Positioning method, system and movable platform

Abstract

A positioning method, system and movable platform. The method obtains a point cloud collected by a sensor (101), the point cloud is used to identify the ground of the surrounding environment of the movable platform, and the sensor (101) is arranged on the movable platform (S201, S801); then determines the target feature points of the point cloud, and determines the reference feature points of a high-precision map (S202); determines the first degree of freedom information of the point cloud relative to the high-precision map according to the target feature points and the reference feature points (S203), and corrects the position and posture of the point cloud according to the first degree of freedom information (S204); determines the second degree of freedom information of the point cloud relative to the high-precision map (S205) according to the reference feature points on the high-precision map and the target feature points on the corrected point cloud; because the first degree of freedom information calculation has corrected the position and posture of the point cloud to a certain extent, the calculation range of the subsequent second degree of freedom information is reduced, the calculation amount is reduced, and the calculation speed is improved, so that the real-time performance of the degree of freedom positioning is improved, and the problem of greater difficulty in performing the degree of freedom positioning is overcome.

Description

Technical Field

[0001] The embodiments of the present application relate to positioning technology, and more particularly to a positioning method, system and movable platform. Background Art

[0002] With the development of science and technology, intelligent driving technology has gradually become the focus of people's attention.

[0003] In the related technology, it is proposed to search for the 6-degree-of-freedom posture of the car based on the high-precision map, and find out the current position of the car in the map through exhaustive search, so as to realize important functions such as real-time navigation and path planning in intelligent driving. Among them, the above six degrees of freedom posture include the freedom of movement along the three rectangular coordinate axes of X, Y, and Z (X, Y, Z values) and the freedom of rotation around these three coordinate axes (Pitch, Yaw and Roll values). Here, Pitch is the rotation around the X-axis, also called the pitch angle; Yaw is the rotation around the Z-axis, also called the yaw angle; Roll is the rotation around the Y-axis, also called the roll angle. In addition, the above-mentioned high-precision map, in layman's terms, is an electronic map with higher accuracy and more data dimensions. Higher accuracy is reflected in the accuracy to the centimeter level, and the data dimension is more reflected in the fact that it includes surrounding static information related to traffic in addition to road information.

[0004] However, when performing a 6-DOF exhaustive search on the posture, the amount of data and complexity of the search increases exponentially with the search dimension, making data processing more difficult. Summary of the invention

[0005] The embodiments of the present application provide a positioning method, system and movable platform to overcome the problem of difficulty in performing freedom positioning.

[0006] In a first aspect, an embodiment of the present application provides a positioning method, including:

[0007] Acquire a point cloud collected by a sensor, the point cloud being used to identify the ground surface of an environment surrounding a movable platform, the sensor being disposed on the movable platform;

[0008] Determine the target feature points of the point cloud and determine the reference feature points of the high-precision map;

[0009] Determining first degree of freedom information of the point cloud relative to the high-precision map according to the target feature point and the reference feature point;

[0010] Correcting the pose of the point cloud using the first degree of freedom information;

[0011] Determining second degree of freedom information of the point cloud relative to the high-precision map according to the reference feature points on the high-precision map and the target feature points on the corrected point cloud;

[0012] According to the second degree of freedom information, the movable platform is positioned on the high-precision map.

[0013] In a second aspect, an embodiment of the present application provides a positioning system, including a memory, a processor, and a computer-executable instruction stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer-executable instruction:

[0014] Acquire a point cloud collected by a sensor, the point cloud being used to identify the ground surface of an environment surrounding a movable platform, the sensor being disposed on the movable platform;

[0015] Determine the target feature points of the point cloud and determine the reference feature points of the high-precision map;

[0016] Determining first degree of freedom information of the point cloud relative to the high-precision map according to the target feature point and the reference feature point;

[0017] Correcting the pose of the point cloud using the first degree of freedom information;

[0018] Determining second degree of freedom information of the point cloud relative to the high-precision map according to the reference feature points on the high-precision map and the target feature points on the corrected point cloud;

[0019] According to the second degree of freedom information, the movable platform is positioned on the high-precision map.

[0020] In a third aspect, an embodiment of the present application provides a movable platform, comprising a movable platform body, a sensor, and a positioning system, wherein the sensor and the positioning system are arranged on the movable platform body;

[0021] The positioning system acquires a point cloud collected by the sensor, wherein the point cloud is used to identify the ground surface of the surrounding environment of the movable platform;

[0022] Determine the target feature points of the point cloud and determine the reference feature points of the high-precision map;

[0023] Determining first degree of freedom information of the point cloud relative to the high-precision map according to the target feature point and the reference feature point;

[0024] Correcting the pose of the point cloud using the first degree of freedom information;

[0025] Determining second degree of freedom information of the point cloud relative to the high-precision map according to the reference feature points on the high-precision map and the target feature points on the corrected point cloud;

[0026] According to the second degree of freedom information, the movable platform is positioned on the high-precision map.

[0027] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the positioning method described in the first aspect and various possible designs of the first aspect is implemented.

[0028] The positioning method, system and movable platform provided in the embodiments of the present application obtain a point cloud collected by a sensor, and the point cloud is used to identify the ground of the surrounding environment of the movable platform. The above-mentioned sensor is set on the movable platform, and then the first degree of freedom information of the above-mentioned point cloud relative to the high-precision map is calculated based on the target feature points of the point cloud and the reference feature points of the high-precision map. The posture of the above-mentioned point cloud is corrected according to the first degree of freedom information, and the second degree of freedom information of the point cloud relative to the high-precision map is calculated based on the target feature points on the corrected point cloud and the above-mentioned reference feature points. Since the first degree of freedom information calculation has corrected the posture of the point cloud to a certain extent, the calculation range of the subsequent second degree of freedom information is narrowed, the amount of calculation is reduced, and the calculation speed is improved, so that the real-time performance of the degree of freedom positioning can be improved, and the problem of the existing difficulty of the degree of freedom positioning can be overcome. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0030] Figure 1 A schematic diagram of the positioning system architecture provided in an embodiment of the present application;

[0031] Figure 2 A flowchart of a positioning method provided in an embodiment of the present application;

[0032] Figure 3 A schematic diagram of a point cloud surface before ground alignment provided in an embodiment of the present application;

[0033] Figure 4 A schematic diagram of a point cloud surface after ground alignment provided in an embodiment of the present application;

[0034] Figure 5 A feature point matching relationship diagram of the target feature points and the reference feature points provided in the embodiment of the present application;

[0035] Figure 6 A schematic diagram of a two-layer pyramid exhaustive search provided in an embodiment of the present application;

[0036] Figure 7A plurality of loss distribution diagrams provided for embodiments of the present application;

[0037] Figure 8 A schematic diagram of a flow chart of another positioning method provided in an embodiment of the present application;

[0038] Fig. 9 A schematic diagram of the structure of a positioning device provided in an embodiment of the present application;

[0039] Fig.10 A schematic diagram of the structure of another positioning device provided in an embodiment of the present application;

[0040] Fig.11 A schematic diagram of the hardware structure of the positioning system provided in the embodiment of the present application;

[0041] Fig.12 A schematic diagram of the structure of a movable platform provided in an embodiment of the present application.

[0042] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0043] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0044] In related technologies, a 6-DOF posture search of a car is usually performed based on a high-precision map. An exhaustive search is performed to find out the current position of the car in the map, so as to realize important functions such as real-time navigation and path planning in intelligent driving.

[0045] However, when performing a 6-DOF exhaustive search on the pose, the amount of data and complexity of the search increases exponentially with the search dimension. Therefore, the above 6-DOF pose search has a huge amount of calculation and a low calculation speed that cannot meet the usage requirements.

[0046] In order to solve this technical problem, this embodiment provides a positioning method, which obtains a point cloud collected by a sensor, and the point cloud is used to identify the ground of the surrounding environment of a movable platform. The above-mentioned sensor is set on the movable platform, and then the first degree of freedom information of the above-mentioned point cloud relative to the high-precision map is calculated based on the target feature points of the point cloud and the reference feature points of the high-precision map. The posture of the above-mentioned point cloud is corrected according to the first degree of freedom information, and the second degree of freedom information of the point cloud relative to the high-precision map is calculated based on the target feature points on the corrected point cloud and the above-mentioned reference feature points, thereby realizing 6-degree-of-freedom full posture calculation.

[0047] Since the previous three degrees of freedom calculation has corrected the pose of the point cloud to a certain extent, the calculation range of the subsequent three degrees of freedom is narrowed, and the amount of calculation is reduced, the calculation speed is faster, which can also make the real-time performance of the degree of freedom positioning better.

[0048] Figure 1 This is a schematic diagram of the architecture of the positioning system provided in the embodiment of the present application. Figure 1 As shown, it includes: a sensor 101, a high-precision map acquisition system 102, a first processor 103 and a second processor 104. Taking the movable platform as a vehicle as an example, the sensor 101 is mounted on the vehicle, and the sensor can generate a corresponding point cloud in real time, wherein the point cloud is used to identify the ground of the vehicle's surrounding environment. The high-precision map acquisition system 102 acquires a high-precision map. Exemplarily, the high-precision map acquisition system 102 can acquire a high-precision map within a preset range of the vehicle in real time, wherein the preset range can be set according to actual conditions, such as a high-precision map within a range of 10 meters of the vehicle. The first processor 103 can combine the point cloud generated by the sensor 101 and the high-precision map acquired by the high-precision map acquisition system 102 to determine the target feature points and the reference feature points, and determine the first degree of freedom information of the point cloud relative to the high-precision map based on the target feature points and the reference feature points, correct the position of the point cloud through the first degree of freedom information, and determine the second degree of freedom information of the point cloud relative to the high-precision map based on the target feature points on the corrected point cloud and the reference feature points on the high-precision map, locate the vehicle on the high-precision map based on the second degree of freedom information, and send the positioning result to the second processor 104 for subsequent driving planning and use.

[0049] Here, the above-mentioned movable platform may be a vehicle or an unmanned aerial vehicle. The first processor 103 and the second processor 104 may be a vehicle computing platform, an unmanned aerial vehicle processor, etc. This embodiment does not impose any particular restrictions on the implementation of the first processor 103 and the second processor 104, as long as the first processor 103 and the second processor 104 can perform the above-mentioned corresponding functions.

[0050] It should be understood that the above architecture is only an exemplary system architecture block diagram. In specific implementation, it can be set according to application requirements. For example, the first processor 103 and the second processor 104 can be set separately or combined to meet different application requirements.

[0051] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0052] Figure 2 This is a flow chart of the positioning method provided in the embodiment of the present application. The execution subject of this embodiment can be Figure 1 The first processor in the illustrated embodiment, such as Figure 2 As shown, the method includes:

[0053] S201. Acquire a point cloud collected by a sensor, where the point cloud is used to identify the ground surface of an environment surrounding a movable platform, and the sensor is disposed on the movable platform.

[0054] Among them, the above-mentioned point cloud can be an image point cloud, a radar point cloud, a laser point cloud, etc. In subsequent processing, one or more of the above-mentioned point clouds can be used according to actual conditions.

[0055] Optionally, acquiring the point cloud collected by the sensor includes:

[0056] Acquire a complete point cloud through the sensor;

[0057] Perform ground segmentation on the complete point cloud to obtain the point cloud.

[0058] Here, the first processor can obtain the complete point cloud in real time through the sensor, and perform ground segmentation on the complete laser point cloud to obtain the above point cloud. Point cloud ground segmentation can be achieved by projecting the three-dimensional point cloud into a horizontal grid map, setting the height difference threshold of adjacent grids according to the point cloud height information in each grid, to determine the ground points and non-ground points, thereby achieving point cloud ground segmentation; or, extracting local point features from the normal vectors of neighboring estimated points, establishing smooth constraints, and using Euclidean clustering and regional growth algorithms to quickly segment the ground and non-ground, thereby achieving point cloud ground segmentation.

[0059] In addition, in some embodiments, the above-mentioned sensor may have preliminary data processing functions, such as terminal computing capabilities, so that the above-mentioned sensor can perform preliminary data processing on its detection data, such as ground segmentation of the complete point cloud to obtain the above-mentioned point cloud, and then the processing results can be sent to the first processor for subsequent further calculations.

[0060] S202: Determine the target feature points of the point cloud and determine the reference feature points of the high-precision map.

[0061] Optionally, determining the target feature points of the point cloud includes:

[0062] Determine the target feature points in the point cloud surface obtained by projecting the point cloud in the Z-axis direction.

[0063] Wherein, the above-mentioned point cloud surface includes multiple point cloud projection points.

[0064] Specifically, determining the target feature point in the point cloud surface obtained by projecting the point cloud in the Z-axis direction includes performing any of the following operations:

[0065] Extracting feature points on the point cloud surface as the target feature points according to a feature extraction algorithm, wherein the extracted feature points include the point cloud projection points used to characterize corner points or edge points;

[0066] The point cloud surface obtained by projection is meshed according to a preset mesh size, and the central pixel of the mesh is used as the target feature point.

[0067] Here, the point cloud is first projected. For example, if there are 200,000 points in the point cloud, 30,000 pixels are obtained after projection, and the processing quantity is reduced by 85%. The target feature points in the projected point cloud surface are extracted to further reduce the data processing amount. For example, the number is from 30,000 pixels to 3K pixels, and the processing quantity is reduced by 90%. Since the number of features is much smaller than the total number of laser points, the computing resources need to be reduced to improve the subsequent processing speed.

[0068] The above feature extraction algorithm can be set according to the actual application needs, such as Difference of Gaussian (DOG). The above corner points are extreme points, which can be understood as points with particularly outstanding attributes in some aspects. The above edge points are points where the data changes meet the preset change requirements, such as points where the data changes dramatically. According to the above feature extraction algorithm, corner points or edge points are extracted from the point cloud projection points of the point cloud surface as target feature points.

[0069] In addition, the above-mentioned preset grid size can be set according to actual conditions, and the projected point cloud surface is gridded according to the preset grid size, and the central pixel of the grid is used as the target feature point, wherein the central pixel can be obtained by calculating the weighted average pixel of each point in the grid.

[0070] Optionally, the above method further includes:

[0071] The target location area of ​​the movable platform is predicted on the high-precision map.

[0072] The step of determining the reference feature points of the high-precision map includes:

[0073] Determine reference feature points of the high-precision map surface located in the target location area on the high-precision map.

[0074] In an embodiment of the present application, the high-precision map as described above can be acquired in real time by a high-precision map acquisition system, for example, a high-precision map within a preset range of a movable platform can be acquired in real time.

[0075] Specifically, the movable platform is equipped with one or more sensors, and the sensors include any of the following sensors:

[0076] Wheel speed sensor, IMU sensor, speed sensor, acceleration sensor, gyroscope sensor, GPS positioning sensor, motor speed sensor.

[0077] The above-mentioned predicting the target location area of ​​the movable platform on the high-precision map includes:

[0078] Acquiring driving status information of the movable platform through a sensor carried by the movable platform;

[0079] The target location area of ​​the movable platform is predicted on the high-precision map based on the driving status information.

[0080] The driving status information includes information such as movement speed and acceleration, and the movement of the movable platform at the next moment is predicted on the high-precision map based on this information to determine the target location area where the movable platform is located. After determining the target location area, the reference feature points of the high-precision map surface located in the target location area are determined on the high-precision map.

[0081] Here, if the target feature point is a point cloud projection point that represents a corner point or an edge point, the reference feature point of the high-precision map surface can be a corner point or an edge point in the high-precision map surface, which is convenient for subsequent matching of the target feature point and the reference feature point, and then positioning calculation. Similarly, if the target feature point is the center pixel of the grid, the reference feature point of the high-precision map surface can be the center pixel of the grid in the high-precision map surface, where the grid division method of the high-precision map surface can refer to the grid division method of the point cloud surface.

[0082] S203. Determine first degree of freedom information of the point cloud relative to the high-precision map based on the target feature points and the reference feature points.

[0083] Optionally, the first degree of freedom information includes a Pitch parameter, a Roll parameter and a Z parameter.

[0084] Optionally, determining the first degree of freedom information of the point cloud relative to the high-precision map according to the target feature point and the reference feature point includes:

[0085] Acquire multiple candidate transformation matrices, where the candidate transformation matrices are used to correct the pose of the point cloud surface in three degrees of freedom, namely, pitch, roll and Z, to be consistent with the high-precision map surface;

[0086] Calculate the correction loss corresponding to each candidate transformation matrix according to the height value corresponding to the target feature point and the height value corresponding to the reference feature point;

[0087] Determine the candidate transformation matrix corresponding to the minimum correction loss as the target transformation matrix;

[0088] The first degree of freedom information is determined according to the target transformation matrix.

[0089] In order to further improve the calculation speed, the 3-DOF pose of Pitch / Roll / Z value is calculated by ground alignment. Figure 3 As shown in FIG. 1 , a schematic diagram of the above point cloud surface before ground alignment is performed, and as shown in FIG. Figure 4 Here, firstly, a plurality of candidate transformation matrices are obtained to correct the poses of the above-mentioned point cloud surface in three degrees of freedom, namely, Pitch, Roll and Z, to be consistent with the above-mentioned high-precision map surface, and the correction loss corresponding to each candidate transformation matrix is ​​calculated according to the height values ​​corresponding to the above-mentioned target feature points and the height values ​​corresponding to the reference feature points.

[0090] The height value corresponding to the above target feature point is determined based on the following operation: if the target feature point is a point cloud projection point, the projection height corresponding to the point cloud projection point is used as the height value corresponding to the target feature point. If the target feature point is the center pixel of the grid, the average of the projection heights corresponding to other point cloud projection points in the grid is used as the height value of the target feature point.

[0091] Specifically, the calculation of the correction loss corresponding to each candidate transformation matrix according to the height value corresponding to the target feature point and the height value corresponding to the reference feature point includes:

[0092] Pairing the target feature points with the reference feature points to determine a plurality of feature point pairing groups;

[0093] Calculate the height difference between the height value corresponding to each set of paired target feature points and the height value corresponding to the reference feature points;

[0094] The correction loss amount is determined based on the calculated multiple height differences.

[0095] Here, if Figure 5 As shown, the feature point pairing group of the target feature point and the reference feature point is determined. Exemplarily, by the formula:

[0096] M P i = M T U U P i , M P j = M T U U P j

[0097] Determine a feature point pairing group of the target feature point and the reference feature point, where: M P i and M P j Based on the map coordinate system (such as Figure 5 The feature point pairing group of the target feature point and the reference feature point shown in Map) is U P i and U P j They are feature point pairing groups based on the above target feature points and reference feature points in the IMU coordinate system, M T U is the transformation matrix, ( M T U ) -1 is the inverse matrix of the transformation matrix. Then, the height difference between the height value corresponding to each set of paired target feature points and the height value corresponding to the reference feature point is calculated, and the correction loss amount is determined according to the calculated multiple height differences, for example, the weighted average of the above multiple height differences is calculated, and the correction loss amount is obtained after normalization.

[0098] Further, the candidate transformation matrix corresponding to the minimum correction loss is determined as the target transformation matrix, and the first degree of freedom information is determined according to the target transformation matrix. Exemplarily, by formula:

[0099] min{( M T U ) -1M P j -T prz U P i}

[0100] Determine the target transformation matrix T corresponding to the minimum correction loss prz , thereby determining the Pitch / Roll / Z value.

[0101] The above-mentioned calculation of Pitch / Roll / Z values ​​using ground alignment also determines the relative posture between the point cloud plane and the high-precision map plane to a certain extent. The high-precision map plane corresponding to the mountainous area itself has a certain pitch (Pitch), roll (Roll) and height (Z). Through this optional implementation method, the corrected point cloud plane can fit the actual posture of the mountainous ground, and solve the problem of large errors in the uneven ground when estimating the Pitch / Roll / Z values ​​based on the nearest point position. It can be applied to scenes with large slopes, uneven roads and other scenes in complex urban environments.

[0102] S204: Correcting the posture of the point cloud using the first degree of freedom information.

[0103] Specifically, the first degree of freedom information is used to correct the position and posture of the point cloud surface in the three degrees of freedom of Pitch, Roll and Z to be consistent with the high-precision map surface.

[0104] The correction process can be understood as changes in the three degrees of freedom of the point cloud: pitch, roll, and Z. From the perspective of spatial posture, the posture of the corrected point cloud in the three degrees of freedom of pitch, roll, and Z is similar to that of the high-precision map. With this prior correction step, the accuracy of subsequent searches in the other three degrees of freedom will also be improved.

[0105] S205. Determine the second degree of freedom information of the point cloud relative to the high-precision map based on the reference feature points on the high-precision map and the target feature points on the corrected point cloud.

[0106] Optionally, the second degree of freedom information includes an X parameter, a Y parameter and a Yaw parameter.

[0107] Optionally, determining the second degree of freedom information of the point cloud relative to the high-precision map according to the reference feature points on the high-precision map and the target feature points on the corrected point cloud includes:

[0108] According to the value range of the Yaw parameter, a Yaw parameter to be selected is determined;

[0109] According to the reference feature points and the target feature points on the corrected point cloud surface, the loss amounts corresponding to different X parameters and Y parameters under each selected Yaw parameter are calculated, wherein the different X parameters and Y parameters are determined according to the value ranges of the X parameters and the Y parameters respectively;

[0110] The second degree of freedom information is determined according to the calculated minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter.

[0111] In an embodiment of the present application, the Yaw angle search is placed in the outermost layer of the loop, and the target feature points in the point cloud surface obtained by projecting the point cloud in the Z-axis direction are re-determined when each Yaw angle changes, thereby effectively improving the subsequent positioning accuracy, and then the first degree of freedom information of the point cloud relative to the high-precision map is determined according to the target feature points and the reference feature points, the pose of the point cloud is corrected by the first degree of freedom information, and the loss corresponding to different X parameters and Y parameters under each candidate Yaw parameter is calculated according to the target feature points on the corrected point cloud surface and the reference feature points, and the second degree of freedom information is determined according to the calculated minimum loss under each candidate Yaw parameter and the X parameters and Y parameters corresponding to the minimum loss under each candidate Yaw parameter.

[0112] Specifically, for each Yaw parameter to be selected, after the reference feature points are paired with the target feature points on the corrected point cloud surface, the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points is determined according to the first search range;

[0113] Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference;

[0114] Based on the determined X parameter and Y parameter, determining, according to a second search range, a height difference between a height value corresponding to each group of the paired reference feature points and a height value corresponding to the target feature point after pairing the reference feature points with the target feature points on the corrected point cloud surface, wherein the second search range is smaller than the first search range;

[0115] Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference;

[0116] According to the determined minimum value of the global height difference and the X parameter and Y parameter corresponding to the minimum value of the global height difference, the minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter are calculated.

[0117] Here, the three degrees of freedom X / Y / Yaw are estimated by pyramid exhaustive search. For each candidate Yaw parameter, in order to achieve a more efficient exhaustive search (traversing each pixel within a certain range to find the optimal solution), the search is divided into two layers of pyramid search. The first layer of the pyramid has a larger search step (such as searching in a range of 5x5 meters with a step of 0.5 meters), and a position with the minimum loss is obtained, such as Figure 6 Then, a more precise search is performed on the first-layer pyramid position, with a smaller step size and a smaller range (e.g., 1x1 meter range, searched with a step size of 10 cm), and finally a minimum loss value (optimal solution) is obtained, such as Figure 6 The second point of the Yaw parameter to be selected is determined, and the minimum loss amount under each Yaw parameter to be selected, as well as the X and Y parameters corresponding to the minimum loss amount under each Yaw parameter to be selected, and the three degrees of freedom of X / Y / Yaw are determined according to the minimum loss amount under each Yaw parameter to be selected, as well as the X and Y parameters corresponding to the minimum loss amount under each Yaw parameter to be selected.

[0118] The above loss amount is determined by the height values ​​corresponding to each set of paired target feature points and the height values ​​corresponding to the reference feature points after pairing the target feature points on the corrected point cloud surface with the reference feature points. Specifically, the global height difference is obtained based on the height difference between the height values ​​corresponding to each set of paired target feature points and the height values ​​corresponding to the reference feature points, and the loss amount is determined based on the global height difference, for example, by calculating the weighted average of the height differences, which is the global height difference, and the loss amount can be obtained after normalization.

[0119] Here, the use of a local range pyramid structure exhaustive algorithm in the process of determining the three degrees of freedom X / Y / Yaw can ensure that the algorithm can achieve real-time operation with low resource consumption within a controllable computational complexity.

[0120] In addition, in addition to the pyramid search method in which the search is divided into two layers, other pyramid search methods may be set according to actual needs, and the present application does not impose any limitation on this.

[0121] The above pyramid search method is based on the target feature points of the point cloud and the reference feature points of the high-precision map. These feature points can be quickly unitized and parallelized to improve the real-time performance of the algorithm. Moreover, the above pyramid search method can be implemented on GPU and FPGA to obtain efficient and real-time results, meeting certain working conditions, such as low latency requirements under vehicle working conditions.

[0122] In the embodiment of the present application, after calculating the loss amount corresponding to different X parameters and Y parameters under each selected Yaw parameter, the following is further included:

[0123] Determine whether there is a loss amount to be checked that meets a preset condition among the calculated multiple loss amounts, wherein the preset condition includes a value condition and a position condition, the value condition includes that the loss amount value is consistent, and the position condition includes that the X parameters or Y parameters corresponding to the multiple loss amounts to be checked are consistent;

[0124] If there are multiple loss amounts to be checked that meet the preset conditions among the multiple loss amounts calculated, it is determined that the X parameters and Y parameters corresponding to the multiple loss amounts to be checked are not credible.

[0125] In addition, it is also determined whether the X parameter and / or Y parameter corresponding to the minimum loss amount under each selected Yaw parameter is located at the edge of the target position area;

[0126] If the calculated X parameter and / or Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter is located at the edge of the target position area, it is determined that the X parameter and Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter are unreliable.

[0127] Here, considering the weak texture scenes, such as tunnels, highways and other environments, the textures are similar, and errors are prone to occur in the point cloud point matching process, making it difficult to achieve stable positioning. It is worth mentioning that in order to accurately determine whether the current positioning result is reliable, the following judgment steps can be performed to eliminate invalid data:

[0128] (1) Determine whether the X parameters or Y parameters of the locations where the calculated loss amounts are located are consistent. That is, during the pyramid search process, the loss values ​​of several point clouds corresponding to similar or identical Y values ​​(or X values) are equal. Then this location is likely to be in a weak texture area that is difficult to accurately locate, such as Figure 7 As shown in the figure (the shades of color in the figure represent different amounts of loss), therefore, it is determined that the X parameters and Y parameters corresponding to the above multiple amounts of loss to be tested are unreliable.

[0129] (2) If the X parameter and / or Y parameter corresponding to the minimum loss amount under a certain selected Yaw parameter is located at the edge of the target location area, such as the above Figure 6 If the edge of the box diagram is exceeded, it is very likely that the exact position is beyond the search range. Therefore, the X and Y parameters corresponding to the minimum loss amount under the above-mentioned candidate Yaw parameters are unreliable.

[0130] For the case where the loss values ​​of multiple rows or columns where the loss values ​​are located in (1) are equal, the above Figure 6 For example, the formula:

[0131]

[0132] Determine the entropy value (Entropy) of the Yaw angle direction, where P(x i ) represents the probability of loss in each box diagram. Figure 6 The entropy value calculation of all loss distributions in the Yaw angle direction of each frame diagram can accurately determine whether the current positioning result is stable (unique).

[0133] Here, in order to give the uncertainty of the current positioning, when the Entropy is relatively large (exceeding the preset Entropy threshold), the above Figure 6 Fit a Gaussian function:

[0134]

[0135] Among them, σ x , σ y They are the positioning uncertainty in the x and y directions respectively, and the uncertainty represents the error size of the positioning at this time.

[0136] In the specific implementation, in addition to outputting the positioning result, the uncertainty about the positioning result can also be output, such as the positioning uncertainty in the x and y directions. Subsequent path planning, road navigation, etc. can be performed based on the positioning result and the uncertainty of the positioning result. For example, the positioning result and the uncertainty of the positioning result are sent to the second processor 104, and the second processor 104 gives the path planning result, the road navigation result, and the corresponding path planning result and the uncertainty of the road navigation result, so that relevant personnel can make choices according to actual application needs and meet the needs of various application scenarios.

[0137] In addition, when outputting the positioning result and the uncertainty of the positioning result, a corresponding relationship between the output time and the positioning result and the uncertainty of the positioning result can also be established, and then the positioning result prediction at the next moment can be performed based on the positioning results at different moments and the uncertainty of the positioning result. For example, one uncertainty is obtained at the first moment and another uncertainty is obtained at the second moment. If the uncertainty obtained at the second moment is larger, the positioning result corresponding to the second moment is determined based on the positioning result corresponding to the first moment and the time integral of the speed.

[0138] In the embodiment of the present application, after calculating the loss amount corresponding to different X parameters and Y parameters under each selected Yaw parameter, the following steps may also be included:

[0139] Determine whether the X parameter and / or Y parameter corresponding to the minimum loss amount calculated under each candidate Yaw parameter is located at the edge of the target position area. If not, determine whether there is a loss amount to be checked that meets the above preset conditions among the multiple loss amounts calculated. If not, determine the second degree of freedom information based on the minimum loss amount calculated under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter to ensure the accuracy of subsequent positioning results. In the above, it is also possible to first determine whether there is a loss amount to be checked that meets the above preset conditions among the multiple loss amounts calculated, and then determine whether the X parameter and / or Y parameter corresponding to the minimum loss amount calculated under each candidate Yaw parameter is located at the edge of the target position area. The present application does not limit the order of the two judgments.

[0140] S206. Positioning the movable platform on the high-precision map according to the second degree of freedom information.

[0141] Optionally, after positioning the movable platform on the high-precision map according to the second degree of freedom information, the method further includes:

[0142] According to the positioning position of the movable platform and the driving state information, determining a sensor among the sensors carried by the movable platform that has erroneous output information;

[0143] In a preset calculation module, the weight of the output information of the sensor whose output information is erroneous is adjusted.

[0144] As can be seen from the above, the movable platform is equipped with one or more sensors for obtaining the driving state information of the movable platform.

[0145] Here, based on the driving state information of the movable platform obtained by the sensor carried by the movable platform, the target position area where the movable platform is located is predicted on the high-precision map, and it is determined whether the predicted result is the same as the result of positioning the movable platform on the high-precision map based on the second degree of freedom information (or the result difference is within the preset difference range). If the result of predicting the target position area where the movable platform is located on the high-precision map based on the driving state information of the movable platform obtained by a certain sensor is different from the result of the above positioning (or the result difference exceeds the preset difference range), it is determined that the above sensor is a sensor with incorrect output information. Then, in the preset calculation module, the weight of the output information of the sensor with incorrect output information is adjusted. Among them, the calculation module can be a module for calculating the driving state information, and the accuracy of the driving state information calculated by the calculation module is guaranteed by adjusting the weight of the output information of the sensor with incorrect output information. In addition, the computing module can also be a computing module that participates in other computing programs of the mobile device, such as an obstacle recognition algorithm module, an image acquisition module, an image correction module, etc. By adjusting the weight of the sensor output information with incorrect output information, the accuracy of subsequent obstacle recognition, image acquisition, image correction, etc. is ensured.

[0146] The positioning method provided in this embodiment obtains a point cloud collected by a sensor, and the point cloud is used to identify the ground of the surrounding environment of a movable platform. The above-mentioned sensor is set on the movable platform, and then the 3-degree-of-freedom pose Pitch, Roll and Z of the above-mentioned point cloud relative to the high-precision map are calculated based on the target feature points of the point cloud and the reference feature points of the high-precision map. The pose of the above-mentioned point cloud is corrected according to the calculated Pitch, Roll and Z, and the other 3-degree-of-freedom pose X, Y and Yaw of the point cloud relative to the high-precision map are calculated based on the target feature points on the corrected point cloud and the above-mentioned reference feature points, thereby realizing 6-degree-of-freedom full pose calculation.

[0147] Since the previous calculation of the first degree of freedom information has corrected the posture of the point cloud to a certain extent, the calculation range of the subsequent second degree of freedom information has been narrowed, reducing the amount of calculation, so the calculation speed is faster, which can also make the real-time positioning of the movable platform better.

[0148] It can be seen that the determination of the first degree of freedom information also determines the relative posture between the point cloud plane and the high-precision map plane to a certain extent. The high-precision map plane corresponding to the mountainous area itself has a certain pitch (Pitch), roll (Roll) and height (Z). Through this optional implementation method, the corrected point cloud plane can fit the actual posture of the mountainous ground.

[0149] In addition, the above solution is not only applicable in mountainous areas, but also in relatively small undulating roads. Based on point clouds and high-precision maps, the above solution can quickly extract static object feature points based on real physical meanings. Since the extracted feature points themselves are highly robust to dynamic objects, the system's resistance to environmental disturbances is increased, thus further improving the robustness of positioning.

[0150] Figure 8 A flow chart of another positioning method provided in an embodiment of the present application. Figure 2 Based on the embodiment, the specific implementation process of this embodiment is described in detail. Figure 8 As shown, the method includes:

[0151] S801. Obtain a point cloud collected by a sensor, where the point cloud is used to identify the ground surface of the surrounding environment of a movable platform, and the sensor is set on the movable platform.

[0152] S802: The movable platform is equipped with one or more sensors, and driving status information of the movable platform is obtained through the sensors carried by the movable platform. The target location area of ​​the movable platform is predicted on the high-precision map based on the driving status information.

[0153] S803: Determine the target feature points in the point cloud surface obtained by projecting the point cloud in the Z-axis direction, and determine the reference feature points of the high-precision map surface located in the target position area on the high-precision map.

[0154] S804. Obtain multiple candidate transformation matrices, wherein the candidate transformation matrices are used to correct the pose of the above point cloud surface in three degrees of freedom of Pitch, Roll and Z to be consistent with the high-precision map surface.

[0155] S805. Calculate the correction loss corresponding to each candidate transformation matrix according to the height value corresponding to the target feature point and the height value corresponding to the reference feature point.

[0156] Specifically, the target feature points and the reference feature points are paired to determine a plurality of feature point pairing groups;

[0157] Calculate the height difference between the height value corresponding to each set of paired target feature points and the height value corresponding to the reference feature point;

[0158] The correction loss amount is determined based on the calculated multiple height differences.

[0159] S806. Determine the candidate transformation matrix corresponding to the minimum correction loss as the target transformation matrix, and determine the first degree of freedom information according to the target transformation matrix, wherein the first degree of freedom information includes a Pitch parameter, a Roll parameter, and a Z parameter.

[0160] S807. Correct the position and posture of the point cloud using the first degree of freedom information.

[0161] S808. Determine a Yaw parameter to be selected according to the value range of the Yaw parameter.

[0162] S809, according to the reference feature points and the target feature points on the corrected point cloud surface, calculating the loss amount corresponding to different X parameters and Y parameters under each candidate Yaw parameter, wherein the different X parameters and Y parameters are determined according to the value ranges of the X parameters and the Y parameters, respectively.

[0163] Specifically, for each Yaw parameter to be selected, after the target feature points on the corrected point cloud surface are paired with the reference feature points, the height difference between the corresponding height values ​​of each group of paired target feature points and the corresponding height values ​​of the reference feature points is determined according to the first search range;

[0164] Obtain a global height difference according to the height difference between the corresponding height value of each set of paired target feature points and the corresponding height value of the reference feature point, and determine the X parameter and Y parameter corresponding to the minimum value of the global height difference;

[0165] Based on the determined X parameter and Y parameter, determining, according to a second search range, a height difference between a height value corresponding to each group of paired target feature points and a height value corresponding to the reference feature point after pairing the target feature points with the reference feature points on the corrected point cloud surface, wherein the second search range is smaller than the first search range;

[0166] Obtain a global height difference according to the height difference between the corresponding height value of each set of paired target feature points and the corresponding height value of the reference feature point, and determine the X parameter and Y parameter corresponding to the minimum value of the global height difference;

[0167] According to the determined minimum value of the global height difference and the X parameter and Y parameter corresponding to the minimum value of the global height difference, the minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter are calculated.

[0168] S810, determining whether there is a loss amount to be checked that meets preset conditions among the calculated multiple loss amounts, wherein the preset conditions include value conditions and location conditions, the value conditions include consistency of loss amount values, and the location conditions include: X parameters or Y parameters corresponding to the multiple loss amounts to be checked are consistent.

[0169] S811. If there are multiple loss amounts to be checked that meet the above preset conditions among the multiple loss amounts calculated, it is determined that the X parameters and Y parameters corresponding to the multiple loss amounts to be checked are unreliable.

[0170] S812: Determine whether the X parameter and / or Y parameter corresponding to the minimum loss amount under each selected Yaw parameter is located at the edge of the target position area.

[0171] S813: If the calculated X parameter and / or Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter is located at the edge of the target position area, it is determined that the X parameter and Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter are unreliable.

[0172] S814. If there are no loss amounts to be checked that meet the above preset conditions among the calculated loss amounts, and the X parameter and / or Y parameter corresponding to the minimum loss amount calculated under each to-be-selected Yaw parameter are not located at the edge of the target position area, the second degree of freedom information is determined according to the calculated minimum loss amount under each to-be-selected Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each to-be-selected Yaw parameter, wherein the second degree of freedom information includes the X parameter, the Y parameter, and the Yaw parameter.

[0173] S815. Position the movable platform on the high-precision map based on the second degree of freedom information.

[0174] S816. According to the positioning position of the movable platform and the above-mentioned driving state information, determine the sensor with incorrect output information among the sensors carried by the movable platform, and adjust the weight of the output information of the sensor with incorrect output information in a preset calculation module.

[0175] The positioning method provided in this embodiment, since the calculation of the first degree of freedom information has corrected the posture of the point cloud to a certain extent, the calculation range of the subsequent second degree of freedom information has been narrowed, the amount of calculation has been reduced, and the calculation speed has been improved, thereby making the real-time performance of the degree of freedom positioning better and overcoming the above-mentioned problem of the difficulty of performing degree of freedom positioning.

[0176] Moreover, considering the weak texture scene, in addition to outputting the positioning result, the uncertainty about the positioning result can also be output, and subsequent path planning, road navigation, etc. can be performed based on the positioning result and the uncertainty of the positioning result. The path planning result and road navigation result are given, and the corresponding path planning result and road navigation result uncertainties are given, which is convenient for relevant personnel to make choices according to actual application needs and meet the needs of various application scenarios.

[0177] From the above, we can see that the determination of the first degree of freedom information also determines the relative posture between the point cloud plane and the high-precision map plane to a certain extent. The high-precision map plane corresponding to the mountainous area itself has a certain pitch (Pitch), roll (Roll) and height (Z). Through this optional implementation method, the corrected point cloud plane can fit the actual posture of the mountainous ground.

[0178] In addition, the above solution is not only applicable in mountainous areas, but also in relatively small undulating roads. Based on point clouds and high-precision maps, the above solution can quickly extract static object feature points based on real physical meanings. Since the extracted feature points themselves are highly robust to dynamic objects, the system's resistance to environmental disturbances is increased, thus further improving the robustness of positioning.

[0179] Fig. 9 The following is a schematic diagram of the structure of a positioning device provided in an embodiment of the present application. For ease of explanation, only the parts related to the embodiment of the present application are shown. Fig. 9 As shown, the positioning device 90 includes: a point cloud acquisition module 901, a feature point determination module 902, a first degree of freedom determination module 903, a posture correction module 904, a second degree of freedom determination module 905 and a positioning module 906.

[0180] The point cloud acquisition module 901 is used to acquire a point cloud collected by a sensor, wherein the point cloud is used to identify the ground surface of the surrounding environment of a movable platform, and the sensor is arranged on the movable platform.

[0181] The feature point determination module 902 is used to determine the target feature points of the point cloud and determine the reference feature points of the high-precision map.

[0182] The first degree of freedom determination module 903 is used to determine the first degree of freedom information of the point cloud relative to the high-precision map based on the target feature point and the reference feature point.

[0183] The posture correction module 904 is used to correct the posture of the point cloud using the first degree of freedom information.

[0184] The second degree of freedom determination module 905 is used to determine the second degree of freedom information of the point cloud relative to the high-precision map based on the reference feature points on the high-precision map and the target feature points on the corrected point cloud.

[0185] A positioning module 906 is used to locate the movable platform on the high-precision map according to the second degree of freedom information.

[0186] The device provided in this embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.

[0187] Fig.10 FIG. 1 is a schematic diagram of the structure of another positioning device provided by an embodiment of the present invention. Fig.10 As shown, in this embodiment Fig. 9 Based on the embodiment, the above positioning device further includes: a region prediction module 907 and a weight adjustment module 908 .

[0188] In a possible design, the first degree of freedom information includes a Pitch parameter, a Roll parameter, and a Z parameter, and the second degree of freedom information includes an X parameter, a Y parameter, and a Yaw parameter.

[0189] In a possible design, the feature point determination module 902 determines the target feature points of the point cloud, including:

[0190] Determine the target feature points in the point cloud surface obtained by projecting the point cloud in the Z-axis direction.

[0191] In one possible design, the area prediction module 907 is used to predict the target location area of ​​the movable platform on the high-precision map.

[0192] The feature point determination module 902 determines the reference feature points of the high-precision map, including:

[0193] Determine reference feature points of the high-precision map surface located in the target location area on the high-precision map.

[0194] In a possible design, the first degree of freedom determination module 903 determines the first degree of freedom information of the point cloud relative to the high-precision map according to the target feature point and the reference feature point, including:

[0195] Acquire multiple candidate transformation matrices, where the candidate transformation matrices are used to correct the pose of the point cloud surface in three degrees of freedom, namely, pitch, roll and Z, to be consistent with the high-precision map surface;

[0196] Calculate the correction loss corresponding to each candidate transformation matrix according to the height value corresponding to the target feature point and the height value corresponding to the reference feature point;

[0197] Determine the candidate transformation matrix corresponding to the minimum correction loss as the target transformation matrix;

[0198] The first degree of freedom information is determined according to the target transformation matrix.

[0199] In a possible design, the point cloud surface includes a plurality of point cloud projection points; the feature point determination module 902 determines the target feature points in the point cloud surface obtained by projecting the point cloud in the Z-axis direction, including performing any of the following operations:

[0200] Extracting feature points on the point cloud surface as the target feature points according to a feature extraction algorithm, wherein the extracted feature points include the point cloud projection points used to characterize corner points or edge points;

[0201] The point cloud surface obtained by projection is meshed according to a preset mesh size, and the central pixel of the mesh is used as the target feature point.

[0202] In a possible design, the height value corresponding to the target feature point is determined based on the following operations:

[0203] If the target feature point is the point cloud projection point, the projection height corresponding to the point cloud projection point is used as the height value corresponding to the target feature point;

[0204] If the target feature point is the central pixel of the grid, the average of the projection heights corresponding to other point cloud projection points in the grid is used as the height value of the target feature point.

[0205] In a possible design, the first degree of freedom determination module 903 calculates the correction loss corresponding to each candidate transformation matrix according to the height value corresponding to the target feature point and the height value corresponding to the reference feature point, including:

[0206] Pairing the target feature points with the reference feature points to determine a plurality of feature point pairing groups;

[0207] Calculate the height difference between the height value corresponding to each set of paired target feature points and the height value corresponding to the reference feature points;

[0208] Determine the correction loss amount based on the calculated multiple height differences

[0209] In a possible design, the second degree of freedom determination module 905 determines the second degree of freedom information of the point cloud relative to the high-precision map according to the reference feature points on the high-precision map and the target feature points on the corrected point cloud, including:

[0210] According to the value range of the Yaw parameter, a Yaw parameter to be selected is determined;

[0211] According to the reference feature points and the target feature points on the corrected point cloud surface, the loss amounts corresponding to different X parameters and Y parameters under each selected Yaw parameter are calculated, wherein the different X parameters and Y parameters are determined according to the value ranges of the X parameters and the Y parameters respectively;

[0212] The second degree of freedom information is determined according to the calculated minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter.

[0213] In a possible design, the second degree of freedom determination module 905 is further used to determine, for each selected Yaw parameter, according to the first search range, the height difference between the height value corresponding to each group of the paired reference feature points and the height value corresponding to the target feature point after pairing the reference feature points with the target feature points on the corrected point cloud surface:

[0214] Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference;

[0215] Based on the determined X parameter and Y parameter, determining, according to a second search range, a height difference between a height value corresponding to each group of the paired reference feature points and a height value corresponding to the target feature point after pairing the reference feature points with the target feature points on the corrected point cloud surface, wherein the second search range is smaller than the first search range;

[0216] Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference;

[0217] According to the determined minimum value of the global height difference and the X parameter and Y parameter corresponding to the minimum value of the global height difference, the minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter are calculated.

[0218] In a possible design, after calculating the loss amounts corresponding to different X parameters and Y parameters under each candidate Yaw parameter, the second degree of freedom determination module 905 is further used to:

[0219] Determine whether there is a loss amount to be checked that meets a preset condition among the calculated multiple loss amounts, wherein the preset condition includes a value condition and a position condition, the value condition includes that the loss amount value is consistent, and the position condition includes that the X parameters or Y parameters corresponding to the multiple loss amounts to be checked are consistent;

[0220] If there are multiple loss amounts to be checked that meet the preset conditions among the multiple loss amounts calculated, it is determined that the X parameters and Y parameters corresponding to the multiple loss amounts to be checked are not credible.

[0221] In a possible design, after calculating the loss amounts corresponding to different X parameters and Y parameters under each candidate Yaw parameter, the second degree of freedom determination module 905 is further used to:

[0222] Determine whether the X parameter and / or Y parameter corresponding to the minimum loss amount under each selected Yaw parameter is located at the edge of the target position area;

[0223] If the calculated X parameter and / or Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter is located at the edge of the target position area, it is determined that the X parameter and Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter are unreliable.

[0224] In a possible design, the point cloud acquisition module 901 acquires the point cloud collected by the sensor, including:

[0225] Acquire a complete point cloud through the sensor;

[0226] Perform ground segmentation on the complete point cloud to obtain the point cloud.

[0227] In a possible design, the movable platform carries one or more sensors, and the sensors include any of the following sensors:

[0228] Wheel speed sensor, IMU sensor, speed sensor, acceleration sensor, gyroscope sensor, GPS positioning sensor, motor speed sensor.

[0229] The area prediction module 907 predicts the target location area of ​​the movable platform on the high-precision map, including:

[0230] Acquiring driving status information of the movable platform through a sensor carried by the movable platform;

[0231] The target location area of ​​the movable platform is predicted on the high-precision map based on the driving status information.

[0232] In a possible design, the weight adjustment module 908 is used to determine, after the positioning module 906 positions the movable platform on the high-precision map according to the second degree of freedom information, a sensor among the sensors carried by the movable platform that has erroneous output information according to the positioning position of the movable platform and the driving state information;

[0233] In a preset calculation module, the weight of the output information of the sensor whose output information is erroneous is adjusted.

[0234] The device provided in the embodiment of the present application can be used to execute the technical solution of the above-mentioned method embodiment. Its implementation principle and technical effect are similar, and the embodiment of the present application will not be repeated here.

[0235] Fig.11 Schematic diagram of the hardware structure of the positioning system provided in the embodiment of the present application. Fig.11 As shown, the positioning system 110 of this embodiment includes: a memory 1101 and a processor 1102;

[0236] Memory 1101, used for storing program instructions;

[0237] The processor 1102 is configured to execute the program instructions stored in the memory. When the program instructions are executed, the processor performs the following steps:

[0238] Acquire a point cloud collected by a sensor, the point cloud being used to identify the ground surface of an environment surrounding a movable platform, the sensor being disposed on the movable platform;

[0239] Determine the target feature points of the point cloud and determine the reference feature points of the high-precision map;

[0240] Determining first degree of freedom information of the point cloud relative to the high-precision map according to the target feature point and the reference feature point;

[0241] Correcting the pose of the point cloud using the first degree of freedom information;

[0242] Determining second degree of freedom information of the point cloud relative to the high-precision map according to the reference feature points on the high-precision map and the target feature points on the corrected point cloud;

[0243] According to the second degree of freedom information, the movable platform is positioned on the high-precision map.

[0244] In a possible design, the first degree of freedom information includes a Pitch parameter, a Roll parameter, and a Z parameter, and the second degree of freedom information includes an X parameter, a Y parameter, and a Yaw parameter.

[0245] In a possible design, determining the target feature point of the point cloud includes:

[0246] Determine the target feature points in the point cloud surface obtained by projecting the point cloud in the Z-axis direction.

[0247] In one possible design, the processor further implements the following steps when executing the computer-executable instruction:

[0248] Predicting the target location area of ​​the movable platform on the high-precision map;

[0249] The step of determining the reference feature points of the high-precision map includes:

[0250] Determine reference feature points of the high-precision map surface located in the target location area on the high-precision map.

[0251] In a possible design, determining the first degree of freedom information of the point cloud relative to the high-precision map according to the target feature point and the reference feature point includes:

[0252] Acquire multiple candidate transformation matrices, where the candidate transformation matrices are used to correct the pose of the point cloud surface in three degrees of freedom, namely, pitch, roll and Z, to be consistent with the high-precision map surface;

[0253] Calculate the correction loss corresponding to each candidate transformation matrix according to the height value corresponding to the target feature point and the height value corresponding to the reference feature point;

[0254] Determine the candidate transformation matrix corresponding to the minimum correction loss as the target transformation matrix;

[0255] The first degree of freedom information is determined according to the target transformation matrix.

[0256] In a possible design, the point cloud surface includes a plurality of point cloud projection points; and determining the target feature points in the point cloud surface obtained by projecting the point cloud in the Z-axis direction includes performing any of the following operations:

[0257] Extracting feature points on the point cloud surface as the target feature points according to a feature extraction algorithm, wherein the extracted feature points include the point cloud projection points used to characterize corner points or edge points;

[0258] The point cloud surface obtained by projection is meshed according to a preset mesh size, and the central pixel of the mesh is used as the target feature point.

[0259] In a possible design, the height value corresponding to the target feature point is determined based on the following operations:

[0260] If the target feature point is the point cloud projection point, the projection height corresponding to the point cloud projection point is used as the height value corresponding to the target feature point;

[0261] If the target feature point is the central pixel of the grid, the average of the projection heights corresponding to other point cloud projection points in the grid is used as the height value of the target feature point.

[0262] In a possible design, calculating the correction loss corresponding to each candidate transformation matrix according to the height value corresponding to the target feature point and the height value corresponding to the reference feature point includes:

[0263] Pairing the target feature points with the reference feature points to determine a plurality of feature point pairing groups;

[0264] Calculate the height difference between the height value corresponding to each set of paired target feature points and the height value corresponding to the reference feature points;

[0265] The correction loss amount is determined based on the calculated multiple height differences.

[0266] In a possible design, determining the second degree of freedom information of the point cloud relative to the high-precision map based on the reference feature points on the high-precision map and the target feature points on the corrected point cloud includes:

[0267] According to the value range of the Yaw parameter, a Yaw parameter to be selected is determined;

[0268] According to the reference feature points and the target feature points on the corrected point cloud surface, the loss amounts corresponding to different X parameters and Y parameters under each selected Yaw parameter are calculated, wherein the different X parameters and Y parameters are determined according to the value ranges of the X parameters and the Y parameters respectively;

[0269] The second degree of freedom information is determined according to the calculated minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter.

[0270] In one possible design, it also includes:

[0271] For each Yaw parameter to be selected, after the reference feature points are paired with the target feature points on the corrected point cloud surface, the height difference between the height values ​​corresponding to each set of paired reference feature points and the height values ​​corresponding to the target feature points is determined according to the first search range;

[0272] Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference;

[0273] Based on the determined X parameter and Y parameter, determining, according to a second search range, a height difference between a height value corresponding to each group of the paired reference feature points and a height value corresponding to the target feature point after pairing the reference feature points with the target feature points on the corrected point cloud surface, wherein the second search range is smaller than the first search range;

[0274] Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference;

[0275] According to the determined minimum value of the global height difference and the X parameter and Y parameter corresponding to the minimum value of the global height difference, the minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter are calculated.

[0276] In a possible design, after calculating the loss amount corresponding to different X parameters and Y parameters under each candidate Yaw parameter, the method further includes:

[0277] Determine whether there is a loss amount to be checked that meets a preset condition among the calculated multiple loss amounts, wherein the preset condition includes a value condition and a position condition, the value condition includes that the loss amount value is consistent, and the position condition includes that the X parameters or Y parameters corresponding to the multiple loss amounts to be checked are consistent;

[0278] If there are multiple loss amounts to be checked that meet the preset conditions among the multiple loss amounts calculated, it is determined that the X parameters and Y parameters corresponding to the multiple loss amounts to be checked are not credible.

[0279] In a possible design, after calculating the loss amount corresponding to different X parameters and Y parameters under each candidate Yaw parameter, the method further includes:

[0280] Determine whether the X parameter and / or Y parameter corresponding to the minimum loss amount under each selected Yaw parameter is located at the edge of the target position area;

[0281] If the calculated X parameter and / or Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter is located at the edge of the target position area, it is determined that the X parameter and Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter are unreliable.

[0282] In a possible design, obtaining a point cloud collected by a sensor includes:

[0283] Acquire a complete point cloud through the sensor;

[0284] Perform ground segmentation on the complete point cloud to obtain the point cloud.

[0285] In a possible design, the movable platform carries one or more sensors, and the sensors include any of the following sensors:

[0286] Wheel speed sensor, IMU sensor, speed sensor, acceleration sensor, gyroscope sensor, GPS positioning sensor, motor speed sensor;

[0287] The predicting of the target location area of ​​the movable platform on the high-precision map includes:

[0288] Acquiring driving status information of the movable platform through a sensor carried by the movable platform;

[0289] The target location area of ​​the movable platform is predicted on the high-precision map based on the driving status information.

[0290] In a possible design, after positioning the movable platform on the high-precision map according to the second degree of freedom information, the method further includes:

[0291] According to the positioning position of the movable platform and the driving state information, determining a sensor among the sensors carried by the movable platform that has erroneous output information;

[0292] In a preset calculation module, the weight of the output information of the sensor whose output information is erroneous is adjusted.

[0293] In a possible design, the memory 1101 can be either independent or integrated with the processor 1102 .

[0294] When the memory 1101 is independently provided, the positioning system further includes a bus 1103 for connecting the memory 1101 and the processor 1102 .

[0295] In a possible design, the positioning system 110 may be a separate device, which includes a complete set of the above-mentioned memory 1101, processor 1102, etc. In addition, taking a vehicle as an example, the components of the positioning system 110 may be distributed and integrated in the vehicle, that is, the memory 1101, processor 1102, etc. may be respectively set at different locations of the vehicle.

[0296] Fig.12 This is a schematic diagram of the structure of a movable platform provided in an embodiment of the present application. Fig.12 As shown, the movable platform 120 of this embodiment includes: a movable platform body 1201, a sensor 1202, and a positioning system 1203; the sensor 1202 and the positioning system 1203 are arranged on the movable platform body 1201, and the movable platform body 1201 and the positioning system 1203 are connected wirelessly or by wire.

[0297] The positioning system 1203 acquires a point cloud collected by the sensor, wherein the point cloud is used to identify the ground surface of the surrounding environment of the movable platform;

[0298] Determine the target feature points of the point cloud and determine the reference feature points of the high-precision map;

[0299] Determining first degree of freedom information of the point cloud relative to the high-precision map according to the target feature point and the reference feature point;

[0300] Correcting the pose of the point cloud using the first degree of freedom information;

[0301] Determining second degree of freedom information of the point cloud relative to the high-precision map according to the reference feature points on the high-precision map and the target feature points on the corrected point cloud;

[0302] According to the second degree of freedom information, the movable platform is positioned on the high-precision map.

[0303] In a possible design, the first degree of freedom information includes a Pitch parameter, a Roll parameter, and a Z parameter, and the second degree of freedom information includes an X parameter, a Y parameter, and a Yaw parameter.

[0304] In one possible design, the positioning system determines the target feature point of the point cloud, including:

[0305] Determine the target feature points in the point cloud surface obtained by projecting the point cloud in the Z-axis direction.

[0306] In a possible design, the positioning system is also used for:

[0307] Predicting the target location area of ​​the movable platform on the high-precision map;

[0308] The step of determining the reference feature points of the high-precision map includes:

[0309] Determine reference feature points of the high-precision map surface located in the target location area on the high-precision map.

[0310] In a possible design, the positioning system determines the first degree of freedom information of the point cloud relative to the high-precision map according to the target feature point and the reference feature point, including:

[0311] Acquire multiple candidate transformation matrices, where the candidate transformation matrices are used to correct the pose of the point cloud surface in three degrees of freedom, namely, pitch, roll and Z, to be consistent with the high-precision map surface;

[0312] Calculate the correction loss corresponding to each candidate transformation matrix according to the height value corresponding to the target feature point and the height value corresponding to the reference feature point;

[0313] Determine the candidate transformation matrix corresponding to the minimum correction loss as the target transformation matrix;

[0314] The first degree of freedom information is determined according to the target transformation matrix.

[0315] In a possible design, the point cloud surface includes a plurality of point cloud projection points; the positioning system determines the target feature point in the point cloud surface obtained by projecting the point cloud in the Z-axis direction, including performing any of the following operations:

[0316] Extracting feature points on the point cloud surface as the target feature points according to a feature extraction algorithm, wherein the extracted feature points include the point cloud projection points used to characterize corner points or edge points;

[0317] The point cloud surface obtained by projection is meshed according to a preset mesh size, and the central pixel of the mesh is used as the target feature point.

[0318] In a possible design, the height value corresponding to the target feature point is determined based on the following operations:

[0319] If the target feature point is the point cloud projection point, the projection height corresponding to the point cloud projection point is used as the height value corresponding to the target feature point;

[0320] If the target feature point is the central pixel of the grid, the average of the projection heights corresponding to other point cloud projection points in the grid is used as the height value of the target feature point.

[0321] In a possible design, the positioning system calculates the correction loss corresponding to each candidate transformation matrix according to the height value corresponding to the target feature point and the height value corresponding to the reference feature point, including:

[0322] Pairing the target feature points with the reference feature points to determine a plurality of feature point pairing groups;

[0323] Calculate the height difference between the height value corresponding to each set of paired target feature points and the height value corresponding to the reference feature points;

[0324] The correction loss amount is determined based on the calculated multiple height differences.

[0325] In a possible design, the positioning system determines the second degree of freedom information of the point cloud relative to the high-precision map based on the reference feature points on the high-precision map and the target feature points on the corrected point cloud, including:

[0326] According to the value range of the Yaw parameter, a Yaw parameter to be selected is determined;

[0327] According to the reference feature points and the target feature points on the corrected point cloud surface, the loss amounts corresponding to different X parameters and Y parameters under each selected Yaw parameter are calculated, wherein the different X parameters and Y parameters are determined according to the value ranges of the X parameters and the Y parameters respectively;

[0328] The second degree of freedom information is determined according to the calculated minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter.

[0329] In a possible design, the positioning system is also used for:

[0330] For each Yaw parameter to be selected, after the reference feature points are paired with the target feature points on the corrected point cloud surface, the height difference between the height values ​​corresponding to each set of paired reference feature points and the height values ​​corresponding to the target feature points is determined according to the first search range;

[0331] Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference;

[0332] Based on the determined X parameter and Y parameter, determining, according to a second search range, a height difference between a height value corresponding to each group of the paired reference feature points and a height value corresponding to the target feature point after pairing the reference feature points with the target feature points on the corrected point cloud surface, wherein the second search range is smaller than the first search range;

[0333] Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference;

[0334] According to the determined minimum value of the global height difference and the X parameter and Y parameter corresponding to the minimum value of the global height difference, the minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter are calculated.

[0335] In a possible design, after calculating the loss amount corresponding to different X parameters and Y parameters under each selected Yaw parameter, the positioning system is further used to:

[0336] Determine whether there is a loss amount to be checked that meets a preset condition among the calculated multiple loss amounts, wherein the preset condition includes a value condition and a position condition, the value condition includes that the loss amount value is consistent, and the position condition includes that the X parameters or Y parameters corresponding to the multiple loss amounts to be checked are consistent;

[0337] If there are multiple loss amounts to be checked that meet the preset conditions among the multiple loss amounts calculated, it is determined that the X parameters and Y parameters corresponding to the multiple loss amounts to be checked are not credible.

[0338] In a possible design, after calculating the loss amount corresponding to different X parameters and Y parameters under each selected Yaw parameter, the positioning system is further used to:

[0339] Determine whether the X parameter and / or Y parameter corresponding to the minimum loss amount under each selected Yaw parameter is located at the edge of the target position area;

[0340] If the calculated X parameter and / or Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter is located at the edge of the target position area, it is determined that the X parameter and Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter are unreliable.

[0341] In a possible design, the positioning system acquires a point cloud collected by a sensor, including:

[0342] Acquire a complete point cloud through the sensor;

[0343] Perform ground segmentation on the complete point cloud to obtain the point cloud.

[0344] In a possible design, the movable platform carries one or more sensors, and the sensors include any of the following sensors:

[0345] Wheel speed sensor, IMU sensor, speed sensor, acceleration sensor, gyroscope sensor, GPS positioning sensor, motor speed sensor;

[0346] The positioning system predicts the target location area of ​​the movable platform on the high-precision map, including:

[0347] Acquiring driving status information of the movable platform through a sensor carried by the movable platform;

[0348] The target location area of ​​the movable platform is predicted on the high-precision map based on the driving status information.

[0349] In a possible design, after the positioning system positions the movable platform on the high-precision map according to the second degree of freedom information, the method further includes:

[0350] According to the positioning position of the movable platform and the driving state information, determining a sensor among the sensors carried by the movable platform that has erroneous output information;

[0351] In a preset calculation module, the weight of the output information of the sensor whose output information is erroneous is adjusted.

[0352] The movable platform provided in this embodiment includes: a movable platform body, a sensor, and a positioning system, wherein the sensor and the positioning system are arranged on the movable platform body, wherein the positioning system obtains a point cloud collected by the sensor, and the point cloud is used to identify the ground of the surrounding environment of the movable platform, and the above-mentioned sensor is arranged on the movable platform, and then the 3-DOF posture Pitch, Roll and Z of the above-mentioned point cloud relative to the high-precision map are calculated according to the target feature points of the point cloud and the reference feature points of the high-precision map. The posture of the above-mentioned point cloud is corrected according to the calculated Pitch, Roll and Z, and the other 3-DOF posture X, Y and Yaw of the point cloud relative to the high-precision map are calculated according to the target feature points on the corrected point cloud and the above-mentioned reference feature points, thereby realizing the calculation of the 6-DOF full posture.

[0353] Since the previous calculation of the first degree of freedom information has corrected the posture of the point cloud to a certain extent, the calculation range of the subsequent second degree of freedom information has been narrowed, reducing the amount of calculation, so the calculation speed is faster, which can also make the real-time positioning of the movable platform better.

[0354] It can be seen that the determination of the first degree of freedom information also determines the relative posture between the point cloud plane and the high-precision map plane to a certain extent. The high-precision map plane corresponding to the mountainous area itself has a certain pitch (Pitch), roll (Roll) and height (Z). Through this optional implementation method, the corrected point cloud plane can fit the actual posture of the mountainous ground.

[0355] In addition, the above solution is not only applicable in mountainous areas, but also in relatively small undulating roads. Based on point clouds and high-precision maps, the above solution can quickly extract static object feature points based on real physical meanings. Since the extracted feature points themselves are highly robust to dynamic objects, the system's resistance to environmental disturbances is increased, thus further improving the robustness of positioning.

[0356] An embodiment of the present application provides a computer-readable storage medium, in which program instructions are stored. When a processor executes the program instructions, the positioning method as described above is implemented.

[0357] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules 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 an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0358] The modules described as separate components may or may not be physically separated, and the components shown as modules 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 modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0359] In addition, each functional module in each embodiment of the present invention can be integrated into a processing unit, each module can exist physically separately, or two or more modules can be integrated into one unit. The above-mentioned module-composed unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0360] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: processor) to perform some steps of the method described in each embodiment of the present application.

[0361] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.

[0362] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0363] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0364] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0365] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device or a main control device.

[0366] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0367] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention 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 replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A positioning method, characterized in that: include: Acquire a point cloud collected by a sensor, the point cloud being used to identify the ground surface of an environment surrounding a movable platform, the sensor being disposed on the movable platform; Determine the target feature points of the point cloud and determine the reference feature points of the high-precision map; Determining first degree of freedom information of the point cloud relative to the high-precision map according to the target feature point and the reference feature point; Correcting the pose of the point cloud using the first degree of freedom information; Determining second degree of freedom information of the point cloud relative to the high-precision map according to the reference feature points on the high-precision map and the target feature points on the corrected point cloud; According to the second degree of freedom information, the movable platform is positioned on the high-precision map.

2. The method according to claim 1, characterized in that The first degree of freedom information includes a Pitch parameter, a Roll parameter, and a Z parameter, and the second degree of freedom information includes an X parameter, a Y parameter, and a Yaw parameter.

3. The method according to claim 2, characterized in that The determining of the target feature points of the point cloud comprises: Determine the target feature points in the point cloud surface obtained by projecting the point cloud in the Z-axis direction.

4. The method according to claim 3, characterized in that The method further comprises: Predicting the target location area of ​​the movable platform on the high-precision map; The step of determining the reference feature points of the high-precision map includes: Determine reference feature points of the high-precision map surface located in the target location area on the high-precision map.

5. The method according to claim 4, characterized in that The determining, according to the target feature point and the reference feature point, first degree of freedom information of the point cloud relative to the high-precision map includes: Acquire multiple candidate transformation matrices, where the candidate transformation matrices are used to correct the pose of the point cloud surface in three degrees of freedom, namely, pitch, roll and Z, to be consistent with the high-precision map surface; Calculate the correction loss corresponding to each candidate transformation matrix according to the height value corresponding to the target feature point and the height value corresponding to the reference feature point; Determine the candidate transformation matrix corresponding to the minimum correction loss as the target transformation matrix; The first degree of freedom information is determined according to the target transformation matrix.

6. The method according to claim 5, characterized in that The point cloud surface includes a plurality of point cloud projection points; and determining the target feature points in the point cloud surface obtained by projecting the point cloud in the Z-axis direction includes performing any of the following operations: Extracting feature points on the point cloud surface as the target feature points according to a feature extraction algorithm, wherein the extracted feature points include the point cloud projection points used to characterize corner points or edge points; The point cloud surface obtained by projection is meshed according to a preset mesh size, and the central pixel of the mesh is used as the target feature point.

7. The method according to claim 6, characterized in that The height value corresponding to the target feature point is determined based on the following operations: If the target feature point is the point cloud projection point, the projection height corresponding to the point cloud projection point is used as the height value corresponding to the target feature point; If the target feature point is the central pixel of the grid, the average of the projection heights corresponding to other point cloud projection points in the grid is used as the height value of the target feature point.

8. The method according to any one of claims 5 to 7, characterized in that The calculating the correction loss amount corresponding to each candidate transformation matrix according to the height value corresponding to the target feature point and the height value corresponding to the reference feature point includes: Pairing the target feature points with the reference feature points to determine a plurality of feature point pairing groups; Calculate the height difference between the height value corresponding to each set of paired target feature points and the height value corresponding to the reference feature points; The correction loss amount is determined based on the calculated multiple height differences.

9. The method according to any one of claims 3 to 7, characterized in that The determining, based on the reference feature points on the high-precision map and the target feature points on the corrected point cloud, the second degree of freedom information of the point cloud relative to the high-precision map includes: According to the value range of the Yaw parameter, a Yaw parameter to be selected is determined; According to the reference feature points and the target feature points on the corrected point cloud surface, the loss amounts corresponding to different X parameters and Y parameters under each selected Yaw parameter are calculated, wherein the different X parameters and Y parameters are determined according to the value ranges of the X parameters and the Y parameters respectively; The second degree of freedom information is determined according to the calculated minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter.

10. The method according to claim 8, characterized in that The determining, based on the reference feature points on the high-precision map and the target feature points on the corrected point cloud, the second degree of freedom information of the point cloud relative to the high-precision map includes: According to the value range of the Yaw parameter, a Yaw parameter to be selected is determined; According to the reference feature points and the target feature points on the corrected point cloud surface, the loss amounts corresponding to different X parameters and Y parameters under each selected Yaw parameter are calculated, wherein the different X parameters and Y parameters are determined according to the value ranges of the X parameters and the Y parameters respectively; The second degree of freedom information is determined according to the calculated minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter.

11. The method according to claim 9, characterized in that Also includes: For each Yaw parameter to be selected, after the reference feature points are paired with the target feature points on the corrected point cloud surface, the height difference between the height values ​​corresponding to each set of paired reference feature points and the height values ​​corresponding to the target feature points is determined according to the first search range; Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference; Based on the determined X parameter and Y parameter, determining, according to a second search range, a height difference between a height value corresponding to each group of the paired reference feature points and a height value corresponding to the target feature point after pairing the reference feature points with the target feature points on the corrected point cloud surface, wherein the second search range is smaller than the first search range; Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference; According to the determined minimum value of the global height difference and the X parameter and Y parameter corresponding to the minimum value of the global height difference, the minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter are calculated.

12. The method according to claim 10, characterized in that Also includes: For each Yaw parameter to be selected, after the reference feature points are paired with the target feature points on the corrected point cloud surface, the height difference between the height values ​​corresponding to each set of paired reference feature points and the height values ​​corresponding to the target feature points is determined according to the first search range; Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference; Based on the determined X parameter and Y parameter, determining, according to a second search range, a height difference between a height value corresponding to each group of the paired reference feature points and a height value corresponding to the target feature point after pairing the reference feature points with the target feature points on the corrected point cloud surface, wherein the second search range is smaller than the first search range; Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference; According to the determined minimum value of the global height difference and the X parameter and Y parameter corresponding to the minimum value of the global height difference, the minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter are calculated.

13. The method according to claim 9, characterized in that After calculating the loss amount corresponding to different X parameters and Y parameters under each selected Yaw parameter, the method further includes: Determine whether there is a loss amount to be checked that meets a preset condition among the calculated multiple loss amounts, wherein the preset condition includes a value condition and a position condition, the value condition includes that the loss amount value is consistent, and the position condition includes that the X parameters or Y parameters corresponding to the multiple loss amounts to be checked are consistent; If there are multiple loss amounts to be checked that meet the preset conditions among the multiple loss amounts calculated, it is determined that the X parameters and Y parameters corresponding to the multiple loss amounts to be checked are not credible.

14. The method according to any one of claims 10 to 12, characterized in that After calculating the loss amount corresponding to different X parameters and Y parameters under each selected Yaw parameter, the method further includes: Determine whether there is a loss amount to be checked that meets a preset condition among the calculated multiple loss amounts, wherein the preset condition includes a value condition and a position condition, the value condition includes that the loss amount value is consistent, and the position condition includes that the X parameters or Y parameters corresponding to the multiple loss amounts to be checked are consistent; If there are multiple loss amounts to be checked that meet the preset conditions among the multiple loss amounts calculated, it is determined that the X parameters and Y parameters corresponding to the multiple loss amounts to be checked are not credible.

15. The method according to claim 9, characterized in that After calculating the loss amount corresponding to different X parameters and Y parameters under each selected Yaw parameter, the method further includes: Determine whether the X parameter and / or Y parameter corresponding to the minimum loss amount under each selected Yaw parameter is located at the edge of the target position area; If the calculated X parameter and / or Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter is located at the edge of the target position area, it is determined that the X parameter and Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter are unreliable.

16. The method according to any one of claims 10 to 12, characterized in that After calculating the loss amount corresponding to different X parameters and Y parameters under each selected Yaw parameter, the method further includes: Determine whether the X parameter and / or Y parameter corresponding to the minimum loss amount under each selected Yaw parameter is located at the edge of the target position area; If the calculated X parameter and / or Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter is located at the edge of the target position area, it is determined that the X parameter and Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter are unreliable.

17. The method according to any one of claims 1 to 7, 10 to 13 and 15, characterized in that The step of obtaining a point cloud collected by a sensor includes: Acquire a complete point cloud through the sensor; Perform ground segmentation on the complete point cloud to obtain the point cloud.

18. The method according to claim 8, characterized in that The step of obtaining a point cloud collected by a sensor includes: Acquire a complete point cloud through the sensor; Perform ground segmentation on the complete point cloud to obtain the point cloud.

19. The method according to claim 9, characterized in that The step of obtaining a point cloud collected by a sensor includes: Acquire a complete point cloud through the sensor; Perform ground segmentation on the complete point cloud to obtain the point cloud.

20. The method according to claim 14, characterized in that The step of obtaining a point cloud collected by a sensor includes: Acquire a complete point cloud through the sensor; Perform ground segmentation on the complete point cloud to obtain the point cloud.

21. The method according to claim 16, characterized in that The step of obtaining a point cloud collected by a sensor includes: Acquire a complete point cloud through the sensor; Perform ground segmentation on the complete point cloud to obtain the point cloud.

22. The method according to any one of claims 4 to 7, characterized in that The movable platform may be equipped with one or more sensors, and the sensors may include any of the following sensors: Wheel speed sensor, IMU sensor, speed sensor, acceleration sensor, gyroscope sensor, GPS positioning sensor, motor speed sensor; The predicting of the target location area of ​​the movable platform on the high-precision map includes: Acquiring driving status information of the movable platform through a sensor carried by the movable platform; The target location area of ​​the movable platform is predicted on the high-precision map based on the driving status information.

23. The method according to claim 22, characterized in that After positioning the movable platform on the high-precision map according to the second degree of freedom information, the method further includes: According to the positioning position of the movable platform and the driving state information, determining a sensor among the sensors carried by the movable platform that has erroneous output information; In a preset calculation module, the weight of the output information of the sensor whose output information is erroneous is adjusted.

24. A positioning system, characterized in that: The method comprises a memory, a processor, and a computer-executable instruction stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer-executable instruction: Acquire a point cloud collected by a sensor, the point cloud being used to identify the ground surface of an environment surrounding a movable platform, the sensor being disposed on the movable platform; Determine the target feature points of the point cloud and determine the reference feature points of the high-precision map; Determining first degree of freedom information of the point cloud relative to the high-precision map according to the target feature point and the reference feature point; Correcting the pose of the point cloud using the first degree of freedom information; Determining second degree of freedom information of the point cloud relative to the high-precision map according to the reference feature points on the high-precision map and the target feature points on the corrected point cloud; According to the second degree of freedom information, the movable platform is positioned on the high-precision map.

25. The system according to claim 24, characterized in that The first degree of freedom information includes a Pitch parameter, a Roll parameter, and a Z parameter, and the second degree of freedom information includes an X parameter, a Y parameter, and a Yaw parameter.

26. The system according to claim 25, characterized in that The determining of the target feature points of the point cloud comprises: Determine the target feature points in the point cloud surface obtained by projecting the point cloud in the Z-axis direction.

27. The system according to claim 26, characterized in that When the processor executes the computer-executable instruction, the processor also implements the following steps: Predicting the target location area of ​​the movable platform on the high-precision map; The step of determining the reference feature points of the high-precision map includes: Determine reference feature points of the high-precision map surface located in the target location area on the high-precision map.

28. The system according to claim 26, characterized in that The determining, according to the target feature point and the reference feature point, first degree of freedom information of the point cloud relative to the high-precision map includes: Acquire multiple candidate transformation matrices, where the candidate transformation matrices are used to correct the pose of the point cloud surface in three degrees of freedom, namely, pitch, roll and Z, to be consistent with the high-precision map surface; Calculate the correction loss corresponding to each candidate transformation matrix according to the height value corresponding to the target feature point and the height value corresponding to the reference feature point; Determine the candidate transformation matrix corresponding to the minimum correction loss as the target transformation matrix; The first degree of freedom information is determined according to the target transformation matrix.

29. The system according to claim 28, characterized in that The point cloud surface includes a plurality of point cloud projection points; and determining the target feature points in the point cloud surface obtained by projecting the point cloud in the Z-axis direction includes performing any of the following operations: Extracting feature points on the point cloud surface as the target feature points according to a feature extraction algorithm, wherein the extracted feature points include the point cloud projection points used to characterize corner points or edge points; The point cloud surface obtained by projection is meshed according to a preset mesh size, and the central pixel of the mesh is used as the target feature point.

30. The system according to claim 29, characterized in that The height value corresponding to the target feature point is determined based on the following operations: If the target feature point is the point cloud projection point, the projection height corresponding to the point cloud projection point is used as the height value corresponding to the target feature point; If the target feature point is the central pixel of the grid, the average of the projection heights corresponding to other point cloud projection points in the grid is used as the height value of the target feature point.

31. A system according to any one of claims 28 to 30, characterized in that The calculating the correction loss amount corresponding to each candidate transformation matrix according to the height value corresponding to the target feature point and the height value corresponding to the reference feature point includes: Pairing the target feature points with the reference feature points to determine a plurality of feature point pairing groups; Calculate the height difference between the height value corresponding to each set of paired target feature points and the height value corresponding to the reference feature points; The correction loss amount is determined based on the calculated multiple height differences.

32. A system according to any one of claims 26 to 30, characterized in that The determining, based on the reference feature points on the high-precision map and the target feature points on the corrected point cloud, the second degree of freedom information of the point cloud relative to the high-precision map includes: According to the value range of the Yaw parameter, a Yaw parameter to be selected is determined; According to the reference feature points and the target feature points on the corrected point cloud surface, the loss amounts corresponding to different X parameters and Y parameters under each selected Yaw parameter are calculated, wherein the different X parameters and Y parameters are determined according to the value ranges of the X parameters and the Y parameters respectively; The second degree of freedom information is determined according to the calculated minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter.

33. The system according to claim 31, characterized in that The determining, based on the reference feature points on the high-precision map and the target feature points on the corrected point cloud, the second degree of freedom information of the point cloud relative to the high-precision map includes: According to the value range of the Yaw parameter, a Yaw parameter to be selected is determined; According to the reference feature points and the target feature points on the corrected point cloud surface, the loss amounts corresponding to different X parameters and Y parameters under each selected Yaw parameter are calculated, wherein the different X parameters and Y parameters are determined according to the value ranges of the X parameters and the Y parameters respectively; The second degree of freedom information is determined according to the calculated minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter.

34. The system according to claim 32, characterized in that Also includes: For each Yaw parameter to be selected, after the reference feature points are paired with the target feature points on the corrected point cloud surface, the height difference between the height values ​​corresponding to each set of paired reference feature points and the height values ​​corresponding to the target feature points is determined according to the first search range; Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference; Based on the determined X parameter and Y parameter, determining, according to a second search range, a height difference between a height value corresponding to each group of the paired reference feature points and a height value corresponding to the target feature point after pairing the reference feature points with the target feature points on the corrected point cloud surface, wherein the second search range is smaller than the first search range; Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference; According to the determined minimum value of the global height difference and the X parameter and Y parameter corresponding to the minimum value of the global height difference, the minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter are calculated.

35. The system according to claim 33, characterized in that Also includes: For each Yaw parameter to be selected, after the reference feature points are paired with the target feature points on the corrected point cloud surface, the height difference between the height values ​​corresponding to each set of paired reference feature points and the height values ​​corresponding to the target feature points is determined according to the first search range; Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference; Based on the determined X parameter and Y parameter, determining, according to a second search range, a height difference between a height value corresponding to each group of the paired reference feature points and a height value corresponding to the target feature point after pairing the reference feature points with the target feature points on the corrected point cloud surface, wherein the second search range is smaller than the first search range; Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference; According to the determined minimum value of the global height difference and the X parameter and Y parameter corresponding to the minimum value of the global height difference, the minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter are calculated.

36. The system according to claim 32, characterized in that After calculating the loss amount corresponding to different X parameters and Y parameters under each selected Yaw parameter, the method further includes: Determine whether there is a loss amount to be checked that meets a preset condition among the calculated multiple loss amounts, wherein the preset condition includes a value condition and a position condition, the value condition includes that the loss amount value is consistent, and the position condition includes that the X parameters or Y parameters corresponding to the multiple loss amounts to be checked are consistent; If there are multiple loss amounts to be checked that meet the preset conditions among the multiple loss amounts calculated, it is determined that the X parameters and Y parameters corresponding to the multiple loss amounts to be checked are not credible.

37. A system according to any one of claims 33 to 35, characterized in that After calculating the loss amount corresponding to different X parameters and Y parameters under each selected Yaw parameter, the method further includes: Determine whether there is a loss amount to be checked that meets a preset condition among the calculated multiple loss amounts, wherein the preset condition includes a value condition and a position condition, the value condition includes that the loss amount value is consistent, and the position condition includes that the X parameters or Y parameters corresponding to the multiple loss amounts to be checked are consistent; If there are multiple loss amounts to be checked that meet the preset conditions among the multiple loss amounts calculated, it is determined that the X parameters and Y parameters corresponding to the multiple loss amounts to be checked are not credible.

38. The system according to claim 32, characterized in that After calculating the loss amount corresponding to different X parameters and Y parameters under each selected Yaw parameter, the method further includes: Determine whether the X parameter and / or Y parameter corresponding to the minimum loss amount under each selected Yaw parameter is located at the edge of the target position area; If the calculated X parameter and / or Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter is located at the edge of the target position area, it is determined that the X parameter and Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter are unreliable.

39. A system according to any one of claims 33 to 35, characterized in that After calculating the loss amount corresponding to different X parameters and Y parameters under each selected Yaw parameter, the method further includes: Determine whether the X parameter and / or Y parameter corresponding to the minimum loss amount under each selected Yaw parameter is located at the edge of the target position area; If the calculated X parameter and / or Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter is located at the edge of the target position area, it is determined that the X parameter and Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter are unreliable.

40. The system according to any one of claims 24 to 30, 33 to 36, 38, characterized in that The step of obtaining a point cloud collected by a sensor includes: Acquire a complete point cloud through the sensor; Perform ground segmentation on the complete point cloud to obtain the point cloud.

41. The system according to claim 31, characterized in that The step of obtaining a point cloud collected by a sensor includes: Acquire a complete point cloud through the sensor; Perform ground segmentation on the complete point cloud to obtain the point cloud.

42. The system according to claim 32, characterized in that The step of obtaining a point cloud collected by a sensor includes: Acquire a complete point cloud through the sensor; Perform ground segmentation on the complete point cloud to obtain the point cloud.

43. The system according to claim 37, characterized in that The step of obtaining a point cloud collected by a sensor includes: Acquire a complete point cloud through the sensor; Perform ground segmentation on the complete point cloud to obtain the point cloud.

44. The system according to claim 39, characterized in that The step of obtaining a point cloud collected by a sensor includes: Acquire a complete point cloud through the sensor; Perform ground segmentation on the complete point cloud to obtain the point cloud.

45. The system according to any one of claims 26 to 30, characterized in that The movable platform may be equipped with one or more sensors, and the sensors may include any of the following sensors: Wheel speed sensor, IMU sensor, speed sensor, acceleration sensor, gyroscope sensor, GPS positioning sensor, motor speed sensor; The predicting of the target location area of ​​the movable platform on the high-precision map includes: Acquiring driving status information of the movable platform through a sensor carried by the movable platform; The target location area of ​​the movable platform is predicted on the high-precision map based on the driving status information.

46. ​​The system according to claim 45, characterized in that After positioning the movable platform on the high-precision map according to the second degree of freedom information, the method further includes: According to the positioning position of the movable platform and the driving state information, determining a sensor among the sensors carried by the movable platform that has erroneous output information; In a preset calculation module, the weight of the output information of the sensor whose output information is erroneous is adjusted.

47. A movable platform, characterized in that: It comprises a movable platform body, a sensor, and a positioning system, wherein the sensor and the positioning system are arranged on the movable platform body; The positioning system acquires a point cloud collected by the sensor, wherein the point cloud is used to identify the ground surface of the surrounding environment of the movable platform; Determine the target feature points of the point cloud and determine the reference feature points of the high-precision map; Determining first degree of freedom information of the point cloud relative to the high-precision map according to the target feature point and the reference feature point; Correcting the pose of the point cloud using the first degree of freedom information; Determining second degree of freedom information of the point cloud relative to the high-precision map according to the reference feature points on the high-precision map and the target feature points on the corrected point cloud; According to the second degree of freedom information, the movable platform is positioned on the high-precision map.

48. The movable platform according to claim 47, characterized in that: The first degree of freedom information includes a Pitch parameter, a Roll parameter, and a Z parameter, and the second degree of freedom information includes an X parameter, a Y parameter, and a Yaw parameter.

49. The movable platform according to claim 48, characterized in that The positioning system determines the target feature points of the point cloud, including: Determine the target feature points in the point cloud surface obtained by projecting the point cloud in the Z-axis direction.

50. The movable platform according to claim 49, characterized in that: The positioning system is also used for: Predicting the target location area of ​​the movable platform on the high-precision map; The step of determining the reference feature points of the high-precision map includes: Determine reference feature points of the high-precision map surface located in the target location area on the high-precision map.

51. The movable platform according to claim 50, characterized in that: The positioning system determines, according to the target feature point and the reference feature point, first degree of freedom information of the point cloud relative to the high-precision map, including: Acquire multiple candidate transformation matrices, where the candidate transformation matrices are used to correct the pose of the point cloud surface in three degrees of freedom, namely, pitch, roll and Z, to be consistent with the high-precision map surface; Calculate the correction loss corresponding to each candidate transformation matrix according to the height value corresponding to the target feature point and the height value corresponding to the reference feature point; Determine the candidate transformation matrix corresponding to the minimum correction loss as the target transformation matrix; The first degree of freedom information is determined according to the target transformation matrix.

52. The movable platform according to claim 51, characterized in that: The point cloud surface includes a plurality of point cloud projection points; the positioning system determines the target feature points in the point cloud surface obtained by projecting the point cloud in the Z-axis direction, including performing any of the following operations: Extracting feature points on the point cloud surface as the target feature points according to a feature extraction algorithm, wherein the extracted feature points include the point cloud projection points used to characterize corner points or edge points; The point cloud surface obtained by projection is meshed according to a preset mesh size, and the central pixel of the mesh is used as the target feature point.

53. The movable platform according to claim 52, characterized in that: The height value corresponding to the target feature point is determined based on the following operations: If the target feature point is the point cloud projection point, the projection height corresponding to the point cloud projection point is used as the height value corresponding to the target feature point; If the target feature point is the central pixel of the grid, the average of the projection heights corresponding to other point cloud projection points in the grid is used as the height value of the target feature point.

54. A movable platform according to any one of claims 51 to 53, characterized in that The positioning system calculates the correction loss corresponding to each candidate transformation matrix according to the height value corresponding to the target feature point and the height value corresponding to the reference feature point, including: Pairing the target feature points with the reference feature points to determine a plurality of feature point pairing groups; Calculate the height difference between the height value corresponding to each set of paired target feature points and the height value corresponding to the reference feature points; The correction loss amount is determined based on the calculated multiple height differences.

55. A movable platform according to any one of claims 49 to 53, characterized in that The positioning system determines the second degree of freedom information of the point cloud relative to the high-precision map according to the reference feature points on the high-precision map and the target feature points on the corrected point cloud, including: According to the value range of the Yaw parameter, a Yaw parameter to be selected is determined; According to the reference feature points and the target feature points on the corrected point cloud surface, the loss amounts corresponding to different X parameters and Y parameters under each selected Yaw parameter are calculated, wherein the different X parameters and Y parameters are determined according to the value ranges of the X parameters and the Y parameters respectively; The second degree of freedom information is determined according to the calculated minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter.

56. The movable platform according to claim 54, characterized in that The positioning system determines the second degree of freedom information of the point cloud relative to the high-precision map according to the reference feature points on the high-precision map and the target feature points on the corrected point cloud, including: According to the value range of the Yaw parameter, a Yaw parameter to be selected is determined; According to the reference feature points and the target feature points on the corrected point cloud surface, the loss amounts corresponding to different X parameters and Y parameters under each selected Yaw parameter are calculated, wherein the different X parameters and Y parameters are determined according to the value ranges of the X parameters and the Y parameters respectively; The second degree of freedom information is determined according to the calculated minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter.

57. The movable platform according to claim 55, characterized in that: The positioning system is also used for: For each Yaw parameter to be selected, after the reference feature points are paired with the target feature points on the corrected point cloud surface, the height difference between the height values ​​corresponding to each set of paired reference feature points and the height values ​​corresponding to the target feature points is determined according to the first search range; Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference; Based on the determined X parameter and Y parameter, determining, according to a second search range, a height difference between a height value corresponding to each group of the paired reference feature points and a height value corresponding to the target feature point after pairing the reference feature points with the target feature points on the corrected point cloud surface, wherein the second search range is smaller than the first search range; Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference; According to the determined minimum value of the global height difference and the X parameter and Y parameter corresponding to the minimum value of the global height difference, the minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter are calculated.

58. The movable platform according to claim 56, characterized in that: The positioning system is also used for: For each Yaw parameter to be selected, after the reference feature points are paired with the target feature points on the corrected point cloud surface, the height difference between the height values ​​corresponding to each set of paired reference feature points and the height values ​​corresponding to the target feature points is determined according to the first search range; Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference; Based on the determined X parameter and Y parameter, determining, according to a second search range, a height difference between a height value corresponding to each group of the paired reference feature points and a height value corresponding to the target feature point after pairing the reference feature points with the target feature points on the corrected point cloud surface, wherein the second search range is smaller than the first search range; Obtaining a global height difference according to the height difference between the height values ​​corresponding to each group of paired reference feature points and the height values ​​corresponding to the target feature points, and determining an X parameter and a Y parameter corresponding to the minimum value of the global height difference; According to the determined minimum value of the global height difference and the X parameter and Y parameter corresponding to the minimum value of the global height difference, the minimum loss amount under each candidate Yaw parameter and the X parameter and Y parameter corresponding to the minimum loss amount under each candidate Yaw parameter are calculated.

59. The movable platform according to claim 55, characterized in that: After calculating the loss amount corresponding to different X parameters and Y parameters under each selected Yaw parameter, the positioning system is further used to: Determine whether there is a loss amount to be checked that meets a preset condition among the calculated multiple loss amounts, wherein the preset condition includes a value condition and a position condition, the value condition includes that the loss amount value is consistent, and the position condition includes that the X parameters or Y parameters corresponding to the multiple loss amounts to be checked are consistent; If there are multiple loss amounts to be checked that meet the preset conditions among the multiple loss amounts calculated, it is determined that the X parameters and Y parameters corresponding to the multiple loss amounts to be checked are not credible.

60. The movable platform according to any one of claims 56 to 57, characterized in that After calculating the loss amount corresponding to different X parameters and Y parameters under each selected Yaw parameter, the positioning system is further used to: Determine whether there is a loss amount to be checked that meets a preset condition among the calculated multiple loss amounts, wherein the preset condition includes a value condition and a position condition, the value condition includes that the loss amount value is consistent, and the position condition includes that the X parameters or Y parameters corresponding to the multiple loss amounts to be checked are consistent; If there are multiple loss amounts to be checked that meet the preset conditions among the multiple loss amounts calculated, it is determined that the X parameters and Y parameters corresponding to the multiple loss amounts to be checked are not credible.

61. The movable platform according to claim 55, characterized in that: After calculating the loss amount corresponding to different X parameters and Y parameters under each selected Yaw parameter, the positioning system is further used to: Determine whether the X parameter and / or Y parameter corresponding to the minimum loss amount under each selected Yaw parameter is located at the edge of the target position area; If the calculated X parameter and / or Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter is located at the edge of the target position area, it is determined that the X parameter and Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter are unreliable.

62. The movable platform according to any one of claims 56 to 57, characterized in that After calculating the loss amount corresponding to different X parameters and Y parameters under each selected Yaw parameter, the positioning system is further used to: Determine whether the X parameter and / or Y parameter corresponding to the minimum loss amount under each selected Yaw parameter is located at the edge of the target position area; If the calculated X parameter and / or Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter is located at the edge of the target position area, it is determined that the X parameter and Y parameter corresponding to the minimum loss amount under the target candidate Yaw parameter are unreliable.

63. A movable platform according to any one of claims 47 to 53, 56 to 59, and 61, characterized in that: The positioning system acquires a point cloud collected by a sensor, including: Acquire a complete point cloud through the sensor; Perform ground segmentation on the complete point cloud to obtain the point cloud.

64. The movable platform according to claim 54, characterized in that: The positioning system acquires a point cloud collected by a sensor, including: Acquire a complete point cloud through the sensor; Perform ground segmentation on the complete point cloud to obtain the point cloud.

65. The movable platform according to claim 55, characterized in that: The positioning system acquires a point cloud collected by a sensor, including: Acquire a complete point cloud through the sensor; Perform ground segmentation on the complete point cloud to obtain the point cloud.

66. The movable platform according to any one of claims 60, characterized in that The positioning system acquires a point cloud collected by a sensor, including: Acquire a complete point cloud through the sensor; Perform ground segmentation on the complete point cloud to obtain the point cloud.

67. The movable platform according to any one of claims 62, characterized in that The positioning system acquires a point cloud collected by a sensor, including: Acquire a complete point cloud through the sensor; Perform ground segmentation on the complete point cloud to obtain the point cloud.

68. The movable platform according to any one of claims 50 to 53, characterized in that The movable platform may be equipped with one or more sensors, and the sensors may include any of the following sensors: Wheel speed sensor, IMU sensor, speed sensor, acceleration sensor, gyroscope sensor, GPS positioning sensor, motor speed sensor; The positioning system predicts the target location area of ​​the movable platform on the high-precision map, including: Acquiring driving status information of the movable platform through a sensor carried by the movable platform; The target location area of ​​the movable platform is predicted on the high-precision map based on the driving status information.

69. The movable platform according to claim 68, characterized in that After the positioning system locates the movable platform on the high-precision map according to the second degree of freedom information, the method further includes: According to the positioning position of the movable platform and the driving state information, determining a sensor among the sensors carried by the movable platform that has erroneous output information; In a preset calculation module, the weight of the output information of the sensor whose output information is erroneous is adjusted.

70. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, the positioning method according to any one of claims 1 to 23 is implemented.

Images