A positioning method, device and electronic device

Abstract

The present application discloses a positioning method, apparatus and electronic device, mainly relating to the technical field of automobiles. Among them, the positioning method includes: obtaining current radar data collected by a ground penetrating radar, and calculating first similarity values between the current radar data and each pre-stored radar data in a database, wherein the pre-stored radar data corresponds to vehicle pose information. Further, determining a target radar data corresponding to the maximum similarity value among the first similarity values in each pre-stored radar data, and taking the vehicle pose corresponding to the target radar data as the vehicle pose corresponding to the current radar data. This method of positioning a vehicle based on radar data collected by a ground penetrating radar can achieve high-precision vehicle positioning in driving environments such as snowing, dusty, and long tunnels.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and particularly to a positioning method, device, and electronic device. Background Art

[0002] With the rapid development of autonomous driving technology, achieving high-precision and high-robustness positioning of vehicles has become one of the core technologies in the field of autonomous driving. Among them, positioning refers to estimating the pose of a vehicle. Currently, the commonly used positioning method is multi-source fusion positioning using sensors such as lidar, cameras, Global Navigation Satellite System (GNSS), Inertial Measurement Unit (IMU), and wheel speed sensors. This method of multi-sensor fusion positioning is not applicable to certain specific scenarios. For example, in driving environments such as snowing, dusty, and long tunnels, it is difficult for these sensors to detect the surrounding environmental features, thereby affecting the positioning accuracy of the vehicle. Summary of the Invention

[0003] This application discloses a positioning method, device, and electronic device. According to the radar data collected by a ground-penetrating radar, the vehicle is positioned, thereby ensuring the positioning accuracy of the vehicle in driving environments such as snowing, dusty, and long tunnels.

[0004] In a first aspect, this application provides a vehicle positioning method, and the method includes:

[0005] Obtain current radar data collected by a ground-penetrating radar, where the radar data represents the reflection intensity of radar signals;

[0006] Calculate first similarity values between the current radar data and each pre-stored radar data in a database, where the pre-stored radar data corresponds to vehicle pose information;

[0007] Determine a target radar data corresponding to the maximum similarity value among the first similarity values in each of the pre-stored radar data;

[0008] Use the vehicle pose corresponding to the target radar data as the vehicle pose corresponding to the current radar data.

[0009] By the above method, the vehicle is positioned based on the radar data collected by the ground-penetrating radar, and underground objects such as soil, stones, pipes, and tree roots can be identified, thereby ensuring the positioning accuracy of the vehicle in driving environments such as snowing, dusty, and long tunnels.

[0010] In a possible design, calculating the first similarity values between the current radar data and each pre-stored radar data in the database includes:

[0011] Calculating the inner product values between the column vectors corresponding to any column in the current radar data and the column vectors corresponding to the same column in each pre-stored radar data, where the column vectors represent the radar signal reflection intensity in the radar scanning direction;

[0012] According to the inner product values corresponding to the pre-set radar data respectively, calculating the first similarity values between the current radar data and each pre-stored radar data.

[0013] Through the above method, based on the column vectors in the radar data, the similarity values between the current radar data and each pre-stored radar data are quantified, fully considering the signal reflection intensity in the radar scanning direction, and improving the accuracy of similarity calculation.

[0014] Further, the calculating the first similarity values between the current radar data and each pre-stored radar data according to the inner product values corresponding to the pre-set radar data respectively includes:

[0015] According to the inner product values corresponding to the pre-set radar data respectively, calculating the column vector similarity values between the current radar data and each pre-stored radar data;

[0016] According to the column vector similarity values corresponding to the pre-set radar data respectively, calculating the first similarity values between the current radar data and each pre-stored radar data.

[0017] In a possible design, after using the vehicle pose corresponding to the target radar data as the vehicle pose corresponding to the current radar data, it further includes:

[0018] Calculating the column vector similarity values between any column vector of the current radar data and any column vector of a frame of historical radar data collected by the ground penetrating radar;

[0019] Determining the target column vector similarity values greater than a preset threshold among the column vector similarity values;

[0020] Determining the first column vectors corresponding to the target column vector similarity values in the current radar data and the second column vectors corresponding to the target column vector similarity values in the historical radar data;

[0021] Updating the vehicle pose according to the overall offset between the first column vectors and the second column vectors.

[0022] By the above method, the current vehicle pose is further updated to achieve further positioning of the vehicle and improve the accuracy of vehicle positioning.

[0023] In a possible design, updating the vehicle pose according to the overall offset between each first column vector and each second column vector includes:

[0024] Calculating the overall offset between each first column vector and each second column vector;

[0025] Calculating the total mileage corresponding to the overall offset according to the overall offset and the mileage corresponding to each unit offset;

[0026] Taking the total mileage as the vehicle movement mileage between the current radar data and the historical radar data;

[0027] Updating the vehicle pose according to the vehicle movement mileage.

[0028] By the above method, according to the overall offset of column vectors between two frames of radar data, the vehicle pose is further updated to achieve further positioning of the current vehicle.

[0029] In a second aspect, the present application provides a positioning device, and the device includes:

[0030] An acquisition module, configured to acquire current radar data collected by a ground penetrating radar, where the radar data represents the radar signal reflection intensity;

[0031] A first calculation module, configured to calculate a first similarity value between the current radar data and each pre-stored radar data in a database, where the pre-stored radar data corresponds to vehicle pose information;

[0032] A first determination module, configured to determine a target radar data corresponding to the maximum similarity value among the first similarity values in each pre-stored radar data;

[0033] A positioning module, configured to use the vehicle pose corresponding to the target radar data as the vehicle pose corresponding to the current radar data.

[0034] In a possible design, the first calculation module is specifically configured to:

[0035] Calculating an inner product value between a column vector corresponding to any column in the current radar data and a column vector corresponding to the same column in each pre-stored radar data, where the column vector represents the radar signal reflection intensity in the radar scanning direction;

[0036] Calculate the first similarity value between the current radar data and each pre - stored radar data respectively according to the inner product values corresponding to the preset radar data.

[0037] In a possible design, the first calculation module is further configured to:

[0038] Calculate the column - vector similarity value between the current radar data and each pre - stored radar data respectively according to the inner product values corresponding to the preset radar data;

[0039] Calculate the first similarity value between the current radar data and each pre - stored radar data respectively according to the column - vector similarity values corresponding to the preset radar data.

[0040] In a possible design, the device further includes:

[0041] A second calculation module, configured to calculate the column - vector similarity values between any column vector of the current radar data and any column vector of a frame of historical radar data collected by the ground - penetrating radar;

[0042] A second determination module, configured to determine the target column - vector similarity values greater than a preset threshold among the column - vector similarity values; determine the first column vectors corresponding to the target column - vector similarity values in the current radar data and the second column vectors corresponding to the target column - vector similarity values in the historical radar data;

[0043] An update module, configured to update the vehicle pose according to the overall offset between the first column vectors and the second column vectors.

[0044] In a possible design, the update module is specifically configured to:

[0045] Calculate the overall offset between the first column vectors and the second column vectors;

[0046] Calculate the total mileage corresponding to the overall offset according to the overall offset and the mileage corresponding to each unit offset;

[0047] Use the total mileage as the vehicle movement mileage between the current radar data and the historical radar data;

[0048] Update the vehicle pose according to the vehicle movement mileage.

[0049] In a third aspect, the present application provides an electronic device, including:

[0050] A memory, configured to store a computer program;

[0051] A processor, when executing the computer program stored on the memory, implements the steps of the above-mentioned positioning method.

[0052] In a fourth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned positioning method are implemented.

[0053] Based on the positioning method, the vehicle can be positioned according to the radar data collected by the ground penetrating radar, and underground objects such as soil, stones, pipes, tree roots, etc. can be identified, so as to ensure the accuracy of vehicle positioning in driving environments such as snow, more dust, and long tunnels.

[0054] For the various aspects in the above-mentioned second aspect to fourth aspect and the possible technical effects that each aspect may achieve, reference may be made to the technical effects that can be achieved by the above-mentioned first aspect or various possible solutions in the first aspect, and details will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flowchart of a positioning method provided by the present application;

[0056] Figure 2 It is a schematic diagram of a ground penetrating radar applied to a vehicle provided by the present application;

[0057] Figure 3 It is a schematic structural diagram of a positioning device provided by the present application;

[0058] Figure 4 It is a schematic structural diagram of an electronic device provided by the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. The specific operation methods in the method embodiments can also be applied to the device embodiments or system embodiments. It should be noted that in the description of the present application, "a plurality" is understood as "at least two". "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. The connection between A and B may represent: A is directly connected to B and A is connected to B through C. In addition, in the description of the present application, terms such as "first" and "second" are only used for the purpose of distinguishing descriptions, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying order.

[0060] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0061] The currently commonly used positioning method is to perform multi-source fusion positioning using sensors such as lidar, cameras, GNSS, IMUs, and wheel speed sensors. In some specific scenarios, this method of fusing multiple sensors for positioning affects the vehicle body positioning accuracy because it is difficult for these sensors to detect the surrounding environmental features. For example:

[0062] In extreme weather with heavy snowfall, the road surface or objects around the vehicle are covered with snow, increasing the difference between the points scanned by the lidar and the previously constructed point cloud map. At this time, the positioning accuracy based on the point cloud map is low. At the same time, since road markings such as lane lines, arrows, and zebra crossings are covered with snow, it is difficult to collect road markings, further reducing the vehicle body positioning accuracy.

[0063] In extreme environments with a lot of dust, the lidar will be interfered by dust during the scanning process, and it will also affect the clarity of image acquisition by cameras, etc., thereby affecting the vehicle positioning accuracy.

[0064] In the driving environment of a long tunnel, due to the very similar features and textures of the infrastructure on both sides of the road, both the lidar and the image acquisition device cannot detect enough features, thereby affecting the vehicle positioning accuracy.

[0065] To solve the above problems, the present application provides a positioning method for positioning the vehicle according to the radar data collected by the ground penetrating radar, which can identify underground objects such as soil, stones, pipes, and tree roots, thereby ensuring the vehicle positioning accuracy in driving environments such as snow, a lot of dust, and long tunnels. Among them, the methods and devices in the embodiments of the present application are based on the same technical concept. Since the principles of the problems solved by the methods and devices are similar, the embodiments of the device and the method can be referred to each other, and the repeated parts will not be described again.

[0066] As Figure 1 shown, it is a flowchart of a positioning method provided by the present application, which specifically includes the following steps:

[0067] S11, obtain the current radar data collected by the ground penetrating radar;

[0068] S12, calculate the first similarity values between the current radar data and each pre-stored radar data in the database;

[0069] S13, determine the target radar data corresponding to the maximum similarity value among the first similarity values in each pre-stored radar data;

[0070] S14, use the vehicle pose corresponding to the target radar data as the vehicle pose corresponding to the current radar data.

[0071] In the embodiments of the present application, the ground penetrating radar is a sensor, such asFigure 2 As shown in the figure, it is a schematic diagram of a ground penetrating radar provided by the present application applied to a vehicle. Among them, the ground penetrating radar is installed at the bottom of the vehicle and can emit electromagnetic waves to the ground. Figure 2 The direction indicated by the arrow in the figure is the scanning direction of the ground penetrating radar. Since different object materials have different reflectivities to electromagnetic waves, underground objects such as soil, stones, pipes, and tree roots can be detected by collecting the reflected radar data. Among them, the radar data is a grid matrix of M rows and N columns, and each grid value represents the reflection intensity of the radar signal. Both M and N are integers greater than or equal to 1.

[0072] Since each pre-stored radar data in the database corresponds to a vehicle pose information, after obtaining the current radar data, if the most similar frame of target radar data is determined from each pre-stored radar data, the vehicle pose corresponding to the current radar data can be determined.

[0073] In order to determine the target radar data, first, the first similarity values between the current radar data and each pre-stored radar data in the database need to be calculated. The specific calculation formula can be:

[0074]

[0075] In formula (1), s(I i ,I j ) represents the similarity value between two frames of radar data; I i and I j respectively represent the i-th frame of radar data and the j-th frame of radar data, which are the two frames of radar data for which the similarity is to be calculated. represents the inner product value between the k-th column vector in the i-th frame of radar data and the k-th column vector in the j-th frame of radar data. respectively represent the two-norm of the k-th column vector in the i-th frame of radar data and the two-norm of the k-th column vector in the j-th frame of radar data.

[0076] Based on the above formula, the calculation process of obtaining the first similarity values between the current radar data and each pre-stored radar data in the database includes:

[0077] Calculate the inner product value between the column vector corresponding to any column in the current radar data and the column vector corresponding to the same column in each pre-stored radar data, where the column vector represents the reflection intensity of the radar signal in the radar scanning direction.

[0078] For example, there are two pre-stored radar data in the database, namely the first pre-stored radar data and the second pre-stored radar data. The current radar data and the two pre-stored radar data each contain three column vectors. When calculating the inner product values between any column vector in the current radar data and the corresponding column vectors in each pre-stored radar data, it is necessary to calculate the inner product value between the first column vector in the current radar data and the first column vector in the first pre-stored radar data, the inner product value between the second column vector in the current radar data and the second column vector in the first pre-stored radar data, and the inner product value between the third column vector in the current radar data and the third column vector in the first pre-stored radar data respectively. In addition, the same processing is performed between the current radar data and the second pre-stored radar data to obtain three inner product values. Combining the three inner product values corresponding to the first pre-stored radar data, a total of 3 + 3 = 6 inner product values are obtained.

[0079] Furthermore, according to the inner product values corresponding to the preset radar data respectively, the first similarity values between the current radar data and each pre-stored radar data are calculated. Specifically, first, according to the inner product values corresponding to the preset radar data respectively, the column vector similarity values between the current radar data and each pre-stored radar data are calculated, and then, according to the column vector similarity values corresponding to the preset radar data respectively, the first similarity values between the current radar data and each pre-stored radar data are calculated.

[0080] For example, there are two pre-stored radar data in the database, namely the first pre-stored radar data and the second pre-stored radar data. The current radar data and the two pre-stored radar data each contain three column vectors. At this time, through the above method of calculating the inner product values of column vectors, it can be known that each pre-stored radar data corresponds to three inner product values. When further calculating the first similarity values between the current radar data and each pre-stored radar data, the three inner product values corresponding to each pre-stored radar data are further calculated to obtain the column vector similarity values between each pre-stored radar data and the current radar data. Thus, it can be seen that each pre-stored radar data also corresponds to three column vector similarity values. At this time, the average value of the three column vector similarity values corresponding to the first pre-stored radar data is obtained, and the first similarity value between the current radar data and the first pre-stored radar data can be obtained. Similarly, the average value of the three column vector similarity values corresponding to the second pre-stored radar data is obtained, and the first similarity value between the current radar data and the second pre-stored radar data can be obtained.

[0081] Furthermore, after obtaining each first similarity value, the target radar data corresponding to the maximum similarity value among each first similarity value in each pre-stored radar data is determined.

[0082] For example, there are 2 pre-stored radar data in the database, namely the first pre-stored radar data and the second pre-stored radar data. The current radar data and the 2 pre-stored radar data each contain 3 column vectors. From the method of calculating the first similarity value mentioned above, it can be known that there are 2 similarity values between the current radar data and the 2 pre-stored radar data. If the first similarity value between the current radar data and the first pre-stored radar data is 0.8, and the first similarity value between the current radar data and the second pre-stored radar data is 0.9, then at this time, the second pre-stored radar data is used as the target radar data.

[0083] After determining the target radar data corresponding to the current radar data in the database, the vehicle pose bound to the target radar data is used as the vehicle pose corresponding to the current radar data.

[0084] Through the above method, the vehicle can be positioned based on the radar data collected by the ground penetrating radar, and underground objects such as soil, stones, pipes, and tree roots can be identified, thereby realizing the accuracy of vehicle positioning in driving environments such as snow, more dust, and long tunnels.

[0085] In order to improve the accuracy of vehicle positioning, after determining the vehicle pose corresponding to the current radar data according to the first similarity value, the column vector similarity values between any column vector of the current radar data and any column vector of a frame of historical radar data collected by the ground penetrating radar are further calculated, and the target column vector similarity values greater than the preset threshold are determined among the column vector similarity values.

[0086] Furthermore, the first column vectors corresponding to the respective target column vector similarity values in the current radar data and the second column vectors corresponding to the respective target column vector similarity values in the historical radar data are determined, and the overall offset between the first column vectors and the second column vectors is calculated. The specific algorithm can be: the first column vectors are calculated to obtain equivalent first column vectors according to different weight values, and the second column vectors are calculated to obtain equivalent second column vectors according to different weight values, then the offset between the equivalent first column vector and the equivalent second column vector is calculated, and this offset is used as the overall offset between the first column vectors and the second column vectors, where the setting of the weight value is related to the similarity value between the column vectors.

[0087] For example, each of the first column vectors is the 4th, 5th, and 6th columns in the current radar data, and each of the second column vectors is the 5th, 6th, and 7th columns in the historical radar data. Among them, the first column vector 4 corresponds to the second column vector 5, and the similarity value between them is 0.8; the first column vector 5 corresponds to the second column vector 6, and the similarity value between them is 0.9; the first column vector 6 corresponds to the second column vector 7, and the similarity value between them is 0.8. Then, the equivalent first column vector can be calculated as: (4×0.8 + 5×0.9 + 6×0.8)÷(0.8 + 0.9 + 0.8) = 5, and the similarity of the equivalent second column vector is: (5×0.8 + 6×0.9 + 7×0.8)÷(0.8 + 0.9 + 0.8) = 6. Then, the overall offset is 6 - 5 = 1.

[0088] Further, according to the overall offset, the vehicle pose is updated. The specific method includes:

[0089] According to the overall offset and the mileage corresponding to each unit offset, calculate the total mileage corresponding to the overall offset. Then, use the total mileage as the vehicle movement mileage between the current radar data and the historical radar data. Finally, update the vehicle pose according to the vehicle movement mileage and the pose information corresponding to the historical radar data.

[0090] For example, if the current overall offset is 1 and the mileage corresponding to each unit offset is 20 meters, then the total mileage can be calculated as 1×20 = 20 meters. That is to say, the relative displacement between the current radar data and the historical radar data is 20 meters. At this time, only by determining the pose information of the historical radar data can the vehicle pose be further updated.

[0091] By updating the vehicle pose through the above method, it is possible to further perform more accurate positioning of the vehicle after initially determining the vehicle pose.

[0092] Based on the same inventive concept, an embodiment of the present application also provides a positioning device, as Figure 3 shown, which is a schematic structural diagram of a positioning device in the present application. The device includes:

[0093] An acquisition module 31, configured to acquire the current radar data collected by the ground penetrating radar, where the radar data represents the radar signal reflection intensity;

[0094] A first calculation module 32, configured to calculate the first similarity value between the current radar data and each pre-stored radar data in the database, where the pre-stored radar data corresponds to vehicle pose information;

[0095] A first determination module 33, configured to determine the target radar data corresponding to the maximum similarity value among the first similarity values in each pre-stored radar data;

[0096] A positioning module 34, configured to use the vehicle pose corresponding to the target radar data as the vehicle pose corresponding to the current radar data.

[0097] In a possible design, the first calculation module 32 is specifically configured to:

[0098] Calculate the inner product value between the column vector corresponding to any column in the current radar data and the column vectors corresponding to the same column in each pre-stored radar data, where the column vector represents the radar signal reflection intensity in the radar scanning direction;

[0099] According to the inner product values corresponding to the pre-set radar data respectively, calculate the first similarity values between the current radar data and each pre-stored radar data.

[0100] In a possible design, the first calculation module 32 is further configured to:

[0101] According to the inner product values corresponding to the pre-set radar data respectively, calculate the column vector similarity values between the current radar data and each pre-stored radar data;

[0102] According to the column vector similarity values corresponding to the pre-set radar data respectively, calculate the first similarity values between the current radar data and each pre-stored radar data.

[0103] In a possible design, the device further includes:

[0104] A second calculation module, configured to calculate the column vector similarity values between any column vector of the current radar data and any column vector of a frame of historical radar data collected by the ground penetrating radar;

[0105] A second determination module, configured to determine, from the column vector similarity values, the target column vector similarity values greater than a preset threshold; determine the first column vectors corresponding to the target column vector similarity values in the current radar data and the second column vectors corresponding to the target column vector similarity values in the historical radar data;

[0106] An update module, configured to update the vehicle pose according to the overall offset between the first column vectors and the second column vectors.

[0107] In a possible design, the update module is specifically configured to:

[0108] Calculate the overall offset between the first column vectors and the second column vectors;

[0109] Calculate the total mileage corresponding to the overall offset according to the overall offset and the mileage corresponding to each unit offset;

[0110] Taking the total mileage as the number of vehicle movement journeys between the current radar data and the historical radar data;

[0111] The vehicle posture is updated according to the vehicle movement mileage.

[0112] Through the above positioning device, the vehicle is positioned based on the radar data collected by the ground penetrating radar, and underground objects such as soil, stones, pipes, tree roots, etc. can be identified, thereby ensuring the accuracy of vehicle positioning in driving environments such as snow, dust, and long tunnels. At the same time, the vehicle's position and posture can also be updated, so that after the vehicle's position and posture are initially determined, the vehicle can be further positioned more accurately.

[0113] Based on the same inventive concept, an electronic device is also provided in the embodiment of the present application, and the electronic device can implement the functions of the aforementioned positioning method and device, referring to Figure 4 , the electronic device comprises:

[0114] At least one processor 41, and a memory 42 connected to the at least one processor 41. The specific connection medium between the processor 41 and the memory 42 is not limited in the embodiment of the present application. Figure 4 In the example, the processor 41 and the memory 42 are connected via the bus 40. The bus 40 is Figure 4 The connection between other components is shown by bold lines, and is not intended to be limiting. The bus 40 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. Alternatively, the processor 41 can also be called a controller, and there is no limitation on the name.

[0115] In the embodiment of the present application, the memory 42 stores instructions that can be executed by at least one processor 41. The at least one processor 41 can execute the positioning method discussed above by executing the instructions stored in the memory 42. The processor 41 can implement Figure 3 The functions of each module in the device shown.

[0116] Among them, the processor 41 is the control center of the device, and can use various interfaces and lines to connect the various parts of the entire control device. By running or executing instructions stored in the memory 42 and calling data stored in the memory 42, the various functions of the device and processing data, the device can be monitored as a whole.

[0117] In a possible design, the processor 41 may include one or more processing units. The processor 41 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface, application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor may not be integrated into the processor 41 either. In some embodiments, the processor 41 and the memory 42 may be implemented on the same chip, and in some embodiments, they may also be separately implemented on independent chips.

[0118] The processor 41 may be a general-purpose processor, such as a central processing unit (CPU), a digital signal processor, an application-specific integrated circuit, a field programmable gate array, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the positioning method disclosed in combination with the embodiments of the present application may be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0119] As a non-volatile computer-readable storage medium, the memory 42 can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The memory 42 may include at least one type of storage medium, for example, it may include flash memory, a hard disk, a multimedia card, a card-type memory, a random access memory (RAM), a static random access memory (SRAM), a programmable read-only memory (PROM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 42 is any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 42 in the embodiments of the present application may also be a circuit or any other device capable of implementing a storage function, for storing program instructions and / or data.

[0120] By programming the design of the processor 41, the code corresponding to the positioning method introduced in the foregoing embodiments can be solidified into the chip, so that the chip can execute when running Figure 1Steps of the positioning method of the illustrated embodiment. How to design and program the processor 41 is a well-known technology to those skilled in the art and will not be elaborated here.

[0121] Based on the same inventive concept, an embodiment of the present application also provides a storage medium storing computer instructions, which when run on a computer, cause the computer to execute the positioning method discussed above.

[0122] In some possible implementation manners, each aspect of the positioning method provided by the present application can also be implemented in the form of a program product, which includes program code. When the program product runs on a device, the program code is used to cause the control device to execute the steps in the positioning method according to various exemplary embodiments of the present application described above in this specification.

[0123] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0124] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0125] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device realizes the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0126] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing the functions specified in one process or a plurality of processes and / or blocks Figure 1 one process or a plurality of processes and / or blocks Figure 1 steps for the functions specified in one block or a plurality of blocks.

[0127] Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalent technologies, this application is also intended to include these modifications and variations.

Claims

1. A positioning method, characterized in that, The method includes: Obtaining current radar data collected by a ground penetrating radar, where the radar data represents the radar signal reflection intensity; Calculating a first similarity value between the current radar data and each pre-stored radar data in a database, where the pre-stored radar data corresponds to vehicle pose information; Determining a target radar data in the pre-stored radar data corresponding to the maximum similarity value among the first similarity values; Taking the vehicle pose corresponding to the target radar data as the vehicle pose corresponding to the current radar data; Calculating column vector similarity values between any column vector of the current radar data and any column vector of a frame of historical radar data collected by the ground penetrating radar; Determining target column vector similarity values greater than a preset threshold among the column vector similarity values; Determining first column vectors in the current radar data corresponding to the target column vector similarity values and second column vectors in the historical radar data corresponding to the target column vector similarity values; Updating the vehicle pose according to the overall offset between the first column vectors and the second column vectors; 2. The method according to claim 1, wherein The calculating the first similarity value between the current radar data and each pre-stored radar data in the database includes: Calculating an inner product value between a column vector corresponding to any column in the current radar data and a column vector corresponding to the same column in each pre-stored radar data, where the column vector represents the radar signal reflection intensity in the radar scanning direction; Calculating the first similarity value between the current radar data and each pre-stored radar data respectively according to the inner product values corresponding to the pre-stored radar data; 3. The method according to claim 2, wherein The calculating the first similarity value between the current radar data and each pre-stored radar data respectively according to the inner product values corresponding to the pre-stored radar data includes: Calculating column vector similarity values between the current radar data and each pre-stored radar data respectively according to the inner product values corresponding to the pre-stored radar data; Calculating the first similarity value between the current radar data and each pre-stored radar data respectively according to the column vector similarity values corresponding to the pre-stored radar data; 4. The method according to claim 1, characterized in that The updating the vehicle pose according to the overall offset between the first column vectors and the second column vectors includes: Calculating the overall offset between the first column vectors and the second column vectors; Calculating the total mileage corresponding to the overall offset according to the overall offset and the mileage corresponding to each unit offset; Taking the total mileage as the vehicle movement mileage between the current radar data and the historical radar data; Updating the vehicle pose according to the vehicle movement mileage; 5. A positioning device, characterized in that, The device includes: An obtaining module, configured to obtain current radar data collected by a ground penetrating radar, where the radar data represents the radar signal reflection intensity; A first calculation module, configured to calculate a first similarity value between the current radar data and each pre-stored radar data in a database, where the pre-stored radar data corresponds to vehicle pose information; A first determination module, configured to determine target radar data corresponding to the maximum similarity value among the respective first similarity values in the respective pre-stored radar data; A positioning module, configured to use the vehicle pose corresponding to the target radar data as the vehicle pose corresponding to the current radar data; A second calculation module, configured to calculate respective column vector similarity values between any column vector of the current radar data and any column vector of a frame of historical radar data collected by the ground penetrating radar; A second determination module, configured to determine respective target column vector similarity values greater than a preset threshold among the respective column vector similarity values; determine respective first column vectors corresponding to the respective target column vector similarity values in the current radar data, and respective second column vectors corresponding to the respective target column vector similarity values in the historical radar data; An update module, configured to update the vehicle pose according to an overall offset between the respective first column vectors and the respective second column vectors; 6. The device according to claim 5, characterized in that The first calculation module is specifically configured to: Calculate an inner product value between a column vector corresponding to any column in the current radar data and a column vector corresponding to the same column in the respective pre-stored radar data, where the column vector represents the radar signal reflection intensity in the radar scanning direction; Calculate respective first similarity values between the current radar data and the respective pre-stored radar data according to the inner product values corresponding to the respective pre-stored radar data; 7. The device according to claim 6, characterized in that The first calculation module is further configured to: Calculate respective column vector similarity values between the current radar data and the respective pre-stored radar data according to the inner product values corresponding to the respective pre-stored radar data; Calculate respective first similarity values between the current radar data and the respective pre-stored radar data according to the column vector similarity values corresponding to the respective pre-stored radar data; 8. The device according to claim 5, characterized in that, The update module is specifically configured to: Calculate an overall offset between the respective first column vectors and the respective second column vectors; Calculate a total mileage corresponding to the overall offset according to the overall offset and the mileage corresponding to each unit offset; Use the total mileage as the vehicle movement mileage between the current radar data and the historical radar data; Update the vehicle pose according to the vehicle movement mileage; 9. An electronic device, characterized in that, Including: A memory, configured to store a computer program; A processor, configured to implement the method according to any one of claims 1-4 when executing the computer program stored on the memory; 10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the method according to any one of claims 1-4 is implemented.

Images