Vehicle positioning method, device, vehicle and storage medium

Abstract

The present application relates to the field of autonomous driving technology, and particularly relates to a vehicle positioning method, device, vehicle, and storage medium. Among them, the method includes the following steps: obtaining the current position of the vehicle and an image of the current road section where the vehicle is located; identifying the image to obtain the first lane center line of the lane where the vehicle is currently located, and calculating the first deviation distance between the vehicle and the first lane center line; matching the current road section according to the current position to obtain a map of the current road section where the vehicle is located, determining the second lane center line of the lane where the vehicle is currently located according to the map, and calculating the second deviation distance between the current position and the second lane center line; correcting the current position according to the first deviation distance and / or the second deviation distance. Thus, it solves the problems that in the case of weak signals in the positioning system in the related art, the vehicle is prone to inaccurate positioning or failure, thereby causing safety accidents and other problems.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and particularly to a vehicle positioning method, device, vehicle, and storage medium. Background Art

[0002] Autonomous vehicles generally use RTK (Real Time Kinematic) positioning to obtain the longitude and latitude information of the vehicle itself, so as to know the specific position of the vehicle on the high-precision map and realize functions such as map navigation or vehicle control. Due to the defects of RTK hardware and the satellite communication method itself, when the vehicle is driving in a tunnel or under a viaduct, there is a probability that the positioning will be inaccurate or ineffective. When this situation occurs, if the autonomous driving system still relies on positioning for navigation or vehicle control, it is very likely to cause traffic accidents such as collisions. Summary of the Invention

[0003] This application provides a vehicle positioning method, device, vehicle, and storage medium to solve the problem that when the positioning system signal is weak in related technologies, the vehicle is prone to inaccurate positioning or failure, thus causing safety accidents and other problems.

[0004] The first aspect of the embodiments of this application provides a vehicle positioning method, including the following steps: obtaining the current position of the vehicle and an image of the current section where the vehicle is located; recognizing the image to obtain the first lane center line of the lane where the vehicle is currently located, and calculating the first deviation distance between the vehicle and the first lane center line; matching the map of the current section according to the current position, determining the second lane center line of the lane where the vehicle is currently located according to the map, and calculating the second deviation distance between the current position and the second lane center line; correcting the current position according to the first deviation distance and / or the second deviation distance.

[0005] According to the above technical means, the embodiments of this application can calculate the deviation distances between the vehicle's current position in the visual perception image and the map and the lane center lines in the image and the map respectively, and correct the vehicle position through the first deviation distance and / or the second deviation distance. Only using the original sensors on the vehicle, without additional cost, it can improve the positioning accuracy in scenarios where positioning is prone to inaccuracy in tunnels and under viaducts, enabling the vehicle to pass smoothly and ensuring the safety and stability of the system.

[0006] Optionally, correcting the current position according to the first deviation distance and / or the second deviation distance includes: respectively determining the number of lanes of the current section of road and the current lane in which the vehicle is located according to the image and the map; if the number of lanes and the current lane determined according to the image and the map are both consistent, correcting the current position by using a first correction method, where the first correction method is: correcting the current position according to the distance difference between the first deviation distance and the second deviation distance; if the number of lanes determined according to the image and the map is consistent and the current lanes are inconsistent, correcting the current position by using a second correction method, where the second correction method is: determining the lane center line of the vehicle on the map according to the first lane center line and correcting the current position according to the first deviation distance; if the number of lanes and the current lane determined according to the image and the map are both inconsistent, correcting the current position according to the correction method of the previous correction cycle.

[0007] According to the above technical means, the embodiment of the present application can judge whether the number of lanes and the current lane on the image and the map are consistent, and use different correction methods for correction to ensure the safety of vehicle driving.

[0008] Optionally, correcting the current position by using the first correction method further includes: detecting whether there is an invalid lane in the lane corresponding to the determined image; if there is an invalid lane and the invalid duration of the invalid lane is less than a preset duration, correcting the current position based on the distance difference of the previous correction cycle, otherwise correcting the current position according to the distance difference of the current cycle.

[0009] According to the above technical means, when there is an invalid lane and the invalid duration is less than the preset duration, the embodiment of the present application corrects based on the distance difference of the previous correction cycle, avoiding incorrect correction due to unstable recognition of lanes in visual perception.

[0010] Optionally, correcting the current position by using the first correction method further includes: identifying whether the vehicle is performing a lane change action; if the vehicle performs a lane change action, correcting the current position based on the distance difference of the previous correction cycle, otherwise correcting the current position according to the distance difference of the current cycle.

[0011] According to the above technical means, in the case of the vehicle changing lanes, the embodiment of the present application corrects based on the distance difference of the previous correction cycle, avoiding correcting the positioning into the wrong lane and ensuring driving safety.

[0012] Optionally, identifying whether the vehicle is performing a lane change action includes: detecting the actual distance between the vehicle and any boundary of the current lane; if the actual distance between the vehicle and any boundary of the current lane is less than a preset distance, it is determined that the vehicle is performing a lane change action, otherwise it is determined that the vehicle is not performing a lane change action, or the lane change has ended.

[0013] According to the above technical means, the embodiment of the present application can determine whether the vehicle is in the process of lane change according to the distance between the vehicle and any boundary of the current lane, so as to correct the vehicle in the lane change process using the distance difference of the previous correction cycle, avoiding correction errors.

[0014] Optionally, before correcting the current position using the first correction method, it further includes: determining whether the distance difference is greater than an error threshold; if the distance difference is greater than the error threshold, no correction action is performed, otherwise the current position is corrected using the first correction method.

[0015] According to the above technical means, when the distance difference is too large in the embodiment of the present application, no correction is performed, avoiding the distance difference being too large due to abnormal visual perception recognition.

[0016] Optionally, correcting the current position according to the correction method of the previous correction cycle includes: obtaining the motion information of the vehicle during driving; calculating the current position of the vehicle according to the motion information of the vehicle, and correcting the current position according to the correction method of the previous correction cycle.

[0017] According to the above technical means, the embodiment of the present application can calculate the actual position of the vehicle through the motion information of the vehicle for position correction, avoiding obvious errors in the correction result caused by correcting when there is an abnormality in visual perception recognition, which has a certain safety hazard.

[0018] Optionally, after correcting the current position according to the first deviation distance and / or the second deviation distance, it further includes: performing filtering processing on the corrected position data to obtain the processed position data.

[0019] According to the above technical means, the embodiment of the present application performs filtering processing on the corrected position data, avoiding the problem that if the original calculated value jitters frequently, it may cause unstable lateral control of the vehicle and has a safety hazard.

[0020] Optionally, after correcting the current position according to the first deviation distance and / or the second deviation distance, it further includes: obtaining the actual duration after the current position is corrected; if the actual duration is greater than a preset duration, the current position of the vehicle is corrected again.

[0021] According to the above technical means, in the embodiment of the present application, it is determined whether the duration after the current position is corrected is greater than a preset duration. When it is greater, it means that the vehicle position has not been accurately corrected and needs to be corrected again to ensure the safety of vehicle driving.

[0022] An embodiment of the second aspect of the present application provides a vehicle positioning device, including: an acquisition module, configured to acquire the current position of the vehicle and an image of the current section where the vehicle is located; a first calculation module, configured to identify the image to obtain a first lane center line of the lane where the vehicle is currently located, and calculate a first deviation distance between the vehicle and the first lane center line; a second calculation module, configured to match the map of the current section according to the current position, determine a second lane center line of the lane where the vehicle is currently located according to the map, and calculate a second deviation distance between the current position and the second lane center line; a correction module, configured to correct the current position according to the first deviation distance and / or the second deviation distance.

[0023] An embodiment of the third aspect of the present application provides a vehicle, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the vehicle positioning method as described in the above embodiment.

[0024] An embodiment of the fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, and the program is executed by a processor to implement the vehicle positioning method as described in the above embodiment.

[0025] Therefore, the present application has at least the following beneficial effects:

[0026] (1) In the embodiment of the present application, the deviation distances between the vehicle and the lane center lines in the visual perception image and the map can be calculated respectively, and the vehicle position is corrected through the first deviation distance and / or the second deviation distance. Only the original sensors on the vehicle are used, without additional cost, and the positioning accuracy can be improved in scenarios where positioning is prone to inaccuracy, such as in tunnels and under viaducts, so that the vehicle can pass smoothly, ensuring the safety and stability of the system.

[0027] (2) In the embodiment of the present application, it can be determined whether the number of lanes in the image and on the map is the same as the current lane, and different correction methods are used for correction to ensure the safety of vehicle driving.

[0028] (3) In the embodiment of the present application, when there is an invalid lane and the invalid duration is less than the preset duration, correction is performed based on the distance difference in the previous correction cycle, avoiding incorrect correction due to unstable lane recognition in visual perception.

[0029] (4) In the case where the vehicle changes lanes, the embodiment of the present application corrects based on the distance difference in the previous correction cycle, avoiding correcting the positioning into the wrong lane and ensuring driving safety.

[0030] (5) The embodiment of the present application can determine whether the vehicle is in the process of changing lanes according to the distance between the vehicle and any boundary of the current lane, and thus correct the vehicle in the process of changing lanes using the distance difference in the previous correction cycle to avoid incorrect correction.

[0031] (6) When the distance difference is too large, the embodiment of the present application does not perform correction to avoid the situation where the distance difference is too large due to abnormal visual perception recognition.

[0032] (7) The embodiment of the present application can calculate the actual position of the vehicle through the motion information of the vehicle and perform position correction, avoiding obvious errors in the correction result caused by performing correction when there is an abnormality in visual perception recognition, which has certain potential safety hazards.

[0033] (8) The embodiment of the present application performs filtering processing on the corrected position data, avoiding the problem that if the original calculated value jitters frequently, it may cause unstable lateral control of the vehicle and pose a potential safety hazard.

[0034] (9) The embodiment of the present application determines whether the duration after the current position correction is greater than the preset duration. When it is greater, it means that the vehicle position has not been accurately corrected and needs to be corrected again to ensure the safety of vehicle driving.

[0035] Additional aspects and advantages of the present application will be given in part in the following description, become obvious in part from the following description, or be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The above and / or additional aspects and advantages of the present application will become obvious and easy to understand from the following description of the embodiments in conjunction with the drawings, where:

[0037] Figure 1 is a flowchart of a vehicle positioning method according to an embodiment of the present application;

[0038] Figure 2 is a schematic diagram of visual perception lane lines according to an embodiment of the present application;

[0039] Figure 3 is a schematic diagram of calculating the second deviation distance according to an embodiment of the present application;

[0040] Figure 4 is a schematic diagram of RTK positioning according to an embodiment of the present application;

[0041] Figure 5Schematic diagram of lane consistency correction provided according to an embodiment of the present application;

[0042] Figure 6 Schematic diagram of lane inconsistency correction provided according to an embodiment of the present application;

[0043] Figure 7 Flow chart of a vehicle positioning method provided according to an embodiment of the present application;

[0044] Figure 8 Example diagram of a vehicle positioning device provided according to an embodiment of the present application;

[0045] Figure 9 Schematic diagram of the structure of a vehicle provided according to an embodiment of the present application. Detailed implementation manners

[0046] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions from beginning to end. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present application, but should not be construed as limiting the present application.

[0047] The vehicle positioning method, device, vehicle and storage medium according to the embodiments of the present application will be described below with reference to the accompanying drawings. In view of the problem that due to the defects of RTK hardware and the satellite communication method itself in the above-mentioned background technology, when the vehicle is driving in a tunnel or under a viaduct, there is a probability that the positioning is inaccurate or fails, leading to traffic accidents such as collisions, the present application provides a vehicle positioning method. In this method, only relying on the original sensors on the autonomous vehicle, without additional cost, it can be realized that in the scenarios where the positioning is prone to inaccuracy under tunnels and viaducts, the autonomous driving system can pass smoothly, ensuring the safety and stability of the system. Thus, the problem that in the related technology, when the signal of the positioning system is weak, the vehicle is prone to inaccurate positioning or failure, thereby causing safety accidents and other problems is solved.

[0048] Specifically, Figure 1 Schematic flow diagram of a vehicle positioning method provided by an embodiment of the present application.

[0049] As Figure 1 shown, the vehicle positioning method includes the following steps:

[0050] In step S101, the current position of the vehicle and the image of the current section where the vehicle is located are acquired.

[0051] Among them, the image of the current position and the current section where the vehicle is located (i.e., visual perception information) can be acquired through a camera, and there is no limitation on this.

[0052] In step S102, the image is recognized to obtain the first lane center line of the lane where the vehicle is currently located, and the first deviation distance between the vehicle and the first lane center line is calculated.

[0053] Among them, the first lane center line is the center line of the lane where the vehicle is located in the visual image, that is, the center line of the visual lane.

[0054] Among them, the first deviation distance refers to the distance from the vehicle to the first lane center line (visual lane center line), and the calculation method is as follows: dist2lane = (leftA0 + righ0) / 2, where leftA0 is the lateral distance from the vehicle to the left lane line, and rightA0 is the lateral distance from the vehicle to the right lane line, both from the visual perception result.

[0055] It should be noted that according to the visual perception information, that is, in the image, information on whether the left lane line, right lane line, left adjacent lane line, and right adjacent lane line of the lane where the vehicle is located are valid can be obtained. For example Figure 2 As shown, if only the left and right lane lines are valid, it can be determined that there is only one lane currently; if the left and right lane lines and the left adjacent lane line are valid, it can be determined that there are at least two lanes currently, and the vehicle is in the rightmost lane; if the left and right lane lines and the right adjacent lane line are valid, it can be determined that there are at least two lanes currently, and the vehicle is in the leftmost lane; if the left and right lane lines and the left and right adjacent lane lines are all valid, it can be determined that there are at least three lanes currently, and the vehicle is in the middle lane.

[0056] In step S103, the map of the current section is matched according to the current position, the second lane center line of the lane where the vehicle is currently located is determined according to the map, and the second deviation distance between the current position and the second lane center line is calculated.

[0057] Among them, the second lane center line is the center line of the lane where the vehicle is located in the map, that is, the center line of the lane in the map.

[0058] Among them, the second deviation distance refers to the distance from the vehicle to the second lane center line (map lane center line), and the calculation method is as follows: Among them, x1, y1, x2, y2 are as Figure 3 shown.

[0059] It should be noted that according to RTK positioning and map information, the vehicle position can be matched to the map data, so as to know how many lanes there are at the vehicle location and which lane the vehicle is in. For example Figure 4 shown.

[0060] In step S104, the current position is corrected according to the first deviation distance and / or the second deviation distance.

[0061] It can be understood that in the embodiments of the present application, the current position of the vehicle can be corrected according to the difference between dist2lane and dist2map to compensate for the problem of inaccurate vehicle positioning.

[0062] In the embodiments of the present application, correcting the current position according to the first deviation distance and / or the second deviation distance includes: determining the number of lanes of the current road section and the current lane where the vehicle is located according to the image and the map respectively; if the number of lanes and the current lane determined according to the image and the map are both the same, the first correction method is adopted to correct the current position, where the first correction method is: correcting the current position according to the distance difference between the first deviation distance and the second deviation distance; if the number of lanes determined according to the image and the map is the same but the current lanes are different, the second correction method is adopted to correct the current position, where the second correction method is: determining the lane center line of the vehicle on the map according to the first lane center line and correcting the current position according to the first deviation distance; if the number of lanes and the current lane determined according to the image and the map are both different, the current position is corrected according to the correction method of the previous correction cycle.

[0063] Among them, the first correction method is: correcting according to the difference between the first deviation distance dist2lane and the second deviation distance dist2map; the second correction method is: correcting according to the first deviation distance dist2lane.

[0064] Among them, correcting the current position according to the correction method of the previous correction cycle includes: obtaining the motion information of the vehicle during driving; calculating the current position of the vehicle according to the motion information of the vehicle, and correcting the current position according to the correction method of the previous correction cycle.

[0065] Specifically, the specific steps for correcting the position of the vehicle are as follows: (1) Obtain the number of lanes of the current road section where the vehicle is located on the image and the map and the current lane where the vehicle is located; (2) If the number of lanes and the current lane obtained on the image and the map are both the same, correct according to the first correction method, that is, correct according to the difference between the first deviation distance dist2lane and the second deviation distance dist2map, as Figure 5 shown; (3) If the number of lanes obtained on the image and the map is the same but the lanes are different, correct according to the first deviation distance dist2lane; (3) If the number of lanes and the current lane obtained on the image and the map are both different, by default, correct according to the correction method of the previous correction cycle, that is, (2) or (3) adopted in the previous cycle.

[0066] In the embodiment of the present application, when using the first correction method to correct the current position, it further includes: detecting whether there is an invalid lane in the lane corresponding to the determined image; if there is an invalid lane and the invalid duration of the invalid lane is less than the preset duration, correcting the current position based on the distance difference in the previous correction period, otherwise correcting the current position according to the distance difference in the current period.

[0067] Among them, the preset duration can be set according to specific circumstances, and there is no limitation on this. For example, it can be set to 10s.

[0068] It should be noted that sometimes the visual perception of lane recognition is not accurate enough. When one of the left and right lanes is invalid, within the preset duration (such as 10s) of the invalid situation, the difference between dist2lane and dist2map in the previous period is used for compensation. When the invalid situation exceeds 10 seconds, no compensation is required.

[0069] In the embodiment of the present application, when using the first correction method to correct the current position, it further includes: identifying whether the vehicle is performing a lane change action; if the vehicle is performing a lane change action, correcting the current position based on the distance difference in the previous correction period, otherwise correcting the current position according to the distance difference in the current period.

[0070] It should be noted that when the vehicle is changing lanes, there may be a situation where the perception of lane change is not synchronized with the map positioning judgment of lane change. If correction is performed at this time, it is possible to correct the positioning into the wrong lane. Therefore, when the vehicle is changing lanes, the difference between dist2lane and dist2map in the previous period should be used for compensation.

[0071] Among them, identifying whether the vehicle is performing a lane change action includes: detecting the actual distance between the vehicle and any boundary of the current lane; if the actual distance between the vehicle and any boundary of the current lane is less than the preset distance, it is determined that the vehicle is performing a lane change action, otherwise it is determined that the vehicle is not performing a lane change action, or the lane change is completed.

[0072] Among them, the preset distance can be set according to specific circumstances, and there is no limitation on this.

[0073] Taking the preset distance of 1.2m as an example, when leftA0 is less than 1.2m and leftA1 is less than 0.1rad, it indicates that the vehicle is changing lanes to the left; when leftA0 is greater than -1.2m and leftA1 is greater than -0.1rad, it indicates that the vehicle is changing lanes to the right; where leftA0 is the lateral distance from the vehicle to the left lane line and leftA1 is the heading angle of the left lane line.

[0074] In the embodiment of the present application, before correcting the current position by using the first correction method, the following steps are further included: determining whether the distance difference is greater than the error threshold; if the distance difference is greater than the error threshold, no correction action is performed, otherwise the current position is corrected by using the first correction method.

[0075] Among them, the error threshold can be set according to specific circumstances, and no limitation is imposed here. For example, it can be greater than 1.5 m.

[0076] It can be understood that in the embodiment of the present application, no compensation is performed when the difference between dist2lane and dist2map is too large. For example, when the difference is greater than 1.5 m, positioning correction should not be performed at this time because it may be caused by abnormal visual perception recognition.

[0077] In the embodiment of the present application, correcting the current position according to the correction method of the previous correction cycle includes: obtaining the motion information during the vehicle driving process; calculating the current position of the vehicle according to the motion information of the vehicle, and correcting the current position according to the correction method of the previous correction cycle.

[0078] It should be noted that when the number of lanes obtained from the image and the map is inconsistent with the current lane where the vehicle is located, first find the center line of the lane where the vehicle is visually judged on the map, and then according to the deviation dist2lane of the vehicle from the visual lane center, correct the vehicle position to the position with a deviation dist2lane relative to the center line of the map lane, as Figure 6 shown. However, due to the instability of the visual perception result, the following special situations need to be specially processed, otherwise the performance cannot meet the vehicle control requirements of the autonomous driving system.

[0079] It should be noted that when the number of lanes recognized by visual perception is inconsistent with the number of lanes on the map, there may be an abnormality in visual perception recognition. If the visual perception result is used to correct the positioning at this time, it may lead to obvious errors in the correction result and there are certain safety hazards. Therefore, in this case, the vehicle motion information needs to be used to calculate the actual positioning position of the vehicle, and the calculation method is as follows:

[0080] dist = v * t

[0081] θ = ω * t

[0082]

[0083]

[0084] Where dist is the vehicle motion distance in this cycle, v is the vehicle speed, t is the time per cycle, θ is the vehicle rotation angle in this cycle, ω is the vehicle angular velocity, x is the vehicle longitudinal motion distance in this cycle, and y is the vehicle lateral motion distance in this cycle.

[0085] It can be understood that when the visually perceived number of lanes is inconsistent with the number of lanes on the map, the correction method of the previous cycle is adopted to avoid jumps in the correction results caused by occasional misidentifications in perception. That is, if the first correction method was used for correction in the previous cycle, the first correction method is also adopted in this cycle; if the second correction method was used for correction in the previous cycle, the second correction method is also adopted in this cycle.

[0086] In the embodiment of the present application, after correcting the current position according to the first deviation distance and / or the second deviation distance, it further includes: performing filtering processing on the corrected position data to obtain processed position data.

[0087] It can be understood that since frequent jitter in the original calculated value may cause unstable lateral control of the vehicle and pose a safety hazard, the embodiment of the present application needs to perform filtering processing on the corrected position data. Among them, the filtering processing method can be low-pass filtering, and the formula is as follows:

[0088] Y(n) = *X(n)+(1 - )*(n - 1)

[0089] Where Y(n) is the filter output value, α is the filtering coefficient, X(n) is the measured value, and Y(n - 1) is the filter output value of the previous cycle.

[0090] In the embodiment of the present application, after correcting the current position according to the first deviation distance and / or the second deviation distance, it further includes: obtaining the actual duration after the current position is corrected; if the actual duration is greater than the preset duration, the current position of the vehicle is corrected again.

[0091] Among them, the preset duration is set according to specific circumstances and is not limited thereto. For example, it can be 10s.

[0092] It can be understood that after the vehicle is corrected, it is also necessary to determine whether the actual duration after the current position of the vehicle is corrected is greater than the preset duration. When it is greater, it means that the vehicle position has not been accurately corrected and needs to be corrected again to ensure the safety of vehicle driving.

[0093] In summary, the vehicle positioning method described in the above embodiments does not require additional sensors related to positioning, has a low cost and is conducive to mass production. In scenarios where satellite signals are interfered, such as under tunnels and viaducts, visual compensation can have a good correction effect on positioning, ensuring the safety and continuity of the automatic driving system and increasing the application range of the automatic driving function.

[0094] As Figure 7 shown, the vehicle positioning method is described below through a specific embodiment, and the steps are as follows:

[0095] 1. Determine the number of current lanes and the lane in which the host vehicle is located by visual perception information;

[0096] 2. Determine the number of current lanes and the lane in which the host vehicle is located by positioning and map;

[0097] 3. Judge whether the lane number information obtained by visual perception is consistent with the lane number information obtained from the map, and whether the lane to which the host vehicle belongs is consistent. If the lane numbers are consistent and the lane to which the host vehicle belongs is also consistent, go to step 4; if the lane numbers are consistent but the lane to which the host vehicle belongs is inconsistent, go to step 5; otherwise, go to step 6;

[0098] 4. Calculate the error distance between the vision and the map from the lane line according to the visual lane line information and the map lane line information, so as to correct the positioning position of the host vehicle;

[0099] 5. First, correct the positioning of the host vehicle to the lane determined by vision, and then correct the positioning to the corresponding map position according to the position of the vision from the lane line;

[0100] 6. When the number of lanes perceived by vision is inconsistent with the number of lanes on the map, by default, adopt the positioning correction method of the previous cycle, that is, step 4 or step 5 adopted in the previous cycle;

[0101] 7. Filter the correction result to ensure the stability of the result, so as to ensure the safety of the automatic driving system.

[0102] The vehicle positioning method proposed according to the embodiments of the present application can calculate the deviation distances of the vehicle's current lane in the visual perception image and the map from the lane centerlines in the image and the map respectively, and correct the vehicle position through the first deviation distance and / or the second deviation distance. By only using the original sensors on the vehicle without additional cost, it can improve the positioning accuracy in scenarios where positioning is prone to inaccuracy, such as in tunnels and under viaducts, enabling the vehicle to pass smoothly and ensuring the safety and stability of the system. It can judge whether the number of lanes on the image and the map and the current lane are the same, and use different correction methods for correction to ensure the safety of vehicle driving. When there is an invalid lane and the invalid duration is less than the preset duration, it can be corrected based on the distance difference in the previous correction cycle to avoid unstable lane recognition in visual perception and incorrect correction. In the case of vehicle lane change, it is corrected based on the distance difference in the previous correction cycle to avoid correcting the position to the wrong lane and ensure driving safety. It can judge whether the vehicle is in the process of lane change according to the distance of the vehicle from any boundary of the current lane, and then correct the vehicle in the lane change process using the distance difference in the previous correction cycle to avoid incorrect correction. When the distance difference is too large, no correction is performed to avoid the distance difference being too large caused by abnormal visual perception recognition. It can calculate the actual position of the vehicle through the vehicle's motion information for position correction to avoid obvious errors in the correction result caused by correction when visual perception recognition is abnormal, which has certain safety hazards. By filtering the corrected position data, it avoids the problem that the vehicle's lateral control may be unstable and pose a safety hazard due to frequent jitter of the original calculated value. By judging whether the duration after the current position correction is greater than the preset duration, when it is greater, it means that the vehicle position has not been accurately corrected and needs to be corrected again to ensure the safety of vehicle driving.

[0103] Next, a vehicle positioning device proposed according to the embodiments of the present application will be described with reference to the accompanying drawings.

[0104] Figure 8 It is a block diagram of the vehicle positioning device according to the embodiments of the present application.

[0105] As Figure 8 shown, the vehicle positioning device 10 includes: an acquisition module 101, a first calculation module 102, a second calculation module 103, and a correction module 104.

[0106] Among them, an acquisition module 101 is configured to acquire the current position of the vehicle and an image of the current road section where the vehicle is located; a first calculation module 102 is configured to identify the image to obtain a first lane center line of the current lane where the vehicle is located, and calculate a first deviation distance between the vehicle and the first lane center line; a second calculation module 103 is configured to match the map of the current road section according to the current position, determine a second lane center line of the current lane where the vehicle is located according to the map, and calculate a second deviation distance between the current position and the second lane center line; a correction module 104 is configured to correct the current position according to the first deviation distance and / or the second deviation distance.

[0107] It should be noted that the foregoing explanation of the vehicle positioning method embodiment also applies to the vehicle positioning device of this embodiment, and will not be elaborated here.

[0108] According to the vehicle positioning device provided by the embodiment of the present application, the deviation distances between the vehicle and the lane center lines in the visual perception image and the map of the current lane where the vehicle is located can be calculated respectively, and the vehicle position can be corrected through the first deviation distance and / or the second deviation distance. Only the original sensors on the vehicle are used, without additional cost, so as to improve the positioning accuracy in scenarios where positioning is prone to inaccuracy, such as in tunnels and under overpasses, and the vehicle can pass smoothly, ensuring the safety and stability of the system; it is possible to ensure the safety of vehicle driving by judging whether the number of lanes in the image and the map is the same as the current lane and using different correction methods for correction; when there is an invalid lane and the invalid duration is less than the preset duration, correction can be performed based on the distance difference in the previous correction cycle, avoiding unstable recognition of lanes in visual perception and incorrect correction; in the case of vehicle lane change, correction is performed based on the distance difference in the previous correction cycle, avoiding correcting the positioning into the wrong lane and ensuring driving safety; it is possible to judge whether the vehicle is in the process of lane change according to the distance between the vehicle and any boundary of the current lane where the vehicle is located, so as to correct the vehicle in the process of lane change using the distance difference in the previous correction cycle and avoid incorrect correction; when the distance difference is too large, no correction is performed to avoid large distance differences caused by abnormal visual perception recognition; the actual position of the vehicle can be calculated through the motion information of the vehicle for position correction, avoiding obvious errors in the correction result due to correction when visual perception recognition is abnormal, which has certain potential safety hazards; by filtering the corrected position data, the problem of potential safety hazards caused by unstable lateral control of the vehicle due to frequent jitter of the original calculated value is avoided; by judging whether the duration after the current position is corrected is greater than the preset duration, if it is greater, it means that the vehicle position has not been accurately corrected and needs to be corrected again to ensure the safety of vehicle driving.

[0109] Figure 9 This is a schematic structural diagram of a vehicle provided by an embodiment of the present application. The vehicle may include:

[0110] A memory 901, a processor 902, and a computer program stored on the memory 901 and executable on the processor 902.

[0111] When the processor 902 executes the program, it implements the vehicle positioning method provided in the above embodiments.

[0112] Furthermore, the vehicle further includes:

[0113] A communication interface 903 for communication between the memory 901 and the processor 902.

[0114] The memory 901 is used to store a computer program executable on the processor 902.

[0115] The memory 901 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0116] If the memory 901, the processor 902, and the communication interface 903 are implemented independently, the communication interface 903, the memory 901, and the processor 902 can be interconnected through a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 9 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0117] Optionally, in a specific implementation, if the memory 901, the processor 902, and the communication interface 903 are integrated on a chip, the memory 901, the processor 902, and the communication interface 903 can communicate with each other through an internal interface.

[0118] The processor 902 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0119] The embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the vehicle positioning method described above is implemented.

[0120] In the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0121] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0122] Any process or method description in the flowchart or described in other ways herein can be understood as representing a module, segment, or part of the code including one or more executable instructions for implementing a customized logic function or process. The scope of the preferred embodiment of the present application includes additional implementations, in which the functions can be executed in a substantially simultaneous manner or in a reverse order according to the involved functions, rather than in the order shown or discussed, which should be understood by those skilled in the art of the embodiments of the present application.

[0123] It should be understood that each part of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following technologies well known in the art can be used: discrete logic circuits with logic gate circuits for implementing logic functions on data signals, application specific integrated circuits with suitable combinational logic gate circuits, programmable gate arrays, field programmable gate arrays, etc.

[0124] Those of ordinary skill in the art can understand that all or part of the steps carried out in implementing the above method embodiments can be completed by a program instructing relevant hardware. The program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0125] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A vehicle positioning method, characterized in that, Including the following steps: Obtain the current position of the vehicle and an image of the current section where the vehicle is located; Identify the first lane center line of the lane where the vehicle is currently located from the image, and calculate the first deviation distance between the vehicle and the first lane center line; Match the map of the current section according to the current position, determine the second lane center line of the lane where the vehicle is currently located according to the map, and calculate the second deviation distance between the current position and the second lane center line; Correct the current position according to the first deviation distance and / or the second deviation distance; The correcting the current position according to the first deviation distance and / or the second deviation distance includes: Determine the number of lanes of the current section where the vehicle is located and the lane where the vehicle is currently located respectively according to the image and the map; If the number of lanes and the lane where the vehicle is currently located determined according to the image and the map are both consistent, correct the current position by using the first correction method, where the first correction method is: correct the current position according to the distance difference between the first deviation distance and the second deviation distance; If the number of lanes determined according to the image and the map is consistent and the lane where the vehicle is currently located is inconsistent, correct the current position by using the second correction method, where the second correction method is: determine the lane center line of the vehicle on the map according to the first lane center line, and correct the current position according to the first deviation distance; If the number of lanes and the lane where the vehicle is currently located determined according to the image and the map are both inconsistent, correct the current position according to the correction method of the previous correction cycle.

2. The method according to claim 1, wherein The correcting the current position by using the first correction method further includes: Detect whether there is an invalid lane in the lane corresponding to the determined image; If there is an invalid lane and the invalid duration of the invalid lane is less than a preset duration, correct the current position based on the distance difference of the previous correction cycle, otherwise correct the current position according to the distance difference of the current cycle.

3. The method according to claim 1, characterized in that The correcting the current position by using the first correction method further includes: Identify whether the vehicle is performing a lane change action; If the vehicle performs a lane change action, correct the current position based on the distance difference of the previous correction cycle, otherwise correct the current position according to the distance difference of the current cycle.

4. The method according to claim 3, wherein The identifying whether the vehicle is performing a lane change action includes: Detect the actual distance between the vehicle and any boundary of the current lane where the vehicle is located; If the actual distance between the vehicle and any boundary of the current lane where the vehicle is located is less than a preset distance, it is determined that the vehicle is performing a lane change action, otherwise it is determined that the vehicle has not performed a lane change action, or the lane change is over.

5. The method according to claim 1, characterized in that, Before correcting the current position by using the first correction method, it further includes: Judge whether the distance difference is greater than an error threshold; If the distance difference is greater than the error threshold, do not perform a correction action, otherwise correct the current position by using the first correction method.

6. The method according to claim 1, wherein The correcting the current position according to the correction method of the previous correction cycle includes: Obtain the motion information of the vehicle during the driving process; Calculate the current position of the vehicle based on the motion information of the vehicle, and correct the current position according to the correction method of the previous correction period.

7. The method according to claim 1, characterized in that After correcting the current position according to the first deviation distance and / or the second deviation distance, it further includes: Perform filtering processing on the corrected position data to obtain the processed position data.

8. The method according to claim 1, wherein After correcting the current position according to the first deviation distance and / or the second deviation distance, it further includes: Obtain the actual duration after the current position is corrected; If the actual duration is greater than the preset duration, correct the current position of the vehicle again.

9. A vehicle positioning device, characterized in that, It includes: An acquisition module for acquiring the current position of the vehicle and an image of the current road section where the vehicle is located; A first calculation module for identifying the image to obtain the first lane center line of the lane where the vehicle is currently located, and calculating the first deviation distance between the vehicle and the first lane center line; A second calculation module for matching the map of the current road section according to the current position, determining the second lane center line of the lane where the vehicle is currently located according to the map, and calculating the second deviation distance between the current position and the second lane center line; A correction module for correcting the current position according to the first deviation distance and / or the second deviation distance; The correcting the current position according to the first deviation distance and / or the second deviation distance includes: Determine the number of lanes of the current road section where the vehicle is located and the lane where the vehicle is currently located according to the image and the map respectively; If the number of lanes and the lane where the vehicle is currently located determined according to the image and the map are both the same, correct the current position by using a first correction method, where the first correction method is: correct the current position according to the distance difference between the first deviation distance and the second deviation distance; If the number of lanes determined according to the image and the map is the same and the lane where the vehicle is currently located is different, correct the current position by using a second correction method, where the second correction method is: determine the lane center line of the vehicle on the map according to the first lane center line, and correct the current position according to the first deviation distance; If the number of lanes and the lane where the vehicle is currently located determined according to the image and the map are both different, correct the current position according to the correction method of the previous correction period.

10. A vehicle, characterized in that, It includes: A memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the program to implement the vehicle positioning method according to any one of claims 1-8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to be used for implementing the vehicle positioning method according to any one of claims 1-8.

Images