Lane-level positioning method for high-definition map

Abstract

The application relates to a lane-level positioning method for a high-precision map, comprising the following steps: S1, collecting trajectory point position information of a vehicle in real time through a vehicle-mounted electronic device during driving of the vehicle, and identifying lane marking information of left and right lanes of a lane where the vehicle is located; S2, converting a vector high-precision map stored in the vehicle-mounted electronic device into a double-layer mask raster high-precision map with lane groups and lanes; S3, calculating geometric and transmission probabilities of a vehicle position to a grid high-precision map according to position of a trajectory point and lane marking information of left and right lanes of a current lane; S4, calculating a lane-level map matching result of the vehicle according to the geometric and transmission probabilities, and determining lane-level positioning information of the vehicle. The vehicle can obtain more accurate real-time position services, so as to help a driver or an automatic driving system better understand and predict a driving environment, and has wide applicability and market potential.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving and intelligent transportation technology, and more specifically, to a lane-level positioning method for high-precision maps. Background Technology

[0002] High-precision maps refer to electronic maps with high accuracy, freshness, and richness, covering precise attributes and geometric information of geographical features such as roads, lanes, and traffic facilities. High-precision maps help vehicles achieve high-precision positioning and obtain road environment information in advance, thereby assisting vehicles in real-time perception and dynamic planning. Lane-level positioning is a key prerequisite for achieving high-precision location services, path planning, and navigation. Existing lane-level positioning methods typically rely on complex environmental perception algorithms to construct local semantic maps and achieve high-precision vehicle positioning through feature matching with high-precision maps. This method not only requires expensive onboard sensors but also consumes significant computing resources, making it suitable only for autonomous vehicles with high computing power. In my country, the number of Level 2 and above autonomous vehicles is increasing year by year, but ordinary vehicles with low computing power still dominate the market, and these two types of vehicles will coexist for a considerable period. Currently, the coverage of high-precision maps in my country exceeds 1.5 million kilometers. Fully utilizing high-precision maps to achieve lane-level positioning for ordinary vehicles with low computing power will help improve road traffic efficiency and reduce energy consumption.

[0003] Existing lane-level localization methods typically require building a local semantic map on the vehicle and achieving high-precision localization through feature matching with a high-definition map. These methods rely on expensive sensors, such as LiDAR and high-resolution cameras, and require processing large amounts of real-time data, resulting in high computational costs and making them unsuitable for ordinary vehicles with limited computing power. Currently, the primary issues are high computational load and low efficiency. Existing map matching methods usually use directed graph methods to describe the map, which is convenient for traditional navigation maps. However, high-definition maps contain a massive amount of lane information data, and using directed graphs to represent high-definition maps leads to excessive computational costs, making it difficult to effectively support batch processing and real-time applications. Summary of the Invention

[0004] The technical problem to be solved by this invention is to provide a lane-level positioning method for high-precision maps, which reduces the demand for computing resources through optimized algorithms, does not rely on expensive sensors, and can achieve efficient and accurate lane-level positioning on ordinary cars with limited computing resources.

[0005] The technical solution adopted by this invention to solve its technical problem is: constructing a lane-level positioning method for high-precision maps, including the following steps:

[0006] S1. During the vehicle's operation, the vehicle's trajectory point location information is collected in real time through on-board electronic equipment, and the lane marking information of the left and right lanes of the vehicle's lane is identified.

[0007] S2. Convert the vector high-precision map stored in the vehicle electronic device into a two-layer masked rasterized high-precision map with lane groups and lanes;

[0008] S3. Based on the location of the trajectory point and the left and right lane markings of the current lane, calculate the geometric probability and transmission probability of the vehicle's position to the grid high-precision map.

[0009] S4. Based on geometric probability and transmission probability, calculate the lane-level map matching result of the vehicle and determine the lane-level positioning information of the vehicle.

[0010] According to the above scheme, in step S1, the vehicle trajectory positioning information collected by the vehicle-mounted electronic device includes the vehicle's horizontal and vertical coordinates in the world coordinate system. The identified left and right lane marking information includes the coordinates of the start and end points of the lane markings in the image coordinate system:

[0011] ,

[0012] In the formula, , These are the x and y coordinates of the starting point of the left lane line, respectively. These are the x and y coordinates of the endpoint of the left lane line, respectively. These are the x and y coordinates of the starting point of the right lane line, respectively. These are the x and y coordinates of the endpoint of the right lane line, respectively.

[0013] According to the above scheme, the method for converting the vector high-precision map stored in the vehicle electronic device into a double-layer mask rasterized high-precision map with lane groups and lanes in step S2 includes the following steps:

[0014] S201. Rasterize the lane groups in the high-precision map, convert each lane group into a grid unit with consistent attributes, define the connectivity between grids using the eight-neighborhood method, and construct the first mask of the rasterized high-precision map, namely the lane group grid layer.

[0015] S202. The lane information in the high-precision map is rasterized to form the second layer mask of the raster high-precision map: the lane grid. Each lane is represented as a grid unit in the lane group. The rasterized lane information includes lane type, driving direction and lane restrictions. The lane information is expressed in detail as the attributes of the grid.

[0016] According to the above scheme, in step S3, determining the candidate matching lane group grid and lane grid for vehicle trajectory points includes the following steps:

[0017] S301. Based on the location of the trajectory point, search for lane group grids and lane grids within a range of 0-30m around the trajectory point, and add them to the candidate matching lane group and lane set;

[0018] S302. Calculate the azimuth angle of the trajectory based on the positions of the preceding and following trajectory points. The calculation formula is as follows:

[0019]

[0020] In the formula, The azimuth angle of the trajectory point. For the first The x and y coordinates of each trajectory point For the previous trajectory point The x and y coordinate values;

[0021] S303. Calculate the angle difference between the trajectory azimuth angle and the candidate lane, and delete the lane groups and lanes in the candidate matching lane groups and lane sets whose difference from the trajectory azimuth angle is greater than the threshold of 120°.

[0022] S304. Calculate the geometric probability between the vehicle and each candidate lane group and lane based on the position information, direction information and left and right lane marking information of the vehicle trajectory point;

[0023] S305. Calculate the transmission probability between candidate matching lane group grids of the preceding and following trajectory points.

[0024] According to the above scheme, the method for calculating the geometric probability between the vehicle and each candidate lane group and lane based on the position information, direction information and left and right lane marking information of the vehicle trajectory point in step S304 includes the following steps:

[0025] S304a, Calculating vehicle trajectory Position and candidate grid Vertical distance between lane center points The probability density function of a zero-mean Gaussian distribution is used to measure the distance similarity probability between the vehicle trajectory position and the candidate lane. The specific formula is as follows:

[0026]

[0027] In the formula, This represents the probability of distance similarity. Indicates the number of the trajectory point. Indicates the candidate grid number, Represents trajectory points Position and candidate lane grid The vertical distance between the center points The standard deviation of vehicle positioning error;

[0028] S304b. The similarity between the trajectory direction and the driving direction between the candidate lane grid is calculated using a cosine probability function. The specific formula is as follows:

[0029]

[0030] In the formula, This represents the probability of directional similarity. Indicates the first The trajectory and the first The angle between the candidate lane grids;

[0031] S304c, based on the left and right lane marking information collected by electronic equipment. , The slope of the left and right lane markings is calculated using the following formula:

[0032]

[0033]

[0034] In the formula, The slope of the left lane marking. The slope of the right lane marking;

[0035] S304a. Based on the slope of the lane markings on both the left and right sides, obtain the ratio of the distance from the vehicle to the left lane line to the total lane width. The specific formula is as follows:

[0036]

[0037] S304d, using lane width information provided by high-precision maps and ratio Calculate the vehicle's position within the lane. The specific formula is as follows:

[0038] ;

[0039] S304e. Based on the changes in the vehicle's lateral position, calculate the vehicle's lateral position within the overall road network. Specifically: output the lane the vehicle was in when it started, and calculate the vehicle's lateral position within the current lane. If the vehicle's lateral position gradually increases and then suddenly decreases, and the jump distance exceeds a threshold, it is considered that the vehicle has changed lanes to the right, and the vehicle's lateral displacement within the overall road network is increased by one lane width from its original position. If the vehicle's lateral position gradually decreases and then suddenly increases, and the jump distance exceeds a threshold, it is considered that the vehicle has changed lanes to the left, and the vehicle's lateral displacement within the overall road network is decreased by one lane width from its original position, thus obtaining the vehicle's lateral position within the overall road network. Then, the probability of matching the vehicle position with different lane grids is measured by the lateral deviation probability, and the specific formula is as follows:

[0040]

[0041] In the formula, Lateral deviation of the candidate lane grid centerline The standard deviation of the lateral deviation from the model error. This represents the probability of lateral deviation.

[0042] S304f, Obtain the distance similarity probability between the vehicle trajectory point and the candidate grid lane. Probability of directional similarity lateral deviation probability Then, calculate the overall geometric probability. The specific formula is as follows:

[0043] .

[0044] According to the above scheme, the specific steps in step S305 for calculating the transmission probability between candidate matching lane group grids of previous and subsequent trajectory points are as follows:

[0045] S305a, First, calculate the points on the preceding and following trajectories using the distance formula. and The distance between them is calculated using the following formula:

[0046]

[0047] In the formula, For trajectory points x and y coordinates For trajectory points The x and y coordinates;

[0048] S305b: The distance between candidate lane group grids for preceding and following trajectory points is calculated using the A* algorithm, with the specific formula as follows:

[0049]

[0050] In the formula, For the first The first trajectory point A grid of candidate matching lane groups For the first The first grid One candidate matching lane group grid;

[0051] S305c, Calculate the trajectory points before and after. and The distance between them and the candidate matching lane group grid , Distance between Differences The specific formula is as follows:

[0052]

[0053] S305d, finally, based on the difference in distance between trajectory points and candidate lane group grids... Calculate the overall transmission probability The specific formula is as follows:

[0054]

[0055] In the formula, Current trajectory point Candidate matching lane group grid, For the previous trajectory point Candidate matching lane group grid.

[0056] According to the above scheme, in step S4, the specific steps for calculating the lane-level map matching result of the vehicle based on geometric probability and transmission probability, and determining the lane-level positioning information of the vehicle are as follows:

[0057] S401, the vehicle's trajectory points Matching lane grids with its candidates With grid group The geometric probability and transmission probability are multiplied together, and the lane grid corresponding to the maximum value is taken as the final lane-level matching result for the vehicle. The specific formula is as follows:

[0058] ;

[0059] S402. Based on the lane-level matching results of the vehicle, utilize the vehicle trajectory projection points... The lane-level positioning result of the vehicle is calculated within the matched lane, using the following formula:

[0060]

[0061]

[0062] In the formula, Projection points x and y coordinates It is the lane azimuth angle provided by the high-precision map.

[0063] The lane-level positioning method for high-precision maps according to the present invention has the following advantages:

[0064] 1. This invention is based on the location information collected by the vehicle electronic device and the left and right lane line information of the current lane of the vehicle. Combined with the representation method of the gridded high-precision map, lane-level map matching is realized on low computing power devices, which significantly reduces the demand for computing resources. Ordinary vehicles do not need to be equipped with expensive hardware devices to complete accurate lane-level positioning efficiently. This lays the foundation for the widespread application of high-precision maps. In particular, in intelligent transportation systems, lane-level navigation and control can be realized in an economical and efficient manner.

[0065] 2. The map matching technology of the present invention enables vehicles to perform more accurate lane-level path planning with the support of high-precision maps. This means that the vehicle can adjust its driving path in real time according to the current lane and the actual conditions of the road ahead, thereby improving driving safety and efficiency. This is of great significance for realizing autonomous driving and assisted driving, and can effectively cope with complex road environments, especially in scenarios such as multi-lane highways or complex urban intersections.

[0066] 3. The vehicle of this invention can obtain more accurate real-time location services, thereby helping the driver or autonomous driving system to better understand and predict the driving environment. This precise lane-level matching and positioning helps avoid traffic accidents caused by lane departure, emergency lane changes, etc., thereby improving the overall safety of road traffic. The vehicle's driving decisions are also more efficient, enabling more rational use of road resources, reducing traffic congestion and optimizing the vehicle's energy consumption performance.

[0067] 4. This invention can be implemented using ordinary vehicle electronic equipment without the need for expensive sensor configurations. It is not only suitable for high-end autonomous vehicles, but also applicable to the driving assistance systems of ordinary vehicles. It has wide applicability and market potential. The low-cost and efficient solution enables high-precision positioning services to benefit more users and promotes the popularization of smart transportation and intelligent driving technologies. Attached Figure Description

[0068] The present invention will be further described below with reference to the accompanying drawings and embodiments. In the accompanying drawings:

[0069] Figure 1This is a flowchart of the lane-level positioning method for high-precision maps according to the present invention;

[0070] Figure 2 This is a schematic diagram of the lane group grid structure of the present invention;

[0071] Figure 3 This is a schematic diagram of the lane grid of the present invention;

[0072] Figure 4 This invention provides a vector high-precision map;

[0073] Figure 5 This is a schematic diagram of the lane group mask of the present invention;

[0074] Figure 6 This is a schematic diagram of the lane mask of the present invention. Detailed Implementation

[0075] To provide a clearer understanding of the technical features, objectives, and effects of the present invention, specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0076] like Figure 1-4 As shown, the lane-level positioning method for high-precision maps of the present invention includes the following steps:

[0077] S1, Lane-level positioning device and data acquisition, specifically:

[0078] An electronic device integrating positioning and visual perception functions is installed on the vehicle's windshield. This device can collect the vehicle's positioning data and visual information of the surrounding environment in real time. During vehicle operation, it collects the vehicle's trajectory point location information in real time and identifies the lane markings of the left and right lanes where the vehicle is located. The electronic device has built-in high-precision vector map information of the road, including lane group information, lane marking information, lane centerline information, and road boundary information. The built-in algorithm of the electronic device can identify the lane markings of the left and right lanes in the vehicle's current lane in real time. The vehicle trajectory positioning information collected by the electronic device includes the vehicle's horizontal and vertical coordinates in a world coordinate system. The identified left and right lane marking information includes the coordinates of the start and end points of the lane markings in the image coordinate system:

[0079] ,

[0080] In the formula, , These are the x and y coordinates of the starting point of the left lane line, respectively. These are the x and y coordinates of the endpoint of the left lane line, respectively. These are the x and y coordinates of the starting point of the right lane line, respectively. These are the x and y coordinates of the endpoint of the right lane line, respectively.

[0081] S2. Rasterize the vector high-precision map stored in the vehicle's electronic equipment, converting it into a two-layer mask high-precision map containing lane group raster layers and lane raster layers; the specific steps are as follows:

[0082] S201. In a high-precision map, one or more lanes perpendicular to the direction of travel on a road are represented as a lane group. The number of lanes within a lane group is constant, and they all have the same direction of travel. To achieve rasterization of the map, the lane groups in the high-precision map are first rasterized, converting each lane group into raster cells with consistent attributes, such as... Figure 2 As shown, the connectivity between graticules is defined using the eight-neighborhood method to ensure that adjacent graticules can correctly represent the spatial structure and topological relationships of lane groups. Finally, the first mask layer of the rasterized high-precision map, namely the lane group graticule layer, is constructed.

[0083] S202. The lane information in the high-precision map is rasterized to form the second layer mask of the raster high-precision map: the lane raster. Each lane is independently represented as a raster unit within the lane group. The rasterized lane information includes attributes such as lane type, driving direction, and lane restrictions. These attributes are expressed in detail as raster attributes, such as... Figure 3 As shown.

[0084] S3. Based on the location of the vehicle trajectory points, the information of the left and right lane markings, and the rasterized high-precision map generated in step 2, first calculate the candidate matching grids for the trajectory points. By analyzing the distance similarity, direction similarity, and lateral deviation probabilities between the trajectory points and each candidate matching grid, the overall geometric probability of the trajectory points and candidate grids is synthesized. Subsequently, by calculating the shortest path between consecutive candidate matching grid groups of trajectory points, the transmission probability between trajectory candidate grids is evaluated. The specific steps are as follows:

[0085] First, determine the candidate matching lane group grid and lane grid for vehicle trajectory points. The specific steps are as follows:

[0086] S301. Based on the location of the trajectory point, search for lane group grids and lane grids within a 30m radius around the trajectory point, and add them to the candidate matching lane group and lane set.

[0087] S302. Calculate the azimuth angle of the trajectory based on the positions of the preceding and following trajectory points. The specific calculation formula is as follows:

[0088]

[0089] In the formula, The azimuth angle of the trajectory point. For the first The x and y coordinates of each trajectory point For the previous trajectory point The x and y coordinates.

[0090] S303. Calculate the angle difference between the trajectory azimuth angle and the candidate lane, and delete the lane groups and lanes in the candidate matching lane groups and lane sets whose angle difference with the trajectory azimuth angle is greater than the threshold of 120°.

[0091] S304. Then, based on the vehicle trajectory point's location information, direction information, and the current lane's left and right lane markings, calculate the geometric probability between the vehicle and each candidate lane group and lane. The specific steps are as follows:

[0092] a. First, calculate the vehicle trajectory. Position and candidate grid Vertical distance between lane center points Then, the probability density of a zero-mean Gaussian distribution is used to measure the distance similarity probability between the vehicle trajectory position and the candidate lane, as shown in the following formula:

[0093]

[0094] In the formula, This represents the probability of distance similarity. Indicates the number of the trajectory point. Indicates the candidate grid number, Represents trajectory points Position and candidate lane grid The vertical distance between the center points This represents the standard deviation of the vehicle positioning error.

[0095] b. Then, the similarity between the trajectory direction and the driving direction between the candidate lane grid is calculated using the cosine probability function. The specific formula is as follows:

[0096]

[0097] In the formula, This represents the probability of directional similarity. Indicates the first The trajectory and the first The angle between the candidate lane grids.

[0098] c. Based on the left and right lane marking information collected by electronic devices , The slope of the left and right lane markings is calculated using the following formula:

[0099]

[0100]

[0101] In the formula, The slope of the left lane marking. The slope of the right lane marking.

[0102] d. Based on the slope of the lane markings on both sides, obtain the ratio of the distance from the vehicle to the left lane line to the total lane width. The specific formula is as follows:

[0103]

[0104] e. Use lane width information provided by high-precision maps and ratio Calculate the vehicle's position within the lane. The specific formula is as follows:

[0105]

[0106] f. Based on the changes in the vehicle's lateral position, calculate the vehicle's lateral position within the overall road network. The specific process is as follows: Output the lane the vehicle was in when it started, and calculate the vehicle's lateral position within the current lane. If the vehicle's lateral position gradually increases and then suddenly decreases, and the jump distance exceeds a threshold, it is considered that the vehicle has changed lanes to the right, and the vehicle's lateral displacement within the overall road network is increased by one lane width from its original position. If the vehicle's lateral position gradually decreases and then suddenly increases, and the jump distance exceeds a threshold, it is considered that the vehicle has changed lanes to the left, and the vehicle's lateral displacement within the overall road network is decreased by one lane width from its original position. This yields the vehicle's lateral position within the overall road network. Then, the probability of matching the vehicle position with different lane grids is measured by the lateral deviation probability, and the specific formula is as follows:

[0107]

[0108] In the formula, Lateral deviation of the candidate lane grid centerline The standard deviation of the lateral deviation from the model error. This represents the probability of lateral deviation.

[0109] g. Obtain the distance similarity probability between the vehicle trajectory point and the candidate grid lane. Probability of directional similarity lateral deviation probability Then, calculate the overall geometric probability. The specific formula is as follows:

[0110]

[0111] S305. Calculate the transmission probability between candidate matching lane group grids of preceding and following trajectory points. The specific steps are as follows:

[0112] 1) First, calculate the points on the trajectory before and after using the distance formula. and The distance between them is calculated using the following formula:

[0113]

[0114] In the formula, For trajectory points x and y coordinates For trajectory points The x and y coordinates.

[0115] 2) The distance between candidate lane group grids of preceding and following trajectory points is calculated using the A* algorithm, with the specific formula as follows:

[0116]

[0117] In the formula, It is the first The first trajectory point A grid of candidate matching lane groups It is the first The first grid A grid of candidate matching lane groups.

[0118] 3) Calculate the points on the previous and next trajectories. and The distance between them and the candidate matching lane group grid , Distance between Differences The specific formula is as follows:

[0119]

[0120] 4) Finally, based on the difference in distance between trajectory points and candidate lane group grids... Calculate the overall transmission probability The specific formula is as follows:

[0121]

[0122] In the formula, Current trajectory point Candidate matching lane group grid, For the previous trajectory point Candidate matching lane group grid.

[0123] S4. Combining the geometric probability and transmission probability between the vehicle trajectory point and the candidate matching grid, select the candidate grid with the highest comprehensive probability value to determine the lane-level map matching result for the vehicle. Based on the matching result, calculate the vehicle's precise positioning information in the corresponding lane. The specific steps are as follows:

[0124] S401, the vehicle's trajectory points Matching lane grids with its candidates With grid group The geometric probability and transmission probability are multiplied together, and the lane grid corresponding to the maximum value is taken as the final lane-level matching result for the vehicle. The specific formula is as follows:

[0125]

[0126] S402. Based on the lane-level matching results of the vehicle, utilize the vehicle trajectory projection points... The lane-level positioning result of the vehicle is calculated within the matched lane, using the following formula:

[0127]

[0128]

[0129] In the formula, Projection points x and y coordinates It is the lane azimuth angle provided by the high-precision map.

[0130] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. A lane-level positioning method for high-precision maps, characterized in that, Includes the following steps, S1. During the vehicle's operation, the vehicle's trajectory point location information is collected in real time through on-board electronic equipment, and the lane marking information of the left and right lanes of the vehicle's lane is identified. S2. Convert the vector high-precision map stored in the vehicle electronic device into a two-layer masked rasterized high-precision map with lane groups and lanes; In a high-precision map, one or more lanes perpendicular to the direction of travel on a road are represented as a lane group. The number of lanes in a lane group is constant and they all have the same direction of travel. S3. Based on the location of the trajectory point and the left and right lane markings of the current lane, calculate the geometric probability and transmission probability of the vehicle's position to the grid high-precision map. Determining candidate matching lane group grids and lane grids for vehicle trajectory points includes the following steps: S301. Based on the location of the trajectory point, search for lane group grids and lane grids within a range of 0-30m around the trajectory point, and add them to the candidate matching lane group and lane set; S302. Calculate the azimuth angle of the trajectory based on the positions of the preceding and following trajectory points. The calculation formula is as follows: In the formula, The azimuth angle of the trajectory point. For the first The x and y coordinates of each trajectory point For the previous trajectory point The x and y coordinate values; S303. Calculate the angle difference between the trajectory azimuth angle and the candidate lane, and delete the lane groups and lanes in the candidate matching lane groups and lane sets whose difference from the trajectory azimuth angle is greater than the threshold of 120°. S304. Calculate the geometric probability between the vehicle and each candidate lane group and lane based on the position information, direction information and left and right lane marking information of the vehicle trajectory point; S305. Calculate the transmission probability between candidate matching lane group grids of the preceding and following trajectory points; S4. Based on geometric probability and transmission probability, calculate the lane-level map matching result of the vehicle and determine the lane-level positioning information of the vehicle.

2. The lane-level positioning method for high-precision maps according to claim 1, characterized in that, In step S1, the vehicle trajectory positioning information collected by the on-board electronic device includes the vehicle's horizontal and vertical coordinates in the world coordinate system. The identified left and right lane marking information includes the coordinates of the start and end points of the lane markings in the image coordinate system: , In the formula, , These are the x and y coordinates of the starting point of the left lane line, respectively. These are the x and y coordinates of the endpoint of the left lane line, respectively. These are the x and y coordinates of the starting point of the right lane line, respectively. These are the x and y coordinates of the endpoint of the right lane line, respectively.

3. The lane-level positioning method for high-precision maps according to claim 1, characterized in that, In step S2, the method for converting the vector high-precision map stored in the vehicle electronic device into a two-layer masked rasterized high-precision map with lane groups and lanes includes the following steps: S201. Rasterize the lane groups in the high-precision map, convert each lane group into a grid unit with consistent attributes, define the connectivity between grids using the eight-neighborhood method, and construct the first mask of the rasterized high-precision map, namely the lane group grid layer. S202. The lane information in the high-precision map is rasterized to form the second layer mask of the raster high-precision map: the lane grid. Each lane is represented as a grid unit in the lane group. The rasterized lane information includes lane type, driving direction and lane restrictions. The lane information is expressed in detail as the attributes of the grid.

4. The lane-level positioning method for high-precision maps according to claim 1, characterized in that, In step S304, the method for calculating the geometric probability between the vehicle and each candidate lane group and lane based on the position information, direction information, and left and right lane marking information of the vehicle trajectory point includes the following steps: S304a, Calculating vehicle trajectory Position and candidate grid Vertical distance between lane center points The probability density function of a zero-mean Gaussian distribution is used to measure the distance similarity probability between the vehicle trajectory position and the candidate lane. The specific formula is as follows: In the formula, This represents the probability of distance similarity. Indicates the number of the trajectory point. Indicates the candidate grid number, Represents trajectory points Position and candidate lane grid The vertical distance between the center points The standard deviation of vehicle positioning error; S304b. The similarity between the trajectory direction and the driving direction between the candidate lane grid is calculated using a cosine probability function. The specific formula is as follows: In the formula, This represents the probability of directional similarity. Indicates the first The trajectory and the first The angle between the candidate lane grids; S304c, based on the left and right lane marking information collected by electronic equipment. , The slope of the left and right lane markings is calculated using the following formula: In the formula, The slope of the left lane marking. The slope of the right lane marking; S304a. Based on the slope of the lane markings on both the left and right sides, obtain the ratio of the distance from the vehicle to the left lane line to the total lane width. The specific formula is as follows: S304d, using lane width information provided by high-precision maps and ratio Calculate the vehicle's position within the lane. The specific formula is as follows: ； S304e. Based on the changes in the vehicle's lateral position, calculate the vehicle's lateral position within the overall road network. Specifically: output the lane the vehicle was in when it started, and calculate the vehicle's lateral position within the current lane. If the vehicle's lateral position gradually increases and then suddenly decreases, and the jump distance exceeds a threshold, it is considered that the vehicle has changed lanes to the right, and the vehicle's lateral displacement within the overall road network is increased by one lane width from its original position. If the vehicle's lateral position gradually decreases and then suddenly increases, and the jump distance exceeds a threshold, it is considered that the vehicle has changed lanes to the left, and the vehicle's lateral displacement within the overall road network is decreased by one lane width from its original position, thus obtaining the vehicle's lateral position within the overall road network. Then, the probability of matching the vehicle position with different lane grids is measured by the lateral deviation probability, and the specific formula is as follows: In the formula, Lateral deviation of the candidate lane grid centerline The standard deviation of the lateral deviation from the model error. This represents the probability of lateral deviation. S304f, Obtain the distance similarity probability between the vehicle trajectory point and the candidate grid lane. Probability of directional similarity lateral deviation probability Then, calculate the overall geometric probability. The specific formula is as follows: 。 5. The lane-level positioning method for high-precision maps according to claim 1, characterized in that, In step S305, the specific steps for calculating the transmission probability between candidate matching lane group grids of preceding and following trajectory points are as follows: S305a, First, calculate the points on the preceding and following trajectories using the distance formula. and The distance between them is calculated using the following formula: In the formula, For trajectory points x and y coordinates For trajectory points The x and y coordinates; S305b: The distance between candidate lane group grids for preceding and following trajectory points is calculated using the A* algorithm, with the specific formula as follows: In the formula, For the first The first trajectory point A grid of candidate matching lane groups For the first The first grid One candidate matching lane group grid; S305c, Calculate the trajectory points before and after. and The distance between them and the candidate matching lane group grid , Distance between Differences The specific formula is as follows: S305d, finally, based on the difference in distance between trajectory points and candidate lane group grids... Calculate the overall transmission probability The specific formula is as follows: In the formula, Current trajectory point Candidate matching lane group grid, For the previous trajectory point Candidate matching lane group grid.

6. The lane-level positioning method for high-precision maps according to claim 1, characterized in that, In step S4, the specific steps for calculating the lane-level map matching result of the vehicle based on geometric probability and transmission probability, and determining the lane-level positioning information of the vehicle, are as follows: S401, the vehicle's trajectory points Matching lane grids with its candidates With grid group The geometric probability and transmission probability are multiplied together, and the lane grid corresponding to the maximum value is taken as the final lane-level matching result for the vehicle. The specific formula is as follows: ； S402. Based on the lane-level matching results of the vehicle, utilize the vehicle trajectory projection points... The lane-level positioning result of the vehicle is calculated within the matched lane, using the following formula: In the formula, Projection points x and y coordinates It is the lane azimuth angle provided by the high-precision map.

Images