High-precision positioning methods and products

Abstract

The high-precision positioning method and product provided by the present disclosure obtain the calibration data of the calibration object to be determined in the target area at the current moment; determine the correspondence between the calibration object to be determined and each calibration object in a preset semantic map according to the calibration data, and determine the point cloud data of the calibration object to be determined in the semantic map according to the correspondence; determine the posture state of the vehicle at the current moment according to the point cloud data of the calibration object to be determined; determine the positioning result at the current moment according to the posture state of the vehicle at the current moment, so that the calibration data and the semantic map can be directly used to determine the posture state of the vehicle without using GPS positioning technology, and then obtain the positioning result. In special environments including underground parking lots, compared with GPS positioning technology, its positioning accuracy, stability and robustness are all improved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of positioning technology, and more particularly to a high-precision positioning method and product. Background Art

[0002] With the improvement of living standards, driving has become a daily choice for people. In the process of driving a vehicle, in order to provide people with navigation signals or route guidance, positioning the vehicle has become an indispensable relief.

[0003] In the prior art, the vehicle is generally positioned using the Global Positioning System (GPS), but when the vehicle is located in a special environment, such as an underground parking lot, the transmission of the GPS positioning signal will be limited. At this time, the accuracy of the vehicle positioning cannot be guaranteed. Summary of the invention

[0004] In order to solve the above problems, the present invention provides a high-precision positioning method and product.

[0005] In a first aspect, the present disclosure provides a high-precision positioning method, comprising:

[0006] Obtaining calibration data of the to-be-determined calibration object in the target area at the current moment;

[0007] Determine, according to the calibration data, a correspondence between the calibration object to be determined and each calibration object in a preset semantic map, and determine, according to the correspondence, point cloud data of the calibration object to be determined in the semantic map;

[0008] Determine the position and posture state of the vehicle at the current moment according to the point cloud data of the calibration object to be determined;

[0009] The positioning result at the current moment is determined according to the vehicle's current posture state.

[0010] In a second aspect, the present disclosure provides a high-precision positioning device, comprising:

[0011] An acquisition module is used to acquire the calibration data of the calibration object to be determined in the target area at the current moment;

[0012] A data processing module, used to determine the correspondence between the calibration object to be determined and each calibration object in a preset semantic map according to the calibration data, and determine the point cloud data of the calibration object to be determined in the semantic map according to the correspondence;

[0013] The positioning module is used to determine the position and posture state of the vehicle at the current moment according to the point cloud data of the calibration object to be determined; and is also used to determine the positioning result at the current moment according to the position and posture state of the vehicle at the current moment.

[0014] In a third aspect, the present disclosure provides a high-precision positioning system, comprising: a high-precision positioning device, and a laser radar system carried on a vehicle, wherein the vehicle is located in a target area;

[0015] Wherein, the laser radar system is used to collect calibration data of the object to be determined in the target area at the current moment, and send the calibration data to the high-precision positioning device, so that the high-precision positioning device can perform vehicle positioning using the method described in any one of claims 1-8.

[0016] In a fourth aspect, the present disclosure provides an electronic device, comprising: at least one processor and a memory;

[0017] The memory stores computer-executable instructions;

[0018] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the method as described in any of the preceding items.

[0019] In a fifth aspect, a computer-readable storage medium is provided, wherein computer-executable instructions are stored in the computer-readable storage medium, and when a processor executes the computer-executable instructions, the method described in any of the preceding items is implemented.

[0020] The high-precision positioning method and product provided by the present disclosure obtain the calibration data of the calibration object to be determined in the target area at the current moment; determine the corresponding relationship between the calibration object to be determined and each calibration object in the preset semantic map according to the calibration data, and determine the point cloud data of the calibration object to be determined in the semantic map according to the corresponding relationship; determine the posture state of the vehicle at the current moment according to the point cloud data of the calibration object to be determined; determine the positioning result at the current moment according to the posture state of the vehicle at the current moment, so that the calibration data and the semantic map can be directly used to determine the posture state of the vehicle without using GPS positioning technology, and then obtain the positioning result. In special environments including underground parking lots, compared with GPS positioning technology, its positioning accuracy, stability and robustness are all improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0022] Figure 1 A schematic diagram of the network architecture on which the present disclosure is based;

[0023] Figure 2 A flowchart of a high-precision positioning method provided by an embodiment of the present disclosure;

[0024] Figure 3 A flowchart of another high-precision positioning method provided by an embodiment of the present disclosure;

[0025] Figure 4 A flowchart of another high-precision positioning method provided by an embodiment of the present disclosure;

[0026] Figure 5 A schematic diagram of the structure of a high-precision positioning device provided by the present disclosure;

[0027] Figure 6 A schematic diagram of the structure of a high-precision positioning system provided by the present disclosure;

[0028] Figure 7 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0030] With the improvement of living standards, driving has become a daily choice for people. In the process of driving a vehicle, in order to provide people with navigation signals or route guidance, positioning the vehicle has become an indispensable relief.

[0031] In the prior art, a global positioning system (GPS) is generally used to locate a vehicle. However, when the vehicle is located in a special environment, such as an underground parking lot, the transmission of the GPS positioning signal will be limited.

[0032] In order to solve this problem, existing technologies can also use positioning technology based on visual sensors to solve the problem of low positioning accuracy caused by limited GPS signal transmission in special environments including underground parking lots. However, when using visual sensors for positioning, it is necessary to rely on good lighting conditions in the parking lot. That is, once the lighting conditions in some areas of the environment are poor, the visual positioning technology will fail to locate or fail to locate.

[0033] In response to the above problems, the present invention utilizes the positioning technology of Lidar sensors in combination with a semantic map solution based on point cloud data to achieve effective positioning of vehicles in special environments. Compared with the aforementioned GPS positioning technology, it has higher accuracy and better robustness; compared with the aforementioned visual sensor positioning technology, it no longer relies on lighting conditions and has a wider range of applications.

[0034] Specifically, the present disclosure provides a high-precision positioning method and product, wherein the high-precision positioning product includes but is not limited to a high-precision positioning device, a high-precision positioning system, an electronic device, and a storage medium. For each product, the following embodiments will be described one by one:

[0035] refer to Figure 1 , Figure 1 A schematic diagram of the network architecture on which the present disclosure is based, such as Figure 1 As shown, a network architecture based on which the present disclosure is based may include a high-precision positioning device 1 , a vehicle 2 , and a lidar system 3 .

[0036] Among them, the laser radar system 3 is installed on the vehicle 2, which can be used to scan the environment and collect laser radar data; and the high-precision positioning device 1 is hardware or software that can transmit data and interact with the vehicle 2 and the laser radar system 3 through wireless or wired means, which can be used to receive data sent by the laser radar system 3 and execute the methods described in the following examples.

[0037] When the high-precision positioning device 1 is hardware, it includes a cloud server that can realize computing functions. When the high-precision positioning device 1 is software, it can be installed in an electronic device with computing functions, including but not limited to a laptop computer and a desktop computer.

[0038] First, refer to Figure 2 , Figure 2 A flowchart of a high-precision positioning method provided by an embodiment of the present disclosure. The high-precision positioning method provided by an embodiment of the present disclosure includes:

[0039] Step 101: Acquire calibration data of the to-be-determined calibration object in the target area at the current moment.

[0040] Step 102: Determine the correspondence between the calibration object to be determined and each calibration object in a preset semantic map according to the calibration data, and determine the point cloud data of the calibration object to be determined in the semantic map according to the correspondence.

[0041] Step 103: Determine the position and posture state of the vehicle at the current moment according to the point cloud data of the object to be determined.

[0042] Step 104: Determine the positioning result at the current moment according to the current posture state of the vehicle.

[0043] The execution subject of the high-precision positioning method provided by the embodiment of the present disclosure is the aforementioned high-precision positioning device.

[0044] As mentioned above, the high-precision positioning method provided by the present disclosure can be applied to a variety of fields, including but not limited to autonomous driving equipment performing autonomous driving tasks and intelligent navigation.

[0045] It should be noted that the high-precision positioning method can be used together with the existing GPS positioning technology. For example, when a vehicle is performing an autonomous driving task or a navigation task, the GPS technology and the high-precision positioning method provided by the present invention can be used simultaneously to provide positioning services for the autonomous driving task or the navigation task. In addition, the high-precision positioning method can also independently provide positioning services for the vehicle in the autonomous driving task or the navigation task, especially for the aforementioned scenarios including underground parking lots, smart logistics warehouses, etc. that cannot receive GPS signals well. The method has better universality and better positioning effect.

[0046] Specifically, when the vehicle starts positioning with a high-precision positioning system, the LiDAR system will scan the target area where the vehicle is currently located and collect LiDAR data of the objects to be determined in the target area. The target area refers to the area where the vehicle is located, and the objects to be determined refer to objects with stable features in the target area, such as corners, pillars, railings, etc.

[0047] The positioning device will receive the laser radar data obtained by the laser radar system at the current moment as the data to be processed. After obtaining these data, the positioning device needs to filter the laser radar data of the object to be determined and calibrated from the data to be processed, that is, to obtain the calibration data.

[0048] In addition, a semantic map is also provided in the positioning device, and the semantic map may specifically be a high-precision point cloud map, which stores point cloud data of a large number of objects in the target area.

[0049] In the embodiment of the present disclosure, in order to quickly achieve positioning, the positioning device needs to determine the calibration object corresponding to the calibration object to be determined among the calibration objects included in the semantic map based on the calibration data of the calibration object to be determined, and use its point cloud data as the point cloud data of the calibration object to be determined.

[0050] Specifically, the semantic map includes the point cloud data of each calibration object. By analyzing the point cloud data, the spatial characteristics of each calibration object in the environment can be obtained, such as the contour shape of the calibration object, the relative position between the calibration objects, the position of each calibration object in the environmental space, etc. The calibration data of the calibration object to be determined is compared with the point cloud data of each calibration object in the semantic map to obtain and determine the point cloud data of the calibration object to be determined in the semantic map.

[0051] Afterwards, the positioning device will determine the vehicle's posture state at the current moment based on the point cloud data of the calibration object to be determined. The posture state can be understood as the position and posture information of the vehicle at the current moment relative to the origin of the semantic map. When determining the posture state of the vehicle at the current moment, the posture of the laser radar at the current moment relative to the origin of the map can be calculated through the registration algorithm, and then the posture is multiplied with the transformation matrix from the calibrated laser radar system to the vehicle body to obtain the posture state of the vehicle.

[0052] Finally, the positioning device will also determine and output the positioning result at the current moment according to the vehicle's current posture state. Specifically, in the special environment including the underground parking lot as mentioned above, after the positioning device obtains the posture state at the current moment, it will output the positioning result of the vehicle at the current moment according to the position and posture represented by the posture state of the vehicle. In other words, the positioning result can be composed of the translation position in the posture state and the rotation angle of the posture, which can be used to output to the vehicle and assist the vehicle in positioning itself.

[0053] Optionally, in other embodiments, there is also a step of constructing a semantic map. Point cloud data of each calibration object in the target area can be collected; a semantic map corresponding to the target area is constructed based on the point cloud data of each calibration object. Specifically, after obtaining the point cloud data of each calibration object in the target area, the point cloud data is filtered and feature-point processed in turn to obtain processed point cloud data; the processed point cloud data is subjected to motion distortion processing and motion estimation processing to obtain the semantic map.

[0054] Furthermore, in an optional embodiment, a high-precision point cloud map can be constructed based on the simultaneous positioning and mapping (LidarSimultaneous localization and mapping, referred to as Lidar SLAM) technology of the laser radar system. In the absence of GPS signals, Lidar SLAM is a technology that effectively realizes simultaneous positioning and mapping. The point cloud data in the target area obtained by the collection is filtered, feature point extraction and other pre-processing in turn, so that the point cloud data can be stored in a structured manner, and then the point cloud data is processed by removing motion distortion and performing preliminary adjacent frame motion estimation to obtain a semantic map, which can represent the position of each object in the target area and the relative spatial relationship. The specific implementation methods of the above-mentioned filtering, feature point extraction, motion distortion removal and preliminary adjacent frame motion estimation are similar to the prior art and will not be repeated here.

[0055] In the high-precision positioning method, the determination of the correspondence between the calibration object to be determined and each calibration object in the preset semantic map will affect the accuracy of the positioning result. Figure 3 A flowchart of another high-precision positioning method provided by an embodiment of the present disclosure is shown as follows: Figure 3 As shown, the high-precision positioning method comprises:

[0056] Step 201: Acquire calibration data of the to-be-determined calibration object in the target area at the current moment.

[0057] Step 202: performing cluster segmentation processing and model constraint processing on the calibration data in sequence to obtain the spatial contour features of the calibration object to be determined.

[0058] Step 203: Determine the degree of matching between the to-be-determined calibration object and each calibration object in a preset semantic map according to the spatial contour features of the to-be-determined calibration object.

[0059] Step 204: Determine the point cloud data of the calibration object to be determined in the semantic map according to the matching degree of each calibration object.

[0060] Step 205: Determine the position and posture state of the vehicle at the current moment according to the point cloud data of the object to be determined.

[0061] Step 206: Determine the positioning result at the current moment according to the current posture state of the vehicle.

[0062] Similar to the aforementioned embodiment, the execution subject of the high-precision positioning method provided by the embodiment of the present disclosure is the aforementioned high-precision positioning device.

[0063] The above steps 201 , 205 and 206 are similar to the above steps 101 , 103 and 104 , and are not described in detail here.

[0064] Different from the above-mentioned embodiment, in the process of determining the point cloud data of the calibration object to be determined in the semantic map, a traditional detection method based on clustering idea and a 3D target detection based on deep learning can be used. Specifically, taking the calibration object to be determined as a column as an example, the detection method can be divided into a traditional detection method based on clustering idea and a 3D target detection based on deep learning: the calibration data is sequentially subjected to cluster segmentation processing and model constraint processing to obtain the spatial contour features of the calibration object to be determined, wherein the spatial contour features can be, for example, feature information such as corner points and centroids; then, the degree of matching between the calibration object to be determined and each calibration object in the preset semantic map can be determined according to the spatial contour features, that is, the corner points and centroids are used to find the calibration object corresponding to the calibration object to be determined in each calibration object in the semantic map. Among them, the matching between the calibration object to be determined and each calibration object in the preset semantic map can be implemented based on a combinatorial optimization algorithm, that is, based on set discrimination rules, such as relative position distance, relative spatial ratio, histogram features, etc.

[0065] In addition, when matching the calibration object to be determined with each calibration object in the preset semantic map, different matching combinations can be used to obtain the matching score of the calibration object to be determined for each calibration object, and the matching score will indicate the degree of matching, wherein the combination with the highest score is considered to be the optimal matching correspondence. In other words, for the point cloud data of each calibration object in the preset semantic map, the degree of matching between the point cloud data and the spatial contour features of the calibration object to be determined is calculated; the point cloud data of the calibration object to be determined is determined, wherein the point cloud data of the calibration object with the highest matching degree in the semantic map will be used as the point cloud data of the calibration object to be determined.

[0066] Then, similar to the aforementioned embodiment, the positioning device will determine the posture state of the vehicle at the current moment according to the point cloud data of the calibration object to be determined; and determine the positioning result at the current moment according to the posture state of the vehicle at the current moment.

[0067] Compared with the above-mentioned embodiment, in this embodiment, the spatial contour features of the object to be determined are extracted through cluster segmentation and specific geometric model constraints, and the degree of matching between the spatial contour features of the object to be determined and the spatial contour features of the object to be determined is calculated, and then the point cloud data of the object with the highest matching degree in the semantic map is used as the point cloud data of the object to be determined. Such a processing method can eliminate the negative impact of misdetection on the positioning device, so that the positioning result obtained is more accurate.

[0068] In the high-precision positioning method, in order to further improve the accuracy of the positioning result obtained by the positioning device, it is also possible to determine the credibility of the posture state obtained at the current moment, and determine the positioning result based on the credibility determination result. Specifically, Figure 4 A flowchart of another high-precision positioning method provided in an embodiment of the present disclosure.

[0069] like Figure 4 As shown, the high-precision positioning method comprises:

[0070] Step 301, obtaining calibration data of the to-be-determined calibration object in the target area at the current moment;

[0071] Step 302: determining the correspondence between the calibration object to be determined and each calibration object in a preset semantic map according to the calibration data, and determining the point cloud data of the calibration object to be determined in the semantic map according to the correspondence;

[0072] Step 303: Determine the position and posture state of the vehicle at the current moment according to the point cloud data of the object to be determined.

[0073] Step 304: Calculate the first posture change value between the posture state of the vehicle at the current moment and the previous moment.

[0074] Step 305: judging the first posture change value according to a preset judgment condition to obtain a judgment result, wherein the judgment result is used to indicate the credibility of the posture state at the current moment; or, determining the number of the calibration objects to be determined, and determining the credibility of the posture at the current moment according to the number;

[0075] Step 306: If the current posture state is credible, the current posture is output as the positioning result at the current moment.

[0076] Similar to the aforementioned embodiment, the execution subject of the high-precision positioning method provided by the embodiment of the present disclosure is the aforementioned high-precision positioning device.

[0077] The above steps 301 , 302 and 303 are similar to the above steps 101 , 102 and 103 , and are not described in detail here.

[0078] Different from the above-mentioned implementation, the present disclosure will also determine the credibility of the posture state at the current moment, which can be determined in a variety of ways:

[0079] First, the first posture change value between the posture state of the vehicle at the current moment and the previous moment can be calculated, and the first posture change value can be judged according to the preset judgment conditions to obtain a judgment result, wherein the judgment result is used to indicate the credibility of the posture state at the current moment.

[0080] Specifically, assume that the posture state at time t-1 is P t-1 , the posture state at time t is P t At this time, the difference between the two can be calculated, that is, the first position change value ΔP = P t -P t-1 ; Then, the first position change value ΔP can be determined by using the preset determination condition, wherein the determination condition can be used to determine whether the first position change value ΔP is greater than a preset threshold. That is to say, since the first position change value ΔP represents the degree of deviation of the position change between two adjacent moments, and generally when the degree of deviation is greater than a certain degree, that is, the position state jumps, it can be proved that the credibility of the position state obtained at the current moment is not high. At this time, other methods can be used to determine the positioning result.

[0081] or,

[0082] Secondly, the number of the calibration objects to be determined may be determined, and the credibility of the posture at the current moment may be determined according to the number.

[0083] Specifically, when the number of calibration objects to be determined is greater, the positioning result is more accurate. That is to say, when the data collected by the laser radar system cannot be analyzed to obtain a sufficient number of calibration objects to be determined, the credibility of the posture state obtained based on the semantic map processing is relatively low. For example, taking the calibration objects to be determined as columns as an example, when the number of determined columns is less than 2, the credibility of the posture state at the current moment is not high. At this time, other methods can be used to determine the positioning result.

[0084] Furthermore, if the posture state at the current moment is not credible, the positioning result composed of the second posture change value and the posture state at the previous moment is used as the positioning result at the current moment and output; wherein, the second posture change value is obtained by processing the posture state at the previous moment using a dead reckoning algorithm. Specifically, dead reckoning can be used to obtain the posture change at the current moment relative to the previous moment. Generally, the posture change information between adjacent frames can be obtained by sensors such as IMU, wheel speedometer, and odometer. However, in this embodiment, no other sensors are used, but the posture change is estimated directly by using the point cloud registration between adjacent frames. In other words, based on the posture state P at the previous moment t-1, the second posture change value ΔP' can be calculated, and the second posture change value ΔP' is used to represent the posture change between the posture state at the current moment and the previous moment obtained by inference. Once the posture state P at the current moment is obtained, t The credibility is not high. When the second posture change value is ΔP' and the posture state P at the previous moment is required t-1 Sum, that is, the current posture state P'=P t-1 +ΔP', the positioning result can be obtained based on the current posture state P'.

[0085] This embodiment can directly use calibration data and semantic maps to determine the vehicle's posture state and obtain positioning results without using GPS positioning technology. In special environments including underground parking lots, its positioning accuracy, stability and robustness are improved compared to GPS positioning technology.

[0086] Second, Figure 5 A schematic diagram of a high-precision positioning device provided by the present invention is shown in FIG. Figure 5 As shown, the high-precision positioning device comprises:

[0087] An acquisition module 10 is used to acquire calibration data of the to-be-determined calibration object in the target area at the current moment;

[0088] The data processing module 20 is used to determine the correspondence between the calibration object to be determined and each calibration object in the preset semantic map according to the calibration data, and determine the point cloud data of the calibration object to be determined in the semantic map according to the correspondence;

[0089] The positioning module 30 is used to determine the posture state of the vehicle at the current moment according to the point cloud data of the calibration object to be determined; and is also used to determine the positioning result at the current moment according to the posture state of the vehicle at the current moment.

[0090] Optionally, the device further comprises: a map construction module;

[0091] Collect point cloud data of each calibration object in the target area; and construct a semantic map corresponding to the target area based on the point cloud data of each calibration object.

[0092] Optionally, the map construction module is used to perform filtering processing and feature point processing on the point cloud data in sequence to obtain processed point cloud data; and perform motion distortion processing and motion estimation processing on the processed point cloud data to obtain the semantic map.

[0093] Optionally, the data processing module 20 is used to perform cluster segmentation processing and model constraint processing on the calibration data in sequence to obtain spatial contour features of the object to be determined; and determine the degree of matching between the object to be determined and each calibration object in a preset semantic map according to the spatial contour features of the object to be determined.

[0094] Optionally, the data processing module 20 is specifically used to calculate the degree of matching between the point cloud data of each calibrated object in the preset semantic map and the spatial contour features of the calibrated object to be determined; determine the point cloud data of the calibrated object to be determined, wherein the point cloud data of the calibrated object with the highest matching degree in the semantic map will be used as the point cloud data of the calibrated object to be determined.

[0095] Optionally, the positioning module 30 is specifically used to calculate the first posture change value between the posture state of the vehicle at the current moment and the previous moment; judge the first posture change value according to a preset judgment condition to obtain a judgment result, wherein the judgment result is used to indicate the credibility of the posture state at the current moment; if the posture state at the current moment is credible, the posture at the current moment is output as the positioning result at the current moment.

[0096] Optionally, the positioning module 30 is specifically used to determine the number of the calibration objects to be determined, and determine the credibility of the posture at the current moment according to the number; if the posture state at the current moment is credible, the posture at the current moment is output as the positioning result at the current moment.

[0097] Optionally, the positioning module 30 is specifically used to use the positioning result composed of the second posture change value and the posture state at the previous moment as the positioning result at the current moment, and output it if the posture state at the current moment is unreliable; wherein the second posture change value is obtained by processing the posture state at the previous moment using a dead reckoning algorithm.

[0098] The high-precision positioning device provided by the present disclosure obtains the calibration data of the calibration object to be determined in the target area at the current moment; determines the correspondence between the calibration object to be determined and each calibration object in a preset semantic map according to the calibration data, and determines the point cloud data of the calibration object to be determined in the semantic map according to the correspondence; determines the posture state of the vehicle at the current moment according to the point cloud data of the calibration object to be determined; determines the positioning result at the current moment according to the posture state of the vehicle at the current moment, so that the calibration data and the semantic map can be directly used to determine the posture state of the vehicle without using the GPS positioning technology, and then obtain the positioning result. In special environments including underground parking lots, compared with the GPS positioning technology, the positioning accuracy, stability and robustness are all improved.

[0099] Next, Figure 6 This is a structural schematic diagram of a high-precision positioning system provided by the present disclosure. This embodiment also provides a high-precision positioning system, which includes: a high-precision positioning device, and a laser radar system carried on a vehicle, and the vehicle is located in a target area; wherein the laser radar system is used to collect calibration data of a to-be-determined calibration object in the target area at the current moment, and send the calibration data to the high-precision positioning device, so that the high-precision positioning device can perform positioning of the vehicle using the method described above.

[0100] On the next aspect, this embodiment also provides an electronic device that 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.

[0101] refer to Figure 7 , which shows a schematic diagram of the structure of an electronic device 900 suitable for implementing the embodiment of the present disclosure, and the electronic device 900 may be a terminal device or a server. The terminal device may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (Portable Android Devices, PADs), portable multimedia players (PMPs), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0102] like Figure 7 As shown, the electronic device 900 may include a positioning device (e.g., a central processing unit, a graphics processing unit, etc.) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage device 908 to a random access memory (RAM) 903. Various programs and data required for the operation of the electronic device 900 are also stored in the RAM 903. The positioning device 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0103] Typically, the following devices may be connected to the I / O interface 905: input devices 906 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 907 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 908 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 909. The communication device 909 may allow the electronic device 900 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7 The electronic device 900 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0104] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 909, or installed from the storage device 908, or installed from the ROM 902. When the computer program is executed by the positioning device 901, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0105] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0106] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0107] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0108] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0109] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0110] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a unit does not limit the unit itself in some cases. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses".

[0111] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0112] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0113] The following are some embodiments of the present disclosure.

[0114] In a first aspect, according to one or more embodiments of the present disclosure, a high-precision positioning method includes:

[0115] Obtaining calibration data of the to-be-determined calibration object in the target area at the current moment;

[0116] Determine, according to the calibration data, a correspondence between the calibration object to be determined and each calibration object in a preset semantic map, and determine, according to the correspondence, point cloud data of the calibration object to be determined in the semantic map;

[0117] Determine the position and posture state of the vehicle at the current moment according to the point cloud data of the calibration object to be determined;

[0118] The positioning result at the current moment is determined according to the vehicle's current posture state.

[0119] In an optional embodiment provided by the present disclosure, the method further includes:

[0120] Collect point cloud data of each calibration object in the target area;

[0121] A semantic map corresponding to the target area is constructed based on the point cloud data of each calibration object.

[0122] In an optional embodiment provided by the present disclosure, constructing a semantic map corresponding to the target area according to the point cloud data of each calibration object includes:

[0123] Performing filtering processing and feature point processing on the point cloud data in sequence to obtain processed point cloud data;

[0124] The processed point cloud data is subjected to motion distortion processing and motion estimation processing to obtain the semantic map.

[0125] In an optional embodiment provided by the present disclosure, determining the correspondence between the calibration object to be determined and each calibration object in a preset semantic map according to the calibration data includes:

[0126] Performing cluster segmentation processing and model constraint processing on the calibration data in sequence to obtain the spatial contour features of the calibration object to be determined;

[0127] According to the spatial contour feature of the calibration object to be determined, the matching degree between the calibration object to be determined and each calibration object in the preset semantic map is determined.

[0128] In an optional embodiment provided by the present disclosure, determining the matching degree between the to-be-determined calibration object and each calibration object in a preset semantic map according to the spatial contour feature of the to-be-determined calibration object includes:

[0129] For each point cloud data of the calibration object in the preset semantic map, calculating the matching degree between the point cloud data and the spatial contour features of the calibration object to be determined;

[0130] The point cloud data of the calibration object to be determined is determined, wherein the point cloud data of the calibration object with the highest matching degree in the semantic map is used as the point cloud data of the calibration object to be determined.

[0131] In an optional embodiment provided by the present disclosure, determining the positioning result at the current moment according to the posture state of the vehicle at the current moment includes:

[0132] Calculating a first posture change value between the posture state of the vehicle at a current moment and a previous moment;

[0133] Determine the first posture change value according to a preset determination condition to obtain a determination result, wherein the determination result is used to indicate the credibility of the posture state at the current moment;

[0134] If the posture state at the current moment is credible, the posture at the current moment is output as the positioning result at the current moment.

[0135] In an optional embodiment provided by the present disclosure, determining the positioning result at the current moment according to the posture state of the vehicle at the current moment includes:

[0136] Determining the number of the calibration objects to be determined, and determining the credibility of the posture at the current moment according to the number;

[0137] If the posture state at the current moment is credible, the posture at the current moment is output as the positioning result at the current moment.

[0138] In an optional embodiment provided by the present disclosure, if the posture state at the current moment is not credible, a positioning result composed of the second posture change value and the posture state at the previous moment is used as the positioning result at the current moment and is output;

[0139] The second posture change value is obtained by processing the posture state at the previous moment using a dead reckoning algorithm.

[0140] In a second aspect, according to one or more embodiments of the present disclosure, a high-precision positioning device includes:

[0141] An acquisition module is used to acquire the calibration data of the calibration object to be determined in the target area at the current moment;

[0142] A data processing module, used to determine the correspondence between the calibration object to be determined and each calibration object in a preset semantic map according to the calibration data, and determine the point cloud data of the calibration object to be determined in the semantic map according to the correspondence;

[0143] The positioning module is used to determine the position and posture state of the vehicle at the current moment according to the point cloud data of the calibration object to be determined; and is also used to determine the positioning result at the current moment according to the position and posture state of the vehicle at the current moment.

[0144] In an optional embodiment provided by the present disclosure, it further includes: a map construction module;

[0145] Collect point cloud data of each calibration object in the target area; and construct a semantic map corresponding to the target area based on the point cloud data of each calibration object.

[0146] In an optional embodiment provided in the present disclosure, the map construction module is used to perform filtering processing and feature point processing on the point cloud data in sequence to obtain processed point cloud data; and perform motion distortion processing and motion estimation processing on the processed point cloud data to obtain the semantic map.

[0147] In an optional embodiment provided by the present disclosure, a data processing module is used to perform cluster segmentation processing and model constraint processing on the calibration data in sequence to obtain spatial contour features of the object to be determined; and determine the degree of matching between the object to be determined and each calibration object in a preset semantic map based on the spatial contour features of the object to be determined.

[0148] In an optional embodiment provided by the present disclosure, the data processing module is specifically used to calculate the degree of matching between the point cloud data of each calibrated object in the preset semantic map and the spatial contour features of the calibrated object to be determined; determine the point cloud data of the calibrated object to be determined, wherein the point cloud data of the calibrated object with the highest matching degree in the semantic map will be used as the point cloud data of the calibrated object to be determined.

[0149] In an optional embodiment provided by the present disclosure, a positioning module is specifically used to calculate a first posture change value between the posture state of the vehicle at a current moment and a previous moment; the first posture change value is judged according to a preset judgment condition to obtain a judgment result, wherein the judgment result is used to indicate the credibility of the posture state at the current moment; if the posture state at the current moment is credible, the posture at the current moment is output as the positioning result at the current moment.

[0150] In an optional embodiment provided by the present disclosure, the positioning module is specifically used to determine the number of the calibration objects to be determined, and determine the credibility of the posture at the current moment based on the number; if the posture state at the current moment is credible, the posture at the current moment is output as the positioning result at the current moment.

[0151] In an optional embodiment provided by the present disclosure, the positioning module is specifically used to use the positioning result composed of the second posture change value and the posture state at the previous moment as the positioning result at the current moment, and output it if the posture state at the current moment is unreliable; wherein the second posture change value is obtained by processing the posture state at the previous moment using a dead reckoning algorithm.

[0152] In a third aspect, according to one or more embodiments of the present disclosure, a high-precision positioning system includes: a high-precision positioning device, and a laser radar system carried on a vehicle, wherein the vehicle is located in a target area;

[0153] Wherein, the laser radar system is used to collect calibration data of the object to be determined in the target area at the current moment, and send the calibration data to the high-precision positioning device, so that the high-precision positioning device can perform vehicle positioning using the method described in any one of claims 1-8.

[0154] In a fourth aspect, according to one or more embodiments of the present disclosure, an electronic device includes: at least one processor and a memory;

[0155] The memory stores computer-executable instructions;

[0156] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the method as described above.

[0157] In a fifth aspect, according to one or more embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer-executable instructions, and when a processor executes the computer-executable instructions, the method described above is implemented.

[0158] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0159] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0160] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

[0161] The purpose, technical scheme and advantages of the examples are clearer. The technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

Claims

1. A high-precision positioning method, characterized in that: include: Acquire calibration data of the to-be-determined calibration object in the target area at the current moment through the laser radar system; According to the calibration data, determining the correspondence between the calibration object to be determined and each calibration object in the preset semantic map, and determining the target calibration object corresponding to the calibration object to be determined according to the correspondence, and using the point cloud data of the target calibration object as the point cloud data of the calibration object to be determined; Determine the position and posture state of the vehicle at the current moment according to the point cloud data of the calibration object to be determined; Determine the positioning result at the current moment according to the current posture state of the vehicle; Determining the positioning result at the current moment according to the current posture state of the vehicle includes: Calculate the first posture change value between the posture state of the vehicle at the current moment and the previous moment; determine the first posture change value according to a preset determination condition to obtain a determination result, wherein the determination result is used to indicate the credibility of the posture state at the current moment; if the posture state at the current moment is credible, output the posture at the current moment as the positioning result at the current moment; or, The number of the calibration objects to be determined is determined, and the credibility of the posture at the current moment is determined according to the number; if the posture state at the current moment is credible, the posture at the current moment is output as the positioning result at the current moment.

2. The positioning method according to claim 1, characterized in that: If the posture state at the current moment is unreliable, the positioning result composed of the second posture change value and the posture state at the previous moment is used as the positioning result at the current moment and outputted; The second posture change value is obtained by processing the posture state at the previous moment using a dead reckoning algorithm.

3. The positioning method according to claim 1, characterized in that: Also includes: Collect point cloud data of each calibration object in the target area; A semantic map corresponding to the target area is constructed based on the point cloud data of each calibration object.

4. The positioning method according to claim 3, characterized in that: The step of constructing a semantic map corresponding to the target area according to the point cloud data of each calibration object includes: Performing filtering processing and feature point processing on the point cloud data in sequence to obtain processed point cloud data; The processed point cloud data is subjected to motion distortion processing and motion estimation processing to obtain the semantic map.

5. The positioning method according to claim 1, characterized in that: Determining the correspondence between the calibration object to be determined and each calibration object in the preset semantic map according to the calibration data includes: Performing cluster segmentation processing and model constraint processing on the calibration data in sequence to obtain the spatial contour features of the calibration object to be determined; According to the spatial contour feature of the calibration object to be determined, the matching degree between the calibration object to be determined and each calibration object in the preset semantic map is determined.

6. The positioning method according to claim 5, characterized in that: Determining the matching degree between the to-be-determined calibration object and each calibration object in a preset semantic map according to the spatial contour feature of the to-be-determined calibration object includes: For each point cloud data of the calibration object in the preset semantic map, calculating the matching degree between the point cloud data and the spatial contour features of the calibration object to be determined; The point cloud data of the calibration object to be determined is determined, wherein the point cloud data of the calibration object with the highest matching degree in the semantic map is used as the point cloud data of the calibration object to be determined.

7. A high-precision positioning device, characterized in that: include: An acquisition module, used to acquire calibration data of the to-be-determined calibration object in the target area at the current moment through the laser radar system; A data processing module, used to determine the correspondence between the calibration object to be determined and each calibration object in the preset semantic map according to the calibration data, and determine the target calibration object corresponding to the calibration object to be determined according to the correspondence, and use the point cloud data of the target calibration object as the point cloud data of the calibration object to be determined; A positioning module, used to determine the posture state of the vehicle at the current moment according to the point cloud data of the calibration object to be determined; and also used to determine the positioning result at the current moment according to the posture state of the vehicle at the current moment; The positioning module is specifically used for: Calculate the first posture change value between the posture state of the vehicle at the current moment and the previous moment; determine the first posture change value according to a preset determination condition to obtain a determination result, wherein the determination result is used to indicate the credibility of the posture state at the current moment; if the posture state at the current moment is credible, output the posture at the current moment as the positioning result at the current moment; or, The number of the calibration objects to be determined is determined, and the credibility of the posture at the current moment is determined according to the number; if the posture state at the current moment is credible, the posture at the current moment is output as the positioning result at the current moment.

8. A high-precision positioning system, characterized in that: include: A high-precision positioning device and a laser radar system carried by a vehicle, wherein the vehicle is located in a target area; Wherein, the laser radar system is used to collect calibration data of the to-be-determined calibration object in the target area at the current moment, and send the calibration data to the high-precision positioning device, so that the high-precision positioning device can perform vehicle positioning using the method described in any one of claims 1-6.

9. An electronic device, characterized in that: include: at least one processor and memory; The memory stores computer-executable instructions; The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the method according to any one of claims 1 to 6.

10. 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 method according to any one of claims 1 to 6 is implemented.

Images