A vehicle control method, apparatus, device, and storage medium

Abstract

The application discloses a vehicle control method, device, equipment and storage medium, comprising: determining a candidate area distance between a vehicle driving position and a candidate intersection area according to the vehicle driving position and intersection position information of the candidate intersection area recorded in a high-definition map; determining whether a target intersection area corresponding to the vehicle driving position exists in the candidate intersection area according to the candidate area distance; if yes, reading a target area map of the target intersection area from the high-definition map, and determining a vehicle navigation route based on the target area map and vehicle sensing information after determining that the vehicle enters the target intersection area, and controlling the vehicle to drive based on the vehicle navigation route. The application can save mapping resources, improve the navigation control efficiency of the vehicle while ensuring the accuracy of the vehicle navigation route.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of computers, and in particular, to a vehicle control method, device, equipment and storage medium. BACKGROUND

[0002] At present, when the L3 and above level automatic driving vehicles are navigated and controlled in the industry, the high-precision map is relied on to a certain extent to realize the navigation path planning and vehicle control of the automatic driving vehicle. The main reason is that the high-precision map can provide super-range environmental perception information, which provides a reference basis for the navigation path planning and vehicle control of the vehicle. However, since most of the scenes do not have complex intersections, they are all along a single road to drive forward. In this case, even if the high-precision map is not used, the navigation path of the vehicle can be planned only by relying on the sensing results of the vehicle camera, radar and other sensors. At this time, the lane line information provided by the high-precision map provides little help for the navigation path planning, and the lane line occupies the largest proportion of the map in the high-precision map data. Therefore, the existing vehicle navigation control method has certain limitations and resource waste in using the high-precision map. Based on the above problems, how to save the resources occupied by the high-precision map while ensuring the accuracy of the vehicle navigation route is a problem to be solved. SUMMARY

[0003] The present application provides a vehicle control method, device, equipment and storage medium, which can save map drawing resources, improve the navigation control efficiency of the vehicle while ensuring the accuracy of the vehicle navigation route.

[0004] According to an aspect of the present application, a vehicle control method is provided, comprising:

[0005] According to the vehicle driving position and the intersection position information of the candidate intersection area recorded in the high-precision map, a candidate area distance between the vehicle driving position and the candidate intersection area is determined;

[0006] According to the candidate area distance, it is determined whether there is a target intersection area corresponding to the vehicle driving position in the candidate intersection area;

[0007] If yes, the target area map of the target intersection area is read from the high-precision map, and after it is determined that the vehicle enters the target intersection area, the vehicle navigation route is determined based on the target area map and the vehicle sensing information, and the vehicle is controlled to drive based on the vehicle navigation route.

[0008] According to another aspect of the present application, a vehicle control device is provided, which comprises:

[0009] a candidate region distance determination module, configured to determine a candidate region distance between the vehicle driving position and a candidate intersection region according to the vehicle driving position and intersection position information of the candidate intersection region recorded in the high-definition map;

[0010] a target intersection region determination module, configured to determine whether a target intersection region corresponding to the vehicle driving position exists in the candidate intersection region according to the candidate region distance;

[0011] a vehicle navigation route determination module, configured to read a target region map of the target intersection region from the high-definition map if the target intersection region exists, and determine a vehicle navigation route based on the target region map and vehicle sensing information after determining that the vehicle enters the target intersection region, and control the vehicle to drive based on the vehicle navigation route.

[0012] According to another aspect of the present application, an electronic device is provided, which comprises:

[0013] at least one processor; and

[0014] a memory connected with the at least one processor in communication; wherein,

[0015] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the vehicle control method according to any one of the embodiments of the present application.

[0016] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to execute the vehicle control method according to any one of the embodiments of the present application when executed by the processor.

[0017] The technical scheme of the embodiment of the present application determines the candidate region distance between the vehicle driving position and the candidate intersection region according to the vehicle driving position and the intersection position information of the candidate intersection region recorded in the high-precision map; determines whether the target intersection region corresponding to the vehicle driving position exists in the candidate intersection region according to the candidate region distance; and determines whether the target intersection region corresponding to the vehicle driving region exists in the candidate intersection region according to the candidate region distance. The above scheme solves the problem that when a vehicle navigates through a high-precision map, since most driving scenes do not have intersections, the lane line information provided by the high-precision map provides little help in the navigation control of the vehicle when the vehicle drives in the driving region of the non-intersection region, and even can be ignored, and the driving region of the non-intersection region occupies most of the map proportion in the high-precision map data, which causes resource waste. According to the vehicle driving position and the intersection position information of each candidate intersection region in the high-precision map, the above scheme determines whether the vehicle is about to enter the candidate intersection region, and if so, reads the target region map of the target intersection region that the vehicle is about to enter from the high-precision map, determines the vehicle navigation route according to the target region map and the vehicle sensing information, and controls the vehicle driving according to the vehicle navigation route. Only the intersection region needs to be drawn in the high-precision map, thereby saving the map drawing resources, the vehicle is navigated only through the vehicle sensing information in the non-intersection region, and the vehicle is navigated according to the vehicle sensing information and the high-precision map in the intersection region, which can ensure the accuracy of the vehicle navigation route and improve the navigation control efficiency of the vehicle.

[0018] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0020] Figure 1 A flowchart of a vehicle control method provided for the first embodiment of the present application is shown in FIG. 1;

[0021] Figure 2 A flowchart of a vehicle control method provided for the second embodiment of the present application is shown in FIG. 2;

[0022] Figure 3 A flowchart of a vehicle control method provided for the third embodiment of the present application is shown in FIG. 3;

[0023] Figure 4A structural schematic diagram of a vehicle control device provided for Embodiment Four of the present application is shown in the figure;

[0024] Figure 5 A structural schematic diagram of an electronic device provided for Embodiment Five of the present application is shown in the figure. DETAILED DESCRIPTION

[0025] In order to make the personnel in the technical field better understand the present application scheme, the technical scheme in the embodiments of the present application will be described clearly and completely below in combination with the figures in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by the person skilled in the art without making creative efforts should belong to the protection scope of the present application.

[0026] It should be noted that the terms "candidate" and "target" and the like in the specification and claims of the present application and the above-mentioned figures are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "etc." and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0027] Embodiment One

[0028] Figure 1 A flowchart of a vehicle control method provided for Embodiment One of the present application is shown in the figure. The present embodiment can be applicable to the case of controlling a vehicle to travel according to a planned vehicle navigation route, and is particularly applicable to the case of determining a vehicle navigation route according to vehicle sensing information and a target region map of a target intersection region extracted from a high-definition map, and controlling the vehicle to travel according to the planned vehicle navigation route. The method can be executed by a vehicle control device, which can be realized in the form of hardware and / or software, and can be configured in an electronic device. As shown in the figure, the method comprises: Figure 1

[0029] S110, determining a candidate region distance between the vehicle driving position and the candidate intersection region according to the vehicle driving position and the intersection position information of the candidate intersection region recorded in the high-definition map.

[0030] ​The high-definition map is a high-precision map for automatic driving, and contains map elements such as road shape, road marking, traffic sign, and obstacle, and the map precision can reach centimeter level. Most of the scenes do not have complex intersections, and vehicles drive along a single road. In this case, the vehicle driving route can be accurately controlled by only using vehicle sensor data, and the vehicle driving road information provided by the high-definition map cannot provide effective help for the vehicle driving route. Therefore, the high-definition map in the embodiment only contains intersection area information of a candidate intersection area. The candidate intersection area refers to an intersection area of two or more roads. The candidate intersection area includes a road intersection area and an intersection transition area around the road intersection area. For example, the road intersection area can include ramp entrance, ramp exit, cross intersection, T-shaped intersection, Y-shaped intersection, main auxiliary road entrance, exit, roundabout, and the like. For example, a region of one hundred meters square around the road intersection area can be used as the intersection transition area. The vehicle in the embodiment is an automatic driving vehicle, and the vehicle is provided with a high-definition map and a positioning unit, an automatic driving control unit, a camera, a radar sensor, and the like.

[0031] Specifically, the vehicle driving position of the vehicle is determined according to the vehicle positioning device, and the vehicle is an automatic driving vehicle. The intersection position information of the candidate intersection area recorded in the high-definition map is determined, and the candidate intersection area identification of each candidate intersection area is determined. The distance between the vehicle driving position and the candidate intersection area is used as the candidate area distance.

[0032] S120, whether the target intersection area corresponding to the vehicle driving position exists in the candidate intersection area is determined according to the candidate area distance.

[0033] The target intersection area refers to a candidate intersection area that the vehicle is about to enter.

[0034] Specifically, the minimum area distance is determined from the candidate area distance, and the minimum area distance is the minimum value in the candidate area distance. The minimum area distance is compared with the pre-set area distance threshold value. If the minimum area distance is less than the area distance threshold value, the target intersection area corresponding to the vehicle driving position exists in the candidate intersection area, and the candidate intersection area corresponding to the minimum area distance is the target intersection area corresponding to the vehicle driving position.

[0035] S130, if yes, the target area map of the target intersection area is read from the high-definition map, and after it is determined that the vehicle enters the target intersection area, the vehicle navigation route is determined based on the target area map and the vehicle sensing information, and the vehicle is controlled to drive based on the vehicle navigation route.

[0036] The target area map refers to the high-definition map of the target intersection area. The vehicle sensing information can include radar sensing data and visual sensing data.

[0037] Specifically, if there is a target intersection region corresponding to the vehicle driving position in the candidate intersection region, the candidate intersection region corresponding to the minimum region distance is determined as the target intersection region corresponding to the vehicle driving position, and the target region map of the target intersection region is read from the high-precision map. According to the real-time positioning data of the vehicle, it is determined that the vehicle enters the target intersection region, and according to the target region map, the candidate lane mark and the candidate lane line of the target intersection region are determined. The candidate lane mark can be used to represent the lane in the target intersection region. The lane line can include: single dashed line, single solid line, left dashed right solid line, left solid right dashed line, double dashed line, curb line, guardrail line, double solid line, straight guide lane mark line, left turn guide lane mark line, right turn guide lane mark line and road boundary. According to the vehicle sensing information, the driving region image of the vehicle driving region and the obstacle information of the vehicle driving region are determined. The obstacle can be other vehicles in the vehicle driving region and any object that affects the driving of the vehicle. According to the driving region image and the target region map, the target lane mark of the vehicle driving lane is determined from the candidate lane mark, and the target lane line corresponding to the target lane is determined from the candidate lane line according to the target lane mark. According to the target lane line, the target lane mark, the obstacle information and the target driving address of the vehicle, the driving path of the vehicle is planned, the vehicle navigation route is determined, and the vehicle is controlled to drive based on the vehicle navigation route.

[0038] For example, if there is no target intersection region corresponding to the vehicle driving position in the candidate intersection region, the driving region image of the vehicle driving region is collected by the image collection device, and the image confidence of the driving region image is determined by the perception algorithm; if the image confidence is greater than the confidence threshold, the driving region lane mark and the driving region lane line in the vehicle driving region are determined according to the driving region image, and the target driving lane mark of the vehicle is determined from the driving region lane mark; according to the driving region lane line, the target driving lane mark and the vehicle sensing information, the vehicle navigation route is determined, and the vehicle is controlled to drive based on the vehicle navigation route.

[0039] If the vehicle driving position is far away from each candidate intersection region, the vehicle cannot drive to the candidate intersection region in a short time, and it is determined that there is no target intersection region corresponding to the vehicle driving position in the candidate intersection region. The driving region image can intuitively and clearly display the environmental image information around the vehicle, including the road conditions at the vehicle driving position and the driving region lane line corresponding to the vehicle driving position. The image collection device can be a camera installed on the vehicle.

[0040] Specifically, if the minimum region distance is greater than or equal to the region distance threshold, the target intersection region corresponding to the vehicle driving position does not exist in the candidate intersection region, and the vehicle cannot drive to the candidate intersection region in a short time. According to the driving region image of the vehicle driving region collected by the image collection device. Due to the influence of weather, light, lane line wear, dirt and occlusion and other factors on the perception result of the image collection device, there may be errors between the collected driving region image and the actual driving road information of the vehicle, so the driving region image can be analyzed by a perception algorithm, and the image confidence C_cam of the driving region image is determined according to the analysis result. The higher the image confidence, the more reliable the driving region image. If the image confidence is greater than the preset confidence threshold, the driving region lane mark and the driving region lane line in the vehicle driving region are determined according to the driving region image, and the target driving lane mark of the vehicle is determined from the driving region lane mark according to the driving region image; the obstacle information in the vehicle driving region is determined according to the vehicle sensing information. According to the driving region lane line, the target driving lane mark, the obstacle information and the target driving address of the vehicle, the driving path of the vehicle is planned, the vehicle navigation route is determined, and the vehicle is controlled to drive based on the vehicle navigation route.

[0041] The above scheme provides a method for determining a vehicle navigation route and controlling the vehicle to drive based on the vehicle navigation route when the vehicle driving region is an unrecorded region of the high-precision map. When driving on a non-intersection section, the vehicle can also obtain good vehicle navigation effect by relying on the driving region image to plan the vehicle navigation route, thereby improving the determination efficiency of the vehicle navigation route while ensuring the accuracy of the vehicle navigation route.

[0042] The technical scheme provided by the embodiment determines the candidate region distance between the vehicle driving position and the candidate intersection region according to the vehicle driving position and the intersection position information of the candidate intersection region recorded in the high-definition map, determines whether the target intersection region corresponding to the vehicle driving position exists in the candidate intersection region according to the candidate region distance, and determines whether the target intersection region corresponding to the vehicle driving region exists in the candidate intersection region according to the candidate region distance. The problem that, when a vehicle navigates by using a high-definition map, since most driving scenes do not have intersections, the lane line information provided by the high-definition map provides little help in the navigation control of the vehicle when the vehicle drives in the driving region of the non-intersection region, and even can be ignored, and the driving region of the non-intersection region accounts for most of the map proportion in the high-precision map data, and there is a problem of resource waste. According to the vehicle driving position and the intersection position information of each candidate intersection region in the high-definition map, the above scheme determines whether the vehicle is about to enter the candidate intersection region, if yes, reads the target region map of the target intersection region that the vehicle is about to enter from the high-definition map, determines the vehicle navigation route according to the target region map and the vehicle sensing information, and controls the vehicle driving according to the vehicle navigation route. Only the intersection region needs to be drawn in the high-definition map, thereby saving the map drawing resources, the vehicle is navigated only by using the vehicle sensing information in the non-intersection region, and the vehicle is navigated according to the vehicle sensing information and the high-definition map in the intersection region, so that the navigation control efficiency of the vehicle can be improved while ensuring the accuracy of the vehicle navigation route.

[0043] Embodiment two

[0044] Figure 2 The flowchart of the vehicle control method provided for the second embodiment of the application is optimized on the basis of the above-mentioned embodiments, and an optimal implementation manner of determining the vehicle navigation route based on the target region map and the vehicle sensing information after determining that the vehicle enters the target intersection region is given. Specifically, as shown in the figure, the method comprises the following steps. Figure 2

[0045] S210, determining the candidate region distance between the vehicle driving position and the candidate intersection region according to the vehicle driving position and the intersection position information of the candidate intersection region recorded in the high-definition map.

[0046] S220, determining whether the target intersection region corresponding to the vehicle driving position exists in the candidate intersection region according to the candidate region distance.

[0047] S230, if yes, reading the target region map of the target intersection region from the high-definition map, and determining whether the vehicle enters the target intersection region according to the real-time positioning information of the vehicle.

[0048] ​The vehicle real-time positioning information refers to position information of the vehicle obtained by real-time positioning of the vehicle during vehicle driving. The vehicle real-time positioning information can be obtained by a positioning unit configured on the vehicle.

[0049] Specifically, if the target intersection region corresponding to the vehicle driving position exists in the candidate intersection region, a target region map of the target intersection region is read from the high-definition map to prepare for navigation route planning for the vehicle after the vehicle enters the target intersection region. The vehicle real-time positioning information is obtained according to the positioning unit configured on the vehicle, and whether the vehicle enters the target intersection region is determined according to the vehicle real-time positioning information.

[0050] S240, if yes, a matching region map matched with the vehicle positioning information is determined from the target region map.

[0051] The matching region map refers to a high-definition map of a vehicle driving region corresponding to the vehicle positioning information extracted from the target region map.

[0052] Specifically, if it is determined that the vehicle enters the target intersection region, the vehicle positioning information of the vehicle is obtained in real time, and the vehicle driving region is determined according to the vehicle positioning information. For example, the vehicle driving region can be a circular region with a radius of 20 meters and the vehicle position corresponding to the vehicle positioning information as the center. The corresponding map region of the vehicle driving region is extracted from the target region map as the matching region map matched with the vehicle positioning information.

[0053] S250, determining the target driving lane mark of the vehicle according to the matching region map and a driving region image of the vehicle driving region.

[0054] Specifically, the driving region lane mark in the vehicle driving region is determined according to the matching region map, the driving region image of the vehicle driving region is collected by the image collection device, and the target driving lane mark of the current driving lane of the vehicle is determined from the driving region lane mark according to the driving region image.

[0055] For example, the target driving lane mark of the vehicle can be determined by the following sub-steps:

[0056] S2501, collecting the driving region image of the vehicle driving region by the image collection device, and determining whether the driving region image and the matching region map match.

[0057] Specifically, the driving area image of the vehicle driving area is collected by the image collection device, and whether the driving area image and the matching area map match is determined by the image matching algorithm. For example, the area image similarity of the driving area image and the matching area map can be determined according to the image matching algorithm, and whether the driving area image and the matching area map match is determined according to the area image similarity. If the area image similarity is greater than a preset image similarity threshold, it is determined that the driving area image and the matching area map match. If the area image similarity is less than or equal to the image similarity threshold, it is determined that the driving area image and the matching area map do not match.

[0058] S2502, if not, the image confidence of the driving area image is determined according to the perception algorithm, and the map confidence of the matching area map is determined according to the positioning algorithm.

[0059] Specifically, if the driving area image and the matching area map do not match, the image confidence C_cam of the driving area image is determined according to the perception algorithm, and the map confidence C_map of the matching area map is determined according to the positioning algorithm.

[0060] S2503, according to the image confidence and the map confidence, the reliable area image and the to-be-corrected area image are determined from the driving area image and the matching area map, and the to-be-corrected area image is corrected according to the reliable area image.

[0061] Specifically, the confidence values of the image confidence and the map confidence are compared, and the one with the larger confidence value is taken as the reliable area image, and the one with the smaller confidence value is taken as the to-be-corrected area image. For example, if the image confidence is less than the map confidence, the matching area map is taken as the reliable area image, and the driving area image is taken as the to-be-corrected area image. If the image confidence is greater than the map confidence, the driving area image is taken as the reliable area image, and the matching area map is taken as the to-be-corrected area image. The image correction algorithm is used to correct the to-be-corrected area image according to the reliable area image.

[0062] For example, the step of correcting the to-be-corrected area image according to the reliable area image can be:

[0063] (1) determining the reliable linear road element information in the reliable area image by the automatic driving perception fusion algorithm, and constructing a reliable image matrix according to the reliable linear road element information.

[0064] wherein the reliable linear road element information comprises: a reliable linear road element quantity, a reliable linear road element attribute, and a reliable linear road element distance. The linear road refers to the geometry and size of the road in space, and the linear road is connected by straight lines and various curves, also known as a route. The linear road element attribute can be determined by the lane line on the linear road. For example, the linear road element attribute can be represented by Arabic numerals: 0 represents a single dashed line, 1 represents a single solid line, 2 represents a left dashed and right solid line, 3 represents a left solid and right dashed line, 4 represents a double dashed line, 5 represents a double solid line, 6 represents a curb, 7 represents a guardrail, and 8 represents a virtual road boundary. The linear road element distance refers to the distance between two adjacent linear road elements. The reliability image matrix refers to a matrix used to represent the reliable linear road element information.

[0065] Exemplarily, the total number of lanes in the driving area image of the vehicle driving area collected by the image collection device is denoted as Q cam, and the total number of lanes in the matching area map is denoted as Q map; the target driving lane identification of the vehicle is determined according to the driving area image as S cam, and the target driving lane identification of the vehicle is determined according to the matching area map as S map. When the driving area image and the matching area map are image matched, the definition standard of the lane is unified, and the definition standard of the lane can be that if the distance between two adjacent linear road elements satisfies the lane distance condition, the two adjacent linear road elements are regarded as the road elements on both sides of a lane. The linear road element can include: a lane line, a guardrail, a curb, a natural boundary, and a virtual road boundary, etc. When the target driving lane identification of the vehicle is determined, when the projection of the center point of the rear axle of the vehicle on the ground is located in a certain lane, it is determined that the vehicle is located in the lane, and the driving area lane identification corresponding to the lane is taken as the target driving lane identification. The linear road element information in the driving area image is recorded in the form of a matrix to obtain an image road element matrix, and the image road element matrix can be represented as: (Q cam, S cam, C cam). The linear road element information in the matching area map is recorded in the form of a matrix to obtain a map road element matrix, and the map road element matrix can be represented as: (Q map, S map, C map).

[0066] The image road element matrix in a certain period of time can be an i-row and 3-column array, that is:

[0067] cam[i][3]={{Q_cam_1S_cam_1,C_cam_1},{Q_cam_2,S_cam_2,C_cam_2},……{Q_cam_i,S_cam_i,C_cam_i}}.

[0068] Correspondingly, the map road element matrix in the algorithm time is:

[0069] map[i][3] = { {Q_map_1, S_map_1, C_map_1}, {Q_map_2, S_map_2, C_map_2}, …, {Q_map_i, S_map_i, C_map_i}}.

[0070] The reliability image matrix is an image road element matrix or a map road element matrix.

[0071] Specifically, the number of reliable linear road elements, the attribute of the reliable linear road elements, and the distance of the reliable linear road elements in the reliable region image are determined by the automatic driving perception fusion algorithm. The reliability image matrix is determined according to the number of reliable linear road elements, the attribute of the reliable linear road elements, and the distance of the reliable linear road elements.

[0072] (2) The to-be-corrected linear road element information in the to-be-corrected region image is determined by the automatic driving perception fusion algorithm, and the to-be-corrected image matrix is constructed according to the to-be-corrected linear road element information.

[0073] The to-be-corrected linear road element information includes the number of to-be-corrected linear road elements, the attribute of the to-be-corrected linear road elements, and the distance of the to-be-corrected linear road elements. The to-be-corrected image matrix is an image road element matrix or a map road element matrix.

[0074] Specifically, the number of to-be-corrected linear road elements, the attribute of the to-be-corrected linear road elements, and the distance of the to-be-corrected linear road elements in the to-be-corrected region image are determined by the automatic driving perception fusion algorithm. The to-be-corrected image matrix is determined according to the number of to-be-corrected linear road elements, the attribute of the to-be-corrected linear road elements, and the distance of the to-be-corrected linear road elements.

[0075] (3) According to the matrix difference between the reliability image matrix and the to-be-corrected image matrix, the difference element between the to-be-corrected region image and the reliable region image is determined, and the road element correction function corresponding to the difference element is determined.

[0076] For example, when the number of linear road elements is n, the attribute of each linear road element can be recorded in one-dimensional data as P[n] = {p_1, p_2, …, p_n}, and the distance between each two adjacent linear road elements from left to right can also be represented in the form of one-dimensional array as D[n-1] = {d_1, d_2, …, d_n-1}. When the total number of lanes in the driving region image Q_cam_i is inconsistent with the total number of lanes in the matching region map Q_map_i, if the number of linear road elements in the driving region image is n, based on the above information, the image road element matrix can be represented as:

[0077] Q_cam_rawdata[3][n] = {{n, 0, 0, …, 0}, {cam_p_1, cam_p_2, …, cam_p_n}, {cam_d_1, cam_d_2, …, cam_d_n-1, 0}};

[0078] Correspondingly, if the number of linear road elements in the matching area map is m, based on the above information, the map road element matrix can be represented as:

[0079] Q_map_rawdata[3][m] = {{m, 0, 0, …, 0}, {map_p_1, map_p_2, …, map_p_m}, {map_d_1, map_d_2, …, map_d_m-1, 0}}.

[0080] Subtract Q_cam_rawdata[3][n] and Q_map_rawdata[3][m] to obtain a subtraction matrix, and extract non-zero items from the subtraction matrix as matrix differences between the reliability image matrix and the to-be-corrected image matrix. The difference in the number of linear road elements between the driving area image and the matching area map is denoted as ΔN, and ΔN = n-m; the difference in the attribute of the same road identifier between the driving area image and the matching area map is denoted as ΔP, and ΔP = 0 when cam_p-map_p = 0, otherwise ΔP = 1. The distance deviation between the same two adjacent linear road elements in the driving area image and the matching area map is denoted as ΔD, and ΔD = cam_d-map_d.

[0081] Further, the automatic driving perception fusion algorithm focuses on checking the distance DFL of the vehicle and the leftmost linear road element, the attribute PFL of the leftmost linear road element, the distance DFR of the vehicle and the rightmost linear road element, the attribute PFR of the rightmost linear road element, the distance DL of the vehicle and the left linear road element of the current lane, the attribute PL of the left linear road element of the current lane, the distance DR of the vehicle and the right linear road element of the current lane, and the attribute PR of the right linear road element of the current lane. The current lane is the lane currently driven by the vehicle. When the target driving lane identifier of the vehicle in the driving area image and the target driving lane identifier of the vehicle in the matching area map are inconsistent, the image road element matrix can be represented as:

[0082] S_cam_rawdata[8] = {cam_DFL, cam_PFL, cam_DFR, cam_PFR, cam_DL, cam_PL, cam_DR, cam_PR}.

[0083] Correspondingly, the map road element matrix can be represented as:

[0084] S_map_rawdata[8] = {map_DFL, map_PFL, map_DFR, map_PFR, map_DL, map_PL, map_DR, map_PR}.

[0085] Subtracting S_cam_rawdata[8] from S_map_rawdata[8] obtains road element deviation data, which can be represented as ΔDFL, ΔPFL, ΔDFR, ΔPFR, ΔDL, ΔPL, ΔDR and ΔPR in sequence. ΔN, ΔP and ΔD and the road element deviation data are the difference elements between the to-be-corrected region image and the reliable region image.

[0086] (4) determining a road element correction function according to the difference elements, and correcting the difference elements in the to-be-corrected region image according to the road element correction function.

[0087] For example, the road element correction function is:

[0088] N' = f1(ΔN, ΔP, ΔD);

[0089] P' = f2(ΔN, ΔP, ΔD);

[0090] D' = f3(ΔN, ΔP, ΔD);

[0091] DFL' = f4(ΔDFL, ΔPFL, ΔDFR, ΔPFR, ΔDL, ΔPL, ΔDR, ΔPR);

[0092] PFL' = f5(ΔDFL, ΔPFL, ΔDFR, ΔPFR, ΔDL, ΔPL, ΔDR, ΔPR);

[0093] DFR' = f6(ΔDFL, ΔPFL, ΔDFR, ΔPFR, ΔDL, ΔPL, ΔDR, ΔPR);

[0094] PFR' = f7(ΔDFL, ΔPFL, ΔDFR, ΔPFR, ΔDL, ΔPL, ΔDR, ΔPR);

[0095] DL' = f8(ΔDFL, ΔPFL, ΔDFR, ΔPFR, ΔDL, ΔPL, ΔDR, ΔPR);

[0096] PL' = f9(ΔDFL, ΔPFL, ΔDFR, ΔPFR, ΔDL, ΔPL, ΔDR, ΔPR);

[0097] DR' = f10(ΔDFL, ΔPFL, ΔDFR, ΔPFR, ΔDL, ΔPL, ΔDR, ΔPR);

[0098] PR' = f11(△DFL,△PFL,△DFR,△PFR,△DL,△PL,△DR,△PR);

[0099] The lane total number correction function is Q' = F1(N', P', D').

[0100] The target driving lane mark correction function is S' = F2(DFL', PFL', DFR', PFR', DL', PL', DR', PR').

[0101] N' is the corrected linear road element quantity of the to-be-corrected region image; P' is the linear road element attribute of the to-be-corrected region image; D' is the linear road element distance of the to-be-corrected region image. DFL' is the distance between the vehicle and the leftmost linear road element of the to-be-corrected region image; PFL' is the attribute of the leftmost linear road element of the to-be-corrected region image; DFR' is the distance between the vehicle and the rightmost linear road element of the to-be-corrected region image; PFR' is the attribute of the rightmost linear road element of the to-be-corrected region image; DL' is the distance between the vehicle and the left linear road element of the current lane of the to-be-corrected region image; PL' is the attribute of the left linear road element of the current lane of the to-be-corrected region image; DR' is the distance between the vehicle and the right linear road element of the current lane of the to-be-corrected region image; PR' is the attribute of the right linear road element of the current lane of the to-be-corrected region image. Q' is the total number of lanes of the to-be-corrected region image. S' is the target driving lane mark of the to-be-corrected region image.

[0102] According to the above scheme, the difference between the reliability image matrix constructed according to the reliability linear road element information and the to-be-corrected image matrix constructed according to the to-be-corrected linear road element information is used to determine the difference element and element correction function of the reliability image matrix and the to-be-corrected image matrix, and the difference element in the to-be-corrected region image is corrected according to the element correction function, so that the transition of the vehicle navigation route planning mode can be realized when the vehicle transits from the vehicle driving area not recorded in the high-precision map to the target intersection area recorded in the high-precision map, so as to realize the accurate planning of the vehicle navigation route and improve the accuracy of the vehicle navigation control when the vehicle drives from the vehicle driving area not recorded in the high-precision map to the target intersection area recorded in the high-precision map.

[0103] S2504, when the corrected to-be-corrected region image matches the reliable region image, determining the target driving lane mark of the vehicle according to the reliable region image and the corrected to-be-corrected region image.

[0104] Specifically, the difference elements in the to-be-corrected region image are corrected according to the road element correction function until Q' and S' are consistent with the total number of lanes and the target driving lane mark corresponding to the reliable region image, and it is determined that the corrected to-be-corrected region image matches the reliable region image. The target driving lane mark of the vehicle is determined according to the reliable region image and the corrected to-be-corrected region image.

[0105] Optionally, whether the vehicle drives out of the target intersection region is determined according to the real-time positioning information of the vehicle. If the correction of the to-be-corrected region image is not completed until the vehicle drives out of the target intersection region, the driver can be reminded to take over the vehicle.

[0106] S260, determine the vehicle navigation route according to the vehicle sensing information, the target region map and the target driving lane mark, and control the vehicle to drive based on the vehicle navigation route.

[0107] The technical scheme of the embodiment determines that the vehicle drives into the target intersection region according to the real-time positioning information of the vehicle, and then determines the matching region map matched with the vehicle positioning information according to the target region map, which can avoid invalid reading of the target region map and save network resources. The target driving lane mark of the vehicle is determined according to the matching region map and the driving region image of the vehicle driving region, which can improve the accuracy of the target driving lane mark. The vehicle navigation route is determined according to the vehicle sensing information, the target region map and the target driving lane mark, which can improve the reliability of the vehicle navigation route and thus improve the control accuracy of the vehicle.

[0108] Embodiment three

[0109] Figure 3 A flowchart of a vehicle control method provided by the third embodiment of the application is provided, and the third embodiment is optimized on the basis of the above-mentioned embodiments, and an optimal implementation manner of constructing a high-precision map is given. Specifically, as shown in Figure 3 The method comprises the following steps:

[0110] S310, determine the road intersection region in the standard map, and determine the intersection transition region connected with the road intersection region based on the road intersection region and a preset transition division rule.

[0111] The standard map refers to a map containing all drivable roads of the vehicle. The intersection transition region refers to a region around the intersection position. For example, the preset transition division rule can be to regard a region of 200 meters square around the intersection as the intersection transition region.

[0112] Specifically, the road intersection region can include a ramp entrance, a ramp exit, a crossroad, a T-shaped intersection, a Y-shaped intersection, a main and auxiliary road merging and exiting, and a roundabout, etc. The road intersection region is extracted from the standard map, and the intersection transition region connected with the road intersection region is planned around the road intersection region according to a preset transition region division rule.

[0113] S320, lane line marking is performed on the road intersection region according to a lane line marking rule and a position relationship between the road intersection region and the intersection transition region.

[0114] The lane line marking refers to marking a straight-ahead guide lane marking line, a left-turn guide lane marking line and a right-turn guide lane marking line in the road intersection region.

[0115] Specifically, the straight-ahead guide lane marking line, the left-turn guide lane marking line and the right-turn guide lane marking line are marked in the road intersection region according to the lane line marking rule and the position relationship between the road intersection region and the intersection transition region.

[0116] S330, a candidate intersection region in the standard map is determined according to the marked road intersection region and the intersection transition region, and a high-definition map is generated according to the candidate intersection region.

[0117] Specifically, the road intersection region and the intersection transition region are taken as the candidate intersection region in the standard map, and a fine map of each candidate intersection region is drawn. The fine maps of the candidate intersection regions are integrated to determine the high-definition map, and an intersection region identifier of each candidate intersection region is marked in the high-definition map.

[0118] S340, a candidate region distance between the vehicle driving position and the candidate intersection region is determined according to the vehicle driving position and intersection position information of the candidate intersection region recorded in the high-definition map.

[0119] S350, whether a target intersection region corresponding to the vehicle driving position exists in the candidate intersection region is determined according to the candidate region distance.

[0120] S360, if yes, a target region map of the target intersection region is read from the high-definition map, and after it is determined that the vehicle enters the target intersection region, a vehicle navigation route is determined based on the target region map and vehicle sensing information, and the vehicle is controlled to drive based on the vehicle navigation route.

[0121] The technical scheme of the embodiment provides a method for drawing a high-definition map containing only a candidate intersection region. Since a vehicle can obtain good vehicle navigation effect when driving on a non-intersection section by relying on a driving region image to plan a vehicle navigation route, when a high-definition map is constructed, only a map of an intersection region can be constructed, so that the construction cost of the map is reduced, the construction efficiency of the high-definition map is improved, and subsequent maintenance of the high-definition map is facilitated.

[0122] Embodiment four

[0123] Figure 4 A structural schematic diagram of a vehicle control device provided by the fourth embodiment of the application. The embodiment can be applied to the case that the vehicle is controlled to drive according to the planned vehicle navigation route. As shown in the figure, the vehicle control device comprises a candidate region distance determination module 410, a target intersection region determination module 420 and a vehicle navigation route determination module 430. Figure 4

[0124] The candidate region distance determination module 410 is configured to determine a candidate region distance between the vehicle driving position and the candidate intersection region according to the vehicle driving position and intersection position information of the candidate intersection region recorded in the high-definition map.

[0125] The target intersection region determination module 420 is configured to determine whether there is a target intersection region corresponding to the vehicle driving position in the candidate intersection region according to the candidate region distance.

[0126] The vehicle navigation route determination module 430 is configured to read a target region map of the target intersection region from the high-definition map if the target intersection region exists, and determine a vehicle navigation route based on the target region map and vehicle sensing information after determining that the vehicle drives into the target intersection region, and control the vehicle to drive based on the vehicle navigation route.

[0127] ​The technical scheme provided by the embodiment determines a candidate region distance between the vehicle driving position and the candidate intersection region according to the vehicle driving position and intersection position information of the candidate intersection region recorded in the high-definition map; determines whether the target intersection region corresponding to the vehicle driving position exists in the candidate intersection region according to the candidate region distance; and determines whether the target intersection region corresponding to the vehicle driving region exists in the candidate intersection region according to the candidate region distance. The problem of resource waste is solved, in which, when a vehicle navigates by using a high-definition map, since most driving scenes do not have an intersection, lane line information provided by the high-definition map provides less help or even can be ignored in navigation control of the vehicle when the vehicle drives in a driving region in a non-intersection region, and the driving region in the non-intersection region accounts for most of the map proportion in high-definition map data. According to the vehicle driving position and the intersection position information of each candidate intersection region in the high-definition map, the above scheme determines whether the vehicle is about to drive into the candidate intersection region, and if so, reads a target region map of the target intersection region into which the vehicle is about to drive from the high-definition map, determines a vehicle navigation route according to the target region map and vehicle sensing information, and controls the vehicle to drive according to the vehicle navigation route. Only the intersection region needs to be drawn in the high-definition map, thereby saving map drawing resources, the vehicle is navigated only by using vehicle sensing information in the non-intersection region, and the vehicle is navigated according to the vehicle sensing information and the high-definition map in the intersection region, so that the navigation control efficiency of the vehicle can be improved while ensuring the accuracy of the vehicle navigation route.

[0128] For example, the vehicle navigation route determination module 430 includes:

[0129] The positioning information determination unit is configured to determine, according to the real-time positioning information of the vehicle, whether the vehicle drives into the target intersection region.

[0130] The matching region map determination unit is configured to determine, if so, a matching region map matched with the positioning information of the vehicle from the target region map.

[0131] The target driving lane determination unit is configured to determine, according to the matching region map and the driving region image of the vehicle driving region, a target driving lane mark of the vehicle.

[0132] The vehicle navigation route determination unit is configured to determine a vehicle navigation route according to the vehicle sensing information, the target region map and the target driving lane mark.

[0133] For example, the target driving lane determination unit includes:

[0134] The map matching subunit is configured to collect a driving region image of the vehicle driving region by using an image collection device, and determine whether the driving region image and the matching region map are matched.

[0135] a confidence determination subunit configured to determine, if not, an image confidence of the driving area image according to a perception algorithm, and determine a map confidence of the matching area map according to a localization algorithm;

[0136] an image correction subunit configured to determine, according to the image confidence and the map confidence, a reliable area image and a to-be-corrected area image from the driving area image and the matching area map, and correct the to-be-corrected area image according to the reliable area image;

[0137] a target lane identification determination subunit configured to determine, when the corrected to-be-corrected area image matches the reliable area image, a target driving lane identification of the vehicle according to the reliable area image and the corrected to-be-corrected area image.

[0138] For example, the image correction subunit is specifically configured to:

[0139] determine reliable linear road element information in the reliable area image through an automatic driving perception fusion algorithm, and construct a reliability image matrix according to the reliable linear road element information;

[0140] determine to-be-corrected linear road element information in the to-be-corrected area image through the automatic driving perception fusion algorithm, and construct a to-be-corrected image matrix according to the to-be-corrected linear road element information;

[0141] determine a difference element between the to-be-corrected area image and the reliable area image according to a matrix difference value between the reliability image matrix and the to-be-corrected image matrix;

[0142] determine a road element correction function according to the difference element, and correct the difference element in the to-be-corrected area image according to the road element correction function.

[0143] For example, the vehicle control device further comprises:

[0144] an image confidence determination module configured to determine, if not, a driving area image of a driving area of the vehicle through an image acquisition device, and determine an image confidence of the driving area image through a perception algorithm;

[0145] a lane identification determination module configured to determine, if the image confidence is greater than a confidence threshold, a driving area lane identification and a driving area lane line in the driving area of the vehicle according to the driving area image, and determine a target driving lane identification of the vehicle from the driving area lane identification;

[0146] a navigation route planning module configured to determine a vehicle navigation route according to the driving area lane line, the target driving lane identification and vehicle sensing information, and control the vehicle to drive based on the vehicle navigation route.

[0147] For example, the vehicle control device further comprises:

[0148] a transition region determination module, configured to determine a road intersection region in the standard map, determine a transition region of a road intersection connected to the road intersection region based on the road intersection region and a preset transition region division rule;

[0149] a lane line marking module, configured to mark lane lines of the road intersection region according to a lane line marking rule and a positional relationship between the road intersection region and the transition region of the road intersection;

[0150] a high-definition map generation module, configured to determine a candidate road intersection region in the standard map according to the marked road intersection region and the transition region of the road intersection, and generate a high-definition map according to the candidate road intersection region.

[0151] The vehicle control device provided in this embodiment can be applied to the vehicle control method provided in any of the above embodiments, and has corresponding functions and advantages.

[0152] Embodiment Five

[0153] Figure 5 A structural schematic diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application described and / or claimed in this document.

[0154] As shown in Figure 5 The electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores computer programs that can be executed by the at least one processor 11. The processor 11 can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 12 or loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0155] A plurality of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0156] The processor 11 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the vehicle control method.

[0157] In some embodiments, the vehicle control method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded onto the RAM 13 and executed by the processor 11, one or more steps of the vehicle control method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the vehicle control method by any other appropriate means, such as by means of firmware.

[0158] The various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0159] Computer programs for implementing the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program, when executed, can cause instructions defined in the flow charts and / or block diagrams to be implemented. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, and partially on a remote machine or entirely on a remote machine or server.

[0160] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0161] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0162] The systems and techniques described herein can be implemented in a computing system that includes a back end component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a front end component, e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described herein, or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0163] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0164] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be performed in parallel, in series, or in a different order, and the present disclosure is not limited in this regard.

[0165] The specific embodiments described above are not intended to limit the scope of the present disclosure. Those skilled in the art will understand that various modifications, combinations, sub-combinations, and alternatives can be made to the specific embodiments without departing from the spirit and principles of the present disclosure. Any further modifications, equivalents, and / or alternatives come within the scope of the present disclosure as recited by the claims.

Claims

1. A vehicle control method characterized by, The method comprises the following steps: determining a candidate area distance between the vehicle driving position and a candidate intersection area according to the vehicle driving position and intersection position information of the candidate intersection area recorded in the high-definition map; determining whether a target intersection area corresponding to the vehicle driving position exists in the candidate intersection area according to the candidate area distance; if yes, reading a target area map of the target intersection area from the high-definition map, and determining a vehicle navigation route based on the target area map and vehicle sensing information after determining that the vehicle enters the target intersection area, and controlling the vehicle to drive based on the vehicle navigation route; wherein after determining whether a target intersection area corresponding to the vehicle driving position exists in the candidate intersection area according to the candidate area distance, the method further comprises: if no, collecting a driving area image of the vehicle driving area by an image collection device, and determining an image confidence of the driving area image by a perception algorithm; if the image confidence is greater than a confidence threshold, determining a driving area lane mark and a driving area lane line in the vehicle driving area according to the driving area image, and determining a target driving lane mark of the vehicle from the driving area lane mark; determining a vehicle navigation route according to the driving area lane line, the target driving lane mark and vehicle sensing information, and controlling the vehicle to drive based on the vehicle navigation route.

2. The method of claim 1, wherein, After determining that the vehicle enters the target intersection area, determining a vehicle navigation route based on the target area map and vehicle sensing information comprises: determining whether the vehicle enters the target intersection area according to vehicle real-time positioning information; if yes, determining a matching area map matching the vehicle positioning information from the target area map; determining a target driving lane mark of the vehicle according to the matching area map and a driving area image of the vehicle driving area; determining a vehicle navigation route according to vehicle sensing information, the target area map and the target driving lane mark.

3. The method of claim 2, wherein, Determining a target driving lane mark of the vehicle according to the matching area map and a driving area image of the vehicle driving area comprises: collecting a driving area image of the vehicle driving area by an image collection device, and determining whether the driving area image matches the matching area map; if no, determining an image confidence of the driving area image according to a perception algorithm, and determining a map confidence of the matching area map according to a positioning algorithm; determining a reliable area image and a to-be-corrected area image from the driving area image and the matching area map according to the image confidence and the map confidence, and correcting the to-be-corrected area image according to the reliable area image; when the corrected to-be-corrected area image matches the reliable area image, determining a target driving lane mark of the vehicle according to the reliable area image and the corrected to-be-corrected area image.

4. The method of claim 3, wherein, Correcting the to-be-corrected area image according to the reliable area image comprises: determining reliable linear road element information in the reliable area image by an automatic driving perception fusion algorithm, and constructing a reliability image matrix according to the reliable linear road element information; Determine the to-be-corrected linear road element information in the to-be-corrected region image through an automatic driving perception fusion algorithm, and construct a to-be-corrected image matrix according to the to-be-corrected linear road element information; Determine the difference element between the to-be-corrected region image and the reliable region image according to the matrix difference value between the reliability image matrix and the to-be-corrected image matrix; Determine a road element correction function according to the difference element, and correct the difference element in the to-be-corrected region image according to the road element correction function.

5. The method of claim 1, wherein, Also comprising: Determine a road intersection region in a standard map, determine an intersection transition region connected with the road intersection region based on the road intersection region and a preset transition division rule; According to the lane marking rule and the positional relationship between the road intersection region and the intersection transition region, mark the lane of the road intersection region; According to the marked road intersection region and the intersection transition region, determine a candidate intersection region in the standard map, and generate a high-precision map according to the candidate intersection region.

6. A vehicle control device characterized by comprising: Comprising: A candidate region distance determination module is configured to determine a candidate region distance between a vehicle driving position and a candidate intersection region in a high-precision map according to the vehicle driving position and intersection position information of the candidate intersection region recorded in the high-precision map; A target intersection region determination module is configured to determine whether a target intersection region corresponding to the vehicle driving position exists in the candidate intersection region according to the candidate region distance; A vehicle navigation route determination module is configured to, if yes, read a target region map of the target intersection region from the high-precision map, and determine a vehicle navigation route based on the target region map and vehicle sensing information after determining that the vehicle enters the target intersection region, and control the vehicle to drive based on the vehicle navigation route; The vehicle control device further comprises: An image confidence determination module is configured to, if no, collect a driving region image of a vehicle driving region according to an image collection device, and determine an image confidence of the driving region image through a perception algorithm; A lane identification determination module is configured to, if the image confidence is greater than a confidence threshold, determine a driving region lane mark and a driving region lane line in the vehicle driving region according to the driving region image, and determine a target driving lane mark of the vehicle from the driving region lane mark; A navigation route planning module is configured to determine a vehicle navigation route according to the driving region lane line, the target driving lane mark and vehicle sensing information, and control the vehicle to drive based on the vehicle navigation route.

7. The apparatus of claim 6, wherein, The vehicle navigation route determination module comprises: A positioning information determination unit is configured to determine whether the vehicle enters the target intersection region according to real-time positioning information of the vehicle; A matching region map determination unit is configured to, if yes, determine a matching region map matching the vehicle positioning information from the target region map; A target driving lane determination unit is configured to determine a target driving lane mark of the vehicle according to the matching region map, a driving region image of a vehicle driving region. The vehicle navigation route determining unit is configured to determine a vehicle navigation route according to vehicle sensing information, the target area map and the target driving lane mark.

8. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the vehicle control method according to any one of claims 1-5.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to implement the vehicle control method according to any one of claims 1-5 when executed.

Images