Vehicle positioning method, device, electronic device, and storage medium

The vehicle positioning method enhances lane positioning accuracy and stability by using real-time monitoring and recalculating based on vehicle position, sensed road information, and map data, addressing the limitations of existing systems and reducing costs.

JP7578339B2Active Publication Date: 2024-11-06UISEE SHANGHAI AUTOMOTIVE TECH LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
JP2023579429
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2021-06-28
Filing Date
2022-06-01
Publication Date
2024-11-06
Estimated Expiration
2042-06-01

AI Technical Summary

Technical Problem

Existing vehicle positioning systems, such as consumer GPS and RTK, struggle to accurately determine the lane position in complex environments, leading to misjudgments and increased costs, and conventional methods lack stability and interference prevention capabilities.

Method used

A vehicle positioning method that determines the current positioning lane based on vehicle current position information, vehicle sensed road information, and map information, continuously monitors lane positioning through real-time comparisons, and re-determines the lane if a discrepancy integral value exceeds a preset threshold, eliminating the need for high-precision RTK systems.

Benefits of technology

Improves lane positioning stability and anti-interference ability while reducing implementation costs by continuously monitoring lane accuracy and recalculating when necessary, without relying on high-precision RTK systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007578339000001
    Figure 0007578339000001
  • Figure 0007578339000002
    Figure 0007578339000002
  • Figure 0007578339000003
    Figure 0007578339000003
Patent Text Reader

Abstract

The embodiments of the present disclosure relate to a vehicle positioning method, device, electronic device and storage medium, the method includes: determining a current positioning lane according to vehicle current position information, vehicle-sensing road information and map information; comparing the vehicle-sensing road information acquired in real time with the current positioning lane to determine a discrepancy integral value; after determining that the discrepancy integral value is equal to or greater than a preset integral value, returning to determining a positioning lane according to the vehicle current position information, vehicle-sensing road information and map information. The embodiments of the present disclosure improve the stability and anti-interference ability of lane positioning.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] TECHNICAL FIELD The embodiments of the present disclosure relate to the technical field of trailers, and in particular to a vehicle positioning method, device, electronic device, and storage medium.

[0002] <Related Applications> This disclosure claims priority to a Chinese patent application filed with the China Patent Office on June 28, 2021, application number 202110720086.5, titled "Vehicle positioning method, device, electronic device and storage medium," the entire contents of which are incorporated herein by reference. [Background technology]

[0003] Autonomous vehicles have the potential to alleviate traffic congestion, improve traffic efficiency, and free up both hands to improve social productivity, so related technologies are attracting widespread attention. Autonomous vehicles can ensure safe and smooth driving on roads by sensing the surrounding road environment using sensors such as cameras, lidars, and millimeter-wave radar mounted on the vehicle and quickly and accurately acquiring information on the vehicle's position and the positions, sizes, and movement directions of surrounding objects.

[0004] An autonomous driving system needs to accurately determine the position of a vehicle while driving, which is used to plan the driving route. When using a conventional civilian GPS to determine the position of a vehicle, its accuracy can only identify the road on which the vehicle is located, and cannot accurately obtain the lane on which the vehicle is located. This affects the misjudgment of autonomous vehicles on the driving route and the need for lane changes. When using a high-precision positioning device such as RTK (Real Time Kinematic) to obtain an accurate position, it is necessary to rely on the accuracy of high-precision maps, which is costly and has a limited range of use. In addition, conventional lane positioning methods have difficulty in dealing with complex environments such as road conditions with unclear road edges, hidden targets, and changes in light, and have low stability and anti-interference capabilities. Summary of the Invention [Problem to be solved by the invention]

[0005] To solve at least one problem in the prior art, at least one embodiment of the present disclosure provides a vehicle positioning method, an apparatus, an electronic device, and a storage medium. [Means for solving the problem]

[0006] According to a first aspect, an embodiment of the present disclosure provides a vehicle positioning method, comprising: determining a current positioning lane based on vehicle current position information, vehicle-sensed road information and map information; Comparing the vehicle-sensed road information acquired in real time with the currently positioned lane to determine a discrepancy integral value; After determining that the discrepancy integral value is equal to or greater than a preset integral value, returning to and executing a positioning lane based on the vehicle current position information, the vehicle-sensed road information and the map information.

[0007] According to a second aspect, an embodiment of the present disclosure further provides a vehicle positioning device, the vehicle positioning device including: an initialization module used to determine a current positioning lane based on vehicle current position information, vehicle-sensed road information and map information; a positioning monitoring module used to compare the vehicle-sensed road information acquired in real time with the currently positioned lane to determine a discrepancy integral value; and a judgment module for determining whether the discrepancy integral value is equal to or greater than a preset integral value, and if so, for instructing the initialization module to re-perform an operation of determining a current positioning lane based on vehicle current position information, vehicle-sensed road information and map information.

[0008] According to a third aspect, an embodiment of the present disclosure further provides an electronic device comprising a processor and a memory, The processor invokes programs or instructions stored in the memory to perform the steps of the method according to the first aspect.

[0009] According to a fourth aspect, an embodiment of the present disclosure further provides a computer readable storage medium, adapted to store a program or instructions, the program or instructions causing a computer to perform steps of the method according to the first aspect. Effect of the Invention

[0010] In at least one embodiment of the embodiment of the present disclosure, the current positioning lane is first determined based on the vehicle current position information, the vehicle-sensed road information, and the map information line, that is, the initial lane positioning of the vehicle is first performed. Then, the vehicle-sensed road information acquired in real time is compared with the current positioning lane to determine the discrepancy integral value. This step actually performs lane positioning monitoring, analyzes the discrepancy with the current positioning lane based on the vehicle-sensed road information acquired in real time, and determines the discrepancy integral value. If the discrepancy integral value is equal to or greater than the preset integral value, it means that the positioning lane positioning at this time fails and the positioning lane needs to be determined again, and the positioning lane is returned to be determined again based on the vehicle current position information, the vehicle-sensed road information, and the map information. Compared with the prior art, the embodiment of the present disclosure does not need to use RTK high-precision positioning, and the implementation cost is low. In addition, the embodiment of the present disclosure determines the current positioning lane based on the vehicle current position information, vehicle-detected road information, and map information, and then compares the vehicle-detected road information obtained in real time with the current positioning lane to determine a discrepancy integral value, thereby continuously monitoring whether the positioning lane is correct and improving the stability and anti-interference ability of lane positioning. [Brief description of the drawings]

[0011] In order to more clearly describe the technical solutions of the embodiments of the present disclosure, the following briefly describes the accompanying drawings that need to be used in the description of the embodiments or prior art. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and those skilled in the art can obtain other drawings based on these accompanying drawings. [Figure 1] 1 is a schematic flowchart of a vehicle positioning method provided by an embodiment of the present disclosure. [Diagram 2] This is a schematic diagram of two lanes. [Diagram 3] This is a schematic diagram of three lanes. [Figure 4] This is a schematic diagram of a four-lane road. [Diagram 5] This is a schematic diagram of a two-lane road with a moving vehicle on the left. [Figure 6] This is a schematic diagram of a two-lane road with a moving vehicle on the right side. [Figure 7] This is a schematic diagram of a three-lane road with a moving vehicle on the left. [Figure 8] This is a schematic diagram of a three-lane road with a moving vehicle on the right side. [Figure 9] This is a schematic diagram of a road with three lanes and vehicles moving on both the left and right sides. [Figure 10] 4 is a schematic flowchart of another vehicle positioning method provided by an embodiment of the present disclosure. [Figure 11] FIG. 2 is a schematic diagram of lane changing provided by an embodiment of the present disclosure. [Figure 12] FIG. 2 is a structural block diagram of a vehicle positioning device provided by an embodiment of the present disclosure; [Figure 13] FIG. 2 is a structural schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] In order to make the above objects, features and advantages of the present disclosure more clearly understandable, the present disclosure will be described in more detail below in conjunction with the accompanying drawings and examples. It should be understood that the described embodiments are only some of the embodiments of the present disclosure, and are not all of the embodiments. The specific embodiments described herein are used to interpret the present disclosure, and do not limit the present disclosure. Those skilled in the art will recognize that other embodiments obtained based on the described embodiments of the present disclosure are all within the scope of protection of the present disclosure.

[0013] It should be noted that, in this specification, relational terms such as "first," "second," and the like are used only to distinguish one entity or operation from another, and no such actual relationship or order between those entities or operations is necessarily required or implied.

[0014] 1 is a schematic flowchart of a vehicle positioning method provided by an embodiment of the present disclosure. As shown in FIG 1, the vehicle positioning method provided by an embodiment of the present disclosure includes the following steps S110 to S130.

[0015] S110, determining a current positioning lane based on the vehicle current position information, the vehicle-sensed road information and the map information.

[0016] A vehicle is equipped with a positioning device, such as a Global Positioning System (GPS) positioning device or an Inertial Measurement Unit (IMU). The Global Positioning System positioning device can acquire satellite signals, calculate longitude and latitude information in real time, and determine the vehicle's current position information based on the longitude and latitude information. The vehicle's current position information includes, for example, the road on which the vehicle is located and the driving direction. After determining the road on which the vehicle is located and the driving direction, information such as the total number of lanes corresponding to the currently located road and the presence or absence of an emergency lane (hereinafter referred to as a lane model for convenience of explanation) can be read based on map information.

[0017] A collection device may be provided on the vehicle, including but not limited to a camera, a laser lidar, etc. The collection device in this embodiment can collect vehicle-detected road information. The vehicle-detected road information includes but is not limited to detected lane line information, detected guard bar information, and surrounding vehicle information. The detected guard bar information includes, for example, the lateral position, gradient, curvature, and reliability of the guard bar. The detected lane line information includes, for example, the lateral distance, gradient, curvature, line type (solid line, dotted line), and reliability of the lane line. The surrounding vehicle information includes, for example, the longitudinal position, lateral position, and longitudinal vehicle speed of the moving vehicle. The vehicle-detected road information refers to actual road information around the vehicle location acquired by the collection device in real time.

[0018] In the embodiment of the present disclosure, first obtain the vehicle current position information, search for a lane model corresponding to the map information based on the vehicle current position information, and then preliminarily determine which lane of the current lane model the vehicle is located in based on the vehicle-sensing road information. For example, based on the vehicle current position information and the map information, it is determined that the lane model corresponding to the road where the vehicle is currently located is three lanes. The sensed lane line information in the vehicle-sensing road information is, in order, the second left lane line is a solid line, the first left lane line is a dotted line, the first right lane line is a dotted line, and the second right lane line is a solid line. Based on the sensed lane line information and the lane model, it is preliminarily determined that the vehicle is located in the middle lane of the current lane model, that is, the currently positioned lane is the middle lane.

[0019] In some embodiments, the step S110 of determining a current positioning lane based on the vehicle current position information, the vehicle-sensed road information, and the map information includes: S111, generating a lane integral table based on vehicle current position information and map information; S112, determining an integral value of each lane in a lane integral table based on vehicle-sensed road information; S113 includes determining a lane whose integral value in the lane integral table is greater than a first preset value as a positioning lane.

[0020] For example, when it is determined that the total number of current lanes is 3 based on the vehicle current position information and map information, the generated lane integral table is a 3×1 array for storing the integral value of each lane. Based on the vehicle-sensed road information, the lane that satisfies the condition is integrated according to the integration rule, and the integration result is stored in the lane integral table. If a lane integral value in the lane integral table exceeds a first preset value, it is determined that the vehicle is currently located in that lane, and vehicle positioning is completed. If each lane integral value does not exceed the first preset value, the integration is performed continuously.

[0021] In some embodiments, during the process of determining the current positioning lane based on the vehicle current position information, the vehicle-sensed road information, and the map information, the process further includes determining to clear the lane integral table to zero after the number of current lanes is changed.

[0022] In the process of determining the current positioning lane based on the vehicle current position information, vehicle-sensed road information and map information, if the number of current lanes changes, a judgment error will occur if the current positioning lane is determined based on the integral value in the original lane integral table. Therefore, in this embodiment, the lane integral table is cleared to zero after the number of current lanes changes.

[0023] In some embodiments, the vehicle-sensing road information includes sensed lane line information and sensed guard bar information. The step of determining the integral value of each lane in the lane integral table based on the vehicle-sensing road information includes: The method includes determining the number of lanes in the map information corresponding to the vehicle current position information, and determining an integral value of each lane in the lane integral table based on a first integration rule corresponding to the number of lanes, the detected lane line information, and the detected guard bar information.

[0024] For example, based on the vehicle current position information measured by GPS, lane information corresponding to the position is determined from map information, such as the number of lanes, sensed lane line information, guard bar information, etc., to establish a lane integral table. An integral calculation is performed based on the preset first integral rule, the sensed lane line information and the sensed guard bar information to determine the integral value of each lane in the lane integral table.

[0025] The first integration rule is set individually depending on the number of lanes, and may be set, for example, according to the total number of lanes divided into one lane, two lanes, three lanes, and four or more lanes.

[0026] Therefore, since the guard bar detection is not as reliable as the lane lines, the guard bar may not always be detected. Therefore, in the embodiment of the present disclosure, the sensed lane line information and the guard bar information are integrated together.

[0027] The first integration rule corresponding to one lane is as follows: if the vehicle-detected road information recognizes that one lane line is solid and that there is a guard bar on the left side, one lane present is added. If the number of lanes is one, i.e., one lane, the detected lane line information and guard bar information are integrated and integrated. If the vehicle-detected road information recognizes that the right lane line is solid and that there is a guard bar on the left side, one lane present is added.

[0028] The first integration rule corresponding to the number of lanes being two is as follows: if the sensed lane line information and the sensed guard bar information are recognized as the most adjacent lane line on the left being a solid line and the most adjacent lane line on the right being a dotted line, the left lane is added; if the sensed lane line information and the sensed guard bar information are recognized as the most adjacent lane line on the left being a dotted line, the left lane is added; if the sensed lane line information and the sensed guard bar information are recognized as the most adjacent lane line on the right being a solid line and the most adjacent lane line on the left being a dotted line, the right lane is added; if the sensed lane line information and the sensed guard bar information are recognized as the most adjacent lane line on the right being a dotted line, the right lane is added.

[0029] FIG. 2 is a schematic diagram of two lanes, and for illustrative purposes, the left lane of the two lanes is lane 2 and the right lane is lane 1.

[0030] If the sensed lane line information and sensed guard bar information are recognized as showing that the adjacent lane line on the left is a solid line and the adjacent lane line on the right is a dotted line, this means that there is a high consistency that the actual lane in which the vehicle is currently located is the left lane, i.e., lane 2, and the left lane is added.

[0031] If the sensed lane line information and sensed guard bar information are recognized as indicating that there is a guard bar on the left side and that the adjacent lane line on the right side is dotted, this means that there is a high consistency that the actual lane in which the vehicle is currently located is the left lane, i.e., lane 2, and the left lane is added.

[0032] If the sensed lane line information and sensed guard bar information are recognized as showing that the adjacent lane line on the right is a solid line and the adjacent lane line on the left is a dotted line, this means that there is a high consistency that the actual lane in which the vehicle is currently located is the right lane, i.e., lane 1, and the right lane is added.

[0033] If the sensed lane line information and sensed guard bar information are recognized as indicating that there is a guard bar on the right side and that the adjacent lane line on the left side is dotted, this means that there is a high consistency that the actual lane in which the vehicle is currently located is the right lane, i.e., lane 1, and the right lane is added.

[0034] In the above description, the most adjacent lane line on the left side of the vehicle refers to the first left lane line, and the most adjacent lane line on the right side of the vehicle refers to the first right lane line.

[0035] The first integration rule corresponding to the number of lanes being three is as follows: if the sensed lane line information and sensed guard bar information are recognized as the most adjacent lane lines on both the left and right sides being dotted and there being no guard bars, the middle lane is added; if the sensed lane line information and sensed guard bar information are recognized as the most adjacent lane line on the left side being a solid line and the most adjacent lane line on the right side being dotted and there being no right guard bar, the left lane is added; if the sensed lane line information and sensed guard bar information are recognized as the most adjacent lane line on the left side being dotted and there being no right guard bar, the left lane is added;

[0036] FIG. 3 is a schematic diagram of a three-lane road, and for illustrative purposes, the left lane of the three lanes is lane 3, the right lane is lane 1, and the middle lane is lane 2.

[0037] If the sensed lane line information and sensed guard bar information are recognized as indicating that the adjacent lane lines on both the left and right sides are dotted and have no guard bars, this means that there is a high consistency that the actual lane in which the vehicle is currently located is the middle lane, i.e., lane 2, and the middle lane is added.

[0038] If the sensed lane line information and sensed guard bar information are recognized as showing that the adjacent lane line on the left is a solid line, the adjacent lane line on the right is a dotted line, and there is no right guard bar, this means that there is a high consistency that the actual lane in which the vehicle is currently located is the left lane, i.e., lane 3, and the left lane is added.

[0039] If the sensed lane line information and sensed guard bar information are recognized as indicating that there is a guard bar on the left side, the adjacent lane line on the right side is dotted, and there is no right-side guard bar, this indicates that there is a high consistency that the actual lane in which the vehicle is currently located is the left lane, i.e., lane 3, and the left lane is added.

[0040] If the sensed lane line information and sensed guard bar information are recognized as showing that the adjacent lane line on the right is a solid line and the adjacent lane line on the left is a dotted line with no guard bar on the left, this means that there is a high consistency that the actual lane in which the vehicle is currently located is the right lane, i.e., lane 1, and the right lane is added.

[0041] The first integration rule corresponding to a road with four or more lanes is as follows: if the sensed lane line information and sensed guard bar information are recognized as the most adjacent lane line on the left being a solid line and the most adjacent lane line on the right being a dotted line with no right guard bar, the leftmost lane is added; if the sensed lane line information and sensed guard bar information are recognized as the most adjacent lane line on the left being a dotted line with no right guard bar, the leftmost lane is added; if the sensed lane line information and sensed guard bar information are recognized as the most adjacent lane line on the right being a solid line and the most adjacent lane line on the left being a dotted line with no left guard bar, the rightmost lane is added; if the sensed lane line information and sensed guard bar information are recognized as the most adjacent lane lines on both the left and right sides being dotted lines with no guard bars, the sensed lane line information and sensed guard bar information are compared with the lane lines of each intermediate lane, and the intermediate lane that relatively matches is added.

[0042] FIG. 4 is a schematic diagram of a four-lane road, exemplarily designated as lane 1, lane 2, lane 3, and lane 4 from right to left.

[0043] If the sensed lane line information and sensed guard bar information are recognized as showing that the adjacent lane line on the left is a solid line and the adjacent lane line on the right is a dotted line with no right guard bar, this means that there is a high consistency that the actual lane in which the vehicle is currently located is the leftmost lane, i.e., lane 4, and the left lane is added.

[0044] If the sensed lane line information and sensed guard bar information are recognized as indicating that there is a guard bar on the left, the adjacent lane line on the right is a dotted line, and there is no right guard bar, this means that there is a high consistency that the actual lane in which the vehicle is currently located is the leftmost lane, i.e., lane 4, and the left lane is added.

[0045] If the sensed lane line information and sensed guard bar information are recognized as showing that the adjacent lane line on the right is a solid line and the adjacent lane line on the left is a dotted line with no guard bar on the left, this means that there is a high consistency that the actual lane in which the vehicle is currently located is the rightmost lane, i.e., lane 1, and the right lane is added.

[0046] If the sensed lane line information and sensed guard bar information are recognized as indicating that the adjacent lane lines on both the left and right sides are dotted and have no guard bars, this means that there is a high degree of consistency between the actual lane in which the vehicle is currently located and the middle lane, for example, lane 2 or lane 3. The lane line information and sensed guard bar information are compared with the lane lines of each middle lane, and middle lanes that are relatively consistent are added.

[0047] Here, the sensed lane line information and sensed guard bar information are compared with the lane lines of each intermediate lane, and by crossing each intermediate lane, in the example of Fig. 4, the sensed lane line information and sensed guard bar information are compared with the lane lines on both sides of lane 2, and if the comparisons match, lane 2 is added. If there is no match, the sensed lane line information and sensed guard bar information are compared with the lane lines on both sides of lane 3, and if the comparisons match, lane 3 is added. If there is no match, no point is added.

[0048] In the above integration process, the more conditions that are satisfied, the more integration there will be.

[0049] In some embodiments, the vehicle-sensing road information further includes surrounding vehicle information, and determining the number of lanes in the map information corresponding to the vehicle current position information, and determining the integral value of each lane in the lane integral table according to the first integration rule corresponding to the number of lanes, the sensed lane line information, and the sensed guard bar information, and then: The method further includes updating the integral value of each lane in the lane integral table based on a second integral rule corresponding to the number of lanes and the surrounding vehicle information.

[0050] In the embodiment of the present disclosure, the integral value of each lane in the lane integral table is modified according to the detected surrounding vehicle information, the surrounding vehicle information is obtained by a device such as a camera or a laser lidar, and the lanes that satisfy the condition are integrated according to the second integration rule corresponding to the number of lanes, and the integral value of each lane in the lane integral table is updated.

[0051] For example, the second integration rule corresponding to two lanes is as follows: if the surrounding vehicle information is recognized to indicate that there is a moving vehicle on the left and that the lateral distance from the current vehicle is greater than the second preset value, the right lane is added; if the surrounding vehicle information is recognized to indicate that there is a moving vehicle on the right and that the lateral distance from the current vehicle is greater than the second preset value, the left lane is added.

[0052] As shown in FIG. 5, when the surrounding vehicle information is recognized as indicating that there is a moving vehicle on the left side, it means that the moving vehicle is on the left side of the vehicle. When the lateral distance h between the left moving vehicle and the current vehicle is recognized as being greater than the second preset value, it means that the left moving vehicle and the current vehicle are not in the same lane. The second preset value may be set according to the actual road scene. In this case, it means that the real lane in which the current vehicle is located is highly consistent with being located in the right lane, i.e., lane 1, so the right lane is added.

[0053] As shown in Figure 6, when the surrounding vehicle information is recognized as indicating that there is a moving vehicle on the right side, it means that the moving vehicle is on the right side of the vehicle. When the lateral distance h between the vehicle moving on the right side and the current vehicle is recognized as being greater than the second preset value, it means that the vehicle moving on the right side and the current vehicle are not in the same lane. In this case, it means that the actual lane in which the current vehicle is located is highly consistent with being located in the left lane, i.e., lane 2, so the left lane is added.

[0054] The second integration rule corresponding to three or more lanes is as follows: if the surrounding vehicle information is recognized as indicating that there is a moving vehicle on the left and that the lateral distance from the current vehicle is greater than the second preset value, the leftmost lane is deducted; if the surrounding vehicle information is recognized as indicating that there is a moving vehicle on the right and that the lateral distance from the current vehicle is greater than the second preset value, the rightmost lane is deducted; and if the number of lanes is three, if the surrounding vehicle information is recognized as indicating that there are moving vehicles on both the left and right sides and that the lateral distance from the current vehicle is greater than the second preset value, the middle lane is added.

[0055] As shown in Figure 7, taking a three-lane road as an example, if the surrounding vehicle information recognizes that there is a moving vehicle on the left, it means that the moving vehicle is located to the left of the vehicle. If it recognizes that the lateral distance h between the left-hand moving vehicle and the current vehicle is greater than the second preset value, it means that the left-hand moving vehicle and the current vehicle are not in the same lane. Since the current vehicle is unlikely to be located in the leftmost lane, the leftmost lane (lane 3 in Figure 7) is deducted points.

[0056] As shown in Fig. 8, when the surrounding vehicle information is recognized as indicating that there is a moving vehicle on the right side, it means that the moving vehicle is located to the right side of the vehicle. When the lateral distance h between the right-side moving vehicle and the current vehicle is recognized as being greater than the second preset value, it means that the right-side moving vehicle and the current vehicle are not in the same lane. Since the current vehicle is unlikely to be located in the right-most lane, the right-most lane (lane 1 in Fig. 8) is deducted points.

[0057] When the number of lanes exceeds three, if the surrounding vehicle information is recognized as indicating that there are moving vehicles on both the left and right sides and that the lateral distance from the current vehicle is greater than the second preset value, it means that the current vehicle is located in an intermediate lane, but it is unclear which intermediate lane that is. Therefore, as shown in FIG. 9, when the number of lanes is three and there is only one intermediate lane, if the surrounding vehicle information is recognized as indicating that there are moving vehicles on both the left and right sides and that the lateral distance from the current vehicle is greater than the second preset value, it means that the current vehicle is located in the intermediate lane, and the intermediate lane is added.

[0058] During the point deduction process, the lower limit value of the integral value of each lane in the lane integral table is controlled to zero, that is, when the integral value becomes zero, the point deduction operation is not performed.

[0059] In some embodiments, in order to prevent erroneous determination by a sensor (e.g., a camera, a laser rider, etc.) when determining the surrounding vehicle information, after determining that the duration during which the lateral distance between the moving vehicle and the current vehicle is greater than the second preset value is longer than the first preset time, the surrounding vehicle information performs an operation of updating the integral value of each lane in the lane integral table according to the second integral rule corresponding to the number of lanes and the surrounding vehicle information. In this way, erroneous determination caused by short-term fluctuations when the sensor detects data can be avoided.

[0060] S120, comparing the vehicle-sensed road information acquired in real time with the currently positioned lane to determine a discrepancy integral value.

[0061] After completing the preliminary lane positioning of the vehicle, the currently positioned lane is continuously monitored. In this step, vehicle-detected road information is obtained in real time, the vehicle-detected road information obtained in real time is compared with the currently positioned lane determined at a previous time, and a discrepancy integral value is determined according to the comparison result. In this step, a comparison integral rule is set according to actual needs. For example, different comparison integral rules are assigned to different currently positioned lanes, and when the comparison integral rule is met, the discrepancy integral value is increased by 1.

[0062] In some embodiments, comparing the vehicle-sensed road information acquired in real time with the currently positioned lane to determine a discrepancy integral value includes determining the discrepancy integral value based on a third integration rule corresponding to the currently positioned lane and the vehicle-sensed road information acquired in real time.

[0063] The types of the currently positioned lanes correspond to different third integration rules, for example, the left lane, the right lane, and the middle lane correspond to different third integration rules.

[0064] The third integration rule, which corresponds to the case where the current positioning lane is the leftmost lane, is as follows: if the vehicle-sensing road information acquired in real time is recognized as the leftmost adjacent lane line being a dotted line and there being no guard bar on the left side, the discrepancy integration value is increased; if the vehicle-sensing road information acquired in real time is recognized as the guard bar being on the right side and the total number of lanes is greater than 1, the discrepancy integration value is increased.

[0065] The third integration rule, which corresponds to the case where the current positioning lane is the rightmost lane, is as follows: if the vehicle-sensing road information acquired in real time is recognized as the adjacent lane line on the right being a dotted line and there is no guard bar on the right side, the discrepancy integration value is increased; if the vehicle-sensing road information acquired in real time is recognized as the guard bar on the left side and the total number of lanes is greater than 1, the discrepancy integration value is increased.

[0066] The third integration rule corresponding to the case where the current positioning lane is an intermediate lane is as follows: if the vehicle-detected road information acquired in real time is recognized as having a distance between the second lane line on the left and the current vehicle that is smaller than a first threshold and the second lane line on the left is a solid line, the discrepancy integral value is increased; if the vehicle-detected road information acquired in real time is recognized as having a distance between the second lane line on the right and the current vehicle that is smaller than a first threshold and the second lane line on the right is a solid line, the discrepancy integral value is increased; if the vehicle-detected road information acquired in real time is recognized as having a guard bar on the left and the distance between the guard bar and the current vehicle that is smaller than a second threshold, the discrepancy integral value is increased; if the vehicle-detected road information acquired in real time is recognized as having a guard bar on the right and the distance between the guard bar and the current vehicle that is smaller than the second threshold, the discrepancy integral value is increased.

[0067] When the currently measured lane is the leftmost lane, if the vehicle-detected road information acquired in real time is recognized as having a dotted lane line on the left-most adjacent lane with no guard bar on the left, the lane in which the vehicle is actually currently located is predicted to be not the leftmost lane based on the vehicle-detected road information acquired in real time, and the mismatch integral value of the currently measured lane is increased to indicate that the lane in which the vehicle is actually currently located is not in line with the currently measured lane.When the currently measured lane is the leftmost lane, if the vehicle-detected road information acquired in real time is recognized as having a guard bar on the right-most lane with a total number of lanes greater than 1, the lane in which the vehicle is actually currently located is predicted to be not the leftmost lane based on the vehicle-detected road information acquired in real time, and the mismatch integral value of the currently measured lane is increased to indicate that the lane in which the vehicle is actually currently located is not in line with the currently measured lane.

[0068] If the currently positioned lane is the rightmost lane and the vehicle-detected road information acquired in real time is recognized as having a dotted lane line on the right-most adjacent lane with no guard bar on the right, the lane in which the vehicle is actually currently located is predicted to be not the rightmost lane based on the vehicle-detected road information acquired in real time, and the mismatch integral value of the currently positioned lane is increased to indicate that the lane in which the vehicle is actually currently located is incompatible with the currently positioned lane. If the currently positioned lane is the rightmost lane and the vehicle-detected road information acquired in real time is recognized as having a guard bar on the left side with a total number of lanes greater than 1, the lane in which the vehicle is actually currently located is predicted to be not the rightmost lane based on the vehicle-detected road information acquired in real time, and the mismatch integral value of the currently positioned lane is increased to indicate that the lane in which the vehicle is actually currently located is incompatible with the currently positioned lane.

[0069] When the currently positioned lane is an intermediate lane, and the vehicle-detected road information acquired in real time is recognized as a distance between the left second lane line and the current vehicle being less than a first threshold value, the left second lane line is a solid line, and the lane in which the currently positioned vehicle is actually located is predicted to be not an intermediate lane based on the vehicle-detected road information acquired in real time, indicating that the lane in which the currently positioned vehicle is actually located is not in line with the currently positioned lane, the discrepancy integral value of the currently positioned lane is increased.When the currently positioned lane is an intermediate lane, and the vehicle-detected road information acquired in real time is recognized as a distance between the right second lane line and the current vehicle being less than a first threshold value, the right second lane line is a solid line, and the lane in which the currently positioned vehicle is actually located is predicted to be not an intermediate lane based on the vehicle-detected road information acquired in real time, indicating that the lane in which the currently positioned vehicle is actually located is not in line with the currently positioned lane, the discrepancy integral value of the currently positioned lane is increased. If the currently positioned lane is the middle lane and the vehicle-detected road information acquired in real time is recognized as having a guard bar on the left side and a distance between the guard bar and the current vehicle being smaller than a second threshold, the lane in which the currently positioned vehicle is actually located is predicted to be not the middle lane based on the vehicle-detected road information acquired in real time, indicating that the lane in which the currently positioned vehicle is actually located is not in line with the currently positioned lane, and the mismatch integral value of the currently positioned lane is increased. If the currently positioned lane is the middle lane and the vehicle-detected road information acquired in real time is recognized as having a guard bar on the right side and a distance between the guard bar and the current vehicle being smaller than a second threshold, the lane in which the currently positioned vehicle is actually located is predicted to be not the middle lane based on the vehicle-detected road information acquired in real time, indicating that the lane in which the currently positioned vehicle is actually located is not in line with the currently positioned lane, and the mismatch integral value of the currently positioned lane is increased.

[0070] In the above process of adding points, the more conditions that are met simultaneously, the more points will be added.

[0071] In some embodiments, after it is determined that the vehicle-detected road information acquired in real time does not conform to any of the third integration rules, the mismatch integral value is cleared to zero. Before comparing the vehicle-detected road information acquired in real time with the currently positioned lane, the mismatch integral value is set to zero. In order to prevent erroneous determination due to short-term fluctuations in the sensor detection data, after it is determined that the vehicle-detected road information acquired in real time does not conform to any of the third integration rules, the mismatch integral value is cleared to zero.

[0072] S130, after determining that the discrepancy integral value is equal to or greater than the preset integral value, return to determining the positioning lane based on the vehicle current position information, the vehicle-sensed road information and the map information.

[0073] During the process of determining the discrepancy integral value, the more conditions that satisfy the comparison integral rule, the more points the discrepancy integral value is added, and if the discrepancy integral value is equal to or greater than the preset integral value, it means that the discrepancy between the current positioning lane and the currently detected vehicle-detected road information is serious, and the current positioning lane is incorrect, and the positioning lane needs to be re-determined. Therefore, in the embodiment of the present disclosure, after determining that the discrepancy integral value is equal to or greater than the preset integral value, the process returns to the operation S110 of determining the positioning lane based on the vehicle current position information, the vehicle-detected road information, and the map information.

[0074] In the embodiment of the present disclosure, first, initial lane positioning is performed based on the vehicle current position information, vehicle-sensing road information, and map information, and the current positioning lane is first determined, and then the lane positioning is monitored, and the vehicle-sensing road information acquired in real time is compared with the current positioning lane to determine the discrepancy integral value. If the discrepancy integral value is equal to or greater than the preset integral value, the positioning lane positioning at this time fails, and the positioning lane needs to be re-determined, and the positioning lane is re-determined based on the vehicle current position information, vehicle-sensing road information, and map information. Compared with the prior art, the embodiment of the present disclosure does not require positioning using RTK high accuracy, and has low implementation costs. In addition, in the embodiment of the present disclosure, after determining the current positioning lane based on the vehicle current position information, vehicle-sensing road information, and map information, the vehicle-sensing road information acquired in real time is compared with the current positioning lane to determine the discrepancy integral value, and continuously monitor whether the positioning lane is correct, and after determining that the discrepancy integral value is equal to or greater than the preset integral value, the current positioning lane is determined again based on the vehicle current position information, vehicle-sensing road information, and map information. Therefore, compared to the conventional technology of comparing the types of lane lines detected by a camera with map information, the stability of lane positioning and the ability to prevent interference can be improved.

[0075] In some embodiments, referring to FIG. 10, the vehicle positioning method may further include S140 to S160.

[0076] S140, after determining that the discrepancy integral value is less than the preset integral value, determine whether the vehicle is in a steering state.

[0077] If the discrepancy integral value is smaller than the preset integral value, it means that the current positioning lane is compatible with the vehicle-sensed road information, and in the embodiment of the present disclosure, the vehicle steering is continuously monitored to determine whether the vehicle is in a steering state.

[0078] In some embodiments, determining whether the vehicle is in a steering state includes determining whether the vehicle is in a steering state based on a steering wheel angle and / or yaw rate signal, for example, reading the vehicle's steering wheel angle and / or yaw rate signal from a chassis system, and determining that the vehicle is in a steering state when one of the steering wheel angle and yaw rate signal exceeds a threshold.

[0079] S150, after determining that the vehicle is in a steering state, determining whether the vehicle has changed lanes based on the vehicle-sensed road information, and generating a lane change sign after determining that the vehicle has changed lanes.

[0080] When the vehicle is in a steering state, determine whether the vehicle has changed lanes based on the vehicle-sensed road information, monitor the lane change, and generate a lane change sign after determining that the vehicle has changed lanes. When the vehicle is in a steering state, if it is determined that the vehicle has changed lanes based on the vehicle-sensed road information acquired by a collecting device such as a camera, generate a lane change sign for subsequent positioning lane updates. The lane change sign includes, for example, a lane change to the left and a lane change to the right.

[0081] In some embodiments, in S150, determining whether the vehicle has changed lanes based on the vehicle-sensed road information and generating a lane change sign after determining that the vehicle has changed lanes includes: The method includes determining that a lane has changed when there is a jump change in the distance between at least one lane line in the vehicle-sensed road information and the current vehicle.

[0082] A lane change sign is generated based on the lane line change direction in the vehicle-sensed road information.

[0083] 11 is a schematic diagram of lane changing provided by an embodiment of the present disclosure. As shown in FIG. 11, taking three lanes as an example, the lane lines are displayed as n1, n2, n3, and n4 from left to right in sequence. The previous vehicle is located in lane 2, and the first left lane line of the vehicle is n2, and the first right lane line of the vehicle is n3. The vehicle gradually changes lanes from lane 2 to lane 1.

[0084] Before the lane change, the first left lane line of the vehicle is n2, the second left lane line is n1, the first right lane line is n3, and the second right lane line is n4. Hereinafter, a detailed explanation will be given by taking the case where the distance between the lane line and the vehicle is the distance between the lane line and the vehicle center axis as an example. During the process of the vehicle changing to lane 1, the vehicle gradually approaches lane line n2. For example, the distance d1 between the first left lane line n2 and the vehicle center axis gradually decreases from 1.7 m to 0. At the same time, the distance d2 between the first right lane line n3 and the vehicle center axis gradually decreases from -1.7 m to -3.4 m. At the moment when the vehicle center axis crosses lane line n2, n1 changes to the first left lane line, and n2 changes to the first right lane line (the first left lane line before the lane change). At the moment of lane change, the distance between the first left lane line and the vehicle center axis jumps from the original d1=0m to d3=3.4m, and the distance between the first right lane line and the vehicle center axis jumps from the original d2=-3.4m to d4=0m. When the distance between at least one lane line in the vehicle-sensing road information and the current vehicle jumps, it means that the vehicle has changed lanes. In FIG. 11, the second left lane line changes to the first left lane line, which means that the vehicle has changed to the left lane, so a lane change sign for changing to the left lane is generated.

[0085] In this embodiment, if there is a jump change in the distance between the current vehicle and the lane lines on both sides of the vehicle in the vehicle-detected road information, it is determined that a lane change has occurred. In another embodiment, in order to prevent a problem of asynchronous signal transmission during the signal collection process, if there is a jump change in the distance between at least one lane line in the vehicle-detected road information and the current vehicle, it may be determined that a lane change has occurred.

[0086] S160, updating the currently positioned lane based on the map information and the lane change sign.

[0087] When lane change monitoring is performed, the currently located lane is updated in real time based on map information and lane change signs. The map information includes information such as the total number of lanes where the vehicle is located. Taking FIG. 11 as an example, if the currently located lane determined at the previous time was lane 2, and it is found that the vehicle has changed to the left lane during the lane change monitoring process, the currently located lane is updated to lane 1.

[0088] If the vehicle changes to the right lane, update the currently positioned lane to lane 2. If the vehicle does not change lanes, do not change the currently positioned lane.

[0089] Taking FIG. 11 as an example, in this process, if it is found based on the map information that n lanes have been added to the left of the vehicle's current positioning lane, n is added to the current positioning lane, and if n lanes have been reduced to the left, n is reduced from the current positioning lane. If it is found based on the map information that the total number of lanes has not changed, the current positioning lane is not changed. The increase or decrease in the number of lanes on the right side of the vehicle's current positioning lane does not affect the result of the current positioning lane. It should be noted that the exemplary setting of FIG. 11 in which the lane numbers increase sequentially from left to right does not limit the embodiment of the present invention. In another embodiment, as shown in FIG. 3, the lane numbers are set to increase sequentially from right to left. When the lane numbers are named as shown in FIG. 3, if it is found based on the map information that n lanes have been added to the right of the vehicle's current positioning lane, n is added to the current positioning lane, and if n lanes have been reduced to the right, n is subtracted from the current positioning lane. If it is found based on the map information that the total number of lanes has not changed, the current positioning lane is not changed. An increase or decrease in the number of lanes to the left of the lane currently being located does not affect the result of currently being located lane. In this embodiment, the naming order of the lane line numbers is not limited.

[0090] In some embodiments, the generation times of two adjacent lane change signs are separated by at least a second preset time.

[0091] Since it takes a certain time, for example 5 seconds, for a vehicle to change lanes normally, if it is detected that the distance between the lane line and the current vehicle frequently jumps within 5 seconds, the collecting device may detect an error or the processing process may be incorrect. For example, under ideal conditions, a vehicle jumps from the first left lane line to the second left lane line at the previous time, and at the same time, jumps from the first right lane line to the first left lane line. When a camera collects detected lane line information, it generally transmits the first left lane line and the first right lane line information through two messages, respectively, and the reception of the two messages is sequential. In some cases, when one message is received, the other message has not yet been updated, so there may be a short time between the jump change of the left lane line and the jump change of the right lane line. In such a case, it can be recognized that two lane changes have occurred. Therefore, in this embodiment, in order to avoid erroneous judgment, the generation times of two adjacent lane change signs are separated by at least a second preset time.

[0092] The collection device in the vehicle collects vehicle-sensed road information as follows, but is not limited to this.

[0093] 1. The forward camera can identify the nearest lane line information on the left and right sides of the vehicle, and the forward millimeter-wave radar can obtain the position information of more than 10 reflection points on the guard bars within 5 m on both sides of the vehicle.

[0094] 2. The forward-facing camera can identify the nearest lane lines on the left and right of the vehicle, and obtain road boundary information within 5m on both sides.

[0095] 3. The forward camera can identify the nearest lane line information on the left and right sides of the vehicle, as well as the second lane line information on the left and second lane line information on the right side, and obtain road boundary information within 7m on both sides.

[0096] 4. The forward camera can identify information on the nearest lane lines on the left and right of the vehicle, as well as information on the second lane lines on the left and right, and the forward millimeter-wave radar can obtain information on the reflection points of more than 10 guardrails within 7 m on both sides of the vehicle.

[0097] Scheme 1 and Scheme 2 can support initial positioning of any lane on a three-lane road, initial positioning of both lanes on a four or more lane road, and stable positioning and tracking of five or fewer lanes.

[0098] Scheme 3 and Scheme 4 can support initial positioning of any lane on a five-lane road, initial positioning of both lanes on a road with six or more lanes, and stable positioning and tracking for roads with seven or fewer lanes.

[0099] In the embodiments of the present disclosure, in order to adapt to the driving positioning needs, appropriate collection devices such as a forward camera, a forward millimeter wave radar, etc. can be selected according to the actual situation.

[0100] Based on the same inventive concept, the embodiment of the present disclosure also provides a vehicle positioning device, and FIG. 12 is a structural block diagram of the vehicle positioning device provided by the embodiment of the present disclosure. Referring to FIG. 12, an initialization module 10 for determining a current positioning lane based on vehicle current position information, vehicle-sensed road information and map information; a positioning monitoring module 20 for comparing the vehicle-sensed road information acquired in real time with the currently positioned lane to determine a discrepancy integral value; and a determination module 30 for determining whether the discrepancy integral value is equal to or greater than the preset integral value, and if so, for causing the initialization module to re-execute an operation of determining a current positioning lane based on vehicle current position information, vehicle-sensed road information and map information.

[0101] FIG. 13 is a structural schematic diagram of an electronic device provided by an embodiment of the present disclosure, which includes a processor 40 and a memory 50, and the processor 40 calls a program or instruction stored in the memory 50 to execute the steps of the vehicle positioning method described in any of the above embodiments. In addition, the electronic device further includes at least one communication interface 60. Each component in the electronic device is coupled to each other via a bus system 70. The communication interface 60 is used to transfer information with an external device. It should be understood that the bus system 70 is used to enable connection communication between these components. The bus system 70 includes a power bus, a control bus, and a status signal bus in addition to a data bus.

[0102] The vehicle positioning method provided by the embodiment of the present disclosure may be applied to or implemented by the processor 40. The processor 40 may be an integrated circuit chip having signal processing capabilities. In the process of implementation, each step of the above method may be achieved by the processor 40 calling instructions in the form of hardware integrated logic circuits or software in a program or instruction stored in the memory 50. The above processor 40 may be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The general-purpose processor may be a microprocessor, and the processor may also be any conventional processor, etc.

[0103] An embodiment of the present disclosure further provides a computer-readable storage medium, the computer-readable storage medium storing a program or instructions, the program or instructions being used to cause a computer to execute steps of each embodiment of the vehicle positioning method, and repeated descriptions are omitted to avoid duplication.

[0104] The present application discloses a vehicle positioning method, A1: determining a current positioning lane based on vehicle current position information, vehicle-sensed road information and map information; Comparing the vehicle-sensed road information acquired in real time with the currently positioned lane to determine a discrepancy integral value; After determining that the discrepancy integral value is equal to or greater than a preset integral value, returning to and executing a positioning lane based on the vehicle current position information, the vehicle-sensed road information and the map information.

[0105] A2: According to the vehicle positioning method described in A1, determining whether the vehicle is in a steering condition after determining that the discrepancy integral value is less than the preset integral value; determining whether the vehicle has changed lanes based on the vehicle-sensed road information after determining that the vehicle is in a steering state, and generating a lane change sign after determining that the vehicle has changed lanes; The method further includes updating a currently positioned lane based on the map information and the lane change sign.

[0106] According to the vehicle positioning method described in A3:A1, determining a current positioning lane based on the vehicle current position information, the vehicle-sensed road information, and the map information, generating a lane integral table based on vehicle current position information and map information; determining an integral value for each lane in said lane integral table based on vehicle-sensed road information; determining a lane whose integral value in the lane integral table is greater than a first preset value as a positioning lane.

[0107] A4: According to the vehicle positioning method described in A3, the vehicle-detected road information includes detected lane line information and detected guard bar information, and determining an integral value of each lane in the lane integral table based on the vehicle-detected road information includes: The method includes determining the number of lanes in the map information corresponding to the vehicle current position information, and determining an integral value of each lane in the lane integral table based on a first integration rule corresponding to the number of lanes, the sensed lane line information, and the sensed guard bar information.

[0108] A5: According to the vehicle positioning method described in A4, the first integration rule corresponding to one lane is as follows. When the vehicle-detected road information recognizes that one lane line is a solid line and there is a guard bar on the left side, add one lane where the vehicle is located. The first integration rule corresponding to the number of lanes 2 is as follows: if the sensed lane line information and the sensed guard bar information are recognized as a solid line for the most adjacent lane line on the left and a dotted line for the most adjacent lane line on the right, the left lane is added; if the sensed lane line information and the sensed guard bar information are recognized as a guard bar on the left and a dotted line for the most adjacent lane line on the right, the left lane is added; if the sensed lane line information and the sensed guard bar information are recognized as a solid line for the most adjacent lane line on the right and a dotted line for the most adjacent lane line on the left, the right lane is added; if the sensed lane line information and the sensed guard bar information are recognized as a guard bar on the right and a dotted line for the most adjacent lane line on the left, the right lane is added; The first integration rule corresponding to the number of lanes 3 is as follows: when the sensed lane line information and the sensed guard bar information are recognized as the most adjacent lane lines on both the left and right sides being dotted and there being no guard bar, the middle lane is added; when the sensed lane line information and the sensed guard bar information are recognized as the most adjacent lane line on the left side being a solid line and the most adjacent lane line on the right side being a dotted line and there being no right guard bar, the left lane is added; when the sensed lane line information and the sensed guard bar information are recognized as the most adjacent lane line on the left side being a dotted line and there being no right guard bar, the left lane is added;

[0109] A6: According to the vehicle positioning method described in A4, the first integration rule corresponding to four or more lanes is as follows: if the sensed lane line information and the sensed guard bar information are recognized as the most adjacent lane line on the left being a solid line and the most adjacent lane line on the right being a dotted line with no right guard bar, the leftmost lane is added; if the sensed lane line information and the sensed guard bar information are recognized as the most adjacent lane line on the left being a dotted line with no right guard bar, the leftmost lane is added; if the sensed lane line information and the sensed guard bar information are recognized as the most adjacent lane line on the right being a solid line and the most adjacent lane line on the left being a dotted line with no left guard bar, the rightmost lane is added; if the sensed lane line information and the sensed guard bar information are recognized as the most adjacent lane lines on both the left and right sides being dotted lines with no guard bars, the sensed lane line information and the sensed guard bar information are compared with the lane lines of each intermediate lane, and the intermediate lane that is relatively consistent is added.

[0110] A7: According to the vehicle positioning method described in A4, the vehicle-sensed road information further includes surrounding vehicle information, and determines the number of lanes in the map information corresponding to the vehicle current position information, and determines the integral value of each lane in the lane integral table according to a first integration rule corresponding to the number of lanes, the sensed lane line information and the sensed guard bar information, and then: The method further includes updating an integral value of each lane in the lane integral table based on a second integral rule corresponding to the number of lanes and the surrounding vehicle information.

[0111] According to the vehicle positioning method described in A8:A7, the second integration rule corresponding to the number of lanes 2 is as follows: When the surrounding vehicle information is recognized as a moving vehicle on the left side and the lateral distance from the current vehicle is greater than a second preset value, the right lane is added; When the surrounding vehicle information is recognized as a moving vehicle on the right side and the lateral distance from the current vehicle is greater than a second preset value, the left lane is added; The second integration rule corresponding to three or more lanes is as follows: if the surrounding vehicle information is recognized as indicating that there is a moving vehicle on the left and that the lateral distance from the current vehicle is greater than a second preset value, the leftmost lane is deducted; if the surrounding vehicle information is recognized as indicating that there is a moving vehicle on the right and that the lateral distance from the current vehicle is greater than the second preset value, the rightmost lane is deducted; and if the number of lanes is three, if the surrounding vehicle information is recognized as indicating that there are moving vehicles on both the left and right sides and that the lateral distance from the current vehicle is greater than the second preset value, the middle lane is added.

[0112] According to the vehicle positioning method described in A9:A7, after determining that the duration during which the lateral distance between the moving vehicle and the current vehicle is greater than a second preset value based on the surrounding vehicle information is greater than a first preset time, an operation is performed to update the integral value of each lane in the lane integral table based on a second integration rule corresponding to the number of lanes and the surrounding vehicle information.

[0113] According to the vehicle positioning method described in A10:A3, in the process of determining the current positioning lane based on the vehicle current position information, the vehicle-sensed road information, and the map information, The method further includes clearing the lane integral table to zero after determining that the number of current lanes has changed.

[0114] According to the vehicle positioning method described in A11:A1, the step of comparing the vehicle-sensed road information acquired in real time with the currently-positioned lane to determine a discrepancy integral value includes: Determining a discrepancy integral value based on a third integral rule corresponding to the currently positioned lane and the vehicle-sensing road information acquired in real time.

[0115] A12: According to the vehicle positioning method described in A11, The third integral rule corresponding to the case where the current positioning lane is the leftmost lane is as follows: if the vehicle-sensing road information acquired in real time is recognized as the leftmost adjacent lane line being a dotted line and there being no guard bar on the left side, the discrepancy integral value is increased; if the vehicle-sensing road information acquired in real time is recognized as the rightmost adjacent lane line being a guard bar and the total number of lanes being greater than 1, the discrepancy integral value is increased; The third integration rule, which corresponds to the case where the current positioning lane is the rightmost lane, is as follows: if the vehicle-sensing road information acquired in real time is recognized as the rightmost adjacent lane line being a dotted line and there being no guard bar on the right side, the discrepancy integration value is increased; if the vehicle-sensing road information acquired in real time is recognized as the leftmost adjacent lane line being a guard bar and the total number of lanes is greater than 1, the discrepancy integration value is increased; The third integration rule corresponding to the case where the current positioning lane is an intermediate lane is as follows: if the vehicle-detected road information acquired in real time is recognized as having a distance between the second lane line on the left and the current vehicle that is smaller than a first threshold and the second lane line on the left is a solid line, the discrepancy integral value is increased; if the vehicle-detected road information acquired in real time is recognized as having a distance between the second lane line on the right and the current vehicle that is smaller than a first threshold and the second lane line on the right is a solid line, the discrepancy integral value is increased; if the vehicle-detected road information acquired in real time is recognized as having a guard bar on the left and the distance between the guard bar and the current vehicle that is smaller than a second threshold, the discrepancy integral value is increased; if the vehicle-detected road information acquired in real time is recognized as having a guard bar on the right and the distance between the guard bar and the current vehicle that is smaller than the second threshold, the discrepancy integral value is increased.

[0116] A13: According to the vehicle positioning method described in A12, after it is determined that the vehicle-sensed road information acquired in real time does not conform to any of the third integration rules, the mismatched integration value is cleared to zero.

[0117] According to the vehicle positioning method described in A14:A2, determining whether the vehicle is in a steering state includes: Determining whether the vehicle is in a steering condition based on the steering wheel angle and / or yaw rate signal.

[0118] According to the vehicle positioning method described in A15:A2, determining whether the vehicle has changed lanes based on the vehicle-sensed road information, and generating a lane change sign after determining that the vehicle has changed lanes, determining that a lane has been changed when a distance between at least one lane line in the vehicle-sensing road information and the current vehicle changes; generating a lane change flag based on a lane line change direction in the vehicle-sensed road information;

[0119] According to the vehicle positioning method described in A16:A2, the generation times of two adjacent lane change signs are spaced apart by at least a second preset time.

[0120] B1: The vehicle positioning device is An initialization module is used to determine a current positioning lane based on vehicle current position information, vehicle-sensed road information and map information; a positioning monitoring module used to compare the vehicle-sensed road information acquired in real time with the currently positioned lane to determine a discrepancy integral value; and a judgment module for judging whether the discrepancy integral value is equal to or greater than a preset integral value, and if so, instructing the initialization module to re-perform an operation of determining a current positioning lane based on vehicle current position information, vehicle-sensed road information and map information.

[0121] C1: An electronic device includes a processor and a memory; The processor invokes a program or instructions stored in the memory to execute the steps of the method according to any one of A1 to A16.

[0122] D1: A computer-readable storage medium stores a program or instructions, the program or instructions being used to cause a computer to execute the steps of the method according to any one of A1 to A16.

[0123] It should be noted that, for the sake of simplicity, the above method embodiments are all expressed as a combination of a series of operations, but those skilled in the art can understand that the embodiments of the present disclosure are not limited by the order of operations described, and that some steps may be performed in other orders or simultaneously according to the embodiments of the present disclosure. In addition, those skilled in the art can understand that all the embodiments described in this specification are optional embodiments.

[0124] It should be noted that, as used herein, the terms "comprise," "contain," or other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus consisting of a collection of elements includes not only those elements, but also other elements not expressly listed. Without further limitation, the fact that an element is defined with the phrase "comprises" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0125] Those skilled in the art will understand that some of the embodiments described herein include some features that are included in other embodiments but not others, but that combinations of features of different embodiments mean that they fall within the scope of the present disclosure and form different embodiments.

[0126] Those skilled in the art will appreciate that the descriptions of the various embodiments have different emphasis, and that parts not described in detail in one embodiment may be found in the relevant descriptions of other embodiments.

[0127] Although the embodiments of the present disclosure are described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations fall within the scope defined by the appended claims. [Industrial Applicability]

[0128] The present disclosure provides a method for determining a current positioning lane based on vehicle current position information, vehicle-detected road information, and map information, and then comparing the vehicle-detected road information obtained in real time with the current positioning lane to determine a discrepancy integral value, thereby continuously monitoring whether the positioning lane is correct, thereby improving the stability and anti-interference ability of lane positioning, and having high industrial applicability.

Claims

1. determining a current positioning lane based on vehicle current position information, vehicle-sensed road information and map information; Comparing the vehicle-sensed road information acquired in real time with the currently positioned lane to determine a discrepancy integral value; Comparing the vehicle-detected road information acquired in real time with the currently positioned lane to determine a discrepancy integral value includes acquiring the vehicle-detected road information in real time, comparing the vehicle-detected road information acquired in real time with the currently positioned lane determined at a previous time, and determining a discrepancy integral value based on a comparison result; Comparing the vehicle-detected road information acquired in real time with a currently positioned lane determined at a previous time and determining a discrepancy integral value based on the comparison result includes assigning different comparison integral rules to different currently positioned lanes, and increasing a discrepancy integral value when the vehicle-detected road information acquired in real time conforms to the comparison integral rule based on the comparison integral rule corresponding to the currently positioned lane and the vehicle-detected road information acquired in real time; and returning to determining a positioning lane based on the vehicle current position information, the vehicle-sensed road information, and the map information after determining that the discrepancy integral value is equal to or greater than a preset integral value.

2. determining whether the vehicle is in a steering condition after determining that the discrepancy integral value is less than the preset integral value; determining whether the vehicle has changed lanes based on the vehicle-sensed road information after determining that the vehicle is in a steering state, and generating a lane change sign after determining that the vehicle has changed lanes; 2. The vehicle positioning method of claim 1, further comprising: updating a current positioned lane based on the map information and the lane change sign.

3. Determining a current positioning lane based on the vehicle current position information, the vehicle-sensed road information, and the map information, generating a lane integral table based on vehicle current position information and map information; determining an integral value for each lane in said lane integral table based on vehicle-sensed road information; 2. The vehicle positioning method according to claim 1, further comprising: determining a lane whose integral value in the lane integral table is greater than a first preset value as a positioning lane.

4. The vehicle-detected road information includes detected lane line information and detected guard bar information, and determining an integral value of each lane in the lane integral table based on the vehicle-detected road information includes:

4. The vehicle positioning method according to claim 3, further comprising: determining the number of lanes in the map information corresponding to the vehicle current position information; and determining an integral value of each lane in the lane integral table based on a first integration rule corresponding to the number of lanes, the detected lane line information, and the detected guard bar information.

5. The first integration rule corresponding to one lane is as follows: When the vehicle-sensing road information is recognized as a solid lane line on one side and a guard bar on the left side, add one lane. The first integration rule corresponding to two lanes is as follows: if the sensed lane line information and the sensed guard bar information are recognized as a solid line for the most adjacent lane line on the left and a dotted line for the most adjacent lane line on the right, the left lane is added; if the sensed lane line information and the sensed guard bar information are recognized as a guard bar on the left and a dotted line for the most adjacent lane line on the right, the left lane is added; if the sensed lane line information and the sensed guard bar information are recognized as a solid line for the most adjacent lane line on the right and a dotted line for the most adjacent lane line on the left, the right lane is added; if the sensed lane line information and the sensed guard bar information are recognized as a guard bar on the right and a dotted line for the most adjacent lane line on the left, the right lane is added; 5. The vehicle positioning method according to claim 4, wherein the first integration rule corresponding to three lanes is as follows: when the sensed lane line information and the sensed guard bar information are recognized as the most adjacent lane lines on both the left and right sides being dotted and having no guard bar, a middle lane is added; when the sensed lane line information and the sensed guard bar information are recognized as the most adjacent lane line on the left side being a solid line and the most adjacent lane line on the right side being a dotted line and having no right guard bar, a left lane is added; when the sensed lane line information and the sensed guard bar information are recognized as the most adjacent lane line on the left side being a dotted line and having no right guard bar, a left lane is added; and when the sensed lane line information and the sensed guard bar information are recognized as the most adjacent lane line on the right side being a solid line and the most adjacent lane line on the left side being a dotted line and having no guard bar on the left, a right lane is added.

6. 5. The vehicle positioning method of claim 4, wherein the first integration rule corresponding to four or more lanes is as follows: when the sensed lane line information and the sensed guard bar information are recognized as a left-most adjacent lane line being a solid line and a right-most adjacent lane line being a dotted line with no right-side guard bar, the leftmost lane is added; when the sensed lane line information and the sensed guard bar information are recognized as a left-most adjacent lane line being a dotted line with no right-side guard bar, the leftmost lane is added; when the sensed lane line information and the sensed guard bar information are recognized as a right-most adjacent lane line being a solid line and a left-most adjacent lane line being a dotted line with no left-side guard bar, the rightmost lane is added; and when the sensed lane line information and the sensed guard bar information are recognized as a left-most adjacent lane line being a dotted line with no left-side guard bar, the sensed lane line information and the sensed guard bar information are compared with the lane lines of each intermediate lane, and an intermediate lane that is relatively consistent is added.

7. The vehicle-detected road information further includes surrounding vehicle information, and determines the number of lanes in the map information corresponding to the vehicle current position information, and determines an integral value of each lane in the lane integral table according to a first integration rule corresponding to the number of lanes, the detected lane line information, and the detected guard bar information, and then:

5. The vehicle positioning method according to claim 4, further comprising: updating the integral value of each lane in the lane integral table based on a second integral rule corresponding to the number of lanes and the surrounding vehicle information.

8. The second integration rule corresponding to two lanes is as follows: if the surrounding vehicle information is recognized as indicating that there is a moving vehicle on the left side and that the lateral distance from the current vehicle is greater than a second preset value, the right lane is added; if the surrounding vehicle information is recognized as indicating that there is a moving vehicle on the right side and that the lateral distance from the current vehicle is greater than a second preset value, the left lane is added; 8. The vehicle positioning method according to claim 7, wherein the second integration rule corresponding to three or more lanes is as follows: when the surrounding vehicle information is recognized as indicating that there is a moving vehicle on the left side and that the lateral distance from the current vehicle is greater than a second preset value, the leftmost lane is deducted from the score; when the surrounding vehicle information is recognized as indicating that there is a moving vehicle on the right side and that the lateral distance from the current vehicle is greater than the second preset value, the rightmost lane is deducted from the score; and when the number of lanes is three, when the surrounding vehicle information is recognized as indicating that there are moving vehicles on both the left and right sides and that the lateral distance from the current vehicle is greater than the second preset value, the middle lane is added to the score.

9. 8. The vehicle positioning method according to claim 7, further comprising: performing an operation of updating the integral value of each lane in the lane integral table based on a second integration rule corresponding to the number of lanes and the surrounding vehicle information after determining that the duration during which the lateral distance between the moving vehicle and the current vehicle is greater than a second preset value based on the surrounding vehicle information is greater than a first preset time.

10. In the process of determining a current positioning lane based on the vehicle current position information, the vehicle-detected road information, and the map information, 4. The vehicle positioning method according to claim 3, further comprising clearing the lane integral table to zero after determining that the number of current lanes has changed.

11. The step of comparing the vehicle-sensed road information acquired in real time with the currently-positioned lane to determine a discrepancy integral value includes: Determining a discrepancy integral value according to a third integral rule corresponding to the current positioning lane and the vehicle-sensed road information acquired in real time; The third integration rule, which corresponds to the case where the current positioning lane is the leftmost lane, is as follows: if the vehicle-sensing road information acquired in real time is recognized as the leftmost adjacent lane line being a dotted line and there being no guard bar on the left side, the discrepancy integration value is increased; if the vehicle-sensing road information acquired in real time is recognized as the rightmost adjacent lane line being a dotted line and there being no guard bar on the left side, the discrepancy integration value is increased; The third integration rule, which corresponds to the case where the current positioning lane is the rightmost lane, is as follows: if the vehicle-sensing road information acquired in real time is recognized as the lane line closest to the right being a dotted line and there is no guard bar on the right side, the discrepancy integration value is increased; if the vehicle-sensing road information acquired in real time is recognized as the lane line with a guard bar on the left side and the total number of lanes is greater than 1, the discrepancy integration value is increased; 2. The vehicle positioning method of claim 1, wherein the third integration rule corresponding to the case where the current positioning lane is an intermediate lane is as follows, and includes: increasing the discrepancy integral value when the vehicle-detected road information acquired in real time is recognized as a distance between the second lane line on the left and the current vehicle that is smaller than a first threshold and the second lane line on the left is a solid line; increasing the discrepancy integral value when the vehicle-detected road information acquired in real time is recognized as a distance between the second lane line on the right and the current vehicle that is smaller than the first threshold and the second lane line on the right is a solid line; increasing the discrepancy integral value when the vehicle-detected road information acquired in real time is recognized as a guard bar on the left and the distance between the guard bar and the current vehicle is smaller than a second threshold; and increasing the discrepancy integral value when the vehicle-detected road information acquired in real time is recognized as a guard bar on the right and the distance between the guard bar and the current vehicle is smaller than the second threshold.

12. The vehicle positioning method according to claim 11, further comprising: clearing the discrepancy integral value to zero after determining that the vehicle-sensed road information acquired in real time does not conform to any of the third integral rules.

13. Determining whether the vehicle is in a steering state includes:

3. The method of claim 2, further comprising determining whether the vehicle is in a steering condition based on a steering wheel angle and / or yaw rate signal.

14. Determining whether the vehicle has changed lanes based on the vehicle-sensed road information and generating a lane change sign after determining that the vehicle has changed lanes, determining that a lane has been changed when a distance between at least one lane line in the vehicle-sensing road information and the current vehicle changes; 3. The vehicle positioning method according to claim 2, further comprising: generating a lane change flag based on a lane line change direction in the vehicle-sensed road information.

15. 3. The vehicle positioning method according to claim 2, wherein the generation times of two adjacent lane change signs are spaced apart by at least a second preset time.

16. An initialization module is used to determine a current positioning lane based on vehicle current position information, vehicle-sensed road information and map information; A positioning monitoring module is used to determine a discrepancy integral value by comparing the vehicle-detected road information acquired in real time with a current positioning lane, and the determining of the discrepancy integral value by comparing the vehicle-detected road information acquired in real time with the current positioning lane includes acquiring the vehicle-detected road information in real time, comparing the vehicle-detected road information acquired in real time with the current positioning lane determined at a previous time, determining the discrepancy integral value based on the comparison result, assigning different comparison integral rules to different current positioning lanes, and increasing the discrepancy integral value when the comparison integral rule is met; and a judgment module for determining whether the discrepancy integral value is equal to or greater than a preset integral value, and if so, for instructing the initialization module to re-perform an operation of determining a current positioning lane based on vehicle current position information, vehicle-sensed road information, and map information.

17. An electronic device comprising a processor and a memory, The electronic device, wherein the processor invokes a program or instructions stored in the memory to perform the steps of the method according to any one of claims 1 to 15.

18. A computer readable storage medium storing a program or instructions, characterized in that said program or instructions cause a computer to carry out the steps of the method according to any one of claims 1 to 15.

Citation Information

Patent Citations

  • Lane change support device

    JP2018203103A

  • Course estimation device and course estimation program

    JP2021146820A

  • Lane correction system, lane correction apparatus and method of correcting lane

    US20140063251A1

  • Method and apparatus for controlling a vehicle's driving operation using advance information

    US20200361489A1