Fusion positioning method, device, computer equipment, storage medium and program product
By analyzing the satellite distribution characteristics and setting the positioning weight, the problem that the deviation of GNSS positioning results affects the accuracy of fusion positioning is solved, and the accuracy of fusion positioning results is improved.
Patent Information
- Application Number
- CN202310141940.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-02-13
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2043-02-13
Smart Images

Figure CN116068604B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of maps, and in particular to a fusion positioning method, device, computer equipment, storage medium and program product. Background Art
[0002] The Global Navigation Satellite System (GNSS), also known as the Global Navigation Satellite System, is an air-based radio navigation and positioning system that can provide users with all-weather three-dimensional coordinates, speed and time information at any location on the Earth's surface or in near-Earth space.
[0003] In the process of using GNSS for positioning, in order to improve positioning accuracy, it is usually necessary to fuse observation data from multiple sources such as GNSS, inertial navigation system (INS) and visual camera, and perform fusion positioning based on optimization algorithms such as filtering. However, during the fusion positioning process, if there is a deviation in the GNSS positioning result, it will affect the accuracy of the fusion positioning result.
[0004] Obviously, how to estimate the accuracy of GNSS positioning results is the key to improving the accuracy of fusion positioning results. Summary of the invention
[0005] The embodiments of the present application provide a fusion positioning method, device, computer equipment, storage medium and program product. The technical solution is as follows:
[0006] On the one hand, an embodiment of the present application provides a fusion positioning method, the method comprising:
[0007] Determine the satellite distribution characteristics of each satellite observed at the location of the positioning device;
[0008] Determining a positioning accuracy value of a satellite positioning result based on the satellite distribution characteristics, wherein the satellite positioning result is determined based on the observed satellite signals of each of the satellites;
[0009] Based on the positioning accuracy value, determining a satellite positioning weight of the satellite positioning result in a fusion positioning process, wherein the satellite positioning weight is negatively correlated with the positioning accuracy value;
[0010] Based on the satellite positioning weight and the satellite positioning result, a fused positioning result of the positioning device is determined.
[0011] On the other hand, an embodiment of the present application provides a fusion positioning device, the device comprising:
[0012] A determination module, used to determine satellite distribution characteristics of each satellite observed at the location of the positioning device;
[0013] The determination module is further used to determine a positioning accuracy value of a satellite positioning result based on the satellite distribution characteristics, wherein the satellite positioning result is determined based on the observed satellite signals of each satellite;
[0014] The determination module is further configured to determine, based on the positioning accuracy value, a satellite positioning weight of the satellite positioning result in a fusion positioning process, wherein the satellite positioning weight is negatively correlated with the positioning accuracy value;
[0015] The fusion positioning module is used to determine the fusion positioning result of the positioning device based on the satellite positioning weight and the satellite positioning result.
[0016] On the other hand, an embodiment of the present application provides a computer device, which includes a processor and a memory, wherein the memory stores at least one program, and the at least one program is loaded and executed by the processor to implement the fusion positioning method as described in the above aspects.
[0017] On the other hand, the present application provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the fusion positioning method provided in the above aspect.
[0018] In an embodiment of the present application, the satellite distribution characteristics of each satellite observed at the location of the positioning device are analyzed, and the positioning accuracy value of the satellite positioning result is determined based on the satellite distribution characteristics, so as to determine the satellite positioning weight of the satellite positioning result in the fusion positioning process based on the positioning accuracy value, so as to quantify the credibility of the satellite positioning result in the fusion positioning process; since the process of determining the satellite positioning weight is related to the satellite distribution characteristics of the satellites involved in the calculation of the satellite positioning result, and the satellite distribution characteristics will affect the accuracy of the satellite positioning result, the satellite positioning weight in the fusion positioning process is made consistent with the actual positioning error of the satellite positioning result, thereby improving the accuracy of the fusion positioning result. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0020] Figure 1 A schematic diagram showing an implementation environment provided by an exemplary embodiment of the present application is shown;
[0021] Figure 2 A flow chart of a fusion positioning method provided by an exemplary embodiment of the present application is shown;
[0022] Figure 3 A schematic diagram of a fusion positioning process provided by an exemplary embodiment of the present application is shown;
[0023] Figure 4 A flow chart of a fusion positioning method provided by another exemplary embodiment of the present application is shown;
[0024] Figure 5 A schematic diagram of a satellite view shown in an exemplary embodiment of the present application is shown;
[0025] Figure 6 A schematic diagram of a fusion positioning process provided by another exemplary embodiment of the present application is shown;
[0026] Figure 7 A training method for a positioning accuracy estimation model shown in an exemplary embodiment of the present application is shown;
[0027] Figure 8 A flow chart of a fusion positioning method provided by another exemplary embodiment of the present application is shown;
[0028] Fig. 9 A structural block diagram of a fusion positioning device provided by an exemplary embodiment of the present application is shown;
[0029] Fig.10 A schematic diagram of the structure of a computer device provided by an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION
[0030] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.
[0031] First, the nouns involved in the embodiments of the present application are briefly introduced:
[0032] (1) Global Navigation Satellite System (GNSS): Also known as the Global Navigation Satellite System, it is an air-based radio navigation and positioning system that can provide users with all-weather three-dimensional coordinates, speed and time information at any location on the Earth's surface or in near-Earth space. Common systems include GPS (Global Positioning System), BDS (Beidou navigation Satellite), GLONASS and GALILEO. Satellite navigation systems have been widely used in navigation, communication, personnel positioning, consumer entertainment, mapping, vehicle management, and automotive navigation and information services, and the general development trend is to provide high-precision services for real-time applications.
[0033] (2) Positioning equipment: an electronic device used to process satellite signals and measure the geometric distance between the device and the satellite (pseudorange observation value) and the Doppler effect of the satellite signal (Doppler observation value); positioning equipment usually includes antenna, satellite signal loop, baseband signal processing and other modules. Positioning equipment is widely used in map navigation, surveying and mapping, location services and other fields, such as smartphone map navigation, high-precision geodesy, civil aviation, etc.
[0034] (3) Fusion positioning: A common fusion solution is to fuse the observation data of GNSS / INS (Inertial Navigation System) / visual camera, and use filtering or optimization-based methods for fusion positioning. Among them, the measurement noise covariance matrix of GNSS positioning is mainly assigned by the standard deviation of the positioning solution output by the GNSS positioning algorithm. The consistency between the measurement noise covariance matrix of GNSS positioning and the actual accuracy of GNSS positioning is one of the important factors affecting the positioning accuracy of the fusion positioning algorithm.
[0035] Due to the poor consistency between the standard deviation of the GNSS positioning solution and the actual positioning error, there will be two unexpected situations: one is that the actual GNSS positioning error meets the requirements, but the standard deviation of the GNSS positioning solution is greater than the threshold, resulting in a reduction in available GNSS positioning points; the other is that the actual GNSS positioning error is greater than the threshold, and the standard deviation of the GNSS positioning solution meets the requirements, resulting in the use of incorrect GNSS positioning results in the fusion positioning. Both situations will lead to poor positioning accuracy of the lane-level fusion positioning method.
[0036] In order to improve the positioning accuracy of the fusion positioning algorithm, the present application embodiment proposes a method for weighting GNSS based on satellite distribution characteristics. Figure 1, which shows a schematic diagram of an implementation environment provided by an exemplary embodiment of the present application, wherein the implementation environment includes: a satellite device 110 and a positioning device 120.
[0037] The satellite device 110 is a device with a satellite signal transmission function. The satellite device 110 in this embodiment is mainly an artificial satellite with a navigation function. Common satellite positioning systems mainly include four major satellite navigation systems: GPS, BDS, GLONASS and GALILEO. By sending a satellite positioning model through the satellite device 110, the positioning device 120 can determine its own spatial position based on the satellite positioning signal.
[0038] The positioning device 120 refers to an electronic device with a positioning function. A global satellite navigation system positioning chip may be integrated in the positioning device 120 to process satellite signals and perform precise positioning. Optionally, the positioning device 120 generally includes functional components such as an antenna, a satellite signal loop, and a baseband signal processing. The positioning device 120 may be a tablet computer, a portable notebook, a vehicle-mounted terminal, a smart phone, a POS machine, etc., or a desktop computer, etc., which is not limited in the embodiments of the present application.
[0039] Optionally, in this embodiment, the satellite distribution characteristics of each satellite observed at the location of the positioning device are analyzed, and the positioning accuracy value of the satellite positioning result is determined based on the satellite distribution characteristics, so as to determine the satellite positioning weight of the satellite positioning result in the fusion positioning process based on the positioning accuracy value, so as to quantify the credibility of the satellite positioning result in the fusion positioning process; because the process of determining the satellite positioning weight is related to the satellite distribution characteristics of the satellites involved in the calculation of the satellite positioning result, and the satellite distribution characteristics will affect the accuracy of the satellite positioning results, the satellite positioning weight in the fusion positioning process is made consistent with the actual positioning error of the satellite positioning result, thereby improving the accuracy of the fusion positioning result.
[0040] It should be noted that before collecting relevant data of users and during the process of collecting relevant data of users, this application can display a prompt interface, pop-up window or output voice prompt information, and the prompt interface, pop-up window or voice prompt information is used to prompt the user that its relevant data is currently being collected, so that this application only starts to execute the relevant steps of obtaining relevant data of users after obtaining the confirmation operation issued by the user to the prompt interface or pop-up window, otherwise (that is, when the confirmation operation issued by the user to the prompt interface or pop-up window is not obtained), the relevant steps of obtaining relevant data of users are terminated, that is, the relevant data of users are not obtained. In other words, all user data collected by this application are collected with the consent and authorization of the user, and the collection, use and processing of relevant user data need to comply with the relevant laws, regulations and standards of relevant countries and regions.
[0041] Please refer to Figure 2 , which shows a flow chart of a fusion positioning method provided by an exemplary embodiment of the present application. The present application embodiment takes the method applied to the positioning device 120 in the above embodiment as an example for explanation. The method includes:
[0042] Step 201, determining satellite distribution characteristics of each satellite observed at the location of the positioning device.
[0043] During the GNSS positioning process, the positioning device processes satellite signals to calculate the coordinates of the current position of the positioning device. Since the position of the positioning device changes at any time, and the satellite positions (satellite distribution) and satellite signals (which may be blocked by obstacles) that can be observed at different positions are different, which affects the positioning accuracy of GNSS positioning. In order to enable the positioning device to clearly understand the GNSS positioning level at the current position, in a possible implementation method, the positioning device obtains the satellite distribution characteristics of each satellite observed at the position of the positioning device during the fusion positioning process, and analyzes the satellite distribution characteristics to quantify the quality of satellite signals involved in the calculation of the satellite positioning result, thereby estimating the positioning accuracy of the satellite positioning result.
[0044] Optionally, the satellite distribution characteristics may include characteristic values of multiple dimensions of the satellite, such as satellite altitude angle dimension, satellite azimuth angle dimension, satellite signal dimension, satellite quantity dimension, satellite precision attenuation factor dimension, etc. The embodiments of the present application do not limit the specific characteristic values contained in the satellite distribution characteristics.
[0045] Step 202, based on the satellite distribution characteristics, determine the positioning accuracy value of the satellite positioning result, the satellite positioning result is determined based on the satellite signals of each observed satellite.
[0046] Optionally, after the positioning device obtains the satellite distribution characteristics of the currently observed satellite, it can use a preset analysis algorithm to analyze the satellite distribution characteristics to determine the quality of the satellite signals corresponding to each observed satellite involved in the calculation of the satellite positioning result, and use the positioning accuracy value to quantify the positioning quality of the satellite positioning result.
[0047] Among them, the positioning accuracy value is used to characterize the error between the satellite positioning result and the actual device position of the positioning device. If the positioning accuracy value is smaller, it means that the error between the satellite positioning result and the actual device position is smaller, the satellite positioning result is more accurate (higher credibility), and a higher satellite positioning weight can be set for the satellite positioning result; conversely, if the positioning accuracy value is larger, it means that the error between the satellite positioning result and the actual device is larger, the satellite positioning result is more inaccurate (lower credibility), and a lower satellite positioning weight can be set for the satellite positioning result. It can be seen that the satellite positioning weight is negatively correlated with the positioning accuracy value.
[0048] Illustratively, if the positioning accuracy value of satellite positioning result A is 3m, and the positioning accuracy value of satellite positioning result B is 10m, satellite positioning result A is more accurate than satellite positioning result B, then the satellite positioning weight of satellite positioning result A is greater than the satellite positioning weight of satellite positioning result B.
[0049] Optionally, if the positioning accuracy is used to determine the satellite positioning weight, the higher the positioning accuracy, the smaller the positioning accuracy value, the smaller the error between the satellite positioning result and the real device, the more accurate the satellite positioning result, and the higher the satellite positioning weight is set for the satellite positioning result; conversely, if the positioning accuracy is lower, the larger the positioning accuracy value, the larger the error between the satellite positioning result and the real device, the more inaccurate the satellite positioning result, and the lower the satellite positioning weight is set for the satellite positioning result. It can be seen that the satellite positioning weight is positively correlated with the satellite accuracy.
[0050] Optionally, when determining the satellite positioning result, at least four non-coplanar satellites are required to determine the spatial position of the positioning device. Correspondingly, before determining the positioning accuracy value of the satellite positioning result based on the satellite distribution characteristics, it is first necessary to determine whether the conditions for determining the satellite positioning result are met based on the acquired satellite positioning information. If so, continue to perform subsequent steps such as determining the positioning accuracy value.
[0051] Optionally, when determining the satellite positioning result based on the satellite signals of each observed satellite, the positioning algorithm adopted may include: pseudorange measurement (measuring the propagation time of the ranging code signal transmitted by the satellite to reach the user receiver) and carrier phase measurement (measuring the phase difference between the satellite carrier signal with carrier Doppler frequency shift and the reference carrier signal generated by the receiver).
[0052] Step 203, based on the positioning accuracy value, determine the satellite positioning weight of the satellite positioning result in the fusion positioning process, and the satellite positioning weight is negatively correlated with the positioning accuracy value.
[0053] In the fusion positioning process, the positioning device needs to fuse the GNSS positioning results (satellite positioning results) with other positioning results (for example, inertial navigation positioning results or visual camera positioning results) to jointly determine the spatial position of the positioning device. The error between the satellite positioning result and the actual positioning result needs to be taken into account in the fusion process to determine the credibility of the satellite positioning result in the fusion process. In order to clarify the credibility of the satellite positioning result in the positioning fusion process, in a possible implementation manner, the positioning device can set a satellite positioning weight in the fusion positioning process for the satellite positioning result based on the positioning accuracy value of the satellite positioning result. The larger the positioning accuracy value, the larger the error of the satellite positioning result and the lower the credibility of the satellite positioning result. Accordingly, a lower satellite positioning weight needs to be set for the satellite positioning result. If the smaller the positioning accuracy value, the smaller the error of the satellite positioning result and the higher the credibility of the satellite positioning result, accordingly, a higher satellite positioning weight needs to be set for the satellite positioning result. That is, the satellite positioning weight is negatively correlated with the positioning accuracy value.
[0054] Optionally, the positioning device may pre-set the operational relationship between the satellite positioning weight and the positioning accuracy value, so that the satellite positioning weight and the positioning accuracy value satisfy a negative correlation; or, the positioning device may pre-set different satellite positioning weights for positioning accuracy values in different ranges, so that in the application process, the corresponding satellite positioning weight can be matched based on the range of the positioning accuracy value. Schematically, if the positioning accuracy value of the satellite positioning result is 3m, the satellite positioning weight of the satellite positioning result can be set to 1, and if the positioning accuracy value of the satellite positioning result is 5m, the satellite positioning weight of the positioning result can be set to 0.5.
[0055] Step 204: Determine the fused positioning result of the positioning device based on the satellite positioning weight and the satellite positioning result.
[0056] Optionally, when the positioning device determines the satellite positioning weight of the satellite positioning result, that is, determines the credibility of the satellite positioning result in the fusion positioning process, the satellite positioning weight and the satellite positioning result can be input into the fusion positioning algorithm (the fusion positioning algorithm can be a filtering algorithm) to obtain the fusion positioning result of the positioning device output by the fusion positioning algorithm.
[0057] like Figure 3As shown, it shows a schematic diagram of the process of fusion positioning of an exemplary embodiment of the present application. In the fusion positioning process, the positioning accuracy value 302 of the satellite positioning result 304 is first estimated according to the satellite distribution characteristics 301, and the satellite positioning weight 303 of the satellite positioning result 304 in the fusion positioning process is determined based on the positioning accuracy value 302; then, the satellite positioning result 304, the satellite positioning weight 303, and other positioning results (inertial navigation positioning result and / or visual camera positioning result 305) are input into the fusion positioning algorithm 306, and the fusion positioning result 307 output by the fusion positioning algorithm 306 can be obtained.
[0058] To sum up, in this embodiment, the satellite distribution characteristics of each satellite observed at the location of the positioning device are analyzed, and the positioning accuracy value of the satellite positioning result is determined based on the satellite distribution characteristics, so as to determine the satellite positioning weight of the satellite positioning result in the fusion positioning process based on the positioning accuracy value, so as to quantify the credibility of the satellite positioning result in the fusion positioning process; because the process of determining the satellite positioning weight is related to the satellite distribution characteristics of the satellites involved in the calculation of the satellite positioning result, and the satellite distribution characteristics will affect the accuracy of the satellite positioning result, the satellite positioning weight in the fusion positioning process is made consistent with the actual positioning error of the satellite positioning result, thereby improving the accuracy of the fusion positioning result.
[0059] In order to improve the accuracy of determining satellite distribution characteristics, the satellites are projected into the satellite view (Skyplot) according to the satellite altitude angle and satellite azimuth angle, and the sub-distribution characteristics in each grid position are determined to comprehensively obtain the satellite distribution characteristics of all satellites observed at the location.
[0060] Please refer to Figure 4 , which shows a flow chart of a fusion positioning method provided by another exemplary embodiment of the present application. The present application embodiment takes the method applied to the positioning device 120 in the above embodiment as an example for explanation. The method includes:
[0061] Step 401: Obtain satellite positioning information of each satellite observed by a positioning device.
[0062] Optionally, the satellite positioning information includes at least one of the satellite number, satellite altitude angle, satellite azimuth angle, satellite signal-to-noise ratio and satellite precision reduction factor. Among them, the satellite precision reduction factor (Dilution Of Precision, DOP) is an indicator of position quality. In navigation, the concept of DOP is generally used to represent the error magnification factor, and the receiver of the positioning device usually outputs the precision factor together with the positioning result for user reference. A small DOP value indicates a strong satellite geometric position and a higher probability of accuracy. A high DOP value indicates a weak satellite geometric position and a lower probability of accuracy. Optionally, the common calculation types of DOP values may include: HDOP, VDOP, PDOP, etc.
[0063] Optionally, after the receiver of the positioning device receives the satellite signal of each observed satellite, it can output satellite positioning information related to the satellite, so that the satellite distribution characteristics can be determined subsequently based on the satellite positioning information.
[0064] Optionally, the positioning device can receive satellite signals from multiple satellite systems, including GPS, BDS, GLONASS, GALILEO, QZSS and other satellite systems. The number of visible satellites can reach more than 30 in an open environment.
[0065] Step 402: Determine satellite distribution characteristics of each satellite observed at the location of the positioning device based on the satellite positioning information.
[0066] Considering the influence of satellite distribution on satellite positioning accuracy, in order to analyze the satellite distribution characteristics of the satellites currently observed by the positioning device, each observed satellite can be projected into a satellite view (Skyplot) according to the satellite altitude angle and the satellite azimuth angle, so as to analyze the corresponding satellite distribution characteristics based on the satellite view later. Correspondingly, in an illustrative example, step 402 may include steps 402A to 402C.
[0067] Step 402A, based on the satellite elevation angle and the satellite azimuth angle, determine the grid position of each satellite in the satellite view, and the number of grids containing the grid position in the satellite view is determined by the satellite elevation angle range and the satellite azimuth angle range.
[0068] The satellite view is obtained by dividing the satellite elevation angle range and the satellite azimuth angle range. Since the satellite elevation angle range is 0-90 degrees and the satellite elevation angle range is 0-360 degrees, 4*6=24 grid positions can be divided on the satellite view (Skyplot) according to the satellite elevation angle range and the satellite azimuth angle range.
[0069] Taking into account the impact of satellite distribution on the accuracy of satellite positioning, before extracting satellite distribution characteristics, the positioning device first determines the grid position of each satellite in the satellite view based on the satellite altitude angle and satellite azimuth angle of each observed satellite. That is, based on the satellite altitude angle and satellite azimuth angle of the satellite, the satellite can be projected into a uniquely determined grid position in the satellite view.
[0070] like Figure 5 As shown, it shows a schematic diagram of a satellite view shown in an exemplary embodiment of the present application. The satellite view 501 is divided into 24 grid positions 502, wherein the satellite elevation angle range is divided into 4 ranges: 0-15 degrees, 15-45 degrees, 45-60 degrees, 60-90 degrees, and the satellite azimuth angle range is divided into 6 ranges: 0-60 degrees, 60-120 degrees, 120-180 degrees, 180-240 degrees, 240-300 degrees, 300-360 degrees, each range is 60 degrees, thereby obtaining 24 grid positions. If the satellite elevation angle of satellite A is 15 degrees and the satellite azimuth angle is 60 degrees, the position of satellite A in the satellite view can be shown as projection point A. If the satellite elevation angle of satellite B is 30 degrees. The satellite azimuth angle is 120 degrees, and the position of satellite B in the satellite view can be shown as projection point B.
[0071] Optionally, this embodiment only takes the example of dividing the satellite view into 24 grid positions for illustrative description. In order to obtain more detailed satellite distribution features, the satellite view can also be divided into more grid positions, for example, 4*8=32 grid positions, or 5*6=30 grid positions, etc. This embodiment does not limit the specific grid positions. And the more grid positions there are, the more satellite distribution features can be obtained.
[0072] Step 402B, based on the satellite positioning information of the satellite included in the grid position, determine the first sub-distribution feature of the satellite corresponding to the grid position.
[0073] In one possible implementation, after projecting each satellite observed by the positioning device onto the satellite view according to the satellite altitude angle and the satellite azimuth angle, the satellite contained in each grid position can be determined, and then the first sub-distribution characteristics of the satellite corresponding to each grid position are determined based on the satellite positioning information of the satellite contained in each grid position, and then the feature value set of the first sub-distribution characteristics corresponding to each grid position is determined as the satellite distribution characteristics of each satellite observed by the positioning device.
[0074] Optionally, by dividing the grid positions, the distribution positions of each observed satellite can be clarified according to the first sub-distribution characteristics of each grid position.
[0075] Optionally, since it is necessary to calculate the first sub-distribution feature corresponding to each grid position, the number of eigenvalues contained in the satellite distribution feature is determined by the number of grids at the grid position and the eigenvalue dimension contained in the satellite distribution eigenvalue; schematically, if the number of grids is 24 and the eigenvalue dimension (the eigenvalue dimension refers to the eigenvalue category that needs to be calculated) is 5, then the satellite distribution feature contains 5*24=120 eigenvalues.
[0076] Since the positioning device can observe satellites of different satellite systems, common satellite systems are roughly divided into four satellite systems: GPS, BDS, GLONASS, QZSS, etc. In order to further enrich the number of eigenvalues of satellite eigenvalues, for each grid position, the distribution characteristics of different satellite systems in each grid position can also be calculated respectively. Correspondingly, in an exemplary example, step 402B can also include steps 402B1 to 402B3.
[0077] Step 402B1, based on the satellite positioning information of the satellites contained in the grid locations, the satellites contained in the grid locations are divided into different satellite systems.
[0078] Step 402B2, determining a second sub-distribution feature of the satellite system in the grid location based on the satellite positioning information of the satellites of the same satellite system in the grid location.
[0079] Step 402B3, determine the set of second sub-distribution features corresponding to each satellite system in the grid position as the first sub-distribution feature of the satellite corresponding to the grid position, and the number of feature values of the satellite distribution feature is determined by the number of grids and the number of system categories of the satellite system.
[0080] When calculating the first sub-distribution feature of the grid position, the satellites contained in the grid position can be divided according to different satellite systems based on the satellite positioning information of the satellites contained in the grid position to obtain different satellite sets. The satellites in the same satellite set are the same satellite system in the same grid position.
[0081] Optionally, after different satellite systems are divided, for each grid position, the second sub-distribution characteristics of the same satellite system in the grid position can be calculated based on the satellite positioning information of the satellites of the same satellite system in the grid position, and then the set of second sub-distribution characteristics corresponding to each satellite system can be determined as the first sub-distribution characteristics of the satellites corresponding to the grid position.
[0082] Optionally, since the distribution characteristics of the satellites corresponding to each grid position are also divided into different satellite systems for calculation, the number of characteristic values contained in the satellite distribution characteristics is determined by the grid position, the number of system categories of the satellite system, and the characteristic value dimension. Schematically, if the grid position is 24, there are four satellite systems, and the characteristic value dimension is 5, the number of characteristic values contained in the satellite distribution characteristics is 4*24*5=480.
[0083] Optionally, in order to save the amount of calculation in the satellite positioning process, it is not necessary to divide each grid position into different satellite systems, which can reduce the number of eigenvalues of the satellite distribution characteristics accordingly; if higher positioning accuracy (smaller positioning accuracy value) is required, it is possible to choose to further divide the grid positions according to the satellite system, thereby increasing the number of eigenvalues contained in the satellite distribution characteristics.
[0084] Optionally, taking the calculation process of the second sub-distribution feature of the satellite corresponding to the same satellite system in the same grid position as an example, the positioning device can determine at least one of the number of satellites, average satellite altitude angle, average signal-to-noise ratio, target satellite ratio, and satellite azimuth standard deviation of the satellite system in the grid position based on the satellite positioning information of the satellites in the same satellite system in the grid position, and the target satellite ratio refers to the ratio of satellites whose satellite signal-to-noise ratio is greater than the signal-to-noise ratio threshold. In other words, the characteristic value dimensions contained in the satellite distribution feature include five dimensions: the number of satellites, the average satellite altitude angle, the average signal-to-noise ratio, the target satellite ratio, the satellite azimuth standard deviation, etc.
[0085] If the grid position is not further divided into different satellite systems, then in the first sub-distribution feature: the number of satellites is the number of satellites contained in the grid position, the average satellite altitude angle is the average value of the satellite altitude angles of the satellites contained in the grid position, the average signal-to-noise ratio is the average value of the satellite signal-to-noise ratio of the satellites contained in the grid position, the satellite azimuth standard deviation is the standard deviation of the satellite azimuth of the satellites contained in the grid position, and the target satellite ratio is the ratio of satellites in the grid position whose satellite signal-to-noise ratio is greater than the signal-to-noise ratio threshold. The signal-to-noise ratio threshold can be 30.
[0086] If the grid position is further divided into different satellite systems, for example, 4 satellite systems, the first sub-distribution feature includes 4 groups of second sub-distribution features, and in the second sub-distribution feature of the first satellite system: the number of satellites is the number of satellites included in the first satellite system at the grid position, the average satellite altitude angle is the average value of the satellite altitude angles of the satellites included in the first satellite system at the grid position, the average signal-to-noise ratio is the average value of the satellite signal-to-noise ratio of the satellites included in the first satellite system at the grid position, the satellite azimuth standard deviation is the standard deviation of the satellite azimuth of the satellites included in the first satellite system at the grid position, and the target satellite proportion is the proportion of satellites in the first satellite system at the grid position whose satellite signal-to-noise ratio is greater than the signal-to-noise ratio threshold.
[0087] Step 402C: determine the set of first sub-distribution features corresponding to each grid position as a satellite distribution feature, and the number of feature values of the satellite distribution feature is determined by the number of grids.
[0088] Optionally, after determining the first sub-distribution feature corresponding to each grid position, the set of first sub-distribution features corresponding to each grid position is the satellite distribution feature of each satellite observed by the positioning device.
[0089] Optionally, the satellite distribution feature may also include three values of HDOP, VDOP, PDOP factors, etc. Schematically, if the classification calculation is performed according to the satellite system, there are 4 satellite systems, the number of grids is 24, and the eigenvalue dimension is 5, then the satellite distribution feature includes 480+3=483 eigenvalues.
[0090] Step 403: input the satellite distribution characteristics into the positioning accuracy estimation model to obtain the positioning accuracy value output by the positioning accuracy estimation model.
[0091] Optionally, a positioning accuracy estimation model is also deployed in the positioning device. The positioning accuracy estimation model is trained based on sample satellite distribution characteristics and sample labeled positioning accuracy values, so that the positioning accuracy estimation model can output the positioning accuracy value of the satellite positioning result reflected by it based on the satellite distribution characteristics. Correspondingly, in a possible implementation, after the positioning device extracts the satellite distribution characteristics of the satellite observed at the current position, the satellite distribution characteristics can be input into the positioning accuracy estimation model, and the positioning accuracy estimation model performs positioning accuracy value analysis to obtain the positioning accuracy value output by the positioning accuracy estimation model.
[0092] Optionally, the positioning accuracy estimation model can adopt a gradient boosting tree model (XGBoost) or other neural network models. This embodiment does not limit the specific structure of the positioning accuracy estimation model, and the specific model training process can refer to the following embodiment, which will not be described in detail in this embodiment.
[0093] Step 404, determining a weight coefficient of the satellite positioning result under the positioning accuracy value, where the weight coefficient is negatively correlated with the positioning accuracy value.
[0094] Optionally, the satellite positioning weight is determined by the positioning accuracy value and a weight coefficient. The weight coefficient is determined by the size of the positioning accuracy value, and the weight coefficient is negatively correlated with the positioning accuracy value, that is, the larger the positioning accuracy value, the smaller the weight coefficient, and the smaller the positioning accuracy value, the larger the weight coefficient.
[0095] Optionally, based on the availability of satellite positioning results and the application scenarios of satellite positioning results, multiple positioning accuracy ranges are divided, and different weight coefficients are set for each positioning accuracy range. This allows the weight coefficient of the satellite positioning result under the positioning accuracy value to be determined based on the relationship between the positioning accuracy value and the positioning accuracy range. Correspondingly, in an illustrative example, step 404 may also include step 404A and step 404B.
[0096] Step 404A, determining the positioning accuracy range in which the positioning accuracy value is located, and different positioning accuracy ranges correspond to different weight coefficients.
[0097] Step 404B, determining the weight coefficient corresponding to the positioning accuracy range as the weight coefficient of the satellite positioning result under the positioning accuracy value.
[0098] Among them, the positioning device is pre-set with multiple positioning accuracy ranges, and different positioning accuracy ranges correspond to different weight coefficients. When determining the weight coefficient, the positioning device first determines the positioning accuracy range in which the positioning accuracy value is located, and then determines the weight coefficient of the satellite positioning result under the current positioning accuracy value according to the weight coefficient corresponding to the positioning accuracy range.
[0099] In an exemplary example, the relationship between the positioning accuracy range and the weight coefficient can be shown in Table 1.
[0100] Table 1
[0101] Positioning accuracy range Weight coefficient 0~3m 1 3~10m 0.5 >10m 0.01
[0102] It can be seen from Table 1 that when the positioning accuracy value is greater than 10m, the weight of the satellite positioning result is reduced to the minimum (10 represents the available threshold of the satellite positioning result, that is, when the positioning accuracy value of the satellite positioning result is greater than 10m, the satellite positioning result is not available), and the weight coefficient corresponding to the positioning accuracy range is set to 0.01; when the positioning accuracy range is 3-10m, the weight of the satellite positioning result is reduced (3m can represent the accuracy requirement of the lane-level positioning scenario for GNSS positioning, that is, when the positioning accuracy value of the satellite positioning result is greater than 3m, the satellite positioning result is not available in the lane-level positioning scenario), and the weight coefficient corresponding to the positioning accuracy range is set to 0.5; when the positioning accuracy range is 0-3m, the weight of the satellite positioning result is increased (3m represents the accuracy requirement of the lane-level positioning scenario for the satellite positioning result, and it is considered that the lane-level positioning is available when the positioning accuracy value of the satellite positioning result is less than 3m), and the weight coefficient corresponding to the accuracy range is set to 1.
[0103] Optionally, since different positioning application scenarios have different requirements for the positioning accuracy of satellite positioning results, for example, the positioning accuracy requirement for satellite positioning results in lane-level positioning scenarios is 0 to 3 m, in order to enable the fusion positioning method to be used in different positioning application scenarios, in other possible implementations, the positioning device may also dynamically adjust the positioning accuracy range according to the positioning application scenario of the fusion positioning result; during the fusion positioning process, the corresponding positioning device may obtain the positioning application scenario of the fusion positioning result, and then divide the positioning accuracy requirement of the fusion positioning result in the positioning application scenario into different accuracy ranges, so that the weight coefficient corresponding to the satellite positioning result in the current positioning application scenario can be dynamically determined according to the different accuracy ranges.
[0104] Optionally, the positioning device may be pre-set with multiple relationships between positioning application scenarios and accuracy ranges, so that corresponding weight coefficients are adapted in different positioning application scenarios. As shown in Table 2, it shows the relationship between positioning application scenarios and accuracy ranges.
[0105] Table 2
[0106] Positioning application scenarios Accuracy range Scenario 1 0~3m、3~10m、>10m Scenario 2 0~0.1m、0.1~10m、>10m Scene 3 0~1m、1~10m、>10m … …
[0107] It can be seen from Table 2 that if the current positioning application scenario is scenario 2, when the positioning accuracy value of the satellite positioning result is 0.05m, the corresponding weight coefficient is 1; if the positioning accuracy value of the satellite positioning result is 1m, the corresponding weight coefficient is 0.5; if the positioning accuracy value of the satellite positioning result is 20m, the corresponding weight coefficient is 0.01.
[0108] Step 405: Determine the satellite positioning weight of the satellite positioning result in the fusion positioning process based on the weight coefficient and the positioning accuracy value.
[0109] In an exemplary example, the calculation process of the satellite positioning weight may be as shown in formula (1).
[0110]
[0111] Among them, p represents the satellite positioning weight, std_predict represents the positioning accuracy value, and k represents the weight coefficient. It can be seen that the satellite positioning weight is negatively correlated with the positioning accuracy value, and the satellite positioning weight is positively correlated with the weight coefficient.
[0112] Step 406: Determine the fused positioning result of the positioning device based on the satellite positioning weight and the satellite positioning result.
[0113] like Figure 6As shown, it shows a schematic diagram of the process of fusion positioning of another exemplary embodiment of the present application. Based on satellite positioning information 601 such as satellite number, signal-to-noise ratio, altitude angle, azimuth angle and DOP factor, satellite distribution characteristics 602 such as the number of satellites, average signal-to-noise ratio, average satellite altitude angle, standard deviation of satellite azimuth angle and proportion of satellites with a signal-to-noise ratio greater than 60 are extracted, and the satellite distribution characteristics 602 are input into the positioning accuracy estimation model 603 to estimate the positioning accuracy value, and obtain the positioning accuracy value 604 output by the model; further, based on the positioning accuracy value 604, a weight coefficient 605 is determined, so as to calculate the satellite positioning weight 606 of the satellite positioning result according to the positioning accuracy value 604 and the weight coefficient 605; and then the satellite positioning result 607, the satellite positioning weight 606 and other positioning results (inertial navigation positioning result and / or visual camera positioning result 608) are input into the fusion positioning pan 609 to obtain the fusion positioning result 610.
[0114] The implementation of step 406 may refer to the above embodiment, and will not be described in detail in this embodiment.
[0115] In this embodiment, multiple grid positions are obtained by dividing the satellite view, and the satellite is projected into a unique grid position based on the satellite altitude angle and the satellite azimuth angle, so as to calculate the first sub-distribution feature of each grid position respectively, and obtain the satellite distribution feature, so that the characteristics of the satellite distribution position can be better extracted by dividing the grid position, thereby enriching the number of features contained in the satellite distribution feature, which is conducive to analyzing the positioning accuracy value. In addition, by estimating the positioning accuracy value through the positioning accuracy estimation model, the estimation accuracy of the positioning accuracy value can be improved; in addition, by dividing the accuracy range according to different positioning application scenarios, the fusion positioning method can be applied to different positioning application scenarios, and adapt to the positioning accuracy requirements of the positioning application scenarios.
[0116] In order to enable the positioning accuracy estimation model to have the function of estimating the positioning accuracy value, it is necessary to pre-train the positioning accuracy estimation model so that the positioning accuracy estimation model can learn the relationship between satellite distribution characteristics and positioning accuracy values from the input satellite distribution characteristics.
[0117] Please refer to Figure 7 , which shows a training method for a positioning accuracy estimation model shown in an exemplary embodiment of the present application, the method comprising:
[0118] Step 701, obtain sample satellite distribution characteristics and sample annotation positioning accuracy values.
[0119] Similar to the model application process, in the model training process, it is also necessary to obtain the sample satellite distribution characteristics, and use the actual positioning accuracy value of the satellite positioning result as the target result value of the positioning accuracy estimation model, that is, to obtain the sample labeled positioning accuracy value. Schematically, each sample satellite distribution feature can include 483 eigenvalues, or 123 eigenvalues. The number of eigenvalues contained in the sample satellite distribution feature is determined by the number of grids * the number of eigenvalue dimensions, or the number of grids * the number of eigenvalue dimensions * the number of system categories of the satellite system.
[0120] Step 702: Input the sample satellite distribution characteristics into the positioning accuracy estimation model to obtain the sample predicted positioning accuracy value output by the positioning accuracy estimation model.
[0121] Exemplarily, if the positioning accuracy model is an XGBoost model, then before model training, the model parameters of the XGBoost model need to be set, for example, booster (weak learner type) is defined as gbtree, objective (problem type and corresponding loss function) is defined as reg:squarederror, gamma (loss reduction threshold brought by XGBoost's decision tree splitting) is defined as 0.01, max_depth (tree depth) is defined as 6, subsample (subsampling parameter) is defined as 0.7, colsample_bytree (feature sampling ratio of the tree) is defined as 0.7, min_child_weight (minimum child node weight threshold) is defined as 0.5, and num_rounds (number of iterations) is defined as 500.
[0122] After setting the above model parameters, the sample satellite distribution characteristics can be input into the positioning accuracy estimation model, and the positioning accuracy estimation model will perform accuracy estimation to obtain the sample predicted positioning accuracy value output by the positioning accuracy estimation model.
[0123] Step 703: training a positioning accuracy estimation model based on the loss between the sample labeled positioning accuracy value and the sample predicted positioning accuracy value.
[0124] Optionally, the positioning accuracy estimation model can use MSE mean square error as the loss function. The model loss calculation function can be shown as formula (2).
[0125]
[0126] Among them, dist predict Indicates the sample prediction positioning accuracy value output by the positioning accuracy estimation model, dist truth Indicates the sample annotation positioning accuracy value.
[0127] During the model training process, the positioning accuracy estimation model can be iteratively trained based on the loss (error function) between the sample labeled positioning accuracy value and the sample predicted positioning accuracy value. When a predetermined number of iterations is reached and / or the loss of the positioning accuracy estimation model is less than a predetermined threshold, it is determined that the training of the positioning accuracy estimation model is completed. This can be used to estimate the positioning accuracy value of the satellite positioning result based on the input satellite distribution characteristics during the fusion positioning process.
[0128] It should be noted that steps 701 to 703 may be performed before the step of determining satellite distribution characteristics of each satellite observed at the location of the positioning device.
[0129] Optionally, after the positioning accuracy estimation model is deployed on each positioning device, the locations of various positioning devices may be different. In order to make each positioning accuracy estimation model adapt to the personalized positioning device, the positioning accuracy estimation model can also be optimized and trained based on user feedback during the application of the positioning accuracy estimation model. The corresponding optimization training process can include the following steps 1 and 2.
[0130] Step 1: upon receiving a negative feedback signal for a fused positioning result, obtaining satellite distribution characteristics and positioning accuracy values corresponding to the fused positioning result, wherein the negative feedback signal is used to indicate that the positioning error of the fused positioning result is greater than a positioning error threshold.
[0131] Step 2: Based on the satellite distribution characteristics and positioning accuracy values, optimize the positioning accuracy estimation model.
[0132] In order to improve the accuracy of the precision prediction of the positioning accuracy estimation model, the positioning accuracy estimation model can also be regularly optimized and trained during the use of the model. The purpose of the optimization training is mainly to target samples with incorrect positioning accuracy value estimation during the use of the positioning accuracy estimation model. Incorrect positioning accuracy value estimation will lead to deviations in the fusion positioning result. Therefore, in one possible implementation, when the positioning device receives a negative feedback signal for the fusion positioning result, indicating that the positioning error of the fusion positioning result is greater than the positioning error threshold, the positioning accuracy value and satellite distribution characteristics used in the process of determining the fusion positioning result can be obtained, and the satellite distribution characteristics and positioning accuracy value are determined as negative samples, and the positioning accuracy estimation model is optimized and trained to improve the accuracy of the positioning accuracy estimation model's estimation of the positioning accuracy value.
[0133] Optionally, after accumulating a certain number of negative samples, the positioning accuracy estimation model may be optimized and trained to improve the generalization of the model.
[0134] In this embodiment, the positioning accuracy estimation model is trained by using sample satellite distribution characteristics and sample annotated positioning accuracy values, so that the positioning accuracy estimation model can have the ability to estimate the positioning accuracy value, thereby estimating the positioning accuracy value during the fusion positioning process; in addition, during the use of the positioning accuracy estimation model, negative samples of the positioning accuracy estimation error during use can be collected to optimize the positioning accuracy estimation model, which can further improve the accuracy of the accuracy estimation of the positioning accuracy estimation model, thereby improving the accuracy of determining the subsequent fusion positioning results.
[0135] In a satellite positioning scenario, a positioning device can observe more satellites in an open location. The more satellites there are, the more satellites are available to determine the satellite positioning results, thereby providing more accurate satellite positioning results than with a smaller number of satellites. Correspondingly, in a possible implementation manner, the number of satellites can be introduced as a reference factor when determining the satellite positioning weight of the satellite positioning result.
[0136] Please refer to Figure 8 , which shows a flow chart of a fusion positioning method provided by another exemplary embodiment of the present application. The present application embodiment takes the method applied to the positioning device 120 in the above embodiment as an example for explanation. The method includes:
[0137] Step 801: Obtain satellite positioning information of each satellite observed by a positioning device.
[0138] Step 802: Based on the satellite positioning information, determine the satellite distribution characteristics of each satellite observed at the location of the positioning device.
[0139] Step 803: Determine the positioning accuracy value of the satellite positioning result based on the satellite distribution characteristics.
[0140] The implementation of steps 801 to 803 may refer to the above embodiments, and will not be described in detail in this embodiment.
[0141] Step 804: determine the total number of satellites observed by the positioning device at the location from the satellite positioning information.
[0142] Step 805: When the total number of satellites is less than the quantity threshold, the satellite positioning weight of the satellite positioning result in the fusion positioning process is determined based on the positioning accuracy value.
[0143] Since the satellite positioning result requires at least 4 satellites to be determined, the quantity threshold is an integer greater than 4. For example, the quantity threshold may be 10.
[0144] If the total number of satellites that the positioning device can observe is larger, it means that the current location of the positioning device is relatively open, and the satellite signal is less likely to be blocked by other buildings or obstacles, so the satellite positioning result is relatively accurate. On the contrary, if the total number of satellites is small, it means that the current location of the positioning device may be more blocked, and the satellite positioning result is relatively less accurate; when the total number of satellites is less than the number threshold, the satellite positioning weight of the satellite positioning result in the fusion positioning process can be determined only based on the positioning accuracy value; if the total number of satellites is greater than the number threshold, the satellite positioning weight of the satellite positioning result in the fusion positioning process can be determined based on the positioning accuracy value and the total number of satellites, and the satellite positioning weight is positively correlated with the total number of satellites. That is, on the basis of the positioning accuracy value, the corresponding satellite weight will be added to the satellite positioning result determined in the scenario with a large number of satellites.
[0145] Optionally, the positioning device may be provided with a relationship between the total number of satellites and the added satellite weight. Correspondingly, during use, the added satellite weight that needs to be added may be determined according to the total number of satellites, and then the satellite positioning weight of the satellite positioning result may be determined according to the sum of the added satellite weight and the satellite weight determined by the positioning accuracy value.
[0146] Step 806: Determine the fused positioning result of the positioning device based on the satellite positioning weight and the satellite positioning result.
[0147] The implementation of step 806 may refer to the above embodiment, and will not be described in detail in this embodiment.
[0148] In this embodiment, taking into account the relationship between the total number of satellites observed by the positioning device and the positioning accuracy corresponding to the satellite positioning results, the total number of satellites is introduced as a consideration in the process of determining the satellite positioning weight, which can further improve the consistency between the satellite positioning weight and the actual positioning error, thereby improving the accuracy of the fused positioning result.
[0149] Please refer to Fig. 9 , which shows a structural block diagram of a fusion positioning device provided by an exemplary embodiment of the present application, the device includes:
[0150] The determination module 901 is used to determine the satellite distribution characteristics of each satellite observed at the location of the positioning device;
[0151] The determination module 901 is further configured to determine a positioning accuracy value of a satellite positioning result based on the satellite distribution characteristics, wherein the satellite positioning result is determined based on the satellite signals of each of the satellites observed;
[0152] The determination module 901 is further configured to determine, based on the positioning accuracy value, a satellite positioning weight of the satellite positioning result in a fusion positioning process, wherein the satellite positioning weight is negatively correlated with the positioning accuracy value;
[0153] The fusion positioning module 902 is used to determine the fusion positioning result of the positioning device based on the satellite positioning weight and the satellite positioning result.
[0154] Optionally, the determining module 901 is further configured to:
[0155] Acquire satellite positioning information of each satellite observed by the positioning device, wherein the satellite positioning information includes at least one of a satellite number, a satellite altitude angle, a satellite azimuth angle, a satellite signal-to-noise ratio, and a satellite precision reduction factor;
[0156] Based on the satellite positioning information, the satellite distribution characteristics of the respective satellites observed at the location of the positioning device are determined.
[0157] Optionally, the determining module 901 is further configured to:
[0158] Based on the satellite elevation angle and the satellite azimuth angle, determining the grid position of each satellite in the satellite view, wherein the number of grids containing the grid positions in the satellite view is determined by the satellite elevation angle range and the satellite azimuth angle range;
[0159] Based on the satellite positioning information including the satellite in the grid position, determining a first sub-distribution feature of the satellite corresponding to the grid position;
[0160] A set of the first sub-distribution features corresponding to each of the grid positions is determined as the satellite distribution feature, and the number of feature values of the satellite distribution feature is determined by the number of grids.
[0161] Optionally, the determining module 901 is further configured to:
[0162] Based on the satellite positioning information of the satellites included in the grid positions, the satellites included in the grid positions are divided into different satellite systems;
[0163] determining a second sub-distribution feature of the satellite system at the grid location based on satellite positioning information of satellites of the same satellite system at the grid location;
[0164] A set of the second sub-distribution characteristics corresponding to each satellite system in the grid position is determined as the first sub-distribution characteristics of the satellite corresponding to the grid position, and the number of characteristic values of the satellite distribution characteristics is determined by the number of grids and the number of system categories of the satellite system.
[0165] Optionally, the determining module 901 is further configured to:
[0166] Based on the satellite positioning information of the satellites of the same satellite system in the grid position, at least one of the number of satellites of the satellite system in the grid position, the average satellite altitude angle, the average signal-to-noise ratio, the proportion of target satellites, and the standard deviation of satellite azimuth angles is determined, wherein the proportion of target satellites refers to the proportion of satellites whose satellite signal-to-noise ratio is greater than a signal-to-noise ratio threshold.
[0167] Optionally, the determining module 901 is further configured to:
[0168] Determine the total number of satellites of each satellite observed at the location of the positioning device from the satellite positioning information;
[0169] When the total number of satellites is less than a quantity threshold, determining the satellite positioning weight of the satellite positioning result in a fusion positioning process based on the positioning accuracy value;
[0170] The device also includes:
[0171] A determination module is used to determine the satellite positioning weight of the satellite positioning result in the fusion positioning process based on the positioning accuracy value and the total number of satellites when the total number of satellites is greater than the number threshold, and the satellite positioning weight is positively correlated with the total number of satellites.
[0172] Optionally, the determining module 901 is further configured to:
[0173] The satellite distribution characteristics are input into a positioning accuracy estimation model to obtain the positioning accuracy value output by the positioning accuracy estimation model, wherein the positioning accuracy estimation model is trained based on sample satellite distribution characteristics and sample annotated positioning accuracy values.
[0174] Optionally, the device further comprises:
[0175] An acquisition module, used to acquire the satellite distribution characteristics of the sample and the positioning accuracy value of the sample annotation;
[0176] An accuracy prediction module, used to input the sample satellite distribution characteristics into the positioning accuracy estimation model to obtain a sample predicted positioning accuracy value output by the positioning accuracy estimation model;
[0177] The training module is used to train the positioning accuracy estimation model based on the loss between the sample labeled positioning accuracy value and the sample predicted positioning accuracy value.
[0178] Optionally, the device further comprises:
[0179] The acquisition module is further used to acquire the satellite distribution characteristics and the positioning accuracy value corresponding to the fused positioning result when a negative feedback signal for the fused positioning result is received, wherein the negative feedback signal is used to indicate that the positioning error of the fused positioning result is greater than a positioning error threshold;
[0180] The training module is also used to optimize the positioning accuracy estimation model based on the satellite distribution characteristics and the positioning accuracy value.
[0181] Optionally, the determining module 901 is further configured to:
[0182] Determine a weight coefficient of the satellite positioning result under the positioning accuracy value, wherein the weight coefficient is negatively correlated with the positioning accuracy value;
[0183] Based on the weight coefficient and the positioning accuracy value, the satellite positioning weight of the satellite positioning result in the fusion positioning process is determined.
[0184] Optionally, the determining module 901 is further configured to:
[0185] Determine the positioning accuracy range in which the positioning accuracy value is located, and different positioning accuracy ranges correspond to different weight coefficients;
[0186] The weight coefficient corresponding to the positioning accuracy range is determined as the weight coefficient of the satellite positioning result under the positioning accuracy value.
[0187] Optionally, the device further comprises:
[0188] An acquisition module, used to acquire the positioning application scenario of the fused positioning result;
[0189] The division module is used to divide the positioning accuracy range based on the positioning accuracy requirements of the positioning application scenario for the fused positioning result, and different positioning application scenarios correspond to different positioning accuracy range division methods.
[0190] To sum up, in this embodiment, the satellite distribution characteristics of each satellite observed at the location of the positioning device are analyzed, and the positioning accuracy value of the satellite positioning result is determined based on the satellite distribution characteristics, so as to determine the satellite positioning weight of the satellite positioning result in the fusion positioning process based on the positioning accuracy value, so as to quantify the credibility of the satellite positioning result in the fusion positioning process; because the process of determining the satellite positioning weight is related to the satellite distribution characteristics of the satellites involved in the calculation of the satellite positioning result, and the satellite distribution characteristics will affect the accuracy of the satellite positioning result, the satellite positioning weight in the fusion positioning process is made consistent with the actual positioning error of the satellite positioning result, thereby improving the accuracy of the fusion positioning result.
[0191] It should be noted that: the device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.
[0192] Please refer to Fig.10 , which shows a schematic diagram of the structure of a computer device provided by an exemplary embodiment of the present application. The computer device can be applied to the positioning device in the above embodiment. Specifically: the computer device 1000 includes a central processing unit (CPU) 1001, a system memory 1004 including a random access memory 1002 and a read-only memory 1003, and a system bus 1005 connecting the system memory 1004 and the central processing unit 1001. The computer device 1000 also includes a basic input / output system (I / O system) 1006 that helps transmit information between various devices in the computer, and a large-capacity storage device 1007 for storing an operating system 1013, an application program 1014 and other program modules 1015.
[0193] In some embodiments, the basic input / output system 1006 includes a display 1008 for displaying information and an input device 1009 such as a mouse and a keyboard for user inputting information. The display 1008 and the input device 1009 are connected to the central processing unit 1001 through an input / output controller 1010 connected to the system bus 1005. The basic input / output system 1006 may also include an input / output controller 1010 for receiving and processing inputs from a plurality of other devices such as a keyboard, a mouse, or an electronic stylus. Similarly, the input / output controller 1010 also provides output to a display screen, a printer, or other types of output devices.
[0194] The mass storage device 1007 is connected to the central processing unit 1001 through a mass storage controller (not shown) connected to the system bus 1005. The mass storage device 1007 and its associated computer readable medium provide non-volatile storage for the computer device 1000. That is, the mass storage device 1007 may include a computer readable medium (not shown) such as a hard disk or drive.
[0195] Without loss of generality, the computer readable medium may include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer readable instructions, data structures, program modules or other data. Computer storage media include random access memory (Random Access Memory, RAM), read-only memory (Read Only Memory, ROM), flash memory or other solid-state storage technology, read-only optical disc (Compact Disc Read-Only Memory, CD-ROM), digital versatile disc (Digital Versatile Disc, DVD) or other optical storage, cassettes, magnetic tapes, disk storage or other magnetic storage devices. Of course, those skilled in the art will know that the computer storage medium is not limited to the above. The above-mentioned system memory 1004 and mass storage device 1007 can be collectively referred to as memory.
[0196] The memory stores one or more programs, and the one or more programs are configured to be executed by one or more central processing units 1001. The one or more programs include instructions for implementing the above-mentioned method. The central processing unit 1001 executes the one or more programs to implement the fusion positioning method provided by the above-mentioned various method embodiments.
[0197] According to various embodiments of the present application, the computer device 1000 can also be connected to a remote computer on a network through a network such as the Internet. That is, the computer device 1000 can be connected to the network 1011 through the network interface unit 1012 connected to the system bus 1005, or the network interface unit 1012 can be used to connect to other types of networks or remote computer systems (not shown).
[0198] The memory also includes one or more programs, which are stored in the memory. The one or more programs include a fusion positioning method performed by the positioning device in the method provided in the embodiment of the present application.
[0199] An embodiment of the present application also provides a computer-readable storage medium, which stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor to implement the fusion positioning method described in any of the above embodiments.
[0200] The embodiment of the present application provides a computer program product, which includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the fusion positioning method provided in the above aspect.
[0201] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the relevant hardware through a program, and the program can be stored in a computer-readable storage medium, which can be a computer-readable storage medium contained in the memory in the above embodiments; or it can be a computer-readable storage medium that exists independently and is not assembled into a computer device. The computer-readable storage medium stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, the at least one program, the code set or instruction set is loaded and executed by the processor to implement the method for generating a virtual-reality fusion screen described in any of the above method embodiments.
[0202] Optionally, the computer readable storage medium may include: ROM, RAM, solid state drives (SSD) or optical disks, etc. Among them, RAM may include resistance random access memory (ReRAM) and dynamic random access memory (DRAM). The serial numbers of the above embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.
[0203] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.
[0204] It should be understood that the "multiple" mentioned in this article refers to two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated with each other are in an "or" relationship. And the "first", "second", etc. mentioned in this article are used to distinguish similar objects, and are not used to limit a specific order or sequence. In addition, the step numbers described in this article only exemplify a possible execution sequence between the steps. In some other embodiments, the above steps may not be executed in the order of the numbers, such as two steps with different numbers are executed at the same time, or two steps with different numbers are executed in the opposite order to the diagram. The embodiments of the present application do not limit this.
[0205] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.
Claims
1. A fusion positioning method, characterized in that: The method comprises: Obtain satellite positioning information of each satellite observed by a positioning device, the satellite positioning information including at least one of a satellite number, a satellite altitude angle, a satellite azimuth angle, a satellite signal-to-noise ratio, and a satellite precision reduction factor; determine the grid position of each satellite in a satellite view based on the satellite altitude angle and the satellite azimuth angle, wherein the number of grids in the satellite view containing the grid position is determined by a satellite altitude angle range and a satellite azimuth angle range; determine a first sub-distribution feature of the satellite corresponding to the grid position based on the satellite positioning information containing the satellite in the grid position; determine a set of the first sub-distribution features corresponding to each of the grid positions as a satellite distribution feature, wherein the number of feature values of the satellite distribution feature is determined by the number of grids; Determining a positioning accuracy value of a satellite positioning result based on the satellite distribution characteristics, wherein the satellite positioning result is determined based on the observed satellite signals of each of the satellites; Based on the positioning accuracy value, determining a satellite positioning weight of the satellite positioning result in a fusion positioning process, wherein the satellite positioning weight is negatively correlated with the positioning accuracy value; Based on the satellite positioning weight and the satellite positioning result, a fused positioning result of the positioning device is determined.
2. The method according to claim 1, characterized in that The determining, based on the satellite positioning information of the satellite included in the grid position, a first sub-distribution feature of the satellite corresponding to the grid position includes: Based on the satellite positioning information of the satellites included in the grid positions, the satellites included in the grid positions are divided into different satellite systems; determining a second sub-distribution feature of the satellite system at the grid location based on satellite positioning information of satellites of the same satellite system at the grid location; A set of the second sub-distribution characteristics corresponding to each satellite system in the grid position is determined as the first sub-distribution characteristics of the satellite corresponding to the grid position, and the number of characteristic values of the satellite distribution characteristics is determined by the number of grids and the number of system categories of the satellite system.
3. The method according to claim 2, characterized in that The determining, based on satellite positioning information of satellites of the same satellite system at the grid location, a second sub-distribution feature of the satellite system at the grid location comprises: Based on the satellite positioning information of the satellites of the same satellite system in the grid position, at least one of the number of satellites of the satellite system in the grid position, the average satellite altitude angle, the average signal-to-noise ratio, the proportion of target satellites, and the standard deviation of satellite azimuth angles is determined, wherein the proportion of target satellites refers to the proportion of satellites whose satellite signal-to-noise ratio is greater than a signal-to-noise ratio threshold.
4. The method according to claim 1, characterized in that: The determining, based on the positioning accuracy value, a satellite positioning weight of the satellite positioning result in a fusion positioning process includes: Determine the total number of satellites of each satellite observed at the location of the positioning device from the satellite positioning information; When the total number of satellites is less than a quantity threshold, determining the satellite positioning weight of the satellite positioning result in a fusion positioning process based on the positioning accuracy value; The method further comprises: When the total number of satellites is greater than the quantity threshold, the satellite positioning weight of the satellite positioning result in the fusion positioning process is determined based on the positioning accuracy value and the total number of satellites, and the satellite positioning weight is positively correlated with the total number of satellites.
5. The method according to any one of claims 1 to 4, characterized in that: The determining of the positioning accuracy value of the satellite positioning result based on the satellite distribution characteristics includes: The satellite distribution characteristics are input into a positioning accuracy estimation model to obtain the positioning accuracy value output by the positioning accuracy estimation model, wherein the positioning accuracy estimation model is trained based on sample satellite distribution characteristics and sample annotated positioning accuracy values.
6. The method according to claim 5, characterized in that The method further comprises: Obtaining the satellite distribution characteristics of the sample and the positioning accuracy value of the sample annotation; Inputting the sample satellite distribution characteristics into the positioning accuracy estimation model to obtain a sample predicted positioning accuracy value output by the positioning accuracy estimation model; The positioning accuracy estimation model is trained based on the loss between the sample labeled positioning accuracy value and the sample predicted positioning accuracy value.
7. The method according to claim 5, characterized in that The method further comprises: In the case of receiving a negative feedback signal for the fused positioning result, obtaining the satellite distribution feature and the positioning accuracy value corresponding to the fused positioning result, wherein the negative feedback signal is used to indicate that the positioning error of the fused positioning result is greater than a positioning error threshold; Based on the satellite distribution characteristics and the positioning accuracy value, the positioning accuracy estimation model is optimized and trained.
8. The method according to any one of claims 1 to 4, characterized in that: The determining, based on the positioning accuracy value, a satellite positioning weight of the satellite positioning result in a fusion positioning process includes: Determine a weight coefficient of the satellite positioning result under the positioning accuracy value, wherein the weight coefficient is negatively correlated with the positioning accuracy value; Based on the weight coefficient and the positioning accuracy value, the satellite positioning weight of the satellite positioning result in the fusion positioning process is determined.
9. The method according to claim 8, characterized in that The determining of the weight coefficient of the satellite positioning result under the positioning accuracy value includes: Determine the positioning accuracy range in which the positioning accuracy value is located, and different positioning accuracy ranges correspond to different weight coefficients; The weight coefficient corresponding to the positioning accuracy range is determined as the weight coefficient of the satellite positioning result under the positioning accuracy value.
10. The method according to claim 9, characterized in that The method further comprises: Obtaining a positioning application scenario of the fused positioning result; The positioning accuracy range is divided based on the positioning application scenario's requirements for the fused positioning result, and different positioning application scenarios correspond to different positioning accuracy range division methods.
11. A fusion positioning device, characterized in that: The device comprises: A determination module is used to obtain satellite positioning information of each satellite observed by a positioning device, wherein the satellite positioning information includes at least one of a satellite number, a satellite altitude angle, a satellite azimuth angle, a satellite signal-to-noise ratio, and a satellite precision reduction factor; based on the satellite altitude angle and the satellite azimuth angle, determine the grid position of each satellite in the satellite view, wherein the number of grids in the satellite view containing the grid position is determined by the satellite altitude angle range and the satellite azimuth angle range; based on the satellite positioning information containing the satellite in the grid position, determine a first sub-distribution feature of the satellite corresponding to the grid position; determine a set of the first sub-distribution features corresponding to each of the grid positions as a satellite distribution feature, wherein the number of feature values of the satellite distribution feature is determined by the number of grids; The determination module is further used to determine a positioning accuracy value of a satellite positioning result based on the satellite distribution characteristics, wherein the satellite positioning result is determined based on the observed satellite signals of each satellite; The determination module is further configured to determine, based on the positioning accuracy value, a satellite positioning weight of the satellite positioning result in a fusion positioning process, wherein the satellite positioning weight is negatively correlated with the positioning accuracy value; The fusion positioning module is used to determine the fusion positioning result of the positioning device based on the satellite positioning weight and the satellite positioning result.
12. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores at least one program, and the at least one program is loaded and executed by the processor to implement the fusion positioning method according to any one of claims 1 to 10.
13. A computer-readable storage medium, characterized in that: The readable storage medium stores at least one program, and the at least one program is loaded and executed by the processor to implement the fusion positioning method according to any one of claims 1 to 10.
14. A computer program product, characterized in that The computer program product includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to implement the fusion positioning method as described in any one of claims 1 to 10.
