vehicle's line of sight along the first direction is blocked by an obstacle, including: if it is determined that the vehicle's line of sight along the first direction is blocked by an obstacle based on the image data, then based on laser data within the preset range collected by the laser radar, it is determined whether the vehicle's line of sight along the first direction is blocked by the obstacle.

[0008] In one possible implementation, based on laser data within a preset range collected by a laser radar, it is determined whether the vehicle's line of sight along a first direction is blocked by an obstacle, including: determining an obstruction angle of the image sensor along the first direction; controlling the laser radar to emit a detection beam within the obstruction angle, and receiving a reflected beam within a preset range, the reflected beam being a beam obtained by reflecting the detection beam, and the laser data including the reflected beam; based on the reflected beam, determining whether the vehicle's line of sight along the first direction is blocked by an obstacle.

[0009] In one possible implementation, a vehicle includes multiple storage devices, which are used to respectively store target high-precision maps of multiple preset areas. Searching for the target high-precision map corresponding to the current area where the vehicle is located includes: determining the target preset area to which the current area where the vehicle is located belongs, where the target preset area is one of the multiple preset areas; based on the target preset area to which the current area belongs, searching for the target high-precision map corresponding to the current area where the vehicle is located from the storage device corresponding to the target preset area.

[0010] In one possible implementation, the target high-precision map is determined in the following manner: an original high-precision map is obtained, the original high-precision map includes element information of each area, and the areas include road areas and intersection areas; for the road areas in the original high-precision map, part of the element information of the road areas is deleted, and for the intersection areas in the original high-precision map, all the element information of the intersection areas is retained to obtain the target high-precision map.

[0011] In one possible implementation, the road edge recognition result is used to determine the autonomous driving decision result in the autonomous driving mode. The method also includes: if a target high-precision map corresponding to the current area is not found, exiting the autonomous driving mode and initiating a prompt to take over the vehicle.

[0012] In a second aspect, an embodiment of the present invention provides a road edge recognition device, which is applied to a vehicle, and the vehicle includes at least one road data acquisition device. The road edge recognition device includes: a collection module, which is used to collect road data within a preset range of the vehicle through the road data acquisition device during the vehicle's driving; a judgment module, which is used to judge whether the vehicle's line of sight along a first direction is blocked by an obstacle based on the road data within the preset range collected by the road data acquisition device; a map search module, which is used to search for a target high-precision map corresponding to the current area where the vehicle is located if the vehicle's line of sight along the first direction is blocked by an obstacle; and an identification module, which is used to determine a road edge recognition result of the vehicle along the first direction using the target high-precision map when the target high-precision map corresponding to the current area is found, and the road edge recognition result is used to indicate whether the vehicle's line of sight along the first direction is a road edge.

[0013] In a third aspect, an embodiment of the present invention provides an electronic device including a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method of the first aspect.

[0014] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method of the first aspect.

[0015] The embodiments of the present invention bring about the following beneficial effects: during vehicle driving, road data within a preset range of the vehicle is collected by a road data collection device; based on the road data within the preset range collected by the road data collection device, it is determined whether the vehicle's line of sight along a first direction is blocked by an obstacle; if the vehicle's line of sight along the first direction is blocked by an obstacle, a target high-precision map corresponding to the current area where the vehicle is located is searched; when the target high-precision map corresponding to the current area is found, the target high-precision map is used to determine the road edge recognition result of the vehicle along the first direction, and the road edge recognition result is used to indicate whether the vehicle's line of sight along the first direction is a road edge, so that when the road data collected by the road data collection device cannot obtain an accurate road edge recognition result, the high-precision map can be used to obtain the road edge recognition result, thereby when the road data collection device is blocked by an obstacle, the high-precision map can be used to obtain the road edge recognition result, so that the reliability of automatic driving can be improved.

[0016] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 A schematic diagram of a flow chart of a road edge recognition method provided by an embodiment of the present invention;

[0020] Figure 2 A schematic diagram of the structure of a road edge recognition device provided by an embodiment of the present invention;

[0021] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0023] In related technologies, vehicles collect road data and then use the road data to make decisions for autonomous driving. However, during the driving process, the vehicle may be blocked by obstacles, such as other vehicles, which will make it impossible to determine the road conditions in the blocked direction, thereby greatly increasing the risk of autonomous driving.

[0024] It should be noted that in some example situations, when a vehicle arrives at an intersection, due to obstruction by other vehicles, the vehicle cannot determine whether the obscured direction belongs to the edge of the road or the intersection through the road data collected by its installed road data acquisition device (such as image sensors or lidar, etc.). In this way, the vehicle may mistakenly believe that the obscured direction is the edge of the road, and may miss the turning intersection during automatic driving, resulting in reduced reliability of automatic driving.

[0025] In view of this, an embodiment of the present invention provides a method, device, electronic device and storage medium for recognizing road edges of multiple vehicles, which can improve the effect of image processing.

[0026] To facilitate understanding of the present embodiment, an application scenario of the embodiment of the present invention is first exemplarily described.

[0027] Application scenario: When a vehicle is driving, it is blocked by other driving vehicles or vehicles parked on the roadside, making it impossible to accurately determine whether the blocking direction is the road edge (referred to as the curb) or the intersection.

[0028] See also Figure 1 , Figure 1 A schematic diagram of a road edge recognition method provided by an embodiment of the present invention. Figure 1 The method shown can be applied to a vehicle, wherein the vehicle includes at least one road data collection device, which is used to collect road-related data, thereby determining the road conditions through the road-related data and making decisions on automatic driving. Figure 1 The methods shown may include:

[0029] S110. While the vehicle is traveling, a road data collection device collects road data within a preset range of the vehicle.

[0030] The road data collection device may be installed on the vehicle and used to collect road data within a preset range of the vehicle. Optionally, the road data collection device may be, for example, an image sensor or a laser radar, wherein the road data collected by the image sensor may be, for example, image data, and the road data collected by the laser radar may be laser data.

[0031] S120. Based on the road data within a preset range collected by the road data collection device, determine whether the sight line of the vehicle along the first direction is blocked by an obstacle.

[0032] In this embodiment, the obstacle may be an object that blocks the sight line of the vehicle along the first direction, for example, it may be another vehicle, and this is not limited here. In this embodiment, the sight line of the vehicle along the first direction may be understood as the sight line of the road data acquisition device along the first direction. In this embodiment, any direction may be used as the first direction, for example, the first direction may refer to the direction in which the vehicle is blocked.

[0033] S130: If the sight line of the vehicle along the first direction is blocked by an obstacle, search for a target high-precision map corresponding to the current area where the vehicle is located.

[0034] Among them, high-precision map (Precision Map) is a highly refined and digital map form, and its accuracy has been significantly improved compared with traditional electronic navigation maps, reaching the centimeter level. The characteristics of high-precision maps include high precision, integrity, real-time and rich semantic information. Among them, high precision: The precision requirements of high-precision maps are extremely high, and the description of elements such as roads, traffic signs, lane lines, etc. have reached the centimeter level, which provides accurate spatial positioning information for applications such as autonomous driving. Integrity: High-precision maps can fully describe the characteristics that affect human driving behavior, such as traffic signs, lane lines, road markings, street lights, guardrails, signal lights, etc., and provide comprehensive environmental perception information for autonomous driving systems. Real-time: High-precision maps can update road information in real time, including traffic conditions, construction conditions, etc., to ensure that the autonomous driving system can obtain the latest road data. Rich semantic information: High-precision maps contain not only road geometry information, but also rich semantic information, such as road type, lane direction, traffic rules, etc., which are crucial for the decision-making and planning of autonomous driving systems. The current area can be a circle formed within a preset radius with the vehicle's position coordinates as the origin.

[0035] S140. When a target high-precision map corresponding to the current area is found, a road edge recognition result of the vehicle along a first direction is determined using the target high-precision map, where the road edge recognition result is used to indicate whether the vehicle's line of sight along the first direction is a road edge.

[0036] Among them, the road edge recognition result is used to indicate whether the sight line of the vehicle along the first direction is the road edge, and can be used to indicate that the sight line of the vehicle along the first direction is the road edge or the intersection. Among them, the road edge can refer to the outer boundary or limit of the road. It marks the end of the road and the beginning of the surrounding environment (such as a sidewalk, a green belt, a building area or a field, etc.). In this embodiment, since the target high-precision map records the road information of the current area, the road edge recognition result of the vehicle along the first direction can be determined by the target high-precision map, that is, the road edge recognition result in the direction where the vehicle is blocked by an obstacle can be determined, so as to determine whether the direction where the vehicle is blocked is the road edge or the intersection, so as to make a decision on automatic driving in time, for example, when it is the road edge, the vehicle is controlled to go straight or change lanes according to the road conditions; for example, when it is an intersection, the vehicle is controlled to slow down or turn, etc., which is not limited here. In this embodiment, the road conditions around the position of the vehicle in the target high-precision map can be used to determine whether the sight line of the vehicle along the first direction is the road edge.

[0037] In this embodiment, during the driving process of the vehicle, the road data within the preset range of the vehicle is collected by the road data collection device; based on the road data within the preset range collected by the road data collection device, it is determined whether the sight line of the vehicle along the first direction is blocked by an obstacle; if the sight line of the vehicle along the first direction is blocked by an obstacle, the target high-precision map corresponding to the current area where the vehicle is located is searched; in the case of finding the target high-precision map corresponding to the current area, the target high-precision map is used to determine the road edge recognition result of the vehicle along the first direction, and the road edge recognition result is used to indicate whether the sight line of the vehicle along the first direction is the road edge, so that when the road data collected by the road data collection device cannot obtain an accurate road edge recognition result, the high-precision map can be used to obtain the road edge recognition result, thereby when the road data collection device is blocked by an obstacle, the high-precision map can be used to obtain the road edge recognition result, so that the reliability of the automatic driving can be improved. In addition, there is no need to load the high-precision map in real time, and the high-precision map can be called only when the road data collected by the road data collection device is judged to be blocked, which can reduce the resources required for calling the high-precision map.

[0038] In a possible implementation, the road data acquisition device includes an image sensor and a laser radar, and based on the road data within a preset range acquired by the road data acquisition device, determining whether the sight line of the vehicle along the first direction is blocked by an obstacle includes:

[0039] Based on first road data within a preset range collected by one of the image sensors or laser radars, determine whether the vehicle's line of sight along the first direction is blocked by an obstacle; based on the first road data, determine whether the vehicle's line of sight along the first direction is blocked by an obstacle, then based on second road data within a preset range collected by the other of the image sensors or laser radars, determine whether the vehicle's line of sight along the first direction is blocked by an obstacle.

[0040] Among them, the image sensor is a device that uses the photoelectric conversion function of the photoelectric device to convert the light image on the photosensitive surface into an electrical signal that is proportional to the light image. In this embodiment, the image sensor is used to collect image data within a preset range of the vehicle. Laser radar is a radar system that emits a laser beam to detect characteristic quantities such as the position and speed of the target. The working principle of laser radar is based on the emission, propagation and reception of light. It first emits a beam of laser pulses, which are usually infrared or near-infrared light. When the laser pulse encounters the target object, part of the light will be reflected back and then captured by the receiver in the laser radar device. The timer inside the device records the time interval between the emission and reception of the laser pulse. Since the speed of light is known, this time interval can be used to calculate the distance of the light pulse to and from the target object. The distance calculation formula is: distance = speed of light × time / 2 (where time is the time for the light pulse to go back and forth). In addition, the laser radar can also obtain the three-dimensional shape of the target object by scanning the transmitting and receiving devices.

[0041] Correspondingly, if the sight line of the vehicle along the first direction is blocked by an obstacle, the target high-precision map corresponding to the current area where the vehicle is located is searched, including:

[0042] If it is determined based on the second road data that the vehicle's line of sight along the first direction is blocked by an obstacle, a target high-precision map corresponding to the current area where the vehicle is located is searched.

[0043] In this embodiment, the image data collected by one of the image sensors or the laser radar is first used to determine whether it is blocked. If blocked, the other of the image sensor or the laser radar is also blocked. If both are blocked, it means that it is impossible to identify whether the blocked part in the first direction is the road edge or the intersection through the road data collected by the image sensor and the laser radar. Therefore, the high-precision map is used for identification. The high-precision map is called only when all road data collection devices cannot detect the road conditions of the blocked part in the first direction. This can improve the accuracy of calling the high-precision map.

[0044] In a possible implementation, the image sensor is installed at a height lower than the laser radar. Accordingly, based on first road data within a preset range collected by one of the image sensor or the laser radar, determining whether the sight line of the vehicle along the first direction is blocked by an obstacle includes:

[0045] Based on image data within a preset range collected by the image sensor, it is determined whether the sight line of the vehicle along the first direction is blocked by an obstacle, and the first road data includes the image data.

[0046] Correspondingly, if it is determined based on the first road data that the sight line of the vehicle along the first direction is blocked by an obstacle, then based on the second road data within a preset range collected by the other of the image sensor or the laser radar, it is determined whether the sight line of the vehicle along the first direction is blocked by the obstacle, including:

[0047] If it is determined based on the image data that the vehicle's line of sight along the first direction is blocked by an obstacle, then it is determined based on the laser data within a preset range collected by the lidar whether the vehicle's line of sight along the first direction is blocked by the obstacle.

[0048] For example, the image sensor can be installed around the vehicle, such as at the bumper, and the laser radar can be installed on the roof of the vehicle, etc., without limitation here.

[0049] In this embodiment, an image sensor installed at a lower height is first used to detect whether the vehicle's line of sight along the first direction is blocked. If not, the image data collected by the image sensor can be used to determine whether the first direction is a road edge or an intersection. If so, a lidar installed at a higher height is continued to be used to detect whether the vehicle's line of sight along the first direction is blocked. If not, the laser data collected by the lidar can be used to determine whether the first direction is a road edge or an intersection. If so, a high-precision map is called to identify the edge of the road.

[0050] Based on any of the above embodiments, an exemplary description is given below of how to detect whether image data and laser data are blocked.

[0051] When using image data to determine whether it is blocked, pixel-based analysis, machine learning-based methods, etc. can be used. Pixel-based analysis can be to check whether there are areas in the image that are significantly different from the surrounding color and brightness. These differences may be caused by occluders; or the occluders may change the texture or details of the image. For example, if the occluder is rough, it may produce a blurred texture on the image; or edge detection algorithms (such as Canny edge detection) can be used to identify edges in the image. If the edge between the occluder and the background is obvious, it can be detected by this method. The machine learning-based method can be: use a machine learning algorithm (such as a convolutional neural network CNN) to train a model that can identify occluders in the image. This requires a large amount of image data with occluders annotated for training. Feature extraction: extract features such as shape, color, texture, etc. from the image, and use these features to train a classifier. The classifier can be used to determine whether there are occluders in the image.

[0052] When using laser data to determine whether it is blocked, the laser radar obtains the three-dimensional coordinate information of the target object by emitting a laser beam and receiving the signal reflected back. This information is usually expressed in the form of a point cloud, and each point contains its coordinates (x, y, z) in three-dimensional space and possible intensity values. Then, the point cloud data is denoised to remove noise points caused by equipment errors or environmental factors. Downsampling is performed to reduce the number of data points and improve processing efficiency. Then, the ground point cloud is segmented from the total point cloud using an algorithm (such as RANSAC, etc.). Then, for each detected obstacle cluster, the distribution and density of its point cloud data are analyzed. If the point cloud data of a cluster becomes sparse or missing in a certain direction (such as the front), it may indicate that the obstacle is blocked by other objects. Combine multiple frames of point cloud data for analysis to observe the changes in the obstacle cluster. If the occlusion phenomenon persists in several consecutive frames, and the occluded area gradually expands or changes in shape, it can be confirmed that the obstacle is blocked. The severity of occlusion can be evaluated by calculating indicators such as the area, volume or occlusion ratio of the occluded region.

[0053] In a possible implementation, judging whether the sight line of the vehicle along the first direction is blocked by an obstacle based on laser data within a preset range collected by a laser radar includes:

[0054] Determine an obstruction angle of the image sensor along the first direction due to the obstruction of the object; control the laser radar to emit a detection beam within the obstruction angle, and receive a reflected beam within a preset range, the reflected beam is a beam obtained by reflecting the detection beam, and the laser data includes the reflected beam; based on the reflected beam, determine whether the vehicle's line of sight along the first direction is blocked by an obstacle.

[0055] Among them, the obstruction angle of the image sensor along the first direction due to the obstructing object may be an angle at which the image sensor does not sense light, or an angle at which the intensity of the sensed light is lower than the average light intensity. The average light intensity may be the average value of the intensities of all light sensed by the image sensor.

[0056] In this embodiment, the blocking angle of the image sensor along the first direction blocked by the obstructed object is determined; the laser radar is controlled to emit a detection beam within the blocking angle, and a reflected beam within a preset range is received, the reflected beam is a beam obtained by reflecting the detection beam, and the laser data includes the reflected beam; based on the reflected beam, it is determined whether the vehicle's line of sight along the first direction is blocked by an obstacle. In this way, the laser radar can only emit the detection beam within the blocking angle, which can reduce the resources required for data processing, such as reducing the resources required for occlusion judgment.

[0057] In a possible implementation, the vehicle includes a plurality of storage devices, which are used to store target high-precision maps of a plurality of preset areas respectively, and searching for the target high-precision map corresponding to the current area where the vehicle is located includes:

[0058] Determine a target preset area to which a current area where the vehicle is located belongs, where the target preset area is one of multiple preset areas; based on the target preset area to which the current area belongs, search a target high-precision map corresponding to the current area where the vehicle is located from a storage device corresponding to the target preset area.

[0059] Wherein, the storage device is used to store data. In this embodiment, multiple storage devices are used to store target high-precision maps of multiple preset areas respectively. Wherein, any two preset areas among the multiple preset areas do not include the same area. Exemplarily, assuming that the multiple storage devices include storage device 1 and storage device 2, storage device 1 is used to store the target high-precision map of preset area 1, and storage device 2 is used to store the target high-precision map of preset area 2. If the current area belongs to target area 1, the target high-precision map corresponding to the current area is searched from storage device 1; if the current area belongs to target area 2, the target high-precision map corresponding to the current area is searched from storage device 2. Optionally, the storage device may be, for example, a read-only memory (ROM).

[0060] In this embodiment, multiple storage devices are used to respectively store target high-precision maps of multiple preset areas. When searching for the target high-precision map corresponding to the current area where the vehicle is located, the target preset area to which the current area where the vehicle is located belongs is determined; based on the target preset area to which the current area belongs, the target high-precision map corresponding to the current area where the vehicle is located is searched from the storage device corresponding to the target preset area. In this way, the target high-precision map can be searched from the corresponding storage device, which can improve the efficiency of searching for high-precision maps and is conducive to improving the efficiency of autonomous driving decisions.

[0061] In another possible implementation, all target high-precision maps may be stored in one storage device, which is not limited here.

[0062] In one possible implementation, the target high-precision map is determined by:

[0063] The original high-precision map is obtained, and the original high-precision map includes element information of each area, and the area includes a road area and an intersection area; for the road area in the original high-precision map, part of the element information of the road area is deleted, and for the intersection area in the original high-precision map, all the element information of the intersection area is retained to obtain the target high-precision map.

[0064] The element information may be, for example, element information of roads, traffic signs, lane lines, traffic conditions, construction conditions, etc. For example, element information such as traffic conditions and construction conditions are irrelevant to road edge recognition, so this part of element information may be deleted.

[0065] In this embodiment, part of the element information of the road area in the original high-precision map is deleted, and all the element information of the intersection area in the original high-precision map is retained to obtain the target high-precision map. In this way, the resource information required to store the high-precision map can be reduced, and the efficiency of finding the target high-precision map can be improved.

[0066] In a possible implementation, the road edge recognition result is used to determine the autonomous driving decision result in the autonomous driving mode, and the method further includes:

[0067] If the target high-precision map corresponding to the current area is not found, the automatic driving mode is exited and a prompt to take over the vehicle is initiated.

[0068] The autonomous driving decision results are used in the autonomous driving mode, which is an advanced driving assistance system that uses a variety of on-board sensors to identify the surrounding environment and status of the vehicle. Based on the environmental information obtained (such as road information, traffic information, vehicle location and obstacle information, etc.), the system autonomously makes analysis and judgments to autonomously control the vehicle's movement. The autonomous driving decision results are used to guide the driving control of the vehicle.

[0069] In summary, in this embodiment, if the target high-precision map corresponding to the current area is not found in the automatic driving mode, it is difficult to know what is behind the obstruction. For example, it is difficult to determine whether the obstruction is the edge of the road or an intersection. Therefore, the automatic driving mode is exited and a prompt to take over the vehicle is initiated, thereby prompting the driver to take over manually. In this way, the safety of automatic driving can be improved.

[0070] See also Figure 2 , Figure 2 Schematic diagram of a road edge recognition device provided by an embodiment of the present invention. The device of this embodiment is applied to a vehicle, such as Figure 2 The apparatus shown may include:

[0071] The acquisition module 210 is used to collect road data within a preset range of the vehicle through a road data acquisition device during the vehicle's driving process; the judgment module 220 is used to judge whether the vehicle's line of sight along the first direction is blocked by an obstacle based on the road data within the preset range collected by the road data acquisition device; the map search module 230 is used to search for a target high-precision map corresponding to the current area where the vehicle is located if the vehicle's line of sight along the first direction is blocked by an obstacle; the identification module 240 is used to determine the road edge recognition result of the vehicle along the first direction using the target high-precision map when the target high-precision map corresponding to the current area is found, and the road edge recognition result is used to indicate whether the vehicle's line of sight along the first direction is a road edge.

[0072] The road edge recognition device provided by the embodiment of the present invention has the same technical features as the road edge recognition method provided by the above embodiment, so it can also solve the same technical problems and achieve the same technical effects. The device of this embodiment can refer to the description of the above method embodiment, and will not be repeated here.

[0073] This embodiment also provides an electronic device, including a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the above road edge recognition method. The electronic device can be a server or a terminal device.

[0074] See also Figure 3As shown, the electronic device includes a processor 100 and a memory 101. The memory 101 stores computer executable instructions that can be executed by the processor 100. The processor 100 executes the computer executable instructions to implement the above-mentioned road edge recognition method.

[0075] Further, Figure 3 The electronic device shown further includes a bus 102 and a communication interface 103 , and the processor 100 , the communication interface 103 and the memory 101 are connected via the bus 102 .

[0076] The memory 101 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 103 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used. The bus 102 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0077] The processor 100 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 100. The above processor 100 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present invention can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 101, and the processor 100 reads the information in the memory 101 and completes the steps of the method of the above embodiment in combination with its hardware.

[0078] The processor in the above electronic device can implement the steps in the above road edge recognition method by executing computer executable instructions.

[0079] This embodiment further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the above-mentioned road edge recognition method.

[0080] The computer-executable instructions stored in the computer-readable storage medium can implement the steps in the road edge recognition method by executing the computer-executable instructions.

[0081] This embodiment also provides a computer program product, including program code. The instructions included in the program code can be used to execute the method in the previous method embodiment. The specific implementation can be found in the method embodiment, which will not be described in detail here.

[0082] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0083] In addition, in the description of the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0084] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0085] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0086] Finally, it should be noted that the above embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above embodiments, those skilled in the art should understand that any person skilled in the art can still modify the technical solutions recorded in the above embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for identifying a road edge, characterized in that: Applied to a vehicle, the vehicle includes at least one road data collection device, and the method includes: During the driving of the vehicle, the road data collection device collects road data within a preset range of the vehicle; Based on the road data within the preset range collected by the road data collection device, determining whether the sight line of the vehicle along the first direction is blocked by an obstacle; If the sight line of the vehicle along the first direction is blocked by the obstacle, searching for a target high-precision map corresponding to the current area where the vehicle is located; When a target high-precision map corresponding to the current area is found, the target high-precision map is used to determine a road edge recognition result of the vehicle along the first direction, and the road edge recognition result is used to indicate whether the vehicle's line of sight along the first direction is a road edge.

2. The method according to claim 1, characterized in that The road data acquisition device includes an image sensor and a laser radar, and judging whether the sight line of the vehicle along the first direction is blocked by an obstacle based on the road data within the preset range acquired by the road data acquisition device includes: Based on the first road data within the preset range collected by the image sensor or the laser radar, determining whether the sight line of the vehicle along the first direction is blocked by an obstacle; If it is determined based on the first road data that the sight line of the vehicle along the first direction is blocked by the obstacle, then based on the second road data within the preset range collected by the other of the image sensor or the laser radar, it is determined whether the sight line of the vehicle along the first direction is blocked by the obstacle; If the sight line of the vehicle along the first direction is blocked by the obstacle, searching for a target high-precision map corresponding to the current area where the vehicle is located, including: If it is determined based on the second road data that the vehicle's line of sight along the first direction is blocked by an obstacle, a target high-precision map corresponding to the current area where the vehicle is located is searched.

3. The method according to claim 2, characterized in that The image sensor is installed at a height lower than the laser radar, and judging whether the sight of the vehicle along the first direction is blocked by an obstacle based on the first road data within the preset range collected by one of the image sensor or the laser radar includes: Based on the image data within the preset range collected by the image sensor, determining whether the sight line of the vehicle along a first direction is blocked by an obstacle, the first road data including the image data; If it is determined based on the first road data that the sight line of the vehicle along the first direction is blocked by the obstacle, then based on the second road data within the preset range collected by the other of the image sensor or the laser radar, determining whether the sight line of the vehicle along the first direction is blocked by the obstacle includes: If it is determined based on the image data that the vehicle's line of sight along the first direction is blocked by the obstacle, then based on the laser data within the preset range collected by the laser radar, it is determined whether the vehicle's line of sight along the first direction is blocked by the obstacle.

4. The method according to claim 3, characterized in that Based on the laser data within the preset range collected by the laser radar, determining whether the sight line of the vehicle along the first direction is blocked by an obstacle includes: Determining an occlusion angle of the image sensor along a first direction due to being blocked by the object; Controlling the laser radar to emit a detection beam within the shielding angle, and receiving a reflected beam within the preset range, wherein the reflected beam is a beam obtained by reflecting the detection beam, and the laser data includes the reflected beam; Based on the reflected light beam, it is determined whether the sight line of the vehicle along the first direction is blocked by an obstacle.

5. The method according to any one of claims 1 to 4, characterized in that The vehicle includes a plurality of storage devices, the plurality of storage devices being used to store target high-precision maps of a plurality of preset areas respectively, and the step of searching for the target high-precision map corresponding to the current area where the vehicle is located includes: Determine a target preset area to which the current area where the vehicle is located belongs, wherein the target preset area is one of the multiple preset areas; Based on the target preset area to which the current area belongs, a target high-precision map corresponding to the current area where the vehicle is located is searched from a storage device corresponding to the target preset area.

6. The method according to any one of claims 1 to 4, characterized in that The target high-precision map is determined in the following way: Acquire an original high-precision map, wherein the original high-precision map includes element information of each area, and the area includes a road area and an intersection area; For the road area in the original high-precision map, some element information of the road area is deleted, and for the intersection area in the original high-precision map, all element information of the intersection area is retained to obtain the target high-precision map.

7. The method according to any one of claims 1 to 4, characterized in that The road edge recognition result is used to determine an autonomous driving decision result in the autonomous driving mode, and the method further includes: If the target high-precision map corresponding to the current area is not found, the automatic driving mode is exited and a prompt to take over the vehicle is initiated.

8. A road edge recognition device, characterized in that: Applied to a vehicle, the vehicle comprises at least one road data collection device, and the road edge recognition device comprises: A collection module, used for collecting road data within a preset range of the vehicle through the road data collection device during the driving of the vehicle; A judgment module, configured to judge whether the sight line of the vehicle along the first direction is blocked by an obstacle based on the road data within the preset range collected by the road data collection device; A map search module, configured to search for a target high-precision map corresponding to a current area where the vehicle is located if the sight line of the vehicle along the first direction is blocked by the obstacle; The identification module is used to determine the road edge identification result of the vehicle along the first direction using the target high-precision map when the target high-precision map corresponding to the current area is found, and the road edge identification result is used to indicate whether the vehicle's line of sight along the first direction is a road edge.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method according to any one of claims 1 to 7.

Images