A method for predicting flight positioning deviation of terminal logistics UAV route planning in urban low-altitude scenarios
By constructing a spatiotemporal relationship model of the mathematical characteristics of urban building distribution curves and flight positioning deviations, the GTWR method is used to solve the problem of difficult prediction of route deviations on small and light drones, and the route deviations without sensors and ground facilities are achieved The forecast meets the demand for rapid development of low-altitude economy and improves route safety and operational efficiency.
Patent Information
- Application Number
- CN202410384035.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-01
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-04-01
AI Technical Summary
The existing technology is difficult to effectively predict the flight positioning deviation of the planned route of urban low-altitude logistics drones. Especially when installing sensors on small and light drones, it will reduce battery life, increase ground infrastructure, and increase cost, and field verification sum Real-time monitoring cannot meet the needs of rapid development of low-altitude economy.
By constructing a spatiotemporal relationship model between the mathematical characteristics of urban buildings distribution curves and flight positioning deviations, using the spatiotemporal geographic weighted regression (GTWR) method, the planned route historical data of the terminal logistics drone and the mathematical characteristics of the distribution curves of surrounding buildings are used to use the spatiotemporal geographic weighted regression (GTWR) method. Data predicts route flight positioning deviations and realizes route deviation prediction without sensors and ground infrastructure.
Without adding drone sensors and ground facilities, ensure the safety of the newly planned routes of terminal logistics drones, meet the needs of rapid development of low-altitude economy, improve the accuracy of route flight positioning, and reduce operating costs.
Smart Images

Figure CN118376244B_ABST
Abstract
Description
[0001] The present invention relates to a method for predicting the flight positioning deviation of a planned route of a terminal logistics UAV in an urban low-altitude scene. Specifically, the flight positioning deviation historical data of the terminal logistics UAV in the urban low-altitude scene at each equally spaced position and the mathematical characteristic data of the distribution curve of surrounding buildings are first obtained, and then a relationship model between the mathematical characteristics of the distribution curve of urban buildings and the flight positioning deviation is constructed by using a spatiotemporal geographic weighted regression (GTWR) method. Finally, based on the model, the flight positioning deviation of a newly planned route of the terminal logistics UAV is predicted. At the same time, new ideas can be provided for the enhancement, fusion and other positioning technologies of micro-light and small UAVs. Background Art
[0002] With the development of drone technology and the proposal of the Central Economic Work Conference in 2023 to build a number of strategic emerging industries such as the low-altitude economy, the drone logistics industry has shown huge market potential. Among them, the emergence of terminal logistics drone application scenarios provides an effective solution to the problem of the "last mile" of goods delivery in remote areas and urban scenarios with high timeliness requirements. On the one hand, most terminal logistics drones are light and small, with an operating altitude below 120m, that is, the operating area (space) of terminal logistics drones is mostly below the city skyline. At the same time, the positioning of light and small drones often relies only on satellite positioning methods such as Beidou and GPS to achieve positioning, but due to the obstruction of high-rise buildings in the city, the accuracy of satellite positioning has spatial differences (heterogeneity); on the other hand, due to the different heights and distributions (three-dimensional spatial forms) of urban buildings, the meteorological conditions such as wind direction, wind speed, and temperature in different areas of the city also have spatial differences.
[0003] At present, in order to ensure the safety of the planned routes of UAVs, the safety of the actual operation of the planned routes of UAVs is mainly ensured by improving the positioning accuracy (such as multi-source data fusion positioning, adding RTK equipment, cooperative target perception integration, etc.) and combining the field verification flight before operation with real-time monitoring during operation. Among them, the former relies on the sensor equipment carried by the UAV itself and requires the effective layout of low-altitude meteorological stations, communication navigation and monitoring equipment, mainly for medium and large UAVs. On the one hand, this method increases the cost of infrastructure investment. At the same time, the installation of sensors on UAVs will undoubtedly reduce the endurance of UAVs, and the economy is poor; the latter can be achieved through field verification flights without increasing infrastructure investment and reducing the endurance of UAVs. It is mainly for micro-light UAVs, but considering the density of low-altitude UAV routes in cities in the later period and the exponential growth of the number of routes, on the one hand, the field verification flight before operation cannot meet the needs of the future urban low-altitude logistics UAV market, and on the other hand, real-time monitoring during operation will undoubtedly increase operating costs and the work pressure of UAV controllers.
[0004] In summary, in order to ensure the operational safety of planned routes for terminal logistics drones in urban low-altitude scenarios, the key point is to improve the positioning accuracy of terminal logistics drones or to effectively predict the flight positioning deviations at each location of the planned route. The former is not practical for micro-light terminal logistics drones by increasing airborne sensors and ground infrastructure (sensors cannot be installed or sensors can be installed but the endurance is seriously affected), while the latter is limited by the fact that there are many factors that affect the flight positioning deviation. There is currently no effective way to predict the flight positioning deviation. For example, there are spatial differences (heterogeneity) in positioning accuracy, wind direction, wind force, temperature, etc. in different areas of urban low altitude. Therefore, in order to ensure the safety of planned route operations for terminal logistics drones (mainly micro-light drones) in urban low-altitude scenarios, the main method is to conduct field verification flights for each planned route before operation and real-time monitoring during operation, which cannot meet the needs of the rapid development of the low-altitude economy in the future. Summary of the invention
[0005] In summary, the existing technologies and solutions related to the prediction of flight positioning deviation in UAV route planning mainly have the following shortcomings:
[0006] (1) Since it is impossible to add airborne sensors to micro-light UAVs or the addition of sensors will greatly reduce the UAV's endurance, this method is not suitable for improving the prediction of flight positioning deviation of terminal logistics UAVs in route planning. That is, the method of reducing flight positioning deviation by adding sensors is not suitable for micro-light UAVs;
[0007] (2) Since adding ground infrastructure will greatly increase local fiscal investment, it is unable to meet the market demand for terminal logistics drones and has poor economic efficiency, that is, adding ground communication, navigation and surveillance (CNS) facilities lacks economic efficiency;
[0008] (3) At present, the main way to ensure the safety of terminal logistics drone operations is to conduct field verification flights on each planned route before operation and real-time monitoring during operation. On the one hand, this method cannot meet the needs of the rapid development of the low-altitude economy and achieve the rapid promotion of terminal logistics drones. On the other hand, it increases the workload of drone remote controllers. In other words, manual pre-operation surveys and real-time monitoring during operation cannot meet the actual needs of the rapid development of the low-altitude economy.
[0009] In view of the above shortcomings, the present invention starts from the perspective of constructing the spatiotemporal relationship between the mathematical characteristics of the urban building distribution curve and the flight positioning deviation, and with the help of the spatiotemporal geographic weighted regression (GTWR) method in geography, constructs a relationship model between the mathematical characteristics of the urban building distribution curve and the flight positioning deviation, thereby proposing a method for predicting the flight positioning deviation of the terminal logistics UAV planning route in urban low-altitude scenes.
[0010] The basic idea of the present invention is to obtain the historical data of the planned route of the terminal logistics UAV and the mathematical characteristic data of the distribution curve of the surrounding buildings, and to construct a relationship model between the mathematical characteristics of the urban building distribution curve and the flight positioning deviation based on the GTWR method, so as to complete the prediction of the flight positioning deviation of the newly planned route of the terminal logistics UAV in the urban low-altitude scene at any location, and ensure the safety of the newly planned route of the terminal logistics UAV without adding UAV sensors and ground infrastructure.
[0011] The specific technical solution adopted by the present invention is as follows:
[0012] A method for predicting the flight positioning deviation of a terminal logistics UAV in a low-altitude urban scene, the specific steps are as follows:
[0013] S1, obtaining the historical data of flight positioning deviation at each equally spaced position according to the planned route and the historical data of the actual operation route of the terminal logistics UAV, where the interval size is the maximum value of the historical data of flight positioning deviation;
[0014] S2, oblique photography modeling and individualization of buildings within the three-dimensional buffer zone of the planned route of the terminal logistics drone, and obtaining building data containing longitude, latitude, total floor height, number of floors, digital elevation model (DEM) and other information around each equally spaced position, where the radius of the three-dimensional buffer zone is the maximum value of the historical data of flight positioning deviation;
[0015] S3, based on UrbanTexture v1.0 software and the data of surrounding buildings at each equally spaced position, obtain the mathematical characteristic data of the distribution curve of the surrounding buildings at each equally spaced position;
[0016] S4, based on the historical data of flight positioning deviations at each equally spaced position and the mathematical characteristic data of the distribution curves of the surrounding buildings, the spatiotemporal relationship between the mathematical characteristics of the distribution curves of the surrounding buildings at each equally spaced position and the flight positioning deviations is analyzed by using the Geographical and Temporal Weighted Regression (GTWR) method, and a relationship model between the mathematical characteristics of the distribution curves of the surrounding buildings and the flight positioning deviations is constructed;
[0017] S5, based on the relationship model between the mathematical characteristics of the building distribution curve and the flight positioning deviation, the building data and distribution curve characteristic data including longitude, latitude, total floor height, number of floors, DEM and other information of the surrounding buildings at each equally spaced position of the newly planned route of the terminal logistics UAV, so as to realize the prediction of the flight positioning deviation of the planned route of the terminal logistics UAV in the urban low-altitude scene.
[0018] Furthermore, in step S1, according to the planned route of the terminal logistics UAV and the historical data of the actual operation route, the three-dimensional vector set {V1, V2, ..., V n}, where the three-dimensional vector of the flight positioning deviation at each equally spaced position is V n =[x n -x n ',y n -y n ',z n -z n '],(x n ,y n ,z n )、(x n ',y n ',z n ') respectively represent the three-dimensional coordinates of the planned route and the actual operation route historical data of the terminal logistics drone at the nth equally spaced position; the interval size d is the maximum deviation between the planned route and the actual operation route historical data of the terminal logistics drone, that is, d = max{|x n -x n '|,|y n -y n '|,|z n -z n '|}.
[0019] Furthermore, in step S2, firstly, a drone equipped with a multi-view camera is used to take aerial photos of the urban buildings included in the three-dimensional buffer zone of the historical route of the terminal logistics drone, and oblique photography modeling is performed using Context Capture software to obtain oblique photography model data and DEM data of urban buildings around the historical route of the terminal logistics drone; then the oblique photography model data and DEM data around the three-dimensional buffer zones at n equally spaced positions (the radius of the three-dimensional buffer zone is d) are imported into SuperMap iServer, SVSModeler, OSketch and other software for individualization operations, and .CSV format data of information such as longitude (plane geometric center), latitude (plane geometric center), total floor height, number of floors, DEM height value, etc. of the buildings around the n equally spaced positions are obtained.
[0020] Furthermore, in step S3, based on UrbanTexture v1.0 software and the .CSV format data of the surrounding buildings at each equally spaced position, the .CSV format data of the surrounding urban buildings at n equally spaced positions obtained in step S2, which includes information such as longitude (plane geometric center), latitude (plane geometric center), total floor height, number of floors, and DEM height value, is imported into UrbanTexture v1.0 software to extract mathematical features of the distribution curve of the surrounding buildings at n equally spaced positions (software download address: https: / / www.urbancomp.net / archives / urban-texture-v10-3d-urban-texture-computing-software-based-on-improved-rdf), thereby obtaining the mathematical feature data {CVD} of the distribution curve of the surrounding buildings at each equally spaced position. n , B n , Sh n , Sk n , K n , FP n , M.P. n , FPA n , MPA n , Tg n}, where CV, B, Sh, Sk, K, FP, MP, FPA, MPA, and Tg are parameters that describe the mathematical characteristics of the building distribution curve (reference: Qingfeng Guan, Yao Yao, Teng Ma, et al (2021): A 3D Urban Texture Model and Its Relationship with Urban Land Surface Temper ature, Annals of the American Association of Geographers, DOI: 10.1080 / 24694452.2021.1972790).
[0021] Furthermore, in step S4, based on the historical data V of the flight positioning deviation of the terminal logistics drone at each equally spaced position obtained in step S1, n =(x n -x n ',y n -y n ',z n -z n ') and the distribution curve mathematical characteristic data {CV n , B n , Shn , Sk n , K n , FP n , M.P. n , FPA n , MPA n , Tg n}, using the spatiotemporal geographic weighted regression (GTWR) method, the spatiotemporal relationship between the mathematical characteristics of the building distribution curve around each equally spaced position and the flight positioning deviation is analyzed, and a relationship model between the mathematical characteristics of the urban building distribution curve and the flight positioning deviation is constructed.
[0022] Furthermore, in step S5, based on the relationship model between the mathematical characteristics of the building distribution curve and the flight positioning deviation obtained in step S4, by performing oblique photography modeling and singulation of the buildings around the newly planned route of the terminal logistics UAV in step S2 and extracting the mathematical characteristics of the distribution curve in step S3, the predicted value of the flight positioning deviation at each equally spaced position of the newly planned route can be obtained, thereby realizing the prediction of the flight positioning deviation of the planned route of the terminal logistics UAV in the urban low-altitude scene.
[0023] Technical features and beneficial effects of the present invention:
[0024] 1. Starting from the perspective of constructing the spatiotemporal relationship between the mathematical characteristics of the urban building distribution curve and the flight positioning deviation, the present invention uses the spatiotemporal geographic weighted regression (GTWR) method in geography to construct a relationship model between the mathematical characteristics of the urban building distribution curve and the flight positioning deviation, thereby proposing a method for predicting the flight positioning deviation of the terminal logistics drone planning route in the urban low-altitude scene;
[0025] 2. The present invention constructs the relationship between the mathematical characteristics of the building distribution curve and the flight positioning deviation. Since the mathematical characteristics of the three-dimensional spatial morphology curve of the building distribution in different areas of the urban low-altitude scene (i.e., the three-dimensional spatial morphology of the building) are related to the wind direction, wind speed, temperature and other factors that affect the flight positioning deviation of the terminal logistics UAV in the area, it is only necessary to know the three-dimensional spatial morphology of the buildings around the newly planned route of the terminal logistics UAV to realize the prediction of the flight positioning deviation. Without adding UAV sensors and ground infrastructure, the safety of the newly planned route of the terminal logistics UAV is ensured, and the needs of the rapid development of new low-altitude economic application scenarios such as terminal logistics UAVs in the future are met. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] Figure 1 It is a flow chart of the method for predicting the flight positioning deviation of the terminal logistics UAV planning route in the urban low-altitude scene according to the present invention. DETAILED DESCRIPTION
[0027] The present invention designs a method for predicting the flight positioning deviation of the planned route of the terminal logistics UAV in the urban low-altitude scene. Figure 1 As shown in the figure, the technical process covers five steps: obtaining the historical data of flight positioning deviation at each equally spaced position, obtaining building data containing various information, obtaining the mathematical characteristic data of the building distribution curve around each equally spaced position, constructing the relationship model between the mathematical characteristics of the building distribution curve and the flight positioning deviation, and predicting the flight positioning deviation of the terminal logistics drone planning route in the urban low-altitude scene. The specific steps are as follows:
[0028] Step 1: Obtain historical data of flight positioning deviations at equally spaced locations
[0029] Required data: Historical data on planned routes of terminal logistics drones and historical data on actual operating routes of terminal logistics drones.
[0030] First, the maximum value of the deviation between the planned route of the terminal logistics drone and the historical data of the actual operation route is obtained, that is, d = max{|x n -x n '|,|y n -y n '|,|z n -z n '|}, and then use this value d as the interval size of the sparse data to calculate and obtain the three-dimensional vector set of flight positioning deviation historical data {V1, V2, ..., V n}, where the three-dimensional vector of the flight positioning deviation at each equally spaced position is V n =[x n -x n ',y n -y n ',z n -z n '],(x n ,y n ,z n )、(x n ',y n ',z n ') respectively represent the three-dimensional coordinates of the planned route and the historical data of the actual operation route of the terminal logistics drone at the nth equally spaced position.
[0031] Step 2: Obtain building data containing various information
[0032] Required data: Multi-perspective drone aerial images of urban buildings contained in the three-dimensional buffer zone of the terminal logistics drone’s historical route, and three evenly distributed control point data.
[0033] Required tools: Context Capture software, SuperMap iServer (or SVSModeler or OSketch, etc.) monomer software.
[0034] Firstly, a drone equipped with a multi-view camera was used to take aerial photos of the urban buildings included in the three-dimensional buffer zone of the terminal logistics drone's historical route. Then, three control point data puncture, aerial triangulation, and reconstruction were performed in the Context Capture software to obtain the oblique photography model data and DEM data of the urban buildings around the terminal logistics drone's historical route. Then, the obtained oblique photography model data and DEM data were imported into SuperMap iServer, SVSModeler, OSketch and other software for monomer operation to obtain the longitude X of the surrounding buildings at n equally spaced positions. n (plane geometric center), dimension Y n (plane geometric center), total floor height H n 、Number of floors C n 、DEM height value h n CSV format data with other information
[0035] Step 3: Obtain mathematical characteristic data of the distribution curve of buildings around each equally spaced location
[0036] Required data: contains longitude X n (plane geometric center), dimension Y n (plane geometric center), total floor height H n 、Number of floors C n 、DEM height value h n Building data with various information.
[0037] Tools required: UrbanTexture v1.0 software.
[0038] First, the CSV format data of urban buildings around n equally spaced locations obtained in the second step, including longitude (plane geometric center), latitude (plane geometric center), total floor height, number of floors, DEM height value, etc., was imported into the UrbanTexture v1.0 software to extract the mathematical features of the distribution curve of the buildings around n equally spaced locations (software download address: https: / / www.urbancomp.net / archives / urban-texture-v10-3d-urban-texture-computing-software-based-on-improved-rdf), so as to obtain the mathematical feature data of the distribution curve of the buildings around each equally spaced location {CV n , Bn , Sh n , Sk n , K n , FP n , M.P. n , FPA n , MPA n , Tg n}, where CV, B, Sh, Sk, K, FP, MP, FPA, MPA, and Tg are parameters describing the mathematical characteristics of the building distribution curve (reference: Qingfeng Guan, Yao Yao, Teng Ma, et al (2021): A 3D Urban Texture Model and Its Relationship with Urban Land Surface Temperature, Annals of the American Association of Geographers, DOI: 10.1080 / 24694452.2021.1972790), and the calculation logic is as follows:
[0039]
[0040] Step 4: Construct a relationship model between the mathematical characteristics of the building distribution curve and the flight positioning deviation
[0041] Required data: mathematical characteristic data of the distribution curve of buildings around each equally spaced position, and historical data of flight positioning deviation at each equally spaced position.
[0042] Tools required: ArcGIS 10.X software, GTWR Beta 1.0 script.
[0043] First, the GTWR Beta 1.0 script was installed in ArcGIS 10.X (download address: http: / / www.grm.cuhk.edu.hk / ~huangbo / GTWR / GTWR_AddIn.rar). The spatial-temporal geographic weighted regression (GTWR) method was used to analyze the mathematical characteristic data of the distribution curve of buildings around each equally spaced position after z-score standardization and the historical data of flight positioning deviation at each equally spaced position to obtain U nk = the average of the regression coefficients of each parameter (dependent variable) {CV, B, Sh, Sk, K, FP, MP, FPA, MPA, Tg} Use the following formula to calculate:
[0044]
[0045] Where Vn is the three-dimensional vector of historical data of flight positioning deviation at the nth equally spaced position, i.e., the dependent variable, where V n =[x n -x n ',y n -y n ',z n -z n '],(x n ,y n ,z n )、(x n ',y n ',z n ') respectively represent the three-dimensional coordinates of the planned route and the historical data of the actual operation route of the terminal logistics drone at the nth equally spaced position; β0 is the intercept; (x n ,y n ,z n ,t n ) is the longitude and latitude and time of the planned path of the terminal logistics drone at each equally spaced position; β k (x n ,y n ,z n ,t n ) is the fitting coefficient of the kth independent variable at the nth equally spaced position; U nk is the value of the kth independent variable at the nth equally spaced position, where U nk ={CV,B,Sh,Sk,K,FP,MP,FPA,MPA,Tg};ε n is a random error.
[0046] Step 5: Predict flight positioning deviations of terminal logistics drones in low-altitude urban scenarios
[0047] Required data: Newly planned route data for terminal logistics drones.
[0048] Based on the relationship model between the mathematical characteristics of the building distribution curve and the flight positioning deviation obtained in the fourth step, by performing the second step of oblique photography modeling and singulation of the buildings around the newly planned route of the terminal logistics UAV and extracting the mathematical characteristics of the distribution curve in the third step, the predicted values of the flight positioning deviation at each equally spaced position of the newly planned route can be obtained. That is, the predicted value of the flight positioning deviation at any position can be obtained through the mathematical characteristics of the building distribution curve around the newly planned route of the terminal logistics UAV in any urban low-altitude scene, thereby realizing the prediction of the flight positioning deviation of the planned route of the terminal logistics UAV in the urban low-altitude scene.
Claims
1. A method for predicting the flight positioning deviation of a terminal logistics UAV in an urban low-altitude scenario, characterized in that: The specific steps are as follows: S1, obtaining the historical data of flight positioning deviation at each equally spaced position according to the planned route and the historical data of the actual operation route of the terminal logistics UAV, where the interval size is the maximum value of the historical data of flight positioning deviation; S2, oblique photography modeling and individualization of buildings within the three-dimensional buffer zone of the planned route of the terminal logistics drone, and obtaining building data containing longitude, latitude, total floor height, number of floors, and digital elevation model information around each equally spaced position, where the radius of the three-dimensional buffer zone is the maximum value of the historical data of flight positioning deviation; S3, based on UrbanTexturev1.0 software and the data of surrounding buildings at each equally spaced position, obtain the mathematical characteristic data of the distribution curve of the surrounding buildings at each equally spaced position; S4, based on the historical data of flight positioning deviations at each equally spaced position and the mathematical characteristic data of the distribution curves of the surrounding buildings, the spatiotemporal relationship between the mathematical characteristics of the distribution curves of the surrounding buildings at each equally spaced position and the flight positioning deviations is analyzed by using the spatiotemporal geographic weighted regression method, and a relationship model between the mathematical characteristics of the distribution curves of the buildings and the flight positioning deviations is constructed; S5, based on the relationship model between the mathematical characteristics of the building distribution curve and the flight positioning deviation, the building data and distribution curve characteristic data including longitude, latitude, total floor height, number of floors, DEM information of the surrounding buildings at each equally spaced position of the new planned route of the terminal logistics UAV, so as to realize the prediction of the flight positioning deviation of the planned route of the terminal logistics UAV in the urban low-altitude scene.
2. According to claim 1, a method for predicting the flight positioning deviation of the planned route of the terminal logistics UAV in the urban low-altitude scene is characterized in that: In step S1, according to the planned route of the terminal logistics UAV and the historical data of the actual operation route, the three-dimensional vector set {V1, V2, ..., V n }, where the three-dimensional vector of the flight positioning deviation at each equally spaced position is V n =[x n -x n ',y n -y n ',z n -z n '],(x n ,y n ,z n )、(x n ',y n ',z n ') respectively represent the three-dimensional coordinates of the planned route and the actual operation route historical data of the terminal logistics drone at the nth equally spaced position; the interval size d is the maximum deviation between the planned route and the actual operation route historical data of the terminal logistics drone, that is, d = max{|x n -x n '|,|y n -y n '|,|z n -z n '|}.
3. According to claim 1, a method for predicting the flight positioning deviation of a terminal logistics drone in an urban low-altitude scene, characterized in that: In the step S2, firstly, a drone equipped with a multi-view camera is used to take aerial photos of the urban buildings included in the three-dimensional buffer zone of the historical route of the terminal logistics drone, and oblique photography modeling is performed using ContextCapture software to obtain oblique photography model data and DEM data of urban buildings around the historical route of the terminal logistics drone; then n equally spaced three-dimensional buffer zones with a radius of d are imported into SuperMapiServer, SVSModeler, and OSketch software for individualization operations to obtain .CSV format data of the plane geometric center longitude, plane geometric center dimension, total floor height, number of floors, and DEM height value information of the surrounding buildings at n equally spaced positions.
4. According to claim 1, a method for predicting the flight positioning deviation of a terminal logistics drone in an urban low-altitude scene, characterized in that: In the step S3, based on the UrbanTexture v1.0 software and the CSV format data of the surrounding buildings at each equally spaced position, the CSV format data of the surrounding urban buildings at the n equally spaced positions obtained in step S2, which includes the plane geometric center longitude, plane geometric center dimension, total floor height, number of floors, and DEM height value information, is imported into the UrbanTexture v1.0 software to extract the mathematical features of the distribution curve of the surrounding buildings at the n equally spaced positions, thereby obtaining the mathematical feature data {CV n , B n , Sh n , Sk n , K n , FP n , M.P. n , FPA n , MPA n , Tg n }, where CV, B, Sh, Sk, K, FP, MP, FPA, MPA, and Tg are parameters that describe the mathematical characteristics of the building distribution curve.
5. According to claim 1, a method for predicting the flight positioning deviation of a terminal logistics drone in an urban low-altitude scene, characterized in that: In step S4, based on the historical data v of the flight positioning deviation of the terminal logistics drone at each equally spaced position obtained in step S1, n =(x n -x n ',y n -y n ',z n -z n ') and the distribution curve mathematical characteristic data {CV n , B n , Sh n , Sk n , K n , FP n , M.P. n , FPA n , MPA n , Tg n }, using the spatiotemporal geographic weighted regression method, the spatiotemporal relationship between the mathematical characteristics of the building distribution curve around each equally spaced position and the flight positioning deviation is analyzed, and a relationship model between the mathematical characteristics of the urban building distribution curve and the flight positioning deviation is constructed.
6. According to claim 1, a method for predicting the flight positioning deviation of the terminal logistics UAV planning route in the urban low-altitude scene is characterized in that: In step S5, based on the relationship model between the mathematical characteristics of the building distribution curve and the flight positioning deviation obtained in step S4, the buildings around the newly planned route of the terminal logistics UAV are subjected to oblique photography modeling and singulation in step S2 and the mathematical characteristics of the distribution curve are extracted in step S3, so as to obtain the predicted values of the flight positioning deviation at each equally spaced position of the newly planned route, thereby realizing the prediction of the flight positioning deviation of the planned route of the terminal logistics UAV in the urban low-altitude scene.
