A vehicle positioning method, device, electronic device and medium in automatic driving

By setting camera identification tags on the vehicle and combining inertial navigation system measurements, and using Kalman filtering fusion technology, high-precision positioning of vehicles in complex environments is achieved, solving the problem of low positioning accuracy in the prior art.

CN117760437BActive Publication Date: 2024-11-15北京远舢智能科技有限公司 +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311759689.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-12-20
Publication Date
2024-11-15
Estimated Expiration
2043-12-20

AI Technical Summary

Technical Problem

In complex driving environments, the vehicle positioning accuracy is low. In the prior art, the combination of GPS and inertial navigation systems cannot meet the positioning accuracy requirements when GNSS signals are blocked or unstable.

Method used

By setting up a camera on the vehicle, identifying the tags in the target area with the camera, measuring the attitude angle in combination with the inertial navigation system, and determining the relative attitude angle and position of the tags using Kalman filtering fusion, converting it into the current position of the vehicle to achieve precise positioning.

Benefits of technology

Even when the GNSS signal is poor or the inertial navigation positioning is inaccurate, accurate vehicle attitude angle and positioning can be obtained, solving the problem of low vehicle positioning accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117760437B_ABST
    Figure CN117760437B_ABST
Patent Text Reader

Abstract

The present application provides a vehicle positioning method, device, electronic device and medium in automatic driving, wherein a camera is arranged on the front of the vehicle, the vehicle travels in a target area, and a plurality of tags are arranged at specific positions in the target area, and the method comprises: during the vehicle travel, the target tag is identified by the camera to obtain the relative position and posture of the tag; the relative attitude angle of the tag is combined with the vehicle measured attitude angle measured by the combined inertial navigation system to determine the current tag posture of the target tag relative to the camera; according to the absolute posture and posture relationship of the target tag, the current tag posture is converted into the current vehicle posture of the vehicle, the absolute posture of the tag is the posture of the target tag calibrated in advance in the world coordinate system, and the posture relationship is the posture relationship between the camera and the vehicle. By adopting the above-mentioned vehicle positioning method, device, electronic device and medium in automatic driving, the problem of low vehicle positioning accuracy in complex driving environments is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and more specifically, to a vehicle positioning method, device, electronic device and medium in autonomous driving. Background Art

[0002] With the rapid development of autonomous driving technology, autonomous driving safety has received more and more attention. As the first step in autonomous driving perception, accurate positioning is the prerequisite for ensuring autonomous driving safety.

[0003] In the prior art, high-precision vehicle positioning technology usually adopts a combined inertial navigation system positioning of the Global Positioning System (GPS) and the Inertial Navigation System (INS). However, since the satellite signals of the Global Navigation Satellite System (GNSS) may be blocked and the accuracy of the wheel odometer is easily affected by wheel slip, the vehicle positioning accuracy requirements cannot be met in complex driving environments. Summary of the invention

[0004] In view of this, the purpose of the present application is to provide a vehicle positioning method, device, electronic device and medium in autonomous driving to solve the problem of low vehicle positioning accuracy in complex driving environments.

[0005] In a first aspect, an embodiment of the present application provides a vehicle positioning method in autonomous driving, wherein a camera is arranged on the front of the vehicle, the vehicle is traveling in a target area, and a plurality of tags are arranged at specific positions in the target area, and the method comprises:

[0006] During the driving process of the vehicle, the target tag is identified by the camera to obtain the relative position and posture of the tag. The relative position and posture of the tag is the position and posture of the tag relative to the camera, and the relative position and posture of the tag includes the relative attitude angle of the tag.

[0007] Combine the tag relative attitude angle with the vehicle measured attitude angle measured by the integrated inertial navigation system to determine the current tag pose of the target tag relative to the camera;

[0008] According to the target tag's absolute tag pose and pose relationship, the current tag pose is converted to the vehicle's current vehicle pose. The tag absolute pose is the pose of the target tag calibrated in advance in the world coordinate system, and the pose relationship is the pose relationship between the camera and the vehicle.

[0009] Optionally, the tag relative posture also includes the tag relative position; the tag relative attitude angle is combined with the vehicle measurement attitude angle measured by the combined inertial navigation system to determine the current tag posture of the target tag relative to the camera, including: converting the vehicle measurement attitude angle into the tag measurement attitude angle, the tag measurement attitude angle is the attitude angle of the tag relative to the camera; using Kalman filtering to merge the tag measurement attitude angle with the tag relative attitude angle to obtain the tag filtering attitude angle; determining the current tag posture according to the tag filtering attitude angle and the tag relative position.

[0010] Optionally, according to the label absolute pose and pose relationship of the target label, the current label pose is converted into the current vehicle pose of the vehicle, including: converting the current label pose into the current vehicle pose by multiplying the label absolute pose, the pose relationship and the current label pose.

[0011] Optionally, before using the camera to identify the target tag to obtain the relative pose of the tag, it also includes: calibrating the intrinsic and extrinsic parameters of the camera; using the camera after calibrating the intrinsic and extrinsic parameters, calibrating the positions of multiple tags in the target area in the world coordinate system to obtain the absolute pose of each tag.

[0012] Optionally, the vehicle is a two-way driving vehicle, the front of the vehicle includes a front front and a rear front, a first camera is arranged on the front front of the vehicle, and a second camera is arranged on the rear front of the vehicle.

[0013] Optionally, a camera is used to identify a target tag to obtain a relative position of the tag, including: using a first camera and a second camera to respectively identify the tag in their respective shooting directions; when the first camera or the second camera identifies the tag, the identified tag is used as a target tag, and the camera that identifies the target tag is used as a target camera, and the relative position of the target tag relative to the target camera is determined.

[0014] Optionally, the multiple tags are two-dimensional codes set on objects located in the target area.

[0015] In a second aspect, an embodiment of the present application further provides a vehicle positioning device in autonomous driving, wherein a camera is arranged on the front of the vehicle, the vehicle travels in a target area, and a plurality of tags are arranged at specific positions in the target area, and the device comprises:

[0016] A posture recognition module is used to use a camera to identify a target tag during vehicle driving to obtain a relative posture of the tag. The relative posture of the tag is the posture of the tag relative to the camera, and the relative posture of the tag includes a relative posture angle of the tag;

[0017] The tag pose determination module is used to combine the tag relative pose angle with the vehicle measured pose angle measured by the satellite positioning system to determine the current tag pose of the target tag relative to the camera;

[0018] The vehicle posture determination module is used to convert the current tag posture into the current vehicle posture of the vehicle according to the tag absolute posture and posture relationship of the target tag. The tag absolute posture is the posture of the target tag calibrated in advance in the world coordinate system, and the posture relationship is the posture relationship between the camera and the inertial navigation center.

[0019] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the vehicle positioning method in autonomous driving as described above are performed.

[0020] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the vehicle positioning method in autonomous driving as described above are executed.

[0021] The embodiments of the present application bring the following beneficial effects:

[0022] The embodiments of the present application provide a method, device, electronic device and medium for positioning a vehicle in an autonomous driving process, which can combine the relative attitude angle of the tag with the vehicle measured attitude angle of the combined inertial navigation system to determine the current tag posture. At this time, the current tag posture is obtained based on the vehicle measured attitude angle measured by the combined inertial navigation system. It utilizes the characteristic that the attitude angle is not affected by the positioning position accuracy. Even when the GNSS signal is not good and the inertial navigation positioning is inaccurate, an accurate attitude angle can be obtained. At the same time, the tag position determined according to the positioning tag is also not affected by the GNSS signal. By combining the attitude angle with the tag position, an accurate vehicle posture can be obtained. Compared with the vehicle positioning method in autonomous driving in the prior art, the problem of low vehicle positioning accuracy in a complex driving environment is solved.

[0023] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1A flow chart of a vehicle positioning method in autonomous driving provided by an embodiment of the present application is shown;

[0026] Figure 2 A schematic diagram showing the structure of a vehicle positioning device in an automatic driving system provided in an embodiment of the present application is shown;

[0027] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0028] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work belongs to the scope of protection of the present application.

[0029] It is worth noting that before the present application was filed, with the rapid development of autonomous driving technology, autonomous driving safety has received more and more attention. As the first step in autonomous driving perception, accurate positioning is a prerequisite for ensuring the safety of autonomous driving. In the prior art, high-precision vehicle positioning technology usually adopts a combined inertial navigation system positioning of the Global Positioning System (GPS) and the Inertial Navigation System (INS). However, since the satellite signal of the Global Navigation Satellite System (GNSS) may be blocked, and the accuracy of the wheel odometer is easily affected by wheel slip, it causes the problem of being unable to meet the vehicle positioning accuracy requirements in complex driving environments.

[0030] Based on this, an embodiment of the present application provides a vehicle positioning method in autonomous driving to improve the vehicle positioning accuracy in complex driving environments.

[0031] See also Figure 1 , Figure 1 This is a flow chart of a vehicle positioning method in an automatic driving provided by an embodiment of the present application. Figure 1As shown, in the vehicle positioning method in the automatic driving provided by the embodiment of the present application, a camera is arranged on the front of the vehicle, the vehicle is traveling in the target area, and a plurality of tags are arranged at specific positions in the target area. The vehicle positioning method includes:

[0032] Step S101, during the driving process of the vehicle, a target tag is identified by using a camera to obtain the relative position and posture of the tag.

[0033] In this step, the vehicle is a two-way driving vehicle and has an automatic driving function.

[0034] The multiple tags are QR codes set on objects located in the target area. Different tags are set on different objects, and the current location of the vehicle can be distinguished by the location of the tag.

[0035] The relative pose of the tag is the pose of the tag relative to the camera. The relative pose of the tag is the position and posture of the tag in the camera coordinate system. The relative pose of the tag is the pose obtained by the camera recognizing the tag. The relative pose of the tag includes the relative pose angle of the tag and the relative position of the tag. Among them, the relative pose angle of the tag includes the yaw angle, pitch angle and roll angle, and the relative position of the tag includes the X, Y, and Z three-dimensional coordinates.

[0036] In the embodiment of the present application, since the GNSS satellite signal may be blocked or unstable, tags may be set at different set positions in the target area, and the driving position of the vehicle may be indirectly determined by the tag position. In order to determine the tag position, a camera is set on the vehicle to continuously obtain the tag image in the shooting direction during the vehicle driving process, identify the tag QR code in the tag image, and obtain the tag relative posture corresponding to the tag by scanning the tag QR code.

[0037] In an optional embodiment, before step S101, the following steps are included: step a1 and step a2.

[0038] Step a1: calibrate the intrinsic and extrinsic parameters of the camera.

[0039] Before starting vehicle positioning, it is necessary to determine the position of each tag in the world coordinate system. To this end, the camera's intrinsic and extrinsic parameters are first calibrated. The intrinsic parameters are parameters that describe the internal properties of the camera, including but not limited to: focal length, principal point coordinates, and distortion coefficients. The extrinsic parameters are parameters that describe the position and posture of the camera in the world coordinate system, including but not limited to: rotation matrix and translation vector.

[0040] Step a2: Use the camera after calibrating the internal and external parameters to calibrate the positions of multiple tags in the target area in the world coordinate system to obtain the absolute position and pose of each tag.

[0041] After calibrating the internal and external parameters of the camera, it is also necessary to calibrate the position and posture of the tag in the world coordinate system, so as to use the calibrated absolute position and posture of the tag to transform the current tag position and posture obtained in real time. Here, for each tag, the camera is used as the origin, and the position and posture of the tag relative to the camera are determined by the camera, and the position conversion relationship between the tag and the camera is established. According to the position conversion relationship between the tag and the camera, and the position conversion relationship between the camera and the vehicle, the position conversion relationship of each tag relative to the vehicle is determined. According to the position conversion relationship of the tag relative to the vehicle and the position and posture of the vehicle in the world coordinate system, the position and posture of the tag in the world coordinate system can be determined, that is, the absolute position and posture of each tag can be obtained.

[0042] In an optional embodiment, the front of the vehicle includes a front front and a rear front, a first camera is arranged on the front front of the vehicle, and a second camera is arranged on the rear front of the vehicle. Step S101 includes: step b1 and step b2.

[0043] Step b1, using the first camera and the second camera to respectively identify the tags in their respective shooting directions.

[0044] Specifically, when the vehicle is traveling in the direction indicated by the front vehicle, the first camera is used to scan the label in the vehicle's forward direction, and the second camera is used to scan the label in the opposite direction of the vehicle's forward direction. When the vehicle is traveling in the direction indicated by the rear vehicle, the first camera is used to scan the label in the opposite direction of the vehicle's forward direction, and the second camera is used to scan the label in the vehicle's forward direction.

[0045] Step b2: when the first camera or the second camera recognizes a tag, the recognized tag is used as a target tag, the camera that recognizes the target tag is used as a target camera, and the relative position of the target tag relative to the target camera is determined.

[0046] Here, since the first camera A and the second camera B shoot in different directions, usually only one camera will capture the tag. When a camera captures a tag, the captured tag is used as the target tag, and the camera that captured the target tag is used as the target camera. If two cameras capture the tag at the same time, the tag with the clearest capture is selected as the target tag, and the camera that captured the target tag is selected as the target camera.

[0047] Assuming that the first camera A captures the target tag a, the relative position of the current target tag a relative to the target camera A is calculated in real time.

[0048] Step S102, combining the tag relative attitude angle with the vehicle measured attitude angle measured by the integrated inertial navigation system to determine the current tag pose of the target tag relative to the camera.

[0049] In this step, the combined inertial navigation system refers to the combination of the GPS system and the INS inertial navigation system.

[0050] The vehicle measured attitude angle is the vehicle attitude angle measured in real time by the combined inertial navigation system.

[0051] The current tag pose is denoted as: Pose(tag_to_camera).

[0052] In the embodiment of the present application, since the GNSS satellite signal may be blocked or unstable, it is inaccurate to directly use the satellite signal to determine the vehicle position. However, the attitude angle in the satellite signal is accurate. Kalman filtering can be used to combine the vehicle attitude angle measured by the combined inertial navigation system with the relative attitude angle of the tag to verify each other and improve the accuracy.

[0053] First, determine whether the relative attitude angle of the tag is stable. Due to the different distances between adjacent frames during the process of the camera shooting the tag, the relative attitude angle of the tag may shake. If the relative attitude angle of the tag is directly used to calculate the vehicle posture at this time, it is inaccurate. Therefore, it is necessary to determine whether the relative attitude angle of the tag is stable. Here, the relative attitude angle of the tag can be determined based on the difference in effective pixel values ​​between multiple consecutive frame tag images. When the difference in effective pixel values ​​between multiple frame tag images is less than the set threshold, the relative attitude angle of the tag is determined to be stable. When the difference in effective pixel values ​​between multiple frame tag images is greater than or equal to the set threshold, the relative attitude angle of the tag is determined to be unstable. If the relative attitude angle of the tag is unstable, that is, there is a large shake in the relative attitude angle of the tag, the Kalman filter can be used to combine the measured attitude angle of the tag with the relative attitude angle of the tag. If the relative attitude angle of the tag is stable, the current tag posture can be directly determined based on the relative attitude angle of the tag and the relative position of the tag.

[0054] In addition, regardless of whether the tag relative attitude angle is stable, the tag filtering attitude angle can be determined by adjusting the weight between the tag measurement attitude angle and the tag relative attitude angle. For example, when the tag relative attitude angle is unstable, the weight of the tag relative attitude angle in the combination process is reduced; when the tag relative attitude angle is stable, the weight of the tag relative attitude angle in the combination process is increased.

[0055] In an optional embodiment, step S102 includes: step c1, step c2, and step c3.

[0056] Step c1, converting the vehicle measured attitude angle into the tag measured attitude angle.

[0057] The vehicle measured attitude angle is converted into the tag measured attitude angle. The tag measured attitude angle is the attitude angle of the tag relative to the camera in the camera coordinate system converted from the vehicle measured attitude angle. The tag measured attitude angle is used to combine with the tag relative attitude angle to obtain the tag filtered attitude angle.

[0058] Step c2: Use Kalman filtering to fuse the tag measured attitude angle with the tag relative attitude angle to obtain the tag filtered attitude angle.

[0059] The Kalman filter is used to estimate the theoretical value of the tag attitude angle, and the weight between the tag measurement attitude angle and the tag relative attitude angle is determined according to the estimated theoretical value of the tag attitude angle. The initial tag filter attitude angle angle(camera_to_tag) is calculated using the determined weight, and then the initial tag filter attitude angle angle(camera_to_tag) and the tag relative position are inversely transformed to obtain the tag filter attitude angle angle(tag_to_camera) and the tag relative position after inverse transformation.

[0060] Step c3, determine the current tag posture according to the tag filtering posture angle and the tag relative position.

[0061] The current tag pose Pose(tag_to_camera) is composed of the tag filtering attitude angle angle(tag_to_camera) and the inverse transformed tag relative position.

[0062] Step S103, converting the current tag pose into the current vehicle pose of the vehicle according to the tag absolute pose and pose relationship of the target tag.

[0063] In this step, the absolute pose of the label is the pose of the target label in the world coordinate system calibrated in advance, and the pose relationship is the pose relationship between the camera and the vehicle, that is, the pose transformation relationship of the camera relative to the vehicle.

[0064] In the embodiment of the present application, the current tag pose is converted to the current vehicle pose by multiplying the absolute pose of the tag, the pose relationship and the current tag pose Pose(tag_to_camera). Here, the current vehicle pose is recorded as: Pose(map_to_ego), the absolute pose of the tag is recorded as: Pose(map_to_ego), and the pose relationship is recorded as: Pose(camera_to_ego), then the following calculation formula is obtained:

[0065] Pose(map_to_ego)=Pose(map_to_tag)×Pose(tag_to_camera)×Pose(camera_to_ego);

[0066] Among them, Pose(map_to_ego) represents the pose of the vehicle in the world coordinate system, Pose(map_to_tag) represents the pose of the tag in the world coordinate system, Pose(tag_to_camera) represents the pose of the camera in the tag coordinate system, and Pose(camera_to_ego) represents the pose of the vehicle in the camera coordinate system.

[0067] In the embodiment of the present application, after obtaining the current vehicle posture, according to the values ​​of the motion parameters such as acceleration and speed in the inertial measurement unit IMU in the combined inertial navigation system, it is determined whether the current vehicle is stable. If it is determined that the current vehicle is unstable, the distance between the target camera and the target tag is determined, and the weights of the current vehicle posture, the vehicle measured posture obtained by the combined inertial navigation system, and the posture prediction value are determined according to the comparison result of the distance and the set distance threshold. The posture prediction value is determined by Kalman filtering, and the posture prediction value, the current vehicle posture, and the posture data measured by the combined inertial navigation system are integrated according to the determined weight value to calculate the final posture of the vehicle. Among them, if the distance is less than the set distance threshold, it is determined that the current vehicle posture obtained according to the target tag is accurate, and the weight of the current vehicle posture can be increased; if the distance is greater than or equal to the set distance threshold, it means that the current vehicle posture obtained according to the target tag is not accurate enough, and it is necessary to reduce the weight of the current vehicle posture, and increase the weight of the posture data and posture prediction value measured by the combined inertial navigation system.

[0068] Compared with the vehicle positioning method in the automatic driving in the prior art, the present application can combine the relative attitude angle of the tag with the vehicle measured attitude angle of the combined inertial navigation system to determine the current tag posture. At this time, the current tag posture is obtained based on the vehicle measured attitude angle measured by the combined inertial navigation system. It utilizes the characteristic that the attitude angle is not affected by the positioning position accuracy. Even in the case of poor GNSS signal or inaccurate inertial navigation positioning, an accurate attitude angle can be obtained. At the same time, the tag position determined by the positioning tag is also not affected by the GNSS signal. By combining the attitude angle with the tag position, an accurate vehicle posture can be obtained, which solves the problem of low vehicle positioning accuracy in complex driving environments.

[0069] Based on the same inventive concept, an embodiment of the present application also provides a vehicle positioning device in autonomous driving corresponding to the vehicle positioning method in autonomous driving. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the vehicle positioning method in autonomous driving mentioned above in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0070] See also Figure 2 , Figure 2This is a schematic diagram of the structure of a vehicle positioning device in an automatic driving system provided in an embodiment of the present application. Figure 2 As shown in , a camera is arranged on the front of the vehicle, the vehicle is traveling in a target area, and a plurality of tags are arranged at specific positions in the target area. The vehicle positioning device 200 in the automatic driving includes:

[0071] The posture recognition module 201 is used to use the camera to recognize the target tag during the vehicle driving process to obtain the relative posture of the tag. The relative posture of the tag is the posture of the tag relative to the camera, and the relative posture of the tag includes the relative posture angle of the tag;

[0072] The tag pose determination module 202 is used to combine the tag relative pose angle with the vehicle measured pose angle measured by the integrated inertial navigation system to determine the current tag pose of the target tag relative to the camera;

[0073] The vehicle posture determination module 203 is used to convert the current tag posture into the current vehicle posture of the vehicle according to the tag absolute posture and posture relationship of the target tag. The tag absolute posture is the posture of the target tag calibrated in advance in the world coordinate system, and the posture relationship is the posture relationship between the camera and the vehicle.

[0074] In an optional embodiment, the tag relative posture also includes the tag relative position; the tag posture determination module 202 is specifically used to: convert the vehicle measurement posture angle into the tag measurement posture angle, the tag measurement posture angle is the posture angle of the tag relative to the camera; use Kalman filtering to merge the tag measurement posture angle with the tag relative posture angle to obtain the tag filtering posture angle; determine the current tag posture according to the tag filtering posture angle and the tag relative position.

[0075] In an optional embodiment, the vehicle posture determination module 203 is specifically used to convert the current label posture into the current vehicle posture by using the product of the label absolute posture, the posture relationship and the current label posture.

[0076] In an optional embodiment, the posture recognition module 201 is also used to: calibrate the intrinsic and extrinsic parameters of the camera; use the camera after calibrating the intrinsic and extrinsic parameters to calibrate the positions of multiple tags in the target area in the world coordinate system to obtain the absolute posture of each tag.

[0077] In an optional embodiment, the vehicle is a two-way driving vehicle, the front of the vehicle includes a front front and a rear front, a first camera is arranged on the front front of the vehicle, and a second camera is arranged on the rear front of the vehicle.

[0078] In an optional embodiment, the posture recognition module 201 is specifically used to: use the first camera and the second camera to respectively identify the tags in their respective shooting directions; when the first camera or the second camera recognizes the tag, the recognized tag is used as the target tag, and the camera that recognizes the target tag is used as the target camera.

[0079] In an optional embodiment, the multiple tags are two-dimensional codes set on objects located in the target area.

[0080] See also Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3 As shown in , the electronic device 300 includes a processor 310 , a memory 320 and a bus 330 .

[0081] The memory 320 stores machine-readable instructions executable by the processor 310. When the electronic device 300 is running, the processor 310 communicates with the memory 320 via the bus 330. When the machine-readable instructions are executed by the processor 310, the above-mentioned Figure 1 The steps of the vehicle positioning method in autonomous driving in the method embodiment shown in the embodiment, and the specific implementation method can be found in the method embodiment, which will not be repeated here.

[0082] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figure 1 The steps of the vehicle positioning method in autonomous driving in the method embodiment shown in the embodiment, and the specific implementation method can be found in the method embodiment, which will not be repeated here.

[0083] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0084] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0085] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0086] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0087] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application can essentially be embodied in the form of a software product, or in other words, the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0088] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A vehicle positioning method in automatic driving, characterized in that: A camera is arranged on the front of the vehicle, and the vehicle is traveling in a target area. A plurality of tags are arranged at specific locations in the target area, including: During the driving of the vehicle, the camera is used to identify the target tag to obtain the tag relative posture, wherein the tag relative posture is the posture of the tag relative to the camera, and the tag relative posture includes the tag relative posture angle; Combining the tag relative attitude angle with the vehicle measurement attitude angle measured by the combined inertial navigation system to determine the current tag pose of the target tag relative to the camera; According to the label absolute pose and pose relationship of the target label, converting the current label pose into the current vehicle pose of the vehicle, wherein the label absolute pose is the pose of the target label in the world coordinate system calibrated in advance, and the pose relationship is the pose relationship between the camera and the vehicle; The relative position of the tag also includes the relative position of the tag; The step of combining the tag relative attitude angle with the vehicle measured attitude angle measured by the combined inertial navigation system to determine the current tag position of the target tag relative to the camera includes: Converting the vehicle-measured attitude angle into a tag-measured attitude angle, wherein the tag-measured attitude angle is the attitude angle of the tag relative to the camera in the camera coordinate system converted from the vehicle-measured attitude angle; The tag measured attitude angle is integrated with the tag relative attitude angle by using Kalman filtering to obtain the tag filtered attitude angle and the tag relative position after inverse transformation; Determine the current tag posture according to the tag filtering posture angle and the relative position of the tag after inverse transformation; The method of using Kalman filtering to fuse the tag measurement attitude angle with the tag relative attitude angle to obtain the tag relative position after inverse transformation of the tag filtering attitude angle includes: The Kalman filter is used to estimate the theoretical value of the tag attitude angle, and the weight between the tag attitude angle and the tag relative attitude angle is determined according to the theoretical value of the tag attitude angle; The weight is used to calculate the initial tag filtering attitude angle, and the initial tag filtering attitude angle and the tag relative position are inversely transformed to obtain the tag filtering attitude angle and the inversely transformed tag relative position.

2. The method according to claim 1, characterized in that: The step of converting the current tag pose into the current vehicle pose of the vehicle according to the tag absolute pose and pose relationship of the target tag includes: The current tag posture is converted into the current vehicle posture by using the product of the tag absolute posture, the posture relationship and the current tag posture.

3. The method according to claim 1, characterized in that Before using the camera to identify the target tag to obtain the relative position and posture of the tag, the method further includes: Calibrate the intrinsic and extrinsic parameters of the camera; Using the camera after calibrating the internal and external parameters, the positions of multiple tags in the target area in the world coordinate system are calibrated to obtain the absolute position and pose of each tag.

4. The method according to claim 1, characterized in that: The vehicle is a two-way driving vehicle, the front of the vehicle includes a front front and a rear front, a first camera is arranged on the front front of the vehicle, and a second camera is arranged on the rear front of the vehicle.

5. The method according to claim 4, characterized in that The step of using the camera to identify the target tag and obtain the relative position of the tag includes: Using the first camera and the second camera to identify tags in their respective shooting directions; When the first camera or the second camera recognizes a tag, the recognized tag is used as a target tag, the camera that recognizes the target tag is used as a target camera, and a tag relative posture of the target tag relative to the target camera is determined.

6. The method according to claim 1, characterized in that The multiple tags are two-dimensional codes set on objects located in the target area.

7. A vehicle positioning device in automatic driving, characterized in that: A camera is arranged on the front of a vehicle, the vehicle is traveling in a target area, a plurality of tags are arranged at specific positions in the target area, and the device comprises: A posture recognition module, used to use the camera to identify the target tag during the driving of the vehicle to obtain the relative posture of the tag, wherein the relative posture of the tag is the posture of the tag relative to the camera, and the relative posture of the tag includes a relative posture angle of the tag; A tag posture determination module is used to combine the tag relative posture angle with the vehicle measurement posture angle measured by the combined inertial navigation system to determine the current tag posture of the target tag relative to the camera; A vehicle posture determination module, used for converting the current tag posture into the current vehicle posture of the vehicle according to the tag absolute posture and posture relationship of the target tag, wherein the tag absolute posture is the posture of the target tag in the world coordinate system calibrated in advance, and the posture relationship is the posture relationship between the camera and the vehicle; The relative position of the tag also includes the relative position of the tag; The tag posture determination module is specifically used for: Converting the vehicle-measured attitude angle into a tag-measured attitude angle, wherein the tag-measured attitude angle is the attitude angle of the tag relative to the camera in the camera coordinate system converted from the vehicle-measured attitude angle; The tag measured attitude angle is integrated with the tag relative attitude angle by using Kalman filtering to obtain the tag filtered attitude angle and the tag relative position after inverse transformation; Determine the current tag posture according to the tag filtering posture angle and the relative position of the tag after inverse transformation; The tag posture determination module is specifically used to fuse the tag measurement posture angle with the tag relative posture angle by using Kalman filtering to obtain the tag filtering posture angle and the inverse transformed tag relative position: The Kalman filter is used to estimate the theoretical value of the tag attitude angle, and the weight between the tag attitude angle and the tag relative attitude angle is determined according to the theoretical value of the tag attitude angle; The weight is used to calculate the initial tag filtering attitude angle, and the initial tag filtering attitude angle and the tag relative position are inversely transformed to obtain the tag filtering attitude angle and the inversely transformed tag relative position.

8. An electronic device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the storage medium communicate through the bus, and the processor executes the machine-readable instructions to perform the steps of the vehicle positioning method in automatic driving as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the vehicle positioning method in automatic driving are performed as described in any one of claims 1 to 6.