Unmanned positioning method and apparatus for vehicle, vehicle, and storage medium

Abstract

An unmanned positioning method and apparatus for a vehicle, the vehicle, and a storage medium. The unmanned positioning method for a vehicle comprises: obtaining a GDOP value of a current positioning policy of a vehicle (S101); calculating a current confidence of the current positioning policy according to the GDOP value (S102); and when the current confidence is less than a trusted confidence, determining that the current positioning policy is invalid, and replacing the current positioning policy with an alternative positioning policy, so as to obtain a current location of the vehicle by performing fusing according to Global Navigation Satellite System (GNSS) data, laser radar data, and inertial measurement data of the vehicle on the basis of the alternative positioning policy (S103). The accuracy of vehicle positioning when a GNSS signal is weak is effectively improved, so that the safety of the vehicle is improved, and in addition, the user driving experience is met.

Description

Unmanned driving positioning method, device, vehicle and storage medium for vehicle

[0001] This application claims priority to Chinese patent application No. 202310699223.0, filed on June 12, 2023, entitled “Unmanned Driving Positioning Method and Device for Vehicles,” the entire contents of which are incorporated herein by reference. Technical Field

[0002] The present application relates to the field of autonomous driving technology, and in particular to a method, device, vehicle, and storage medium for unmanned driving positioning of a vehicle. Background Art

[0003] In related technologies, vehicles can use multi-sensor information fusion positioning technology that combines GNSS (Global Navigation Satellite System) and IMU (Inertial Measurement Unit) to achieve real-time positioning in complex environments by sensing the surrounding environment.

[0004] However, when the vehicle's GNSS signal is weak, using a positioning method that combines GNSS with IMU can easily lead to deviations or jumps in positioning information, resulting in low positioning accuracy, thereby reducing vehicle safety and the user's driving experience, and failing to meet the user's driving needs.

[0005] Summary of the Invention

[0006] The embodiments of the present application provide a method, device, vehicle, and storage medium for unmanned driving positioning of a vehicle, which can solve the problem of low positioning accuracy when the vehicle's GNSS signal is weak by combining GNSS and IMU in related technologies.

[0007] A first aspect embodiment of the present application provides an unmanned driving positioning method for a vehicle, the method comprising: obtaining a geometric dilution of precision (GDOP) value of a current positioning strategy of the vehicle, the GDOP value being used to indicate the positioning accuracy of the global navigation satellite system (GNSS) data of the vehicle, the current positioning strategy being a GNSS positioning strategy; calculating a current confidence level of the current positioning strategy based on the geometric dilution of precision (GDOP) value; and determining, when the current confidence level is less than a trustworthy confidence level, that the current positioning strategy is invalid, replacing the current positioning strategy with an alternative positioning strategy to determine the current positioning of the vehicle based on the alternative positioning strategy, the alternative positioning strategy being a positioning strategy that obtains the current positioning of the vehicle by fusing the global navigation satellite system (GNSS) data, lidar data, and inertial measurement data of the vehicle.

[0008] Optionally, in one embodiment of the present application, the current positioning of the vehicle is obtained by fusing the GNSS data, lidar data and inertial measurement data of the vehicle, including: determining the initial posture information of the vehicle in the map coordinate system based on the GNSS data and the inertial measurement data; generating a point cloud scene graph based on the initial posture information and the lidar data; and determining the current positioning of the vehicle based on the matching results between the point cloud data in the lidar data and the point cloud scene map.

[0009] Optionally, in one embodiment of the present application, determining the initial posture information of the vehicle in the map coordinate system based on the GNSS data and the inertial measurement data includes: determining the global positioning information in the reference coordinate system based on the GNSS data and the inertial measurement data through an extended Kalman filter; determining the initial posture information of the vehicle in the map coordinate system based on the conversion relationship between the reference coordinate system and the map coordinate system, and the global positioning information.

[0010] Optionally, in one embodiment of the present application, generating a point cloud scene graph based on the initial pose information and the lidar data includes: constructing a point cloud map based on at least one key frame corresponding to the initial pose information in the lidar data; extracting key frame data from the lidar data; extracting at least one point surface feature from the key frame data, performing pose matching on each point surface feature respectively to obtain key frame pose information; and inserting the point cloud data into the point cloud map based on the key frame pose information to generate a point cloud scene map.

[0011] Optionally, in one embodiment of the present application, before replacing the current positioning strategy with the alternative positioning strategy, the method further includes: obtaining the Euclidean distance residual between the point cloud data and the corresponding points in the point cloud scene map; calculating the confidence of the alternative positioning strategy based on the Euclidean distance residual; when the confidence of the alternative positioning strategy is greater than or equal to the current confidence, executing the operation of replacing the current positioning strategy with the alternative positioning strategy.

[0012] Optionally, in one embodiment of the present application, after calculating the confidence of the alternative positioning strategy based on the Euclidean distance residual, the method further includes: when the confidence of the alternative positioning strategy is less than the current confidence, while still using the current positioning strategy for positioning, issuing a low confidence reminder.

[0013] Optionally, in one embodiment of the present application, after calculating the confidence of the alternative positioning strategy based on the Euclidean distance residual, the method further includes: when the confidence of the alternative positioning strategy is less than the current confidence, determining whether the current confidence is less than an untrustworthy confidence; if the current confidence is less than the untrustworthy confidence, issuing a prompt that positioning is impossible.

[0014] A second aspect of the present application provides an unmanned driving positioning device for a vehicle, the device comprising: an acquisition module for acquiring a geometric dilution of precision (GDOP) value of a current positioning strategy of the vehicle, the GDOP value being used to indicate the positioning accuracy of the global navigation satellite system (GNSS) data of the vehicle, the current positioning strategy being a GNSS positioning strategy; a calculation module for calculating a current confidence level of the current positioning strategy based on the geometric dilution of precision (GDOP) value; and a processing module for determining, when the current confidence level is less than a trustworthy confidence level, that the current positioning strategy is invalid, and replacing the current positioning strategy with an alternative positioning strategy to determine the current positioning of the vehicle based on the alternative positioning strategy, the alternative positioning strategy being a positioning strategy for obtaining the current positioning of the vehicle by fusing the global navigation satellite system (GNSS) data, lidar data, and inertial measurement data of the vehicle.

[0015] Optionally, in one embodiment of the present application, the processing module is used to: determine the initial posture information of the vehicle in the map coordinate system based on the GNSS data and the inertial measurement data; generate a point cloud scene graph based on the initial posture information and the lidar data; and determine the current positioning of the vehicle based on the matching results between the point cloud data in the lidar data and the point cloud scene map.

[0016] Optionally, in one embodiment of the present application, the processing module is used to: determine the global positioning information in the reference coordinate system based on the GNSS data and the inertial measurement data through an extended Kalman filtering method; determine the initial posture information of the vehicle in the map coordinate system based on the conversion relationship between the reference coordinate system and the map coordinate system, and the global positioning information.

[0017] Optionally, in one embodiment of the present application, the processing module is used to: construct a point cloud map based on at least one key frame in the lidar data corresponding to the initial pose information; extract key frame data from the lidar data; extract at least one point surface feature from the key frame data, perform pose matching on each point surface feature respectively, and obtain key frame pose information; insert the point cloud data into the point cloud map based on the key frame pose information to generate a point cloud scene map.

[0018] Optionally, in one embodiment of the present application, the acquisition module is further used to: before replacing the current positioning strategy with the alternative positioning strategy, obtain the Euclidean distance residual between the point cloud data and the corresponding points in the point cloud scene map; the calculation module is further used to: before replacing the current positioning strategy with the alternative positioning strategy, calculate the confidence of the alternative positioning strategy based on the Euclidean distance residual; the replacement module is further used to: before replacing the current positioning strategy with the alternative positioning strategy, when the confidence of the alternative positioning strategy is greater than or equal to the current confidence, execute the operation of replacing the current positioning strategy with the alternative positioning strategy.

[0019] Optionally, in one embodiment of the present application, the device further includes: a control module for, after calculating the confidence of the alternative positioning strategy, when the confidence of the alternative positioning strategy is less than the current confidence, issuing a low confidence reminder while still using the current positioning strategy for positioning.

[0020] Optionally, in one embodiment of the present application, the device further includes: a judgment module for judging whether the current confidence is less than an untrustworthy confidence when the confidence of the alternative positioning strategy is less than the current confidence; the processing module is also used to: issue a positioning failure prompt if the current confidence is less than the untrustworthy confidence.

[0021] The third aspect of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the unmanned driving positioning method for the vehicle as described in the above embodiment.

[0022] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above-mentioned unmanned driving positioning method of the vehicle.

[0023] The fifth embodiment of the present application provides a computer program product, which, when running on a vehicle, enables the vehicle to implement the above-mentioned unmanned driving positioning method for the vehicle.

[0024] The embodiment of the present application can obtain the GDOP value of the vehicle's current positioning strategy, thereby calculating the current confidence of the current positioning strategy. When the current confidence is less than the trusted confidence, the current positioning strategy is replaced with an alternative positioning strategy to obtain the vehicle's current positioning based on the fusion of the vehicle's GNSS data, lidar data and inertial measurement data. This effectively improves the accuracy of vehicle positioning when the GNSS signal is weak, thereby improving the safety of the vehicle while also satisfying the user's driving experience.

[0025] Additional aspects and advantages of the embodiments of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0027] FIG1 is a flow chart of a method for positioning an unmanned vehicle provided in an embodiment of the present application.

[0028] FIG2 is a schematic diagram of edge point feature matching provided in an embodiment of the present application.

[0029] FIG3 is a schematic diagram of planar point feature matching provided in an embodiment of the present application.

[0030] FIG4 is a schematic diagram showing the principle of switching between two positioning modes according to a calculated confidence level, provided in an embodiment of the present application.

[0031] FIG5 is a schematic structural diagram of an unmanned driving positioning device for a vehicle provided in an embodiment of the present application.

[0032] FIG6 is a schematic structural diagram of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0034] Before explaining the embodiments of the present application, the application scenarios of the embodiments of the present application are first introduced.

[0035] A prerequisite for autonomous vehicles on the road is knowing their current position and the position of their target. Therefore, they need sensors to perceive the surrounding environment and achieve real-time positioning of their current position within that environment. Commonly used sensors for positioning include GNSS, LiDAR, and IMU. Each sensor has limitations when determining the vehicle's current position. Multi-sensor information fusion positioning technology overcomes the limitations of single-sensor positioning technology, such as limited information, poor timeliness, and poor robustness. This effectively improves the accuracy and feasibility of positioning perception in complex environments. Therefore, multi-sensor information fusion positioning technology is a promising research area in the current autonomous driving field.

[0036] At present, multi-sensor information fusion positioning technology usually includes positioning technology that combines GNSS and IMU. IMU can make up for the defect of low GNSS update frequency, and GNSS can correct the motion error of IMU. However, if it is in an underground tunnel or other places with poor GNSS signal, GNSS may not be able to correct the motion error of IMU in time. At this time, the current positioning determined has deviated or jumped. If this situation cannot be detected in time, it can easily cause a vehicle accident.

[0037] Based on this, the present application provides a method for unmanned driving positioning of a vehicle, in which the GDOP value of the vehicle's current positioning strategy can be obtained to calculate the current confidence of the current positioning strategy. When the current confidence is less than the trusted confidence, the current positioning strategy is replaced with an alternative positioning strategy to obtain the current positioning of the vehicle based on the fusion of the vehicle's GNSS data, lidar data and inertial measurement data, effectively improving the accuracy of vehicle positioning when the GNSS signal is weak, thereby improving the safety of the vehicle while also satisfying the user's driving experience.

[0038] The following describes the unmanned driving positioning method and device for a vehicle provided by an embodiment of the present application with reference to the accompanying drawings.

[0039] Figure 1 is a flow chart of a method for positioning a vehicle in an unmanned driving state provided by an embodiment of the present application. As shown in Figure 1 , the method for positioning a vehicle in an unmanned driving state includes the following steps.

[0040] In step S101 , a GDOP value of a current positioning strategy of a vehicle is obtained. The GDOP value is used to indicate the positioning accuracy of GNSS data of the vehicle. The current positioning strategy is a GNSS positioning strategy.

[0041] It is understood that embodiments of the present application can obtain the GDOP (geometric dilution precision) value of the vehicle's current positioning strategy. For example, the GDOP value corresponding to the GNSS data can be calculated based on the PDOP (position dilution of precision) and TDOP (time dilution of precision) data, and the calculated value can be used as the GDOP value of the current positioning strategy, thereby effectively improving the executability of the unmanned driving positioning provided by the embodiments of the present application.

[0042] PDOP is not only related to the quality of the observation, but also to the geometry between the satellite being measured and the receiver. Therefore, PDOP can also be considered a measure of precision. For example, PDOP can be calculated from HDOP (Horizontal Dilution of Precision) and VDOP (Vertical Dilution of Precision).

[0043] In some embodiments, the GDOP calculation method can be expressed by the following formula: 2 +VDOP 2 =PDOP 2 PDOP 2 +TDOP 2 =GDOP 2

[0044] Among them, HDOP represents the horizontal component precision dilution, VDOP represents the vertical component precision dilution, PDOP represents the three-dimensional position precision dilution, and TDOP represents the clock precision dilution.

[0045] It should be noted that GDOP can represent the distance vector amplification factor between the receiver and the space satellite caused by the GNSS ranging error, and the volume of the shape outlined by the unit vector from the receiver to the space satellite participating in the positioning solution is inversely proportional to the GDOP. Therefore, GDOP can be called the geometric precision factor.

[0046] In step S102 , the current confidence of the current positioning strategy is calculated based on the GDOP value.

[0047] It is understood that embodiments of the present application can calculate the current confidence of the current positioning strategy based on the GDOP value. For example, the current confidence can be calculated based on the GDOP value to evaluate the accuracy of the position in the ENU (East-North-Up) coordinate system output under the current positioning strategy.

[0048] A larger GDOP value indicates a lower GNSS data positioning accuracy. Conversely, a smaller GDOP value indicates a higher GNSS data positioning accuracy. Therefore, there is a negative correlation between the GDOP value determined in S101 and the current confidence level of the current positioning strategy. In other words, a larger GDOP value indicates a lower confidence level of the current positioning strategy, while a smaller GDOP value indicates a higher confidence level of the current positioning strategy.

[0049] For example, the obtained GDOP value can be normalized and then aligned with the confidence measurement method. For example, when the GDOP value is 0, the current confidence is 1. Similarly, the current confidence of the current positioning strategy is obtained, which serves as the standard for judging the currently adopted GNSS positioning strategy, thereby effectively improving the accuracy of autonomous driving positioning.

[0050] In step S103, when the current confidence level is less than the trustworthy confidence level, the current positioning strategy is determined to be invalid, and the current positioning strategy is replaced with an alternative positioning strategy to determine the current positioning of the vehicle based on the alternative positioning strategy. The alternative positioning strategy is a positioning strategy that obtains the current positioning of the vehicle by fusing the vehicle's GNSS data, lidar data and inertial measurement data.

[0051] The trustworthy confidence level is a preset confidence level.

[0052] It is understandable that the embodiments of the present application may determine that the current positioning strategy is invalid when the current confidence level is less than the trustworthy confidence level, and further replace the current positioning strategy with an alternative positioning strategy to determine the current positioning of the vehicle based on the alternative positioning strategy. After adopting the alternative positioning strategy, the vehicle obtains the current positioning of the vehicle by fusing the vehicle's GNSS data, lidar data, and inertial measurement data in the following steps, thereby effectively improving the accuracy of unmanned driving positioning when the GNSS signal is weak, and improving the quality of the map constructed in the unmanned driving scenario.

[0053] Optionally, in some embodiments, the current positioning of the vehicle is obtained by fusing the vehicle's GNSS data, lidar data and inertial measurement data as follows: determining the initial posture information of the vehicle in the map coordinate system based on the GNSS data and inertial measurement data; generating a point cloud scene graph based on the initial posture information and the lidar data; and determining the current positioning of the vehicle based on the matching results between the point cloud data in the lidar data and the point cloud scene map.

[0054] In an embodiment of the present application, the initial posture information of a vehicle can be determined based on GNSS data and inertial measurement data, and then the initial posture information can be corrected based on the lidar data collected by the vehicle to obtain the current positioning of the vehicle, thereby improving the accuracy of vehicle positioning when the GNSS signal is weak.

[0055] The method for determining the vehicle's initial position and pose in the map coordinate system based on GNSS data and inertial measurement data is exemplified by: determining global positioning information in the reference coordinate system based on the GNSS data and inertial measurement data using an extended Kalman filter; and determining the vehicle's initial position and pose in the map coordinate system based on the conversion relationship between the reference coordinate system and the map coordinate system and the global positioning information. In other words, the global positioning information is transformed into the map coordinate system to obtain the vehicle's initial position and pose.

[0056] As a possible implementation method, the GNSS and IMU in the embodiment of the present application can be fused through the extended Kalman filter method to output the global positioning information in the ENU coordinate system, that is, the reference coordinate system is the ENU coordinate system, and the global positioning information is transformed into the map coordinate system through coordinate transformation, which serves as the initial posture information for positioning through lidar data, thereby effectively improving the robustness of vehicle positioning.

[0057] For example, embodiments of the present application can complete the initialization of positioning of an unmanned vehicle in a map coordinate system based on the longitude and latitude information measured by GNSS in the ENU coordinate system and the attitude angle information measured by IMU. The conversion relationship between the ENU coordinate system and the map coordinate system can be obtained using open source tools and will not be repeated here.

[0058] Optionally, determining the initial position information of the vehicle in the map coordinate system based on the GNSS data and the inertial measurement data can be achieved by other means, such as by a strong tracking filter algorithm, which will not be described in detail here.

[0059] In addition, an example of an implementation method for generating a point cloud scene graph based on the initial pose information and lidar data is as follows: constructing a point cloud map based on at least one key frame corresponding to the initial pose information in the lidar data; extracting key frame data from the lidar data; extracting at least one point surface feature from the key frame data, performing pose matching on each point surface feature respectively, and obtaining key frame pose information; inserting the point cloud data into the map based on the key frame pose information to generate a point cloud scene map.

[0060] Among them, the embodiment of the present application uses the point cloud data scanned by the lidar on the vehicle when the vehicle is in the initial posture information state as at least one key frame in the lidar data corresponding to the initial posture information. In other words, a point cloud map is constructed based on the key frame obtained from the initial posture information.

[0061] Then, keyframe data is extracted from the LiDAR data. For example, keyframe data is extracted from the LiDAR data by setting a translation threshold and a rotation threshold of the LiDAR scan data. For example, the translation threshold is set to 1m translation and the rotation threshold is set to 10 degrees attitude angle.

[0062] After obtaining the key frame data, point and surface features are extracted based on the key frame data, and pose matching is performed on each point and surface feature. The key frame point cloud data is inserted into the point cloud map according to the obtained pose to generate a point cloud scene map, effectively reducing the amount of calculation and lowering computing power.

[0063] The embodiment of the present application can extract features from point cloud data and perform feature matching to calculate the pose transformation relationship. The extracted features include point features and surface features, referred to as point-surface features.

[0064] For example, when receiving new LiDAR scan data, edge points and plane points are calculated based on the average distance of the ten points before and after a point in each scan line of the LiDAR scan data, thereby obtaining point features and surface features. An edge point is a point on a sharp edge in three-dimensional space, with a large size difference between the edge point and the surrounding points, high curvature, and high smoothness. A plane point is a point on a smooth plane in three-dimensional space, with a small size difference between the plane point and the surrounding points, low curvature, and low smoothness.

[0065] For example, the matching of point features is solved by minimizing the distance from the edge point to the edge line, and the matching of surface features is solved by optimizing the distance from the plane point to the plane formed by the adjacent plane points. For example, as shown in Figure 2, Figure 2 represents the matching process of point features corresponding to edge points. Lines (1), (2) and (3) represent the scanning lines of the multi-line laser radar. In the k+1 frame, edge point i is on the scanning line of line (2). In the k frame, edge point j on line (2) is closer to i. If a nearest edge point l is found on the adjacent line (1), then l and j form an edge line. Therefore, for the edge feature point, the optimization goal is to minimize the distance from i to the line lj, and the feature of the edge point i after the final optimization is used as the extracted point feature.

[0066] The distance from edge point i to edge point l, j is calculated as follows:

[0067] Among them, d represents the calculated distance value, and X2, X1, and X0 represent the coordinates of the three edge points respectively.

[0068] For another example, as shown in Figure 3, Figure 3 represents the matching process of surface features corresponding to plane points. Lines (1), (2) and (3) represent the scanning lines of the multi-line laser radar. In the k+1 frame, plane point i is on the scanning line of (2). In the k frame, plane point j on (2) is closer to i. A nearby plane point l is found on the same line, and a nearest plane point m is found on the adjacent (1) line. Then points l, m, and j form a plane. Therefore, for the plane feature points, the optimization goal is to make the distance from plane point i to plane mlj as short as possible, and the features of the finally optimized plane point i are used as the extracted surface features.

[0069] The distance from plane point i to the plane formed by plane points m, l, j is calculated as follows:

[0070] Where d represents the calculated distance value, and X3, X2, X1, and X0 represent the coordinate values ​​of the four plane points.

[0071] In some embodiments, due to the cumulative error of the front-end laser odometer, when the unmanned vehicle repeatedly passes through the same area, the newly created map deviates from the original map and a ghosting problem occurs, so loop detection can be performed. The embodiment of the present application introduces the positioning data of the fusion of GNSS and IMU, that is, the initial posture information, as the initial value of loop detection, sets the loop detection search range within 10m of the initial value, searches for the historical position closest to the current position within the initial value range, uses the 10 key frames before and after the historical position to match the current frame, and finds the key frame with the closest distance to the posture corresponding to the current frame and the longest interval time, which effectively speeds up the loop detection speed and improves the accuracy of loop detection.

[0072] It should be noted that the above embodiment is used to illustrate the implementation method of obtaining the current positioning of the vehicle by fusing the vehicle's GNSS data, lidar data and inertial measurement data. The embodiment of the present application does not limit the implementation method of this alternative positioning strategy, and will not be illustrated one by one here.

[0073] Optionally, in an embodiment of the present application, before replacing the current positioning strategy with the alternative positioning strategy, the Euclidean distance residual between the point cloud data and the corresponding points in the point cloud scene map can also be obtained; the confidence of the alternative positioning strategy is calculated based on the Euclidean distance residual; when the confidence of the alternative positioning strategy is greater than or equal to the current confidence, the operation of replacing the current positioning strategy with the alternative positioning strategy is executed, that is, the current positioning strategy is allowed to be replaced with the alternative positioning strategy.

[0074] In the embodiment of the present application, based on the establishment of a point cloud map, the global posture of the vehicle is first initialized using GNSS and IMU. The posture transformation matrix in the map coordinate system is calculated by matching the point cloud data of the current frame with the point cloud scene graph to obtain the posture information of the current unmanned vehicle. At the same time, the Euclidean distance residual sum between the current lidar scan data, i.e., the point cloud data, and the corresponding points on the point cloud map is calculated based on the obtained posture transformation matrix, i.e., the rotation and translation matrix. The Euclidean distance residual sum is used to characterize the confidence of the alternative positioning strategy. The calculation method is as follows:

[0075] Among them, P i is the coordinate value of the point cloud in the point cloud map, T is the rotation and translation matrix, Q i is the laser scanning data of the current frame, score is the Euclidean distance residual sum, that is, the confidence of the alternative positioning strategy, which is also called the lidar positioning confidence.

[0076] For example, as shown in Figure 4, the confidence of the current positioning strategy, that is, the GNSS positioning strategy, is marked as C2, and the confidence of the alternative positioning strategy, that is, the lidar + IMU + GNSS fusion positioning strategy, is marked as C1. When the calculated confidence C1 is greater than or equal to the current confidence C2, it is allowed to be replaced with the alternative positioning strategy, thereby effectively improving the positioning accuracy and improving the safety and reliability of the vehicle.

[0077] Optionally, in other embodiments, after calculating the confidence of the alternative positioning strategy, when the confidence of the alternative positioning strategy is less than the current confidence, while still using the current positioning strategy for positioning, a low confidence reminder is issued.

[0078] For example, when the confidence of the alternative positioning strategy is lower than the current confidence, it is prohibited to replace the current positioning strategy with the alternative positioning strategy. While the current positioning strategy is still used for positioning, a low confidence reminder is issued through a pop-up window on the central control screen, which effectively improves the interactivity of the vehicle.

[0079] Optionally, in other embodiments, after calculating the confidence of the alternative positioning strategy, if the confidence of the alternative positioning strategy is less than the current confidence, it can be further determined whether the current confidence is less than a preset untrustworthy confidence; if the current confidence is less than the preset untrustworthy confidence, a prompt indicating that positioning cannot be performed is given.

[0080] For example, an embodiment of the present application can determine whether the current confidence level is less than the untrustworthy confidence level. If the current confidence level is less than the untrustworthy confidence level, a pop-up window on the central control screen can be displayed to indicate that positioning is impossible, thereby improving the user's driving safety.

[0081] According to the unmanned driving positioning method for a vehicle proposed in an embodiment of the present application, the GDOP value of the vehicle's current positioning strategy can be obtained, thereby calculating the current confidence of the current positioning strategy. When the current confidence is less than the trusted confidence, the current positioning strategy is replaced with an alternative positioning strategy to obtain the vehicle's current positioning based on the fusion of the vehicle's GNSS data, lidar data and inertial measurement data, effectively improving the accuracy of vehicle positioning when the GNSS signal is weak, thereby improving the safety of the vehicle, while also satisfying the user's driving experience.

[0082] Next, the unmanned driving positioning device for a vehicle proposed in an embodiment of the present application will be described with reference to the accompanying drawings.

[0083] FIG5 is a block diagram of an unmanned driving positioning device for a vehicle according to an embodiment of the present application.

[0084] As shown in FIG5 , the unmanned driving positioning device 10 of a vehicle includes: an acquisition module 100 , a calculation module 200 and a processing module 300 .

[0085] The acquisition module 100 is used to acquire the GDOP value of the current positioning strategy of the vehicle. The GDOP value is used to indicate the positioning accuracy of the GNSS data of the vehicle. The current positioning strategy is the GNSS positioning strategy.

[0086] The calculation module 200 is used to calculate the current confidence of the current positioning strategy based on the GDOP value.

[0087] The processing module 300 is used to determine that the current positioning strategy is invalid when the current confidence level is less than the trusted confidence level, and replace the current positioning strategy with an alternative positioning strategy to determine the current positioning of the vehicle based on the alternative positioning strategy. The alternative positioning strategy is a positioning strategy that obtains the current positioning of the vehicle based on the fusion of the vehicle's global navigation satellite system GNSS data, lidar data and inertial measurement data.

[0088] Optionally, in one embodiment of the present application, the processing module 300 is used to: determine the initial posture information of the vehicle in the map coordinate system based on the GNSS data and the inertial measurement data; generate a point cloud scene graph based on the initial posture information and the lidar data; and determine the current positioning of the vehicle based on the matching results between the point cloud data in the lidar data and the point cloud scene map.

[0089] Optionally, in one embodiment of the present application, the processing module 300 is used to: determine the global positioning information in the reference coordinate system based on the fusion of the GNSS data and the inertial measurement data through an extended Kalman filtering method; determine the initial posture information of the vehicle in the map coordinate system based on the conversion relationship between the reference coordinate system and the map coordinate system, and the global positioning information.

[0090] Optionally, in one embodiment of the present application, the processing module 300 is used to: construct a point cloud map based on at least one key frame corresponding to the initial pose information in the lidar data; extract key frame data from the lidar data; extract at least one point surface feature from the key frame data, perform pose matching on each point surface feature respectively, and obtain key frame pose information; insert the point cloud data into the point cloud map based on the key frame pose information to generate a point cloud scene map.

[0091] Optionally, in one embodiment of the present application, the acquisition module is further configured to: before replacing the current positioning strategy with the alternative positioning strategy, obtain the Euclidean distance residual between the point cloud data and the corresponding points in the point cloud scene map. The calculation module is further configured to: before replacing the current positioning strategy with the alternative positioning strategy, calculate the confidence of the alternative positioning strategy based on the Euclidean distance residual. The replacement module is further configured to: before replacing the current positioning strategy with the alternative positioning strategy, execute the operation of replacing the current positioning strategy with the alternative positioning strategy when the confidence of the alternative positioning strategy is greater than or equal to the current confidence.

[0092] Optionally, in one embodiment of the present application, the apparatus 10 of the embodiment of the present application further includes a control module. The control module is configured to, after calculating the confidence of the alternative positioning strategy, issue a low confidence reminder while still using the current positioning strategy for positioning when the confidence of the alternative positioning strategy is less than the current confidence.

[0093] Optionally, in one embodiment of the present application, the apparatus 10 of the embodiment of the present application further includes a judgment module. The judgment module is configured to, when the confidence level of the alternative positioning strategy is lower than the current confidence level, determine whether the current confidence level is lower than an untrustworthy confidence level. The processing module is further configured to, if the current confidence level is lower than the untrustworthy confidence level, indicate that positioning is unsuccessful.

[0094] It should be noted that the above explanation of the embodiment of the unmanned driving positioning method for a vehicle is also applicable to the unmanned driving positioning device for a vehicle in this embodiment, and will not be repeated here.

[0095] According to the unmanned driving positioning device of a vehicle proposed in the embodiment of the present application, the GDOP value of the vehicle's current positioning strategy can be obtained, thereby calculating the current confidence of the current positioning strategy. When the current confidence is less than the trusted confidence, the current positioning strategy is replaced with an alternative positioning strategy to obtain the current positioning of the vehicle based on the fusion of the vehicle's GNSS data, lidar data and inertial measurement data, effectively improving the accuracy of vehicle positioning when the GNSS signal is weak, thereby improving the safety of the vehicle, while also satisfying the user's driving experience.

[0096] FIG6 is a schematic diagram of the structure of a vehicle provided in an embodiment of the present application. The vehicle may include:

[0097] A memory 601 , a processor 602 , and a computer program stored in the memory 601 and executable on the processor 602 .

[0098] When the processor 602 executes the program, the unmanned driving positioning method for a vehicle provided in the above embodiment is implemented.

[0099] Furthermore, the vehicle further comprises:

[0100] The communication interface 603 is used for communication between the memory 601 and the processor 602 .

[0101] The memory 601 is used to store computer programs that can be run on the processor 602 .

[0102] The memory 601 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0103] If the memory 601, processor 602, and communication interface 603 are implemented independently, the communication interface 603, memory 601, and processor 602 can be interconnected via a bus to enable communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be categorized as address buses, data buses, control buses, and the like. For ease of illustration, FIG6 shows only one thick line, but this does not imply that there is only one bus or only one type of bus.

[0104] Optionally, in a specific implementation, if the memory 601, the processor 602 and the communication interface 603 are integrated on a chip, the memory 601, the processor 602 and the communication interface 603 can communicate with each other through an internal interface.

[0105] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0106] This embodiment also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the above-mentioned unmanned driving positioning method of the vehicle is implemented.

[0107] An embodiment of the present application also provides a computer program product, which, when executed on a vehicle, enables the vehicle to implement the above-mentioned unmanned driving positioning method.

[0108] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0109] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0110] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing a custom logical function or process step, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed in a different order than shown or discussed, including performing functions in a substantially simultaneous manner or in a reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0111] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or N wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program can be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing it in other suitable ways as necessary, and then storing it in a computer memory.

[0112] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0113] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0114] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0115] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for positioning an unmanned vehicle, characterized in that: The method comprises: Acquire a geometric dilution of precision (GDOP) value of a current positioning strategy of the vehicle, wherein the GDOP value is used to indicate the positioning accuracy of the global navigation satellite system (GNSS) data of the vehicle, and the current positioning strategy is a GNSS positioning strategy; Calculating a current confidence of the current positioning strategy based on the GDOP value; When the current confidence is less than the trusted confidence, the current positioning strategy is determined to be invalid, and the current positioning strategy is replaced with an alternative positioning strategy to determine the current positioning of the vehicle based on the alternative positioning strategy. The alternative positioning strategy is a positioning strategy that obtains the current positioning of the vehicle by fusing the vehicle's GNSS data, lidar data, and inertial measurement data.

2. The method according to claim 1, characterized in that The fusing of the GNSS data, the lidar data and the inertial measurement data of the vehicle to obtain the current position of the vehicle includes: Determining initial position information of the vehicle in a map coordinate system according to the GNSS data and the inertial measurement data; Based on the initial pose information and the laser radar data, generating a point cloud scene graph; The current position of the vehicle is determined based on a matching result between the point cloud data in the laser radar data and the point cloud scene map.

3. The method according to claim 2, characterized in that Determining the initial position information of the vehicle in the map coordinate system according to the GNSS data and the inertial measurement data includes: Determine global positioning information in a reference coordinate system based on the GNSS data and the inertial measurement data by using an extended Kalman filter method; The initial position information of the vehicle in the map coordinate system is determined according to the conversion relationship between the reference coordinate system and the map coordinate system and the global positioning information.

4. The method according to claim 2, characterized in that: The step of generating a point cloud scene graph based on the initial pose information and the laser radar data includes: Constructing a point cloud map according to at least one key frame in the laser radar data corresponding to the initial pose information; Extract key frame data from the laser radar data; Extract at least one point-surface feature from the key frame data, and perform pose matching on each point-surface feature to obtain key frame pose information; The point cloud data in the laser radar data is inserted into the point cloud map based on the key frame pose information to generate a point cloud scene map.

5. The method according to claim 2, characterized in that: Before replacing the current positioning strategy with the alternative positioning strategy, the method further includes: Obtaining the Euclidean distance residual between the point cloud data and the corresponding points in the point cloud scene map; Calculating the confidence of the alternative positioning strategy based on the Euclidean distance residual; When the confidence of the candidate positioning strategy is greater than or equal to the current confidence, an operation of replacing the current positioning strategy with the candidate positioning strategy is performed.

6. The method according to claim 5, characterized in that After calculating the confidence of the alternative positioning strategy according to the Euclidean distance residual, the method further includes: When the confidence of the alternative positioning strategy is less than the current confidence, while still using the current positioning strategy for positioning, a reminder of low confidence is given.

7. The method according to claim 5, characterized in that After calculating the confidence of the alternative positioning strategy according to the Euclidean distance residual, the method further includes: When the confidence of the candidate positioning strategy is less than the current confidence, determining whether the current confidence is less than an untrustworthy confidence; If the current confidence level is less than the untrustworthy confidence level, a prompt indicating that positioning is impossible is given.

8. An unmanned driving positioning device for a vehicle, characterized in that: The device comprises: An acquisition module, used for acquiring a geometric dilution of precision (GDOP) value of a current positioning strategy of a vehicle, wherein the GDOP value is used for indicating a positioning accuracy of a global navigation satellite system (GNSS) data of the vehicle, and the current positioning strategy is a GNSS positioning strategy; A calculation module, used for calculating the current confidence of the current positioning strategy based on the GDOP value; A processing module is used to determine that the current confidence level is less than the trustworthy confidence level. If the positioning strategy fails, the current positioning strategy is replaced by an alternative positioning strategy to determine the current positioning of the vehicle based on the alternative positioning strategy. The alternative positioning strategy is a positioning strategy that obtains the current positioning of the vehicle by fusing the vehicle's GNSS data, lidar data and inertial measurement data.

9. A vehicle, characterized in that: The vehicle comprises: a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the unmanned driving positioning method for a vehicle as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement the unmanned driving positioning method for a vehicle as described in any one of claims 1 to 7.

Images