Low-altitude manned vertical take-off and landing site selection method and system for urban congestion resolution requirements

Abstract

The application discloses a low-load manned vertical take-off and landing site selection method and system for urban congestion solving needs. The method comprises the following steps: after obtaining and standardizing multi-source spatial data, performing rigid filtering on original candidate points based on urban space constraints to obtain a feasible candidate point set; constructing a deterministic multi-index feature of demand response, cost agent and environment agent for each feasible candidate point, and mapping the real walking connection distance to the rail joint operation score through the shortest path calculation based on the walking road network; then, according to the preset multi-target weight, the comprehensive score is obtained by weighted summation, and after stable sorting, a specified number of site selection results are sequentially screened out under the constraint of the minimum station spacing, and the site selection results are outputted with the context comparison and review information. The application uniformly processes the space constraints, evaluates the connection based on the real road network, supports the multi-target weight configuration and sensitivity review, and realizes the scientific site selection of the low-load manned vertical take-off and landing field which is compliant, real, traceable and interpretable.

Description

Technical Field

[0001] This invention relates to low-altitude passenger transport infrastructure planning, urban integrated transportation spatial analysis and geographic information computing technology, and in particular to a method and system for selecting low-altitude passenger vertical take-off and landing sites to meet the needs of urban congestion relief. Background Technology

[0002] Existing vertical take-off and landing (VTOL) fields or helicopter landing facilities planning typically employs geographic information system (GIS) spatial overlay, static suitability evaluation, cluster analysis, or maximum coverage models to determine candidate sites. The basic approach is to first exclude certain areas based on administrative boundaries, airport perimeter restrictions, or land availability, and then rank or cluster the remaining sites based on travel demand, road congestion characteristics, construction costs, or accessibility to public transportation.

[0003] In evaluating public transportation connections, existing schemes often use Euclidean distance, straight buffer zone coverage, or nearest neighbor distance between candidate points and rail stations as indicators. These indicators are easy to calculate, but they are difficult to reflect factors such as detours on actual pedestrian routes, road network discontinuities, expressway obstructions, cross-river conditions, and station access routes.

[0004] Existing technologies generally include the following process: First, a set of candidate points in the form of plots, grid centers, or points of interest is generated in the study area, and filtered by administrative boundaries or partial restrictions; second, suitability evaluation values ​​are constructed based on indicators such as travel demand, road congestion, commercial density, land price level, environmental sensitivity, or distance to transportation hubs; third, candidate layouts are generated through weighted scoring, clustering algorithms, or coverage models; finally, the proximity relationship between the selected site and rail stations or other transportation facilities is statistically analyzed using straight-line distance. Although the above process can output a preliminary layout, candidate data, constraint data, indicator calculation, and result evaluation usually lack a unified traceability mechanism; especially in terms of rail connections, straight-line distance is not equivalent to the actual walking connection path that passengers can complete.

[0005] The main drawbacks of existing technologies are: First, in existing technologies, spatial constraint processing and evaluation calculations are often performed separately. If administrative boundaries, airport restricted areas, or other unselectable areas are not uniformly applied to the candidate point base, it may result in unfeasible points being included in the final plan. Second, existing technologies rely solely on Euclidean distance to determine rail connectivity, which can easily misclassify points that are close in a straight line but are actually inaccessible or require a detour on actual walking paths as convenient connection points. Third, there are conflicts among multiple objectives such as demand, cost, environment, and rail connectivity. A single objective or an uninterpretable comprehensive score cannot provide a clear basis for planning trade-offs. Fourth, existing plans typically lack input snapshots, parameter recording, and sensitivity review mechanisms, making it difficult to repeatedly verify and audit different plans.

[0006] It should be noted that the information disclosed in the background section above is only for understanding the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0007] The main objective of this invention is to overcome the deficiencies in the aforementioned background technology and provide a method and system for selecting low-altitude manned vertical take-off and landing sites to meet the needs of urban congestion relief.

[0008] To achieve the above objectives, the present invention adopts the following technical solution: A method for selecting a low-altitude manned vertical take-off and landing site to address urban congestion relief needs includes the following steps: S1. Acquire multi-source spatial data and perform standardization processing. The multi-source spatial data includes at least candidate point bases, urban spatial constraints, rail station data, pedestrian network data, and spatial proxy element data. S2. Based on the urban spatial constraints, perform rigid spatial constraint filtering on the original candidate point set to exclude candidate points located outside the urban administrative boundary or falling inside or on the boundary of the no-fly zone, thus obtaining a feasible candidate point set. S3. For each candidate point in the set of feasible candidate points, construct a deterministic multi-indicator feature that includes at least demand response features, cost proxy penalty features, and environmental proxy penalty features; S4. Based on the pedestrian network data, establish the matching relationship between candidate points and rail stations to pedestrian network nodes, calculate the actual walking connection distance from candidate points to the nearest rail station through shortest path search, and map it to rail intermodal transport score according to a preset connection threshold. S5. Based on the preset multi-objective weights, the demand response characteristics, cost proxy penalty characteristics, environmental proxy penalty characteristics, and rail intermodal transport scores of each candidate point are weighted and summed to obtain a comprehensive evaluation score; the candidate points are stably sorted according to their scores, and under the preset minimum station spacing constraint, a specified number of candidate points that meet the spacing conditions are sequentially selected as the site selection results. S6. Output the site selection results and generate scenario comparison and parameter verification information including evaluation indicators, spatial layout and connection effect.

[0009] A low-altitude manned vertical take-off and landing site selection system for addressing urban congestion relief needs includes: The data input and standardization module is used to receive and uniformly process multi-source spatial data. The spatial rigid constraint filtering module, connected to the data input and standardization module, is used to filter out infeasible points from the original candidate point set according to urban spatial constraints and generate a feasible candidate point set. A multi-indicator feature construction module, connected to the spatial rigid constraint filtering module, is used to calculate deterministic features for each point in the feasible candidate point set, including at least demand response, cost proxy, and environmental proxy. The pedestrian network connection evaluation module is connected to the data input and standardization module and the spatial rigid constraint filtering module, respectively, and is used to calculate the actual pedestrian connection distance of candidate points based on pedestrian network data and generate rail intermodal transport scores. The multi-objective site selection decision module is connected to the multi-index feature construction module and the pedestrian road network connection evaluation module, respectively. It is used to calculate the comprehensive evaluation score according to the preset weights and filter and output the final site selection scheme under the minimum station spacing constraint. The results output and verification module is connected to the multi-objective location decision module and is used to output the location results and generate scenario comparison and parameter verification reports.

[0010] The present invention has the following beneficial effects: This invention provides a method and system for selecting low-altitude manned vertical take-off and landing (VTOL) sites to address urban congestion mitigation needs. By performing spatially rigid constraint filtering on candidate points, calculating rail accessibility based on real pedestrian networks, conducting multi-objective modeling and evaluation, and screening sites with minimum spacing constraints, a continuous computational chain is formed, from data input, constraint filtering, feature calculation, road network access evaluation, scheme selection, to result verification. This ensures that the site selection results possess spatial compliance, evaluation authenticity, and computational repeatability. Specifically, before evaluation, the system uniformly converts urban administrative boundaries, airport restricted areas, and other areal restrictions into calculable spatial constraints and excludes candidate points falling within or on the boundaries of restricted areas. This prevents infeasible locations from entering the final scheme, contributing to improved spatial compliance in site selection calculations. In terms of rail connection evaluation, this invention abandons the traditional approach of relying solely on Euclidean distance or buffer coverage. Instead, it matches candidate points with rail stations to pedestrian network nodes, calculates the actual pedestrian connection distance including access distance using the shortest path, and generates intermodal transport scores based on preset connection thresholds. This effectively identifies misjudgments of straight-line distance caused by road detours or road network disconnections. It can also output comparative indicators such as Euclidean distance coverage, actual pedestrian coverage, and misjudgment rate, greatly improving the authenticity of rail connection evaluation.

[0011] This invention models demand response, cost proxy, environmental proxy, and rail intermodal transport efficiency as deterministic features, with each indicator having a clear physical meaning. Planners can independently configure weights to observe changes in site layout and corresponding costs, avoiding the mixing of factors with different physical meanings into a single, uninterpreted comprehensive score, thus providing a clear multi-objective trade-off interpretation capability. Simultaneously, the system freezes input data, pedestrian network snapshots, spatial constraint files, and various parameter configurations, saving file identifiers, record counts, generation times, and hash records, supporting the repeated generation of consistent calculation results under the same inputs and parameters. By setting multiple scenarios such as demand-oriented, cost-constrained, environmental proxy avoidance, and air-rail intermodal transport priority, and by performing sensitivity checks on key weights (such as intermodal transport incentive weights) through gradual changes, the system outputs spatial layout comparisons, indicator comparisons, and sensitivity analysis results for each scenario. This allows for repeated verification and auditing between different solutions, achieving traceable site selection assessment.

[0012] In a specific experimental example, the calculation results illustrate that the present invention can identify a significant overestimation of rail accessibility by Euclidean distance evaluation using real pedestrian network measures: among all candidate points, the rail access coverage determined by Euclidean distance is significantly higher than the coverage under the real pedestrian network, a considerable proportion of samples are misjudged as covered by Euclidean distance, and the average walking distance is significantly inflated compared to the straight-line distance. In the air-rail intermodal priority scenario, the real pedestrian access coverage of the selected stations reaches a very high level, with only the average real pedestrian access distance of stations accessible by the road network being relatively short, and the intermodal transport score performing excellently. This can be used to illustrate that the method can effectively guide station layout under set target preferences. The intermodal transport weight sensitivity analysis further shows that when the intermodal transport reward weight increases from a low value, the real pedestrian coverage can achieve a significant jump and eventually stabilize in a high range, while the demand score decreases accordingly, reflecting a reasonable trade-off between the improvement of intermodal transport capacity and demand response.

[0013] In summary, this invention, through unified spatial restriction zone filtering and real pedestrian road network connection calculation, forms a traceable and interpretable evaluation scheme for the site selection of low-altitude manned vertical take-off and landing sites, which can provide scientific and reliable decision support for the planning of low-altitude manned transportation infrastructure under the need to alleviate urban congestion.

[0014] Other beneficial effects of the embodiments of the present invention will be further described below. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the low-altitude manned vertical take-off and landing field site selection method according to an embodiment of the present invention.

[0016] Figure 2a This is a diagram illustrating a demand-driven site selection scheme for low-altitude manned vertical take-off and landing fields in an embodiment of the present invention.

[0017] Figure 2b This is a diagram illustrating a low-altitude manned vertical take-off and landing field site selection scheme under cost constraints in an embodiment of the present invention.

[0018] Figure 2c This is a diagram illustrating the site selection scheme for low-altitude manned vertical take-off and landing fields in a noise avoidance scenario according to an embodiment of the present invention.

[0019] Figure 2d This is a diagram illustrating the site selection scheme for a low-altitude manned vertical take-off and landing field in the priority scenario of air-rail intermodal transport in an embodiment of the present invention.

[0020] Figure 3a This is a bar chart comparing the actual 800m walking distance connection coverage under four scenarios in this invention embodiment.

[0021] Figure 3b This is a bar chart comparing the average actual walking distance to stations accessible only by the road network under four scenarios in this embodiment of the invention.

[0022] Figure 4a This is an analysis curve showing the impact of air-rail intermodal transport incentive weights on docking performance in an embodiment of the present invention.

[0023] Figure 4b This is a curve showing the trade-off between demand response and intermodal transport capacity in an embodiment of the present invention. Detailed Implementation

[0024] The embodiments of the present invention will be described in detail below. It should be emphasized that the following description is merely exemplary and not intended to limit the scope and application of the present invention.

[0025] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of embodiments of the present invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0026] This invention aims to solve the problems of inconsistent spatial constraint treatment, distorted track connection evaluation, opaque multi-objective trade-offs, and untraceable calculation results in the existing low-altitude manned vertical take-off and landing site selection. It proposes a site selection method and system that integrates spatial rigid filtering, real pedestrian road network connection evaluation, and interpretable multi-objective ranking to achieve a site selection scheme that is spatially compliant, provides realistic evaluation, and is traceable and interpretable.

[0027] See Figure 1 This invention provides a method for selecting a low-altitude manned vertical take-off and landing site to address urban congestion relief needs, comprising the following steps: Step S1. Acquire multi-source spatial data and perform standardization processing. The multi-source spatial data includes at least candidate point bases, urban spatial constraints, rail station data, pedestrian network data, and spatial proxy element data.

[0028] In some embodiments, the standardization process in step S1 further includes: unifying various types of spatial data into the same geographic coordinate system and converting them into a projected coordinate system when performing distance or area calculations; at the same time, saving snapshot information containing file identifiers, record counts, generation times, and hash values ​​for each batch of input files to support repeatable traceability of the calculation process.

[0029] Step S2. Based on the urban spatial constraints, perform spatial rigid constraint filtering on the original candidate point set to exclude candidate points located outside the urban administrative boundary or inside or on the boundary of the no-fly zone, thus obtaining a feasible candidate point set.

[0030] In some embodiments, the spatial rigid constraint filtering in step S2 specifically includes: converting the boundary of the closed-line type restriction area into a surface type constraint, and directly using the original polygon or multi-polygon type restriction area as a surface constraint; using the coverage relationship between points and surfaces to determine whether candidate points are covered by the restriction area, and candidate points located inside or on the boundary of the restriction area are considered unselectable; the set of feasible candidate points after rigid constraint filtering is used as the sole input for subsequent feature calculation and site selection decision, preventing points covered by the restriction area from entering the final solution.

[0031] Step S3. For each candidate point in the set of feasible candidate points, construct a deterministic multi-indicator feature that includes at least demand response features, cost proxy penalty features, and environmental proxy penalty features.

[0032] In some embodiments, the construction method of the deterministic multi-indicator feature in step S3 specifically includes: the demand response feature is generated by linearly normalizing and mapping the original demand signal; the cost proxy penalty feature generates a basic cost proxy value by statistically analyzing the number of specific commercial and office elements within a preset radius of the candidate point, and replaces the proxy value with a preset incentive value when the candidate point is within a preset proximity threshold of the existing take-off and landing facility; the environmental proxy penalty feature is generated by calculating the shortest distance from the candidate point to the set of major transportation corridors, and segmenting and mapping the distance according to a preset environmental proxy threshold.

[0033] Step S4. Based on the pedestrian network data, establish the matching relationship between candidate points and rail stations to pedestrian network nodes, calculate the actual walking connection distance from candidate points to the nearest rail station through shortest path search, and map it to rail intermodal transport score according to a preset connection threshold.

[0034] In some embodiments, the calculation of the actual walking connection distance and the generation of the rail transit score in step S4 specifically include: matching candidate points and rail stations to the nearest reachable network nodes in the walking network and obtaining the corresponding access distances; using the graph theory shortest path algorithm, with the network edge length as the weight, calculating the shortest network distance between the corresponding node of the candidate point and the corresponding node of each rail station; summing the access distance and the shortest network distance, and taking the minimum value as the actual walking connection distance of the candidate point; when the candidate point is not reachable in the walking network, its rail transit score is set to zero; when it is reachable, the rail transit score is set to a value that decreases linearly with the increase of the actual walking connection distance, and is set to zero when the connection distance exceeds a preset connection threshold.

[0035] In some embodiments, step S4 further includes calculating the comparison index: calculating the Euclidean distance from the candidate point to the rail station; based on the Euclidean distance and the actual walking connection distance, respectively calculating the Euclidean distance coverage rate and the actual walking coverage rate under a preset connection threshold; calculating the proportion of samples that are determined to be covered by Euclidean distance but are misjudged due to the actual walking connection distance exceeding the threshold, as the Euclidean coverage misjudgment rate output.

[0036] In some embodiments, the specific method for establishing a matching relationship and calculating the actual walking connection distance in step S4 includes: matching the candidate point and the rail station to the nearest reachable node in the walking network, wherein the actual walking connection distance is the minimum of the sum of the candidate point access distance, the rail station access distance, and the shortest road network distance between the two nodes.

[0037] Step S5. Based on the preset multi-objective weights, the demand response characteristics, cost proxy penalty characteristics, environmental proxy penalty characteristics, and rail intermodal transport score of each candidate point are weighted and summed to obtain a comprehensive evaluation score. The candidate points are stably sorted according to their scores, and under the preset minimum station spacing constraint, a specified number of candidate points that meet the spacing conditions are sequentially selected as the site selection results.

[0038] In some embodiments, the calculation of the comprehensive evaluation score and the site selection method in step S5 specifically include: the comprehensive evaluation score is the sum of the positive weighted value of the demand response feature, the negative weighted value of the cost proxy penalty feature, the negative weighted value of the environmental proxy penalty feature, and the positive weighted value of the rail intermodal transport score; feasible candidate points are stably sorted from high to low according to the comprehensive evaluation score; during the sequential selection process, a candidate point is included in the selected site set only when the spatial distance between the candidate point and any station in the current selected site set is not less than the minimum station spacing constraint; the selection is repeated until the number of selected sites reaches the preset site number requirement.

[0039] In some embodiments, the specific method of stable sorting and dynamic verification in step S5 includes: traversing candidate points in descending order of comprehensive evaluation score, and immediately verifying the distance between subsequent candidate points and all selected points after each candidate point is selected, and allowing a candidate point to be selected only if the distance is not less than the minimum station spacing constraint.

[0040] Meanwhile, the method also includes: while outputting the site selection results, outputting the coverage rate calculated based on the Euclidean distance and the coverage rate calculated based on the actual walking connection distance, and using the deviation between the two as a misjudgment rate indicator.

[0041] Step S6. Output the site selection results and generate scenario comparison and parameter verification information including evaluation indicators, spatial layout and connection effect.

[0042] In some embodiments, the scenario comparison and parameter verification information in step S6 is generated in the following way: setting at least four preset weight scenarios including demand-oriented, cost-constrained, environmental proxy avoidance and air-rail intermodal transport priority, outputting the site selection layout and indicator comparison under different scenarios; by gradually changing the value of the intermodal transport reward weight, sensitivity analysis is performed to evaluate the trade-off between rail connection efficiency and other objectives.

[0043] In some embodiments, the method further includes a traceable verification step: freezing and storing the candidate point base, urban spatial constraints, pedestrian network data obtained in step S1, as well as the feature parameters, weight configuration, minimum station spacing constraints, and preset number of stations used in step S5, to form an input snapshot and parameter record; responding to a change instruction for the weight configuration or constraint parameters, re-executing steps S2 to S5 based on the frozen same input snapshot, and outputting new site selection results; comparing the new results with the original results in terms of spatial layout, connection coverage, and indicator scores, and generating a sensitivity analysis report.

[0044] When demand data, spatial constraint files, rail station or pedestrian network data are updated, the present invention can regenerate evaluation results and site selection schemes according to the same calculation process.

[0045] This invention also provides a low-altitude manned vertical take-off and landing field site selection system for addressing urban congestion relief needs, comprising: The data input and standardization module is used to receive and uniformly process multi-source spatial data. The spatial rigid constraint filtering module, connected to the data input and standardization module, is used to filter out infeasible points from the original candidate point set according to urban spatial constraints and generate a feasible candidate point set. A multi-indicator feature construction module, connected to the spatial rigid constraint filtering module, is used to calculate deterministic features for each point in the feasible candidate point set, including at least demand response, cost proxy, and environmental proxy. The pedestrian network connection evaluation module is connected to the data input and standardization module and the spatial rigid constraint filtering module, respectively, and is used to calculate the actual pedestrian connection distance of candidate points based on pedestrian network data and generate rail intermodal transport scores. The multi-objective site selection decision module is connected to the multi-index feature construction module and the pedestrian road network connection evaluation module, respectively. It is used to calculate the comprehensive evaluation score according to the preset weights and filter and output the final site selection scheme under the minimum station spacing constraint. The results output and verification module is connected to the multi-objective location decision module and is used to output the location results and generate scenario comparison and parameter verification reports.

[0046] The method and system of this invention ensure site selection compliance through spatial rigidity constraint filtering, avoid misjudgment of Euclidean distance based on the shortest path connection evaluation of a real pedestrian network, and model demand, cost, environment, and intermodal transport indicators separately, supporting weight configuration and minimum spacing constraints to form an interpretable multi-objective ranking and filtering. Simultaneously, it combines input snapshots, parameter records, and sensitivity analysis to achieve repeatable verification, ultimately outputting a site selection scheme with spatial compliance, connection evaluation basis, trade-off explanations, and traceability records. This invention is applicable to technical scenarios such as vertical take-off and landing field layout evaluation within urban built-up areas that require simultaneous consideration of airport restricted areas, rail connection convenience, construction cost proxy factors, environmental proxy factors, and station spatial dispersion requirements.

[0047] The following further describes specific embodiments of the present invention, algorithm examples, and experimental verification.

[0048] A method and system for selecting low-altitude manned vertical take-off and landing (VTOL) sites to address urban congestion mitigation needs. The method mainly includes: acquiring and standardizing multi-source spatial data; obtaining a set of feasible candidate sites through rigid filtering; constructing deterministic multi-indicator features based on demand response, cost proxy, and environmental proxy; calculating real pedestrian connection distances based on pedestrian road networks and mapping them to rail intermodal transport scores; performing weighted comprehensive scoring and stable sorting; sequentially filtering a specified number of site selection results under minimum station spacing constraints; outputting the site selection results and generating scenario comparison and parameter verification information. The system includes at least a data input and standardization module, a spatial rigid constraint filtering module, a multi-indicator feature construction module, a real pedestrian road network connection evaluation module, a multi-objective site selection decision module, and a result output and verification module. Each module executes according to a defined data interface sequence and outputs a set of sites, evaluation indicators, and graphical results for planners to verify.

[0049] 1. Multi-source spatial data input and standardization module This module receives the following data objects: candidate point base, including candidate point identifiers, latitude and longitude, and road congestion or travel demand proxy signals; city administrative boundaries and airport restricted areas data, including polygonal or convertible closed boundary lines; rail station data, including station names and latitude and longitude; pedestrian network data, including network nodes, edges, and edge length attributes; commercial, office, or retail element data, used to form cost proxy; existing take-off and landing facility locations, used to form proximity incentives; and major transportation corridor data, used to form environmental proxy penalties.

[0050] The system unifies all spatial objects to a geographic coordinate system and converts them to a metric projected coordinate system when distance, area, or buffer calculations are required. For each batch of input files, the system saves the file identifier, record count, generation time, and hash record to ensure consistent calculation results can be generated repeatedly under the same input and parameters.

[0051] The original demand signal can be formed by road traffic congestion intensity, periodically updated travel demand proxy data, or other quantifiable congestion relief demand indicators; when the demand data is updated, the system can re-execute subsequent steps to obtain the updated site evaluation results.

[0052] 2. Spatial Rigid Constraint Filtering Module Let the original candidate point set be The administrative boundaries of a city are represented as The set of restricted areas where vertical take-off and landing fields are prohibited is represented as follows: The system converts closed LineString type constraint boundaries into Polygon type face constraints, directly using the original Polygon or MultiPolygon type constraint regions as face constraints. Candidate points located inside or on the boundary of the constraint region are considered unselectable.

[0053] in, This is the set of feasible candidate points after rigid constraint filtering. This set will serve as the sole input for subsequent feature calculations and location decisions, preventing points covered by the restricted area from entering the final solution. To determine whether a candidate point is covered by the restricted area, the system uses the coverage relationship between the point and the area, ensuring that points on the boundary are also excluded.

[0054] 3. Deterministic Multi-Indicator Feature Construction Module For each feasible candidate point x i The system constructs demand response features d respectively. i Cost-based agency penalty feature c i and environmental agent punishment characteristics n iEach feature is calculated using a deterministic process, without introducing random perturbations during the feature generation stage.

[0055] (1) Demand response characteristics. The system's response to the original input demand signal. Perform a normalization mapping to ensure it falls within the preset interval [a, b]. In one specific implementation, a = 0.1, b = 1.0, and the calculation formula is as follows: .

[0056] (2) Cost-based penalty characteristics. The system counts the number of commercial, office, or retail elements within a preset radius Rc of the candidate points. and normalize it to basic cost agency If the candidate point is located within the preset proximity threshold R of the existing take-off and landing facility. h If the cost agent is set to a lower incentive value 'a', then the cost agent is set to a lower incentive value 'a'; otherwise, a lower incentive value 'a' is used. .

[0057] Here, H represents the existing set of take-off and landing facilities. This feature is used to characterize the agency penalty for land and facility utilization conditions and is not equivalent to the actual transaction land price or formal project cost.

[0058] (3) Environmental proxy penalty characteristics. The system calculates the shortest distance from the candidate point to the set of major traffic corridors T. And a penalty value is generated based on the environmental proxy threshold Rn: Under this definition, locations near existing high-noise-base traffic corridors have a lower additional environmental proxy penalty. This feature is only used for acoustic masking proxy in preliminary planning assessments and is not equivalent to measured noise values ​​or noise exposure results obtained through specialized acoustic simulations.

[0059] 4. Rail connection evaluation module based on real pedestrian network The system matches (or attracts) feasible candidate points and rail stations to the nearest reachable nodes in the pedestrian network, and uses the edge length as the weight to calculate the shortest pedestrian network distance between a candidate point and any rail station. Let candidate point x... i The access distance to the matching pedestrian node is δ i Rail station m j The access distance to the matching pedestrian node is δ j The shortest road network distance between two nodes is L. ij The actual walking distance from the candidate point to the nearest rail station is: Let the rail connection threshold be Rm. When a candidate point is inaccessible in the pedestrian network, its intermodal transport score is recorded as zero; when the candidate point is accessible, an intermodal transport score that decreases with walking distance is used. The system also calculates the Euclidean distance from the candidate points to the track stations. As a comparison, the Euclidean distance coverage is output separately. Actual pedestrian coverage And the Euclidean coverage misclassification rate F: Here, A represents the set of sites in a given site selection scheme. The above calculations can identify sites that appear close to rail stations in a straight line but fail to meet the walking connection threshold due to road network detours or inaccessibility.

[0060] 5. Multi-objective scoring and spatially mutually exclusive constraint location selection module The system assigns weights to four indicators—demand response, cost proxy, environmental proxy, and rail connectivity—based on the planning objectives, generating a comprehensive evaluation score for candidate points. For candidate point x... i Its overall evaluation score is: Among them, w d w c w n and w m The weights are respectively for demand response, cost proxy penalty, environmental proxy penalty, and rail connection reward. The system sorts candidate points from high to low according to Si; when the scores are the same or equal within a preset precision, the candidate points are stably sorted according to their identifiers to ensure that the calculation is reproducible.

[0061] The site selection process also imposes a minimum station spacing constraint. Let the set of selected stations be A, and the candidate point x be... i Only if its distance to any station in the selected set is not less than D. min A can only be added when |A| reaches the preset number of sites K; filtering stops when |A| reaches the preset number of sites K. Select x i Conditions: This calculation method can retain high-rated candidate points while avoiding excessive site clustering, and provides a unified solution caliber for comparing scenarios with different target preferences.

[0062] 6. Result Output, Scenario Comparison, and Parameter Verification Module The system outputs the station identifier, latitude and longitude, sorting, index value, rail connection distance, connection coverage status and minimum spacing verification results for each site selection scenario; it also outputs the spatial layout map of each scenario, multi-objective index comparison results, real walking connection effect results and station overlap relationship.

[0063] In one implementation, the system sets up four scenarios: demand-oriented, cost-constrained, environmental agent avoidance, and air-rail intermodal transport priority, and modifies the intermodal transport reward weights. m Sensitivity checks are performed to identify the trade-offs between rail connection efficiency and demand response. Because the site selection process involves discrete point selection and is constrained by minimum station spacing, local fluctuations are allowed for indicators under different weights; therefore, the system does not automatically designate any single weight value as the globally optimal parameter.

[0064] Experimental verification This experimental example uses a specific city as the research object to evaluate the site selection of low-altitude manned vertical take-off and landing fields. Following the calculation process of this invention, candidate point filtering, feature construction, evaluation of real pedestrian road network connections, multi-objective scenario site selection, and sensitivity verification of intermodal transport weights are performed. The inputs and results in this experimental example are used as a traceable calculation snapshot.

[0065] (1) Input data. The initial candidate point base within the city area consists of 8918 points; the cleaned rail station objects consist of 343 points; the existing take-off and landing facility proxy points consist of 70 points; the frozen pedestrian network includes 115674 nodes and 328284 edges. Airport restricted areas include airport control areas and specific airport restricted areas. The rail stations are sourced from the cleaned main station points, and their operational status at a specific study point in time can be verified separately during engineering applications.

[0066] (2) Constraint parameters and characteristic parameters. The mapping range for demand, cost base value and environmental proxy value is [0.1, 1.0]; the statistical radius R_c of commercial, office or retail elements is 500 meters; the proximity threshold R_h of existing take-off and landing facilities is 300 meters; the environmental proxy distance threshold R_n is 500 meters; the rail connection threshold R_m is 800 meters; the number of stations selected in each scenario K is 50; the minimum station spacing D_min is 3000 meters.

[0067] (3) Results of rigid filtering of airport restricted areas. The area of ​​the airport control zone is 386.6759 square kilometers, covering and eliminating 769 candidate points; the area of ​​the restricted area of ​​a certain airport is 78.3472 square kilometers, covering and eliminating 1241 candidate points; the combined area of ​​the two restricted areas is 460.9821 square kilometers, and after deduplication, a total of 1975 candidate points are eliminated, resulting in 6943 officially feasible candidate points.

[0068] (4) Comparison results of rail connection measurement. At the level of all candidate points, the 800-meter rail connection coverage rate judged by Euclidean distance was 69.56%, while the coverage rate judged by the shortest path of the real pedestrian network was 39.58%. Among the samples judged as covered by Euclidean distance, 43.09% failed to meet the 800-meter threshold under the real pedestrian network, with an average walking distance inflation coefficient of 2.083. This result shows that using pedestrian network evaluation can reduce the overestimation of accessibility caused by straight-line distance.

[0069] (5) Results of Formal Scenarios. The system sets up four scenarios: A is the demand-oriented scenario, B is the cost-constrained scenario, C is the environmental agent avoidance scenario, and D is the air-rail intermodal transport priority scenario. The average demand score for scenario A is 0.3310, and the actual 800-meter walking distance coverage is 30%; the average cost penalty for scenario B is 0.1060, and the coverage is 38%; the average environmental agent penalty for scenario C is 0.1001, and the coverage is 36%; the average intermodal transport score for scenario D is 0.7673, and the coverage is 94%, with the average actual walking distance to stations accessible only by the road network being 363.5845 meters. The average demand score for scenario D is 0.1720, indicating that the enhanced intermodal transport capacity is accompanied by trade-offs in demand response. Figures 2a to 2d The comparison of site selection spatial layouts under different objective weights is presented separately. Figures 3a to 3b The study compared the effects of rail connections based on real pedestrian networks in four different scenarios.

[0070] 2. Sensitivity review of intermodal transport weights While keeping the demand weight, cost weight, and environmental proxy weight all at 0.5, this experimental example will assign a combined transport incentive weight w. m The values ​​were set to 0, 0.25, 0.5, 1.0, 1.5, 2.0, and 3.0 respectively. The results show that when w... m When w = 0, the actual 800-meter walking coverage rate is 36%; when w_m = 0.25, the coverage rate increases to 84%; when w m When the score is ≥0.5, the coverage rate remains in the high range of 92% to 96%. At the same time, the average demand score decreases from 0.3050 to the range of 0.1655 to 0.2055, reflecting a trade-off between improved intermodal connectivity and demand response.

[0071] When w m When the value is 2.0, the site set and ranking results obtained from the sensitivity calculation are completely consistent with the formal D scenario, indicating that the results of the formal scenario can be reproduced. Because site selection is affected by the minimum spacing constraint of 3000 meters, coverage and average intermodal transport scores exhibit local fluctuations between adjacent weights. Therefore, this experimental example will use w... m =2.0 is used as a representative parameter for the strong combined transport preference scenario, rather than being expressed as the globally optimal parameter.

[0072] Figures 4a to 4b The results of the sensitivity analysis of the weight of air-rail intermodal transport are presented.

[0073] 3. Implementation Boundary Description In this specific experimental example, the cost characteristics are based on cost proxy penalties formed by the density of commercial, office, and retail elements and the proximity of existing facilities; the environmental characteristics are based on environmental proxy penalties formed by the proximity of major transportation corridors. Neither of these is equivalent to the actual land transaction price, formal construction cost, or measured acoustic results. In engineering applications, further verified land, environmental, safety, or energy constraint data can be accessed through the data interface of this invention, and the results can be updated according to the same candidate point filtering and site selection evaluation process.

[0074] The core technical effect verified in this experiment is: by filtering the unified spatial restriction zone and calculating the connection of the real pedestrian road network, a traceable and interpretable evaluation scheme for the selection of low-altitude manned vertical take-off and landing sites is formed, and the corresponding site layout and trade-off results are output under different target weights.

[0075] In summary, the key innovative contributions of this invention include: First, it provides a method for uniformly converting urban boundaries, airport restricted areas, and other areal restrictions into computable spatial constraints and implementing rigid filtering before evaluation; Second, it provides a rail connection evaluation method based on the shortest path of the pedestrian network rather than solely on planar straight-line distance, thereby reducing misjudgments of connection accessibility; Third, it provides a method for separately modeling demand response, cost proxy, environmental proxy, and rail connection effectiveness, and generating interpretable site selection results under the constraint of minimum station spacing; Fourth, it provides a site selection evaluation system capable of freezing input data, recording calculation parameters, outputting scenario comparison results, and conducting weight sensitivity verification.

[0076] Compared with the prior art, the significant technical advantages of the present invention are reflected in the following aspects: First, this invention improves spatial compliance in site selection calculations. Before evaluation and site selection, the system uniformly performs rigid filtering based on administrative boundaries and airport restricted areas. Candidate points are excluded if they fall within or near the restricted areas, preventing unfeasible locations from entering the final solution.

[0077] Second, this invention improves the accuracy of rail connection evaluation. Compared to existing methods that judge connection capacity solely based on Euclidean distance or buffer zone coverage, this invention calculates connection distances using the shortest path from a real pedestrian network, enabling the identification of misjudgments of straight-line distance caused by road detours or unreachable road networks.

[0078] Third, this invention possesses a clear multi-objective trade-off interpretation capability. The system models demand, cost proxy, environmental proxy, and rail intermodal transport indicators separately, avoiding the mixing of factors with different physical meanings into the same uninterpreted basic feature. Planners can observe changes in site layout and corresponding costs by altering weights.

[0079] Fourth, this invention possesses repeatable verification capability. The system freezes input data and walking network snapshots, records feature parameters, constraint parameters, context parameters, and output files, enabling the calculation results to be reproduced under the same input, and sensitivity analysis can be used to illustrate the impact of key weights on the results.

[0080] Fifth, in the experimental example, this invention uses real pedestrian network measurements to identify a significant overestimation of rail connection accessibility by Euclidean distance evaluation. Under the priority scenario of air-rail intermodal transport, the actual 800-meter walking distance coverage of the selected stations reaches 94%. If this result is verified using the same input snapshot and parameters, it can be used to demonstrate that the method can guide station layout under set target preferences. This result is used to illustrate the technical effectiveness of this embodiment and does not represent individual scenario parameters as globally optimal.

[0081] This invention also provides a storage medium for storing a computer program, which, when executed, performs at least the methods described above.

[0082] This invention also provides a control device, including a processor and a storage medium for storing a computer program; wherein the processor executes the computer program by performing at least the method described above.

[0083] This invention also provides a processor that executes a computer program, at least performing the methods described above.

[0084] The storage medium can be implemented by any type of non-volatile storage device, or a combination thereof. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc or CD-ROM; magnetic surface memory can be disk storage or magnetic tape storage. The storage media described in the embodiments of this invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0085] In the several embodiments provided by this invention, it should be understood that the disclosed systems and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0086] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0087] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0088] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0089] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0090] The methods disclosed in the several method embodiments provided by this invention can be arbitrarily combined without conflict to obtain new method embodiments.

[0091] The features disclosed in the several product embodiments provided by this invention can be arbitrarily combined without conflict to obtain new product embodiments.

[0092] The features disclosed in the several method or device embodiments provided by the present invention can be arbitrarily combined without conflict to obtain new method or device embodiments.

[0093] The above description, in conjunction with specific preferred embodiments, provides a further detailed explanation of the present invention. It should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various equivalent substitutions or obvious modifications can be made without departing from the concept of the present invention, and all such modifications, achieving the same performance or application, should be considered within the scope of protection of the present invention.

Claims

1. A method for selecting low-altitude manned vertical take-off and landing sites to address urban congestion relief needs, characterized in that, Includes the following steps: S1. Acquire multi-source spatial data and perform standardization processing. The multi-source spatial data includes at least candidate point bases, urban spatial constraints, rail station data, pedestrian network data, and spatial proxy element data. S2. Based on the urban spatial constraints, perform rigid spatial constraint filtering on the original candidate point set to exclude candidate points located outside the urban administrative boundary or falling inside or on the boundary of the no-fly zone, thus obtaining a feasible candidate point set. S3. For each candidate point in the feasible candidate point set, construct a deterministic multi-indicator feature that includes at least demand response features, cost proxy penalty features, and environmental proxy penalty features; the construction method of the deterministic multi-indicator feature specifically includes: the demand response feature is generated by linearly normalizing and mapping the original demand signal; the cost proxy penalty feature generates a basic cost proxy value by statistically analyzing the number of specific commercial and office elements within a preset radius of the candidate point, and replaces the proxy value with a preset incentive value when the candidate point is within a preset proximity threshold of existing take-off and landing facilities; the environmental proxy penalty feature is generated by calculating the shortest distance from the candidate point to the set of major transportation corridors, and segmenting and mapping the distance according to a preset environmental proxy threshold; S4. Based on the pedestrian network data, establish the matching relationship between candidate points and rail stations to pedestrian network nodes, calculate the actual walking connection distance from candidate points to the nearest rail station through shortest path search, and map it to rail intermodal transport score according to a preset connection threshold. S5. Based on the preset multi-objective weights, the demand response characteristics, cost proxy penalty characteristics, environmental proxy penalty characteristics, and rail intermodal transport scores of each candidate point are weighted and summed to obtain a comprehensive evaluation score; the candidate points are stably sorted according to their scores, and under the preset minimum station spacing constraint, a specified number of candidate points that meet the spacing conditions are sequentially selected as the site selection results. S6. Output the site selection results and generate scenario comparison and parameter verification information including evaluation indicators, spatial layout and connection effect.

2. The method according to claim 1, characterized in that, The standardization process described in step S1 further includes: Various types of spatial data are unified to the same geographic coordinate system and converted to a projected coordinate system when performing distance or area calculations. At the same time, snapshot information containing file identifier, number of records, generation time and hash value is saved for each batch of input files to support repeatable traceability of the calculation process.

3. The method according to claim 1, characterized in that, The calculation of the actual walking connection distance and the generation of the rail intermodal transport score in step S4 specifically include: The candidate points and rail stations are matched to the nearest reachable network nodes in the pedestrian network, and the corresponding access distances are obtained. Using graph theory's shortest path algorithm, with network edge length as weight, the shortest network distance between the candidate point's corresponding node and the corresponding node of each rail station is calculated. The access distance is summed with the shortest road network distance, and the minimum value is taken as the actual walking connection distance of the candidate point; When a candidate point is inaccessible in the pedestrian network, its rail transit score is set to zero; when it is accessible, the rail transit score is set to a value that decreases linearly with the increase of the actual walking connection distance, and is set to zero when the connection distance exceeds a preset connection threshold.

4. The method according to claim 1 or 3, characterized in that, Step S4 also includes the calculation of control indicators: Calculate the Euclidean distance from the candidate point to the track station; Based on the Euclidean distance and the actual walking connection distance, the Euclidean distance coverage rate and the actual walking coverage rate are calculated respectively under the preset connection threshold. Calculate the proportion of samples that are classified as covered by Euclidean distance but are misclassified due to the actual walking distance exceeding the threshold, and output this as the Euclidean coverage misclassification rate.

5. The method according to claim 1, characterized in that, The calculation of the comprehensive evaluation score and the site selection method in step S5 specifically include: The comprehensive evaluation score is the sum of the positive weighted value of the demand response characteristics, the negative weighted value of the cost agency penalty characteristics, the negative weighted value of the environmental agency penalty characteristics, and the positive weighted value of the rail intermodal transport score. The feasible candidate points are stably sorted from high to low according to the comprehensive evaluation score; During the sequential selection process, a candidate point is included in the selected site set only if the spatial distance between the candidate point and any site in the current selected site set is not less than the minimum station spacing constraint. Repeat the selection until the number of selected sites reaches the preset site count requirement.

6. The method according to claim 4, characterized in that, The specific methods for establishing matching relationships and calculating the actual walking connection distance in step S4 include: Candidate points and rail stations are matched to the nearest reachable nodes in the pedestrian network, and the actual walking connection distance is the minimum of the sum of the candidate point access distance, the rail station access distance, and the shortest road network distance between the two nodes. The specific method of stable sorting and dynamic verification in step S5 includes: traversing candidate points in descending order of comprehensive evaluation score; after selecting a candidate point, immediately verifying the distance between the subsequent candidate point and all selected points; and allowing a candidate point to be selected only if the distance is not less than the minimum station spacing constraint. Furthermore, the method also includes: while outputting the site selection results, simultaneously outputting the coverage rate calculated based on the Euclidean distance and the coverage rate calculated based on the actual walking connection distance, and using the deviation between the two as a misjudgment rate indicator.

7. The method according to claim 1, characterized in that, The scenario comparison and parameter verification information mentioned in step S6 is generated in the following way: Set up at least four preset weighted scenarios, including demand-oriented, cost-constrained, environmental agency avoidance, and air-rail intermodal transport priority, and output the site selection layout and indicator comparison under different scenarios; Sensitivity analysis was conducted by gradually changing the weighting of intermodal transport incentives to assess the trade-off between rail connectivity effectiveness and other objectives.

8. The method according to claim 1, characterized in that, The method also includes a traceable verification step: The candidate point base, urban spatial constraints, pedestrian network data obtained in step S1, as well as the feature parameters, weight configuration, minimum station spacing constraints, and preset number of stations used in step S5, are frozen and stored to form an input snapshot and parameter record. In response to the instruction to change the weight configuration or constraint parameters, steps S2 to S5 are re-executed based on the frozen same input snapshot, and a new addressing result is output. The new results are compared with the original results in terms of spatial layout, connection coverage, and indicator scores to generate a sensitivity analysis report.

9. A low-altitude manned vertical take-off and landing field site selection system for addressing urban congestion relief needs, used to implement the method as described in any one of claims 1 to 8, characterized in that, include: The data input and standardization module is used to receive and uniformly process multi-source spatial data. The spatial rigid constraint filtering module, connected to the data input and standardization module, is used to filter out infeasible points from the original candidate point set according to urban spatial constraints and generate a feasible candidate point set. A multi-indicator feature construction module, connected to the spatial rigid constraint filtering module, is used to calculate deterministic features for each point in the feasible candidate point set, including at least demand response, cost proxy, and environmental proxy. The pedestrian network connection evaluation module is connected to the data input and standardization module and the spatial rigid constraint filtering module, respectively, and is used to calculate the actual pedestrian connection distance of candidate points based on pedestrian network data and generate rail intermodal transport scores. The multi-objective site selection decision module is connected to the multi-index feature construction module and the pedestrian road network connection evaluation module, respectively. It is used to calculate the comprehensive evaluation score according to the preset weights and filter and output the final site selection scheme under the minimum station spacing constraint. The results output and verification module is connected to the multi-objective location decision module and is used to output the location results and generate scenario comparison and parameter verification reports.

Images