Vehicle pose adjusting method and device

Abstract

The invention relates to the technical field of auxiliary driving, and provides a vehicle pose adjusting method and device. The method comprises the following steps: acquiring a point cloud image acquired by a laser radar passing through a target vehicle; according to a point cloud coordinate set of a lane line point cloud corresponding to the lane line in a radar coordinate system in the point cloud image, converting the lane line point cloud from the radar coordinate system to a global coordinate system, and obtaining a current coordinate set of the lane line in the global coordinate system; and adjusting the current pose of the target vehicle according to the current coordinate set of the lane line in the global coordinate system and the prior coordinate set of the lane line in the global coordinate system. According to the vehicle pose adjustment method provided by the embodiment of the invention, the accuracy of vehicle pose adjustment can be improved.

Description

Technical Field

[0001] The present application relates to the field of assisted driving technology, and in particular to a vehicle posture adjustment method and device. Background Art

[0002] At present, more and more vehicles are equipped with assisted driving modes to assist vehicles in driving on fixed routes and improve vehicle driving safety. In related technologies, the method for assisting vehicles in driving on fixed routes is to obtain road information through the front camera of the vehicle, and then adjust the vehicle's posture according to the road information obtained by the front camera to assist the vehicle in driving on the fixed route.

[0003] However, since the front camera can only realize image acquisition and cannot detect the scale information and depth information of the road, the collected road information cannot be used to locate the vehicle body. Therefore, using the above method to achieve vehicle posture adjustment will affect the accuracy of the vehicle posture adjustment. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems existing in the related art. To this end, the present application proposes a vehicle posture adjustment method, which can improve the accuracy of vehicle posture adjustment.

[0005] A vehicle posture adjustment method according to an embodiment of the first aspect of the present application includes:

[0006] Obtain a point cloud image collected by the laser radar of the target vehicle;

[0007] According to a point cloud coordinate set of a lane line point cloud corresponding to the lane line in the point cloud image in the radar coordinate system, converting the lane line point cloud from the radar coordinate system to a global coordinate system to obtain a current coordinate set of the lane line in the global coordinate system;

[0008] The current position and posture of the target vehicle is adjusted according to the current coordinate set of the lane line in the global coordinate system and the priori coordinate set of the lane line in the global coordinate system.

[0009] By acquiring a point cloud image collected by a laser radar of the target vehicle, and according to the point cloud coordinate set of the lane line point cloud corresponding to the lane line in the point cloud image in the radar coordinate system, the lane line point cloud is converted from the radar coordinate system to the global coordinate system to obtain the current coordinate set of the lane line in the global coordinate system, so as to adjust the current posture of the target vehicle according to the current coordinate set of the lane line in the global coordinate system and the prior coordinate set of the lane line in the global coordinate system, so that the lane line can be positioned through the point cloud, and the vehicle posture can be adjusted by determining the vehicle posture calibration amount by using the lane line position detected by the point cloud and the actual position of the lane line in the global coordinate system, thereby improving the accuracy of the vehicle posture adjustment.

[0010] According to one embodiment of the present application, obtaining a point cloud image collected by a laser radar of a target vehicle includes:

[0011] According to the relative position of each of the laser radars and the target laser radar among the laser radars, the point cloud collected by each of the laser radars is converted to the radar coordinate system of the target laser radar to obtain the point cloud image.

[0012] According to an embodiment of the present application, according to the relative position of each of the laser radars and the target laser radar among the laser radars, the point cloud collected by each of the laser radars is converted to the radar coordinate system of the target laser radar to obtain the point cloud image:

[0013] According to the relative position of each of the laser radars and the target laser radar among the laser radars, the point cloud collected by each of the laser radars at each moment in a single frame period is converted to the radar coordinate system generated by the target laser radar at the starting moment of the single frame period to obtain the point cloud image;

[0014] The single-frame period is the period during which the laser radar collects one frame of point cloud.

[0015] According to one embodiment of the present application, it also includes:

[0016] Acquire a road surface point cloud corresponding to the road surface from the point cloud image according to the vertical coordinate of each data point in the point cloud image in the radar coordinate system and the installation height of the target laser radar corresponding to the radar coordinate system;

[0017] A lane line point cloud corresponding to the lane line is obtained from the road surface point cloud.

[0018] According to one embodiment of the present application, obtaining a lane line point cloud corresponding to a lane line from the road surface point cloud includes:

[0019] A lane line point cloud corresponding to the lane line is obtained from the road surface point cloud according to the reflection intensity of each data point in the road surface point cloud.

[0020] According to one embodiment of the present application, obtaining a lane line point cloud corresponding to a lane line from the road surface point cloud includes:

[0021] Acquire target data points corresponding to lane lines from the road surface point cloud;

[0022] Each of the target data points is thinned to obtain the lane line point cloud.

[0023] According to an embodiment of the present application, thinning is performed on each of the target data points to obtain the lane line point cloud, including:

[0024] Clustering each of the target data points according to the coordinates of each of the target data points in the radar coordinate system to obtain a plurality of data point sets;

[0025] The lane line point cloud is obtained according to the centroid of each data point set.

[0026] According to an embodiment of the present application, according to a point cloud coordinate set of a lane line point cloud corresponding to a lane line in the point cloud image in the radar coordinate system, converting the lane line point cloud from the radar coordinate system to a global coordinate system to obtain a current coordinate set of the lane line in the global coordinate system includes:

[0027] According to the point cloud coordinate set of the lane line point cloud in the radar coordinate system, converting the lane line point cloud from the radar coordinate system to a global coordinate system to obtain a point cloud coordinate set of the lane line point cloud in the global coordinate system;

[0028] According to the point cloud coordinate set of the lane line point cloud in the global coordinate system, curve fitting is performed on the lane line point cloud to obtain a current lane curve in the global coordinate system;

[0029] According to the current lane curve, a current coordinate set of the lane line in a global coordinate system is obtained.

[0030] According to one embodiment of the present application, according to the point cloud coordinate set of the lane line point cloud in the radar coordinate system, the lane line point cloud is converted from the radar coordinate system to the global coordinate system to obtain the point cloud coordinate set of the lane line point cloud in the global coordinate system, including:

[0031] According to the point cloud coordinate set of the lane line point cloud in the radar coordinate system, converting the lane line point cloud from the radar coordinate system to the vehicle coordinate system of the target vehicle to obtain the point cloud coordinate set of the lane line point cloud in the vehicle coordinate system;

[0032] According to the relative coordinate position of the vehicle coordinate system of the target vehicle and the global coordinate system, the point cloud coordinate set of the lane line point cloud in the vehicle coordinate system is converted to the global coordinate system to obtain the point cloud coordinate set of the lane line point cloud in the global coordinate system.

[0033] According to one embodiment of the present application, adjusting the current position and posture of the target vehicle according to the current coordinate set of the lane line in the global coordinate system and the prior coordinate set of the lane line in the global coordinate system includes:

[0034] Performing coordinate registration of the current coordinate set of the lane line in the global coordinate system with the prior coordinate set of the lane line in the global coordinate system to determine the position deviation and heading angle deviation of the target vehicle;

[0035] The current posture of the target vehicle is adjusted according to the position deviation and the heading angle deviation.

[0036] According to the second aspect of the present application, the vehicle posture adjustment device includes:

[0037] A point cloud image acquisition module is used to acquire a point cloud image collected by a laser radar of a target vehicle;

[0038] A lane coordinate conversion module, for converting the lane point cloud corresponding to the lane line in the point cloud image from the radar coordinate system to the global coordinate system according to the point cloud coordinate set in the radar coordinate system, so as to obtain a current coordinate set of the lane line in the global coordinate system;

[0039] The vehicle posture adjustment module is used to adjust the current posture of the target vehicle according to the current coordinate set of the lane line in the global coordinate system and the prior coordinate set of the lane line in the global coordinate system.

[0040] According to an electronic device of an embodiment of the third aspect of the present application, the electronic device includes a processor and a memory storing a computer program, and when the processor executes the computer program, the vehicle posture adjustment method described in any of the above embodiments is implemented.

[0041] According to the computer-readable storage medium of the fourth aspect embodiment of the present application, a computer program is stored thereon, and when the computer program is executed by a processor, the vehicle posture adjustment method described in any of the above embodiments is implemented.

[0042] According to the computer program product of the fifth aspect of the present application, a computer program is stored thereon, and when the computer program is executed by a processor, the vehicle posture adjustment method as described in any of the above embodiments is implemented.

[0043] The vehicle according to the sixth aspect embodiment of the present application includes the electronic device as described in the above embodiment. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1 It is a first flow chart of the vehicle posture adjustment method provided in an embodiment of the present application;

[0046] Figure 2a is a coordinate diagram of the lane line in the global coordinate system provided by an embodiment of the present application;

[0047] Figure 2b is another coordinate diagram of the lane line in the global coordinate system provided by an embodiment of the present application;

[0048] Figure 3 is a schematic diagram of the current lane curve provided in an embodiment of the present application;

[0049] Figure 4 is a second flow chart of the vehicle posture adjustment method provided in an embodiment of the present application;

[0050] Figure 5 is a schematic structural diagram of a vehicle posture adjustment device provided in an embodiment of the present application;

[0051] Figure 6 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0053] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0054] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0055] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0056] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0057] At present, more and more vehicles are equipped with assisted driving modes to assist vehicles in driving on fixed routes and improve vehicle driving safety. In related technologies, the method for assisting vehicles in driving on fixed routes is to obtain road information through the front camera of the vehicle, and then adjust the vehicle's posture according to the road information obtained by the front camera to assist the vehicle in driving on the fixed route.

[0058] However, since the front camera can only capture images but cannot detect the scale and depth information of the road, and is sensitive to light, it is impossible to determine the relative position relationship between the captured road information and the vehicle body, and thus is unable to locate the vehicle body. Therefore, using the above method to achieve vehicle posture adjustment will affect the accuracy of the vehicle posture adjustment.

[0059] In response to the above technical problems, the embodiment of the present application obtains a point cloud image collected by a laser radar of the target vehicle, and according to the point cloud coordinate set of the lane line point cloud corresponding to the lane line in the point cloud image in the radar coordinate system, converts the lane line point cloud from the radar coordinate system to the global coordinate system, and obtains the current coordinate set of the lane line in the global coordinate system, so as to adjust the current posture of the target vehicle according to the current coordinate set of the lane line in the global coordinate system and the prior coordinate set of the lane line in the global coordinate system, so that the lane line can be positioned through the point cloud, and the vehicle posture can be adjusted by determining the vehicle posture calibration amount by using the lane line position detected by the point cloud and the actual position of the lane line in the global coordinate system, thereby improving the accuracy of the vehicle posture adjustment.

[0060] According to some embodiments of the present application, embodiments of the present application provide a vehicle posture adjustment method, which can be applied to a controller to achieve vehicle posture adjustment. The controller can be any terminal device such as a mobile terminal, a desktop terminal, a vehicle-mounted terminal or a server. The server can be an independent server or a server cluster composed of multiple servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence sampling point devices.

[0061] like Figure 1 As shown, the vehicle posture adjustment method includes:

[0062] S101, acquiring a point cloud image collected by a laser radar of a target vehicle;

[0063] S102, according to a point cloud coordinate set of a lane line point cloud corresponding to the lane line in the point cloud image in the radar coordinate system, converting the lane line point cloud from the radar coordinate system to a global coordinate system to obtain a current coordinate set of the lane line in the global coordinate system;

[0064] S103, adjusting the current position and posture of the target vehicle according to the current coordinate set of the lane line in the global coordinate system and the priori coordinate set of the lane line in the global coordinate system.

[0065] Among them, LiDAR is the abbreviation of laser detection and ranging system, which is the product of the combination of laser technology and radar technology. It can be used to accurately measure the target position (distance and angle), motion state (speed, vibration and posture) and shape, detect, identify, distinguish and track the target. The target vehicle is any vehicle that needs to adjust its posture, and the target vehicle can be equipped with at least one LiDAR.

[0066] When the vehicle posture needs to be adjusted, the laser radar mounted on the target vehicle, such as the laser radar mounted on the front of the target vehicle, can first scan the point cloud around the vehicle, and form a point cloud image with a frame of point cloud scanned by the laser radar, that is, a single frame of point cloud. Since the point cloud image is obtained by the laser radar, the point cloud image is the point cloud image in the radar coordinate system formed by the laser radar. The radar coordinate system can be a three-dimensional coordinate system.

[0067] After obtaining the point cloud image in the radar coordinate system, the lane line point cloud corresponding to the lane line can be extracted from the point cloud image. For the extraction of the lane line point cloud, the measured point cloud obtained by scanning the lane line with the laser radar can be matched with the point cloud image to extract the point cloud with a similarity greater than a preset similarity with the measured point cloud from the point cloud image and determine it as the lane line point cloud. Alternatively, the point cloud in the point cloud image can be clustered by point cloud segmentation, and then the point cloud with a shape similar to the shape of the lane line can be extracted from the point cloud image according to the shape of the clustered point cloud as the lane line point cloud.

[0068] After the lane line point cloud is extracted, since the point cloud image is in the radar coordinate system and the lane line point cloud is a partial point cloud in the point cloud image, the coordinates of each data point in the lane line point cloud in the radar coordinate system can be used to form a point cloud coordinate set of the lane line point cloud in the radar coordinate system.

[0069] For the point cloud coordinate set of the lane line point cloud in the radar coordinate system, the coordinate system conversion methods such as the grid method, the multi-parameter method and the multivariate regression method can be used to convert the point cloud coordinate set of the lane line point cloud in the radar coordinate system, that is, the coordinates of each data point in the lane line point cloud in the radar coordinate system, to the global coordinate system, and obtain the coordinates of each data point in the lane line point cloud in the global coordinate system, so as to determine the coordinates of each data point in the lane line point cloud in the global coordinate system as the current coordinate set of the lane line in the global coordinate system. Among them, the global coordinate system can be a world coordinate system, a map coordinate system or an absolute coordinate system, which is a coordinate system defined with the entire earth or a specific area as the reference system. The origin of the global coordinate system can be the center of the earth or other fixed geographical location, and the direction and position of the coordinate axis are fixed and do not change with the movement of the object. The global coordinate system can be a two-dimensional coordinate system or a three-dimensional coordinate system.

[0070] After obtaining the current coordinate set of the lane line in the global coordinate system, the current coordinate set of the lane line in the global coordinate system can be matched with the prior coordinate set of the lane line in the global coordinate system, so as to adjust the current posture of the target vehicle according to the matching result between the current coordinate set and the prior coordinate set. The prior coordinate set of the lane line in the global coordinate system includes the coordinates of each point of the lane line actually measured in the global coordinate system.

[0071] Exemplarily, the current coordinate set of the lane line in the global coordinate system is matched with the prior coordinate set of the lane line in the global coordinate system. The data points in the current coordinate set are fitted according to the current coordinate set of the lane line in the global coordinate system to obtain the current lane curve A of the lane line in the global coordinate system, and the actual lane curve A' of the corresponding lane line is generated in the global coordinate system according to the prior coordinate set of the lane line in the global coordinate system, such as Figure 2a shown.

[0072] After obtaining the current lane curve A and the actual lane curve A' in the global coordinate system, the angle between the current lane curve A and the actual lane curve A' can be calculated through the current lane curve A and the actual lane curve A', and the angle can be used as the heading angle deviation of the target vehicle. If the heading angle deviation is greater than the preset value, such as greater than 0, it means that there is a difference in geographic space between the lane line position measured by the lidar and the actual position of the lane line, which will cause the heading of the target vehicle on the fixed line to shift. At this time, the current posture of the target vehicle can be adjusted according to the heading angle deviation until the heading angle deviation is the preset value. If the heading angle deviation is 0, it means that the posture adjustment of the target vehicle is completed.

[0073] Or, if Figure 2b As shown, the current coordinates of any two data points can be extracted from the current lane curve A, such as extracting the coordinates of two data points with ordinates of 0 and 10 from the current lane curve A as a set of coordinate pairs, assuming that they are (a0, 0) and (a0, 10) respectively; and extracting the prior coordinates of points with the same ordinates as the two data points from the actual lane curve A' as another set of coordinate pairs, assuming that they are (a0', 0) and (a0', 10) respectively. Then, the two sets of coordinate pairs are aligned, such as using the I CP (Iterative Closest Point) algorithm for alignment, to obtain the rotation matrix R and the offset vector t. If the rotation matrix R is not the first preset value, such as not 1, or the offset vector is not the second preset value, such as not 0, it means that the lane line position measured by the laser radar and the actual position of the lane line are different in geographic space, which will cause the heading of the target vehicle on the fixed line to deviate. At this time, the current posture of the target vehicle can be adjusted according to the rotation matrix R and the offset vector t, such as adjusting the current pitch angle and the current roll angle of the vehicle, until the rotation matrix R is 1 and the offset vector t is 0, then the adjustment of the current posture of the target vehicle is completed.

[0074] By acquiring a point cloud image collected by a laser radar of the target vehicle, and according to the point cloud coordinate set of the lane line point cloud corresponding to the lane line in the point cloud image in the radar coordinate system, the lane line point cloud is converted from the radar coordinate system to the global coordinate system to obtain the current coordinate set of the lane line in the global coordinate system, so as to adjust the current posture of the target vehicle according to the current coordinate set of the lane line in the global coordinate system and the prior coordinate set of the lane line in the global coordinate system, so that the lane line can be positioned through the point cloud, and the vehicle posture can be adjusted by determining the vehicle posture calibration amount by using the lane line position detected by the point cloud and the actual position of the lane line in the global coordinate system, thereby improving the accuracy of the vehicle posture adjustment.

[0075] Considering that a vehicle may be equipped with multiple laser radars for collecting point clouds, and since each laser radar is installed at a different position of the vehicle, the radar coordinate systems of different laser radars are different, and the scanning areas of each laser radar are not completely overlapped, in order to make the collected point cloud image more complete and avoid affecting the subsequent vehicle posture adjustment due to the different coordinate systems of the point clouds collected by different laser radars, in some embodiments, obtaining the point cloud image collected by the laser radar of the target vehicle includes:

[0076] According to the relative position of each of the laser radars and the target laser radar among the laser radars, the point cloud collected by each of the laser radars is converted to the radar coordinate system of the target laser radar to obtain the point cloud image.

[0077] In some embodiments, since the installation positions of the laser radars are known, the relative positions of the laser radars and the target laser radar can be determined, wherein the target laser radar can be any laser radar among the laser radars, such as the laser radar directly in front of the vehicle.

[0078] After obtaining the single-frame point cloud collected by each laser radar through each laser radar, the point cloud collected by each laser radar can be converted to the radar coordinate system of the target laser radar by using coordinate system conversion methods such as grid method, multi-parameter method and multivariate regression method according to the relative position of each laser radar and the target laser radar, so as to splice the point cloud collected by each laser radar in the radar coordinate system of the target laser radar, and obtain a point cloud image in a single radar coordinate system. In this way, the point cloud collected by each laser radar can be converted to the same radar coordinate system for splicing to obtain a point cloud image, making the collected point cloud image more complete, and at the same time avoiding the influence of the subsequent vehicle posture adjustment due to the different coordinate systems of the point clouds collected by different laser radars, thereby improving the accuracy of the vehicle posture adjustment.

[0079] Considering that it usually takes 100ms for the laser radar to collect a frame of point cloud, if the vehicle is in motion during the process of the laser radar collecting a frame of point cloud, the laser radar at each moment in the single frame of point cloud will have different postures, causing the radar coordinate system of the laser radar to be offset, resulting in the coordinate set of the single frame of point cloud in the radar coordinate system to be offset, thereby affecting the accuracy of the vehicle posture adjustment. Therefore, in some embodiments, according to the relative position of each laser radar and the target laser radar in each laser radar, the point cloud collected by each laser radar is converted to the radar coordinate system of the target laser radar to obtain the point cloud image:

[0080] According to the relative position of each of the laser radars and the target laser radar among the laser radars, the point cloud collected by each of the laser radars at each moment within a single frame period is converted to the radar coordinate system generated by the target laser radar at the starting moment of the single frame period to obtain the point cloud image.

[0081] Among them, a single frame period refers to the period of time when the laser radar collects a frame of point cloud, such as 100ms. The starting time of the single frame period is the time corresponding to the frame header of a frame of point cloud. In the process of laser radar collecting point cloud, the starting time of the target laser radar in the single frame period, that is, the position of the target laser radar at the time corresponding to the frame header of the single frame point cloud can be obtained, and then the accelerometer and angular velocity meter of the vehicle's IMU (Inertial Measurement Unit) are used to calculate the position change and attitude change of the vehicle at each moment in the single frame period, so as to determine the relative position of each laser radar at each moment in the single frame period and the target laser radar at the starting moment of the single frame period.

[0082] After determining the relative position of each laser radar at each moment in a single frame period and the target laser radar at the start moment of the single frame period, the point cloud collected by each laser radar at each moment in a single frame period can be converted to the radar coordinate system generated by the target laser radar at the start moment of the single frame period according to the relative position of each laser radar at each moment in a single frame period and the target laser radar at the start moment of the single frame period to obtain a point cloud image. Thus, when the vehicle is in operation, motion compensation can be performed on the collected point cloud to reduce the offset of the coordinate set of the collected point cloud in the radar coordinate system caused by the movement of the vehicle, thereby reducing the impact of the coordinate offset of the point cloud on the vehicle posture adjustment and improving the accuracy of the vehicle posture adjustment.

[0083] After acquiring the point cloud image in the radar coordinate system, the lane line point cloud corresponding to the lane line can be extracted from the point cloud image. However, since the point cloud category scanned by the laser radar may be relatively complex, for example, in addition to the ground, dynamic and static objects such as tree trunks, walls, and other vehicles may also be scanned, and these objects will interfere with the extraction of the lane line and affect the accuracy of the extracted lane line point cloud. Therefore, in some embodiments, the vehicle posture adjustment method also includes:

[0084] Acquire a road surface point cloud corresponding to the road surface from the point cloud image according to the vertical coordinate of each data point in the point cloud image in the radar coordinate system and the installation height of the target laser radar corresponding to the radar coordinate system;

[0085] A lane line point cloud corresponding to the lane line is obtained from the road surface point cloud.

[0086] In some embodiments, since the radar coordinate system is generated based on the location of the target laser radar, the installation height of the target laser radar can be recorded in advance. After obtaining the point cloud image in the radar coordinate system generated by the target laser radar, the vertical coordinate of the point cloud corresponding to the road surface can be determined according to the height of the target laser radar. If the height of the target laser radar is h, the vertical coordinate of the point cloud corresponding to the road surface is z=-h.

[0087] After determining that the vertical coordinate z=-h of the point cloud corresponding to the road surface, the data point with the vertical coordinate z=-h can be obtained from the point cloud image and determined as the road surface point cloud corresponding to the road surface. Alternatively, based on the vertical coordinate z=-h, the data points in the point cloud image can be clustered to obtain all data points whose distance between the vertical coordinate z and -h is less than a preset distance and determined as the road surface point cloud corresponding to the road surface. Regardless of whether the target vehicle is on an uphill, downhill or flat road, the radar coordinate system of the target laser radar will change with the change of the pitch angle of the target vehicle. At this time, the Z axis of the radar coordinate system will always be perpendicular to the road surface. Therefore, regardless of whether the target vehicle is on an uphill, downhill or flat road, the road surface point cloud corresponding to the road surface can be obtained from the point cloud image in the above manner.

[0088] After obtaining the road surface point cloud corresponding to the road surface, the lane line point cloud corresponding to the lane line can be obtained from the road surface point cloud. For example, the measured point cloud obtained by scanning the lane line with a lidar can be matched with the road surface point cloud to extract the point cloud whose similarity with the measured point cloud is greater than the preset similarity from the road surface point cloud and determine it as the lane line point cloud. Alternatively, the point cloud in the road surface point cloud can be clustered by point cloud segmentation, and then the point cloud with a shape similar to the shape of the lane line can be extracted from the road surface point cloud according to the shape of the clustered point cloud as the lane line point cloud. In this way, the interference caused by redundant objects to the extraction of lane lines can be reduced, and the accuracy of the extracted lane line point cloud can be improved.

[0089] In order to more accurately extract the lane line point cloud corresponding to the lane line, in some embodiments, obtaining the lane line point cloud corresponding to the lane line from the road surface point cloud includes:

[0090] A lane line point cloud corresponding to the lane line is obtained from the road surface point cloud according to the reflection intensity of each data point in the road surface point cloud.

[0091] In some embodiments, since the reflection intensities of different objects vary when the laser radar is scanning an object, the lane lines may be scanned in advance by the laser radar, and the reflection intensities of the data points formed by the lane lines may be recorded as the target reflection intensity.

[0092] After obtaining the road surface point cloud, the reflection intensity of each data point in the road surface point cloud can be matched with the target reflection intensity. If the reflection intensity of a data point matches the target reflection intensity, such as the reflection intensity of the data point is the same as the target reflection intensity, then the data point can be determined to be the target data point corresponding to the lane line. Therefore, according to the reflection intensity of each data point in the road surface point cloud, all target data points corresponding to the lane line can be extracted from the road surface point cloud to form a lane line point cloud.

[0093] Considering that the number of data points corresponding to the lane line in the point cloud image may be large, it may affect the processing efficiency of the subsequent lane line point cloud. Therefore, in order to improve the processing efficiency of the subsequent lane line point cloud, in some embodiments, the lane line point cloud corresponding to the lane line is obtained from the road surface point cloud, including:

[0094] Acquire target data points corresponding to lane lines from the road surface point cloud;

[0095] According to the coordinates of each target data point in the radar coordinate system, each target data point is thinned to obtain the lane line point cloud.

[0096] In some embodiments, all target data points corresponding to lane lines can be extracted from the road surface point cloud according to the reflection intensity of each data point in the road surface point cloud. After obtaining each target data point, each target data point can be thinned out to form a lane line point cloud with the remaining target data points after the thinning out.

[0097] For example, target data points with the same coordinates may be deduplicated according to the coordinates of each target data point in the radar coordinate system, so that the deduplicated target data points form a lane point cloud. Alternatively, the Douglas-Peucker algorithm may be used to perform thinning processing on each target data point, so that the target data points remaining after the thinning processing form a lane point cloud.

[0098] In order to further improve the subsequent processing efficiency of the lane line point cloud, in some embodiments, each of the target data points is thinned to obtain the lane line point cloud, including:

[0099] Clustering each of the target data points according to the coordinates of each of the target data points in the radar coordinate system to obtain a plurality of data point sets;

[0100] The lane line point cloud is obtained according to the centroid of each data point set.

[0101] In some embodiments, for all target data points corresponding to the lane lines, a clustering algorithm, such as a KNN clustering algorithm, may be used to cluster each target data point according to its coordinates in the radar coordinate system to obtain multiple groups of data point sets, wherein any data point set includes all target data points in the same group.

[0102] For any data point set, the centroid of the data point set in the radar coordinate system can be determined based on the coordinates of each target data point in the data point set in the radar coordinate system. The centroid of each set of data points in the radar coordinate system can be used as the data point corresponding to the lane line obtained after thinning each target data point. The centroid of each set of data points in the radar coordinate system can form a lane line point cloud, and the coordinates of each centroid in the radar coordinate system are the point cloud coordinate set of the lane line point cloud in the radar coordinate system. This can reduce the amount of data in the acquired lane line point cloud and improve the efficiency of subsequent processing of the lane line point cloud.

[0103] After obtaining the lane point cloud, the lane point cloud can be converted from the radar coordinate system to the global coordinate system to obtain the current coordinate set of the lane in the global coordinate system. Considering that the lane is usually a smooth curve, in some embodiments, the lane point cloud can be converted from the radar coordinate system to the global coordinate system according to the point cloud coordinate set of the lane point cloud in the radar coordinate system to obtain the point cloud coordinate set of the lane point cloud in the global coordinate system; according to the point cloud coordinate set of the lane point cloud in the global coordinate system, the lane point cloud can be curve fitted to obtain the current lane curve in the global coordinate system; according to the current lane curve, the current coordinate set of the lane in the global coordinate system can be obtained.

[0104] In some embodiments, the point cloud coordinate set of the lane line point cloud in the radar coordinate system can be converted to the global coordinate system through coordinate system conversion to obtain the point cloud coordinate set of the lane line point cloud in the global coordinate system. Figure 3 shown.

[0105] Function fitting is performed on the point cloud coordinate set of the lane line point cloud in the global coordinate system. For example, cubic spline curve fitting can be used for the point cloud coordinate set of the lane line point cloud in the global coordinate system, or linear regression processing can be performed on the point cloud coordinate set of the lane line point cloud in the global coordinate system to obtain the current lane curve L corresponding to the lane line in the global coordinate system, such as Figure 3As shown. The coordinate points of each data point in the current lane curve L in the global coordinate system can constitute the current coordinate set of the lane line in the global coordinate system. In this way, the smoothness of the current coordinate set of the lane line in the global coordinate system can be guaranteed, so that the current coordinate set of the lane line in the global coordinate system is more consistent with the actual situation of the lane line, and the accuracy of the subsequent vehicle posture adjustment using the current coordinate set is improved.

[0106] Considering that when coordinate system conversion is required, the conversion relationship between the radar coordinate system and each coordinate point in the global coordinate system is usually difficult to determine directly, but the conversion relationship between the radar coordinate system and each coordinate point in the vehicle coordinate system, and the conversion relationship between each coordinate point in the vehicle coordinate system and the global coordinate system can be determined directly. Therefore, in order to improve the conversion efficiency of point cloud coordinates, in some embodiments, according to the point cloud coordinate set of the lane line point cloud in the radar coordinate system, the lane line point cloud is converted from the radar coordinate system to the global coordinate system to obtain the point cloud coordinate set of the lane line point cloud in the global coordinate system, including:

[0107] According to the point cloud coordinate set of the lane line point cloud in the radar coordinate system, converting the lane line point cloud from the radar coordinate system to the vehicle coordinate system of the target vehicle to obtain the point cloud coordinate set of the lane line point cloud in the vehicle coordinate system;

[0108] According to the relative coordinate position of the vehicle coordinate system of the target vehicle and the global coordinate system, the point cloud coordinate set of the lane line point cloud in the vehicle coordinate system is converted to the global coordinate system to obtain the point cloud coordinate set of the lane line point cloud in the global coordinate system.

[0109] In some embodiments, the vehicle coordinate system refers to the body coordinate system of the target vehicle itself, and its origin is usually located at the center of gravity of the vehicle, such as the center of the rear axle of the vehicle. After obtaining the point cloud coordinate set of the lane line point cloud in the radar coordinate system, the point cloud coordinate set of the lane line point cloud in the radar coordinate system can be rotated and translated based on the rotation matrix and translation matrix calculated based on the position difference between the origin of the radar coordinate system and the origin of the vehicle coordinate system, and the lane line point cloud is converted from the radar coordinate system to the vehicle coordinate system to obtain the point cloud coordinate set of the lane line point cloud in the vehicle coordinate system.

[0110] After obtaining the point cloud coordinate set of the lane line point cloud in the vehicle coordinate system, the lane line point cloud can be converted from the vehicle coordinate system to the global coordinate system according to the relative coordinate position of the vehicle coordinate system of the target vehicle and the global coordinate system to obtain the point cloud coordinate set of the lane line point cloud in the global coordinate system.

[0111] By first converting the lane line point cloud from the radar coordinate system to the vehicle coordinate system, and then converting the lane line point cloud from the vehicle coordinate system to the global coordinate system, there is no need to determine the coordinate position relationship between the radar coordinate system and the global coordinate system. The lane line point cloud can also be converted from the radar coordinate system to the global coordinate system, thereby improving the conversion efficiency of the point cloud coordinates.

[0112] After obtaining the current coordinate set of the lane line in the global coordinate system, the current coordinate set of the lane line in the global coordinate system can be matched with the prior coordinate set of the lane line in the global coordinate system to adjust the current posture of the target vehicle according to the matching result between the current coordinate set and the prior coordinate set.

[0113] To further improve the accuracy of adjusting the current posture of the vehicle, in some embodiments, adjusting the current posture of the target vehicle according to the current coordinate set of the lane line in the global coordinate system and the prior coordinate set of the lane line in the global coordinate system includes:

[0114] Performing coordinate registration of the current coordinate set of the lane line in the global coordinate system with the prior coordinate set of the lane line in the global coordinate system to determine the position deviation and heading angle deviation of the target vehicle;

[0115] The current posture of the target vehicle is adjusted according to the position deviation and the heading angle deviation.

[0116] In some embodiments, since the current coordinate set of the lane line in the global coordinate system can represent the coordinate set of the data points in the current lane curve A of the lane line in the global coordinate system, after obtaining the current coordinate set of the lane line in the global coordinate system, the current coordinate set of the lane line in the global coordinate system and the prior coordinate set of the lane line in the global coordinate system can be used to calculate the angle between the current lane curve A formed by the current coordinate set and the actual lane curve A' formed by the prior coordinate set, so as to use the angle as the heading angle deviation of the target vehicle. At the same time, the minimum distance between the endpoint coordinates in the current coordinate set and the actual lane curve A' formed by the prior coordinate set can be calculated, or the distance between the midpoint coordinates in the current coordinate set and the actual lane curve A' formed by the prior coordinate set can be calculated as the position deviation of the target vehicle.

[0117] After obtaining the position deviation and heading angle deviation of the target vehicle, the current posture of the target vehicle can be adjusted according to the position deviation and heading angle deviation until the position deviation is less than or equal to the preset distance, such as the position deviation is zero, and the heading angle deviation is less than or equal to the preset angle, such as the heading angle deviation is zero, then it means that the adjustment of the current posture of the target vehicle is completed, thereby further improving the accuracy of the current posture adjustment of the target vehicle.

[0118] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution in the present application will be described clearly and completely below. In some embodiments, Figure 4 As shown, the vehicle posture adjustment method includes:

[0119] S201, according to the relative positions of the laser radars of the target vehicle and the target laser radar among the laser radars, the point clouds collected by the laser radars at each moment in a single frame period are converted to the radar coordinate system generated by the target laser radar at the start moment of the single frame period to obtain a point cloud image. The single frame period is the period during which the laser radar collects one frame of point cloud.

[0120] S202, obtaining a road surface point cloud corresponding to the road surface from the point cloud image according to the vertical coordinate of each data point in the point cloud image in the radar coordinate system and the installation height of the target laser radar corresponding to the radar coordinate system.

[0121] S203, acquiring each target data point corresponding to the lane line from the road surface point cloud according to the reflection intensity of each data point in the road surface point cloud.

[0122] S204, clustering each target data point according to the coordinates of each target data point in the radar coordinate system to obtain a plurality of data point sets, and obtaining a lane line point cloud according to the centroid of each data point set.

[0123] S205 , according to the point cloud coordinate set of the lane line point cloud in the radar coordinate system, convert the lane line point cloud from the radar coordinate system to the vehicle coordinate system of the target vehicle to obtain the point cloud coordinate set of the lane line point cloud in the vehicle coordinate system.

[0124] S206, according to the relative coordinate position between the vehicle coordinate system of the target vehicle and the global coordinate system, convert the point cloud coordinate set of the lane line point cloud in the vehicle coordinate system to the global coordinate system to obtain the point cloud coordinate set of the lane line point cloud in the global coordinate system.

[0125] S207, performing curve fitting on the lane line point cloud according to the point cloud coordinate set of the lane line point cloud in the global coordinate system to obtain a current lane curve in the global coordinate system.

[0126] S208, obtaining a current coordinate set of the lane line in the global coordinate system according to the current lane curve.

[0127] S209, coordinate alignment is performed on the current coordinate set of the lane line in the global coordinate system and the priori coordinate set of the lane line in the global coordinate system to determine the position deviation and heading angle deviation of the target vehicle.

[0128] S210, adjusting the current posture of the target vehicle according to the position deviation and the heading angle deviation.

[0129] The vehicle posture adjustment device provided in the present application is described below. The vehicle posture adjustment device described below and the vehicle posture adjustment method described above can be referenced to each other.

[0130] In one embodiment, if Figure 5 As shown, a vehicle posture adjustment device is provided, comprising:

[0131] The point cloud image acquisition module 210 is used to acquire the point cloud image collected by the laser radar of the target vehicle;

[0132] A lane coordinate conversion module 220 is used to convert the lane point cloud corresponding to the lane line in the point cloud image from the radar coordinate system to the global coordinate system to obtain a current coordinate set of the lane line in the global coordinate system;

[0133] The vehicle posture adjustment module 230 is used to adjust the current posture of the target vehicle according to the current coordinate set of the lane line in the global coordinate system and the prior coordinate set of the lane line in the global coordinate system.

[0134] By acquiring a point cloud image collected by a laser radar of the target vehicle, and according to the point cloud coordinate set of the lane line point cloud corresponding to the lane line in the point cloud image in the radar coordinate system, the lane line point cloud is converted from the radar coordinate system to the global coordinate system to obtain the current coordinate set of the lane line in the global coordinate system, so as to adjust the current posture of the target vehicle according to the current coordinate set of the lane line in the global coordinate system and the prior coordinate set of the lane line in the global coordinate system, so that the lane line can be positioned through the point cloud, and the vehicle posture can be adjusted by determining the vehicle posture calibration amount by using the lane line position detected by the point cloud and the actual position of the lane line in the global coordinate system, thereby improving the accuracy of the vehicle posture adjustment.

[0135] In one embodiment, the point cloud image acquisition module 210 is specifically used for:

[0136] According to the relative position of each of the laser radars and the target laser radar among the laser radars, the point cloud collected by each of the laser radars is converted to the radar coordinate system of the target laser radar to obtain the point cloud image.

[0137] In one embodiment, the point cloud image acquisition module 210 is specifically used for:

[0138] According to the relative position of each of the laser radars and the target laser radar among the laser radars, the point cloud collected by each of the laser radars at each moment in a single frame period is converted to the radar coordinate system generated by the target laser radar at the starting moment of the single frame period to obtain the point cloud image;

[0139] The single-frame period is the period during which the laser radar collects one frame of point cloud.

[0140] In one embodiment, the point cloud image acquisition module 210 is further used for:

[0141] Acquire a road surface point cloud corresponding to the road surface from the point cloud image according to the vertical coordinate of each data point in the point cloud image in the radar coordinate system and the installation height of the target laser radar corresponding to the radar coordinate system;

[0142] A lane line point cloud corresponding to the lane line is obtained from the road surface point cloud.

[0143] In one embodiment, the point cloud image acquisition module 210 is specifically used for:

[0144] A lane line point cloud corresponding to the lane line is obtained from the road surface point cloud according to the reflection intensity of each data point in the road surface point cloud.

[0145] In one embodiment, the point cloud image acquisition module 210 is specifically used for:

[0146] Acquire target data points corresponding to lane lines from the road surface point cloud;

[0147] Each of the target data points is thinned to obtain the lane line point cloud.

[0148] In one embodiment, the point cloud image acquisition module 210 is specifically used for:

[0149] Clustering each of the target data points according to the coordinates of each of the target data points in the radar coordinate system to obtain a plurality of data point sets;

[0150] The lane line point cloud is obtained according to the centroid of each data point set.

[0151] In one embodiment, the lane coordinate conversion module 220 is specifically used for:

[0152] According to the point cloud coordinate set of the lane line point cloud in the radar coordinate system, converting the lane line point cloud from the radar coordinate system to a global coordinate system to obtain a point cloud coordinate set of the lane line point cloud in the global coordinate system;

[0153] According to the point cloud coordinate set of the lane line point cloud in the global coordinate system, curve fitting is performed on the lane line point cloud to obtain a current lane curve in the global coordinate system;

[0154] According to the current lane curve, a current coordinate set of the lane line in a global coordinate system is obtained.

[0155] In one embodiment, the lane coordinate conversion module 220 is specifically used for:

[0156] According to the point cloud coordinate set of the lane line point cloud in the radar coordinate system, converting the lane line point cloud from the radar coordinate system to the vehicle coordinate system of the target vehicle to obtain the point cloud coordinate set of the lane line point cloud in the vehicle coordinate system;

[0157] According to the relative coordinate position of the vehicle coordinate system of the target vehicle and the global coordinate system, the point cloud coordinate set of the lane line point cloud in the vehicle coordinate system is converted to the global coordinate system to obtain the point cloud coordinate set of the lane line point cloud in the global coordinate system.

[0158] In one embodiment, the vehicle posture adjustment module is specifically used to:

[0159] Performing coordinate registration of the current coordinate set of the lane line in the global coordinate system with the prior coordinate set of the lane line in the global coordinate system to determine the position deviation and heading angle deviation of the target vehicle;

[0160] The current posture of the target vehicle is adjusted according to the position deviation and the heading angle deviation.

[0161] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call a computer program in the memory 830 to execute a vehicle posture adjustment method, for example, including:

[0162] Obtain a point cloud image collected by the laser radar of the target vehicle;

[0163] According to a point cloud coordinate set of a lane line point cloud corresponding to the lane line in the point cloud image in the radar coordinate system, converting the lane line point cloud from the radar coordinate system to a global coordinate system to obtain a current coordinate set of the lane line in the global coordinate system;

[0164] The current position and posture of the target vehicle is adjusted according to the current coordinate set of the lane line in the global coordinate system and the priori coordinate set of the lane line in the global coordinate system.

[0165] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable 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 various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-On l yMemory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0166] On the other hand, an embodiment of the present application also provides a storage medium, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the vehicle posture adjustment method provided in the above embodiments.

[0167] On the other hand, an embodiment of the present application also provides a computer program product on which a computer program is stored. When the computer program is executed by a processor, the computer program product can execute the vehicle posture adjustment method provided in the above embodiments.

[0168] On the other hand, an embodiment of the present application further provides a vehicle, which includes the electronic device provided by the above embodiment.

[0169] The device embodiments described above are merely illustrative, wherein 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, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0170] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0171] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A vehicle posture adjustment method, characterized in that: include: Obtain a point cloud image collected by the laser radar of the target vehicle; According to a point cloud coordinate set of a lane line point cloud corresponding to the lane line in the point cloud image in the radar coordinate system, converting the lane line point cloud from the radar coordinate system to a global coordinate system to obtain a current coordinate set of the lane line in the global coordinate system; The current position and posture of the target vehicle is adjusted according to the current coordinate set of the lane line in the global coordinate system and the priori coordinate set of the lane line in the global coordinate system.

2. The vehicle posture adjustment method according to claim 1, characterized in that: Get the point cloud image collected by the laser radar of the target vehicle, including: According to the relative position of each of the laser radars and the target laser radar among the laser radars, the point cloud collected by each of the laser radars is converted to the radar coordinate system of the target laser radar to obtain the point cloud image.

3. The vehicle posture adjustment method according to claim 2, characterized in that: According to the relative position of each of the laser radars and the target laser radar among the laser radars, the point cloud collected by each of the laser radars is converted to the radar coordinate system of the target laser radar to obtain the point cloud image: According to the relative position of each of the laser radars and the target laser radar among the laser radars, the point cloud collected by each of the laser radars at each moment in a single frame period is converted to the radar coordinate system generated by the target laser radar at the starting moment of the single frame period to obtain the point cloud image; The single-frame period is the period during which the laser radar collects one frame of point cloud.

4. The vehicle posture adjustment method according to claim 1, characterized in that: Also includes: Acquire a road surface point cloud corresponding to the road surface from the point cloud image according to the vertical coordinate of each data point in the point cloud image in the radar coordinate system and the installation height of the target laser radar corresponding to the radar coordinate system; A lane line point cloud corresponding to the lane line is obtained from the road surface point cloud.

5. The vehicle posture adjustment method according to claim 4, characterized in that: Acquiring a lane line point cloud corresponding to the lane line from the road surface point cloud, including: A lane line point cloud corresponding to the lane line is obtained from the road surface point cloud according to the reflection intensity of each data point in the road surface point cloud.

6. The vehicle posture adjustment method according to claim 4 or 5, characterized in that: Acquiring a lane line point cloud corresponding to the lane line from the road surface point cloud, including: Acquire target data points corresponding to lane lines from the road surface point cloud; Each of the target data points is thinned to obtain the lane line point cloud.

7. The vehicle posture adjustment method according to claim 6, characterized in that: Performing thinning processing on each of the target data points to obtain the lane line point cloud includes: Clustering each of the target data points according to the coordinates of each of the target data points in the radar coordinate system to obtain a plurality of data point sets; The lane line point cloud is obtained according to the centroid of each data point set.

8. The vehicle posture adjustment method according to any one of claims 1 to 7, characterized in that: According to the point cloud coordinate set of the lane line point cloud corresponding to the lane line in the point cloud image in the radar coordinate system, converting the lane line point cloud from the radar coordinate system to the global coordinate system to obtain the current coordinate set of the lane line in the global coordinate system, including: According to the point cloud coordinate set of the lane line point cloud in the radar coordinate system, converting the lane line point cloud from the radar coordinate system to a global coordinate system to obtain a point cloud coordinate set of the lane line point cloud in the global coordinate system; According to the point cloud coordinate set of the lane line point cloud in the global coordinate system, curve fitting is performed on the lane line point cloud to obtain a current lane curve in the global coordinate system; According to the current lane curve, a current coordinate set of the lane line in a global coordinate system is obtained.

9. The vehicle posture adjustment method according to claim 8, characterized in that: According to the point cloud coordinate set of the lane line point cloud in the radar coordinate system, the lane line point cloud is converted from the radar coordinate system to a global coordinate system to obtain a point cloud coordinate set of the lane line point cloud in the global coordinate system, including: According to the point cloud coordinate set of the lane line point cloud in the radar coordinate system, converting the lane line point cloud from the radar coordinate system to the vehicle coordinate system of the target vehicle to obtain the point cloud coordinate set of the lane line point cloud in the vehicle coordinate system; According to the relative coordinate position of the vehicle coordinate system of the target vehicle and the global coordinate system, the point cloud coordinate set of the lane line point cloud in the vehicle coordinate system is converted to the global coordinate system to obtain the point cloud coordinate set of the lane line point cloud in the global coordinate system.

10. The vehicle posture adjustment method according to any one of claims 1 to 7, characterized in that: According to the current coordinate set of the lane line in the global coordinate system and the priori coordinate set of the lane line in the global coordinate system, adjusting the current posture of the target vehicle includes: Performing coordinate registration of the current coordinate set of the lane line in the global coordinate system with the prior coordinate set of the lane line in the global coordinate system to determine the position deviation and heading angle deviation of the target vehicle; The current posture of the target vehicle is adjusted according to the position deviation and the heading angle deviation.

11. A vehicle posture adjustment device, characterized in that: include: A point cloud image acquisition module is used to acquire a point cloud image collected by a laser radar of a target vehicle; A lane coordinate conversion module, for converting the lane point cloud corresponding to the lane line in the point cloud image from the radar coordinate system to the global coordinate system according to the point cloud coordinate set in the radar coordinate system, so as to obtain a current coordinate set of the lane line in the global coordinate system; The vehicle posture adjustment module is used to adjust the current posture of the target vehicle according to the current coordinate set of the lane line in the global coordinate system and the prior coordinate set of the lane line in the global coordinate system.

12. An electronic device comprising a processor and a memory storing a computer program, characterized in that: When the processor executes the computer program, the vehicle posture adjustment method according to any one of claims 1 to 10 is implemented.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the vehicle posture adjustment method according to any one of claims 1 to 10 is implemented.

14. A computer program product having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the vehicle posture adjustment method according to any one of claims 1 to 10 is implemented.

15. A vehicle, characterized in that: Comprising the electronic device as claimed in claim 12.

Images