An airspace planning method and system based on ground multi-source situation awareness

Abstract

The present application relates to the technical field of aircraft airspace planning, in particular to an airspace planning method and system based on ground multi-source situation awareness; through a data acquisition module, ground traffic flow data, traffic flow data and obstacle static distribution data are collected in real time; then a cloud server pre-processes the multi-source fusion data to generate a unified ground situation awareness graph; then based on the ground situation awareness graph, the target area is planned for airspace in combination with low-altitude aircraft flight safety specification information to determine the released airspace in the target area; the cloud server acquires the starting point, end point and performance parameters of the aircraft, generates an optimized flight path in combination with the released airspace, and a subsequent aircraft controller can control the aircraft to execute a flight task according to the optimized flight path; ground traffic flow, traffic flow, buildings and other factors are included in the constraint conditions to adapt to the complex and changeable urban low-altitude environment.

Description

Technical Field

[0001] This invention relates to the field of airspace planning technology for aircraft, specifically to an airspace planning method and system based on ground-based multi-source situational awareness. Background Technology

[0002] Low-altitude aircraft come in various types and models (including drones, small manned aircraft, and small cargo aircraft), and are mainly used for personal short-distance commuting, logistics distribution, cultural and tourism experiences, and emergency rescue. They also undertake tasks such as communication support, reconnaissance and mapping, rescue and disposal, and patrol and monitoring in emergency management.

[0003] When low-altitude aircraft perform flight missions, due to their low flight altitude, it is necessary to consider the impact on ground human activities, such as avoiding areas with large pedestrian traffic as much as possible to reduce safety risks. However, the current airspace path planning for low-altitude aircraft is formulated by multiple people through manual surveys, and it is difficult to change after it is formulated, making it difficult to adapt to changes in ground activities in a timely manner. Summary of the Invention

[0004] The main objective of this invention is to provide an airspace planning method and system based on ground-based multi-source situational awareness, aiming to solve the problem that current airspace path planning for low-altitude aircraft is formulated manually by multiple people after surveying, and is difficult to change after formulation, and is difficult to adapt to changes in ground activities in a timely manner.

[0005] The technical solution proposed in this invention is as follows: A ground-based multi-source situational awareness-based airspace planning method is applied to an airspace planning system based on ground-based multi-source situational awareness. The system includes a data acquisition module, a cloud server, and an aircraft. The aircraft is equipped with a flight controller. Both the flight controller and the data acquisition module are communicatively connected to the cloud server. The method includes: The data acquisition module collects ground pedestrian flow data, traffic flow data, and static obstacle distribution data in the target area in real time, and packages them into multi-source fusion data and sends them to the cloud server. The airspace of the target area is the flight airspace of the aircraft. The cloud server preprocesses the multi-source fusion data and uses a multi-source data fusion algorithm to extract and fuse features from the preprocessed multi-source fusion data to generate a unified ground situational awareness map. The cloud server performs airspace planning for the target area based on the ground situational awareness map and combined with low-altitude aircraft flight safety regulations information, in order to determine the airspace in the target area that can currently carry out flight missions and mark it as the airspace to be released. The cloud server obtains the aircraft's starting point, ending point, and performance parameters, and uses an improved path search algorithm to generate a preferred flight path in conjunction with the released airspace, and sends the preferred flight path to the aircraft's flight controller; The flight controller controls the aircraft to perform flight missions according to the preferred flight path.

[0006] Preferably, the cloud server performs airspace planning for the target area based on the ground situational awareness map and combined with low-altitude aircraft flight safety regulations information, to determine the airspace in the target area where flight missions can currently be performed, and marks it as released airspace, including: The cloud server constructs an airspace constraint model based on the ground situational awareness map, which includes ground pedestrian flow safety threshold, traffic flow impact threshold, and building avoidance distance threshold. The cloud server performs airspace planning for the target area based on the airspace constraint model to determine the airspace in the target area where flight missions can currently be carried out, and marks it as the airspace to be released.

[0007] Preferably, the flight controller controls the aircraft to perform flight missions according to a preferred flight path, including: During the process of the flight controller controlling the aircraft to perform flight missions according to the preferred flight path, the cloud server monitors and acquires the multi-source fusion data in real time, and obtains the real-time changes in the multi-source fusion data; When the real-time change of the multi-source fusion data exceeds a preset threshold, the cloud server performs preprocessing on the multi-source fusion data, and uses a multi-source data fusion algorithm to extract and fuse features from the preprocessed multi-source fusion data to generate a unified ground situational awareness map, and then proceeds with the following steps.

[0008] Preferably, the obstacles include mountains, trees, signal towers, utility poles, and buildings; the data acquisition module includes: a video surveillance camera for collecting ground pedestrian traffic data; a traffic monitoring radar for collecting traffic flow data; and a laser scanner and total station for collecting static distribution data of buildings.

[0009] Preferably, the airspace constraint model includes a ground pedestrian flow constraint sub-model, a traffic flow constraint sub-model, and a building avoidance constraint sub-model; the cloud server preprocesses the multi-source fusion data, and uses a multi-source data fusion algorithm to extract and fuse features from the preprocessed multi-source fusion data to generate a unified ground situational awareness map, including... The cloud server performs data format standardization and time and space dimension alignment preprocessing on the multi-source fused data; The cloud server constructs a multi-source data fusion algorithm model, which adopts a hierarchical fusion architecture. The multi-source data fusion algorithm model includes a data fusion layer, a feature fusion layer, and a decision fusion layer. The data fusion layer is used to eliminate noise in the multi-source fused data using a Kalman filter algorithm. The feature fusion layer is used to extract common and difference features of the multi-source fused data using a convolutional neural network. The decision fusion layer is used to generate a ground situational awareness map using a weighted voting method.

[0010] Preferably, the performance parameters include maximum range and maximum flight speed; the improved path search algorithm includes a genetic algorithm and an improved A* algorithm; the cloud server obtains the aircraft's starting point, ending point, and performance parameters, combines them with the released airspace, uses the improved path search algorithm to generate a preferred flight path, and sends the preferred flight path to the aircraft's flight controller, including: The cloud server uses a genetic algorithm to perform a global path search on the release airspace based on the aircraft's starting point, ending point, and maximum range, in order to generate multiple candidate paths; The cloud server determines the weights of each optimization objective in the local optimization by weighted summation, and uses an improved A* algorithm to perform local optimization on each candidate path to select the preferred flight path for the final output. The optimization objectives of the local optimization include the shortest path, the lowest flight energy consumption, and the lowest ground risk value. The ground risk value is quantified and calculated from the ground situational awareness map, and the ground risk value has the highest weight.

[0011] Preferably, the data acquisition module further includes building surveillance cameras installed within the target area; the cloud server acquires the aircraft's starting point, ending point, and performance parameters, combines the released airspace with an improved path search algorithm to generate a preferred flight path, and sends the preferred flight path to the aircraft's flight controller, and then further includes: The building surveillance camera captures real-time video of the buildings within the target area and sends it to the cloud server. The cloud server performs image recognition on the real-time video of the buildings to identify each building within the target area and marks it as the target building; The cloud server determines the secure containment three-dimensional area of ​​the target building, wherein the secure containment three-dimensional area is larger than the area occupied by the target building itself, and the secure containment three-dimensional area is a three-dimensional area. The cloud server marks the aircraft currently performing a flight mission as the first target aircraft and traverses the preferred flight paths of each first target aircraft to determine whether there is a first target aircraft whose preferred flight path intersects with the safe containment three-dimensional area. If so, the cloud server will mark the first target aircraft whose preferred flight path intersects with the safe containment three-dimensional area as the second target aircraft; The cloud server modifies the preferred flight path of the second target aircraft to generate a corresponding modified path, and sends the modified path to the flight controller of the second target aircraft. The flight controller of the second target aircraft controls the second target aircraft to perform a flight mission according to the changed path.

[0012] Preferably, the cloud server modifies the preferred flight path of the second target aircraft to generate a corresponding modified path, and sends the modified path to the flight controller of the second target aircraft, including: The cloud server obtains the first intersection point where the preferred flight path of the second target aircraft enters the safe containment three-dimensional area, and the second intersection point where it exits the safe containment three-dimensional area. The cloud server obtains the avoidance distance value and generates a modified path based on the avoidance distance value, the first intersection point, and the second intersection point. The modified path includes a first path from the first intersection point to the second intersection point and a second path from the second intersection point to the endpoint. The first path and the second path are on the same plane. The distance between each point in the first path and the nearest point in the safe containment three-dimensional area is a preset value, which is greater than the avoidance distance value. The cloud server will send the changed path to the flight controller of the second target aircraft.

[0013] Preferably, the system further includes a management terminal communicatively connected to the cloud server; the method further includes: The flight controller acquires the flight status data of the aircraft in real time, including real-time flight speed, real-time flight altitude, real-time remaining range, and real-time distance to the destination. The flight controller sends the flight status data of the aircraft to the cloud server in real time. The cloud server sends the acquired flight status data of each aircraft to the management terminal; The management terminal displays the flight status data of each aircraft in real time via a screen.

[0014] This invention also proposes an airspace planning system based on ground-based multi-source situational awareness, applying an airspace planning method based on ground-based multi-source situational awareness; the system includes a data acquisition module, a cloud server, and an aircraft; the aircraft is equipped with a flight controller; the flight controller and the data acquisition module are both communicatively connected to the cloud server.

[0015] The above technical solution can achieve the following beneficial effects: The proposed airspace planning method based on ground multi-source situational awareness can perform airspace planning based on ground activities in the target area, and plan and modify UAV flight paths based on changes in ground activities. First, a data acquisition module collects real-time ground pedestrian flow data, traffic flow data, and static obstacle distribution data, and packages them into multi-source fused data, which is then sent to a cloud server. The cloud server then preprocesses the multi-source fused data, using a multi-source data fusion algorithm to extract and fuse features, generating a unified ground situational awareness map. Finally, based on the ground situational awareness map and combined with low-altitude aircraft flight safety regulations, airspace planning is performed for the target area. The airspace within the target area capable of performing flight missions is identified and marked as release airspace. The cloud server obtains the aircraft's origin, destination, and performance parameters, and, in conjunction with the release airspace, uses an improved path search algorithm to generate a preferred flight path. This preferred flight path is then sent to the aircraft's flight controller, which can subsequently control the aircraft to perform flight missions according to the preferred flight path. This application constructs a multi-dimensional airspace constraint model, incorporating factors such as ground pedestrian traffic, traffic flow, and buildings into the constraints. It adopts a safety-first optimization objective to plan the airspace of the target area, significantly reducing the collision risk between low-altitude aircraft and the ground environment, and adapting to the complex and ever-changing urban low-altitude environment. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the first embodiment of an airspace planning method based on ground-based multi-source situational awareness proposed in this invention. Detailed Implementation

[0018] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0019] This invention proposes a spatial planning method and system based on ground-based multi-source situational awareness.

[0020] As attached Figure 1As shown, in the first embodiment of the airspace planning method based on ground multi-source situational awareness proposed in this invention, this airspace planning method based on ground multi-source situational awareness is applied to an airspace planning system based on ground multi-source situational awareness; the system includes a data acquisition module, a cloud server, and an aircraft; the aircraft is equipped with a flight controller; the flight controller and the data acquisition module are both communicatively connected to the cloud server; this embodiment includes the following steps: Step S110: The data acquisition module collects ground pedestrian flow data, traffic flow data, and static obstacle distribution data of the target area in real time, and packages them into multi-source fusion data and sends them to the cloud server. The airspace of the target area is the flight airspace of the aircraft.

[0021] Specifically, the acquisition module can collect multi-source situational data in real time (including ground pedestrian flow data, traffic flow data, and static building distribution data). Ground pedestrian flow data includes information such as pedestrian density and flow direction in different areas; traffic flow data includes the number of vehicles, driving speed, and traffic congestion index; and obstacle static distribution data includes mountains, trees, signal towers, utility poles, and buildings. For example, obstacle static distribution data includes building location, height, and outline. All of the above multi-source situational data are in image format. The acquisition frequency of the acquisition module is dynamically adjusted according to the importance of the area, with a minimum acquisition frequency of 10 frames per second in core areas (such as commercial districts and schools) and a minimum acquisition frequency of 5 frames per second in ordinary areas.

[0022] Step S120: The cloud server preprocesses the multi-source fusion data, and uses a multi-source data fusion algorithm to extract and fuse features from the preprocessed multi-source fusion data to generate a unified ground situational awareness map.

[0023] Specifically, the preprocessing here includes noise reduction, data format standardization, and temporal / spatial dimension alignment.

[0024] Step S130: The cloud server performs airspace planning for the target area based on the ground situational awareness map and combined with the low-altitude aircraft flight safety regulations information, so as to determine the airspace in the target area where flight missions can be performed at present, and marks it as the airspace to be released.

[0025] Specifically, in this step, based on the ground situational awareness map and combined with the flight safety regulations information of low-altitude aircraft, the airspace of the target area is planned, thereby dividing the target area into airspaces that can currently carry out flight missions and marking them as released airspaces, and airspaces that are currently unsuitable for carrying out flight missions (marked as locked airspaces).

[0026] Step S140: The cloud server obtains the starting point, ending point, and performance parameters of the aircraft, combines the released airspace with an improved path search algorithm to generate a preferred flight path, and sends the preferred flight path to the flight controller of the aircraft.

[0027] Step S150: The flight controller controls the aircraft to perform flight missions according to the preferred flight path.

[0028] The proposed airspace planning method based on ground multi-source situational awareness can perform airspace planning based on ground activities in the target area, and plan and modify UAV flight paths based on changes in ground activities. First, a data acquisition module collects real-time ground pedestrian flow data, traffic flow data, and static obstacle distribution data, and packages them into multi-source fused data, which is then sent to a cloud server. The cloud server then preprocesses the multi-source fused data, using a multi-source data fusion algorithm to extract and fuse features, generating a unified ground situational awareness map. Finally, based on the ground situational awareness map and combined with low-altitude aircraft flight safety regulations, airspace planning is performed for the target area. The system identifies and marks the currently released airspace within the target area as released airspace. The cloud server obtains the aircraft's origin, destination, and performance parameters, and, in conjunction with the released airspace, uses an improved path search algorithm to generate a preferred flight path. This preferred flight path is then sent to the aircraft's flight controller, which can subsequently control the aircraft to execute flight missions according to the preferred flight path. This application constructs a multi-dimensional airspace constraint model, incorporating factors such as ground pedestrian traffic, traffic flow, and buildings into the constraints. It employs a safety-first optimization objective to plan the airspace for the target area, significantly reducing the collision risk between low-altitude aircraft and the ground environment, and adapting to the complex and ever-changing urban low-altitude environment.

[0029] In addition, this application also has the following beneficial effects: 1. Achieve comprehensive and accurate fusion of ground situational awareness from multiple sources: Collect ground situational data from multiple sources through distributed acquisition modules, and use hierarchical fusion algorithms to solve the problem of heterogeneous multi-source data, generating an accurate ground situational awareness map to provide comprehensive ground environment support for path planning.

[0030] 2. Flexible and reliable system architecture: It adopts a collaborative architecture of edge computing and cloud computing to improve data processing efficiency; it uses 5G+BeiDou dual-mode communication to ensure the real-time performance and reliability of data transmission; it supports plug-and-play sensing devices and dynamic adjustment of algorithm parameters, which facilitates system expansion and maintenance.

[0031] In the second embodiment of the airspace planning method based on ground multi-source situational awareness proposed in this invention, based on the first embodiment, step S140 includes the following steps: Step S210: The cloud server constructs an airspace constraint model based on the ground situational awareness map, which includes ground pedestrian flow safety threshold, traffic flow impact threshold, and building avoidance distance threshold.

[0032] Step S220: The cloud server performs airspace planning on the target area based on the airspace constraint model to determine the airspace in the target area where flight missions can currently be performed, and marks it as the airspace to be released.

[0033] Specifically, the released airspace here refers to the airspace within the target area that is suitable for flight missions at the current moment, which is mainly obtained through the airspace constraint condition model.

[0034] In the third embodiment of the airspace planning method based on ground multi-source situational awareness proposed in this invention, based on the first embodiment, step S150 includes the following steps: Step S210: During the process of the flight controller controlling the aircraft to perform the flight mission according to the preferred flight path, the cloud server monitors the acquired multi-source fusion data in real time and obtains the real-time changes of the multi-source fusion data.

[0035] Step S220: When the real-time change of the multi-source fusion data exceeds the preset threshold, execute step S120 and subsequent steps.

[0036] Specifically, the preset thresholds here include various forms, such as: changes in population density exceeding 2 people / square meter or changes in traffic congestion index exceeding 0.3, triggering path replanning, i.e., re-executing step S120 and subsequent steps. Furthermore, to improve update efficiency, an incremental update method is adopted: only path segments corresponding to areas of situational change are replanned, while other path segments remain unchanged. After replanning is completed, an updated preferred flight path is generated and sent to the aircraft's flight controller. Simultaneously, the cloud server records path data for each version, facilitating subsequent traceability and optimization.

[0037] The above technical solutions enable dynamic airspace planning and real-time dynamic path updates: by monitoring changes in ground situation data in real time, incremental updates are used to trigger path replanning, ensuring that the path always adapts to the latest ground environment and improving the flexibility and reliability of low-altitude aircraft operations.

[0038] For example, during flight, the cloud server monitors multi-source fusion data in real time and detects that the pedestrian density in a certain business district has increased from 4 people / square meter to 6 people / square meter (exceeding a preset threshold), triggering route replanning. Using an incremental update method, only the route segments around the business district are replanned. The new route detours to an adjacent green low-risk area, increasing the route length by 0.5 kilometers and the estimated flight time by 2 minutes. The cloud server sends the updated route to the aircraft's flight controller via 5G communication, and the aircraft adjusts its flight path.

[0039] In the fourth embodiment of the airspace planning method based on ground multi-source situational awareness proposed in this invention, based on the first embodiment, the obstacles include mountains, trees, signal towers, utility poles and buildings; the data acquisition module includes: a video surveillance camera for collecting ground pedestrian traffic data; a traffic monitoring radar for collecting traffic flow data; and a laser scanner and total station for collecting static distribution data of buildings.

[0040] Specifically, for example, distributed data acquisition modules are deployed within the planned area (e.g., 50 square kilometers). This includes 30 video surveillance cameras deployed around commercial areas, schools, and hospitals to collect pedestrian traffic data; 20 traffic monitoring radars deployed at major road intersections to collect traffic flow data; and real-time static distribution data of 200 buildings within the planned area collected via laser scanners and total stations. The data acquisition frequency for the core area is set to 10 frames per second, and for ordinary areas, it is set to 5 frames per second.

[0041] In the fifth embodiment of the airspace planning method based on ground multi-source situational awareness proposed in this invention, based on the fourth embodiment, the airspace constraint model includes a ground pedestrian flow constraint sub-model, a traffic flow constraint sub-model, and a building avoidance constraint sub-model; step S120 includes the following steps: Step S410: The cloud server performs data format standardization and time and space dimension alignment preprocessing on the multi-source fused data.

[0042] Specifically, the cloud server uses a median filtering algorithm to remove noise from the collected video image data (ground pedestrian flow images, traffic flow images, and static obstacle images), and standardizes all data into JSON format; using BeiDou positioning time as a reference, the multi-source fused data is mapped to the WGS-84 coordinate system to complete time / space alignment.

[0043] Step S420: The cloud server constructs a multi-source data fusion algorithm model, wherein the multi-source data fusion algorithm model adopts a hierarchical fusion architecture, the multi-source data fusion algorithm model includes a data fusion layer, a feature fusion layer, and a decision fusion layer, the data fusion layer is used to eliminate noise in the multi-source fused data using a Kalman filter algorithm, the feature fusion layer is used to extract common and difference features of the multi-source fused data using a convolutional neural network, and the decision fusion layer is used to generate a ground situational awareness map using a weighted voting method.

[0044] In addition, the cloud server uses a hierarchical fusion algorithm for data fusion: the data fusion layer uses the Kalman filter algorithm to eliminate data redundancy, the feature fusion layer uses CNN (convolutional neural network) to extract spatial location features and dynamic flow features, and the decision fusion layer uses a weighted voting method to generate a ground situational awareness map; for example, high-risk areas (such as densely populated areas during peak hours in commercial districts, traffic congestion sections, and construction areas) are marked in red, medium-risk areas are marked in yellow, and low-risk areas are marked in green.

[0045] Specifically, the ground pedestrian flow constraint sub-model is used to set safe pedestrian flow thresholds for different areas (e.g., the pedestrian density threshold in core business districts should not exceed 5 people / square meter). When the threshold is exceeded, the airspace above that area is designated as locked, while the airspace corresponding to areas with a pedestrian density threshold of less than or equal to 2 people / square meter is designated as released airspace. The traffic flow constraint sub-model is used to set impact thresholds based on the traffic congestion index. When the congestion index exceeds 0.7, the airspace above that road segment is avoided to ensure emergency access, while the airspace corresponding to areas with a congestion index of less than or equal to 0.3 is designated as released airspace. The model defines the airspace as open; the building avoidance constraint sub-model is used to set avoidance distance thresholds based on obstacles (e.g., when the height of an obstacle exceeds 50 meters, the avoidance distance is not less than 20 meters), and sets the three-dimensional space obtained by extending the avoidance distance outward from the obstacle body as a locked airspace; in addition, the model also integrates the environmental constraint sub-model (based on meteorological data such as ground wind speed and precipitation, setting the maximum flight wind speed threshold to not exceed 12m / s) and the administrative constraint sub-model (integrating administrative control data of low-altitude no-fly zones and restricted flight zones), that is, setting administratively controlled areas (such as no-fly zones or restricted flight zones) as locked airspace.

[0046] In the sixth embodiment of the airspace planning method based on ground multi-source situational awareness proposed in this invention, based on the second embodiment, the performance parameters include maximum range and maximum flight speed; the improved path search algorithm includes a genetic algorithm and an improved A* algorithm; step S140 includes the following steps: Step S610: The cloud server uses a genetic algorithm to perform a global path search on the release airspace based on the aircraft's starting point, ending point, and maximum range to generate multiple candidate paths.

[0047] Step S620: The cloud server determines the weights of each optimization objective in the local optimization by weighted summation, and uses an improved A* algorithm to perform local optimization on each candidate path to filter and obtain the final output preferred flight path. The optimization objectives of the local optimization include the shortest path, the lowest flight energy consumption, and the lowest ground risk value. The ground risk value is quantified and calculated from the ground situational awareness map, and the ground risk value has the highest weight (not less than 50%). The preferred flight path includes parameters such as latitude and longitude coordinate sequence, flight altitude, and flight speed.

[0048] Specifically, the cloud server obtains the user's input regarding the aircraft's starting point (e.g., a logistics warehouse), destination (e.g., a residential area), and maximum range (e.g., 20 kilometers). It then invokes a hybrid algorithm combining genetic and A* algorithms. The genetic algorithm performs a global search to generate 10 candidate paths, while the A* algorithm performs local optimization on these paths, with optimization weights such as: ground risk 50%, shortest path 30%, and lowest energy consumption 20%. Finally, an initial optimal flight path is generated, for example, 12 kilometers in length and an estimated flight time of 15 minutes.

[0049] In the seventh embodiment of the airspace planning method based on ground multi-source situational awareness proposed in this invention, based on the first embodiment, the data acquisition module further includes building monitoring cameras installed in the target area; step S140, followed by the following steps: Step S710: The building monitoring camera captures real-time video of the building within the target area and sends it to the cloud server.

[0050] Step S720: The cloud server performs image recognition on the building live video to identify each building within the target area and marks it as the target building.

[0051] Specifically, image recognition can identify buildings within a target area.

[0052] Step S730: The cloud server determines the secure containment three-dimensional area of ​​the target building, wherein the secure containment three-dimensional area is larger than the area occupied by the target building itself, and the secure containment three-dimensional area is a three-dimensional area.

[0053] Specifically, for example, the safety containment zone of a building is the three-dimensional space area occupied by the building extending outward 20 meters from the building itself.

[0054] Step S740: The cloud server marks the aircraft currently performing a flight mission as the first target aircraft, and traverses the preferred flight paths of each first target aircraft to determine whether there is a first target aircraft whose preferred flight path intersects with the safe containment three-dimensional area.

[0055] If so, proceed to step S750: The cloud server marks the first target aircraft whose preferred flight path intersects with the safe containment three-dimensional area as the second target aircraft.

[0056] Specifically, the second target aircraft here is the aircraft that is currently on a flight mission and may collide with the target building, so the flight path of the second target aircraft needs to be changed.

[0057] Step S760: The cloud server modifies the preferred flight path of the second target aircraft to generate a corresponding modified path, and sends the modified path to the flight controller of the second target aircraft.

[0058] Step S770: The flight controller of the second target aircraft controls the second target aircraft to perform a flight mission according to the changed path.

[0059] In the eighth embodiment of the airspace planning method based on ground multi-source situational awareness proposed in this invention, based on the seventh embodiment, step S760 includes the following steps: Step S810: The cloud server obtains the first intersection point where the preferred flight path of the second target aircraft enters the safe containment three-dimensional area, and the second intersection point where it exits the safe containment three-dimensional area.

[0060] Step S820: The cloud server obtains the avoidance distance value (e.g., 10 meters) and generates a modified path based on the avoidance distance value, the first intersection point, and the second intersection point. The modified path includes a first path from the first intersection point to the second intersection point and a second path from the second intersection point to the endpoint. The first path and the second path are on the same plane. The distance between each point in the first path and the nearest point in the safe containment three-dimensional area is a preset value, which is greater than the avoidance distance value, for example, the preset value is 20m.

[0061] Step S830: The cloud server sends the changed path to the flight controller of the second target aircraft.

[0062] Specifically, the modified paths generated here include a first path and a second path, which can effectively avoid collisions with the target building.

[0063] In the ninth embodiment of the airspace planning method based on ground multi-source situational awareness proposed in this invention, based on the first embodiment, the system further includes a management terminal communicatively connected to the cloud server; this embodiment also includes the following steps: Step S910: The flight controller acquires the flight status data of the aircraft in real time, wherein the flight status data includes real-time flight speed, real-time flight altitude, real-time remaining range, and real-time distance to the destination.

[0064] Step S920: The flight controller sends the flight status data of the aircraft to the cloud server in real time.

[0065] Step S930: The cloud server sends the acquired flight status data of each aircraft to the management terminal.

[0066] Step S940: The management terminal displays the flight status data of each aircraft in real time through the display screen.

[0067] Specifically, the real-time flight status data of the aircraft is sent to the management terminal for display, so that the management personnel can know the flight status of each aircraft in a timely and effective manner.

[0068] This invention also proposes an airspace planning system based on ground-based multi-source situational awareness, applying an airspace planning method based on ground-based multi-source situational awareness; the system includes a data acquisition module, a cloud server, and an aircraft; the aircraft is equipped with a flight controller; the flight controller and the data acquisition module are both communicatively connected to the cloud server.

[0069] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0070] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. A spatial planning method based on ground-based multi-source situational awareness, characterized in that, An application is made to an airspace planning system based on ground-based multi-source situational awareness; the system includes a data acquisition module, a cloud server, and an aircraft; the aircraft is equipped with a flight controller; both the flight controller and the data acquisition module are communicatively connected to the cloud server; the method includes: The data acquisition module collects ground pedestrian flow data, traffic flow data, and static obstacle distribution data in the target area in real time, and packages them into multi-source fusion data and sends them to the cloud server. The airspace of the target area is the flight airspace of the aircraft. The cloud server preprocesses the multi-source fusion data and uses a multi-source data fusion algorithm to extract and fuse features from the preprocessed multi-source fusion data to generate a unified ground situational awareness map. The cloud server performs airspace planning for the target area based on the ground situational awareness map and combined with low-altitude aircraft flight safety regulations information, in order to determine the airspace in the target area that can currently carry out flight missions and mark it as the airspace to be released. The cloud server obtains the aircraft's starting point, ending point, and performance parameters, and uses an improved path search algorithm to generate a preferred flight path in conjunction with the released airspace, and sends the preferred flight path to the aircraft's flight controller; The flight controller controls the aircraft to perform flight missions according to the preferred flight path.

2. The airspace planning method based on ground multi-source situational awareness according to claim 1, characterized in that, The cloud server, based on ground situational awareness maps and combined with low-altitude aircraft flight safety regulations, performs airspace planning for the target area to determine the airspace currently capable of carrying out flight missions within the target area, and marks it as released airspace, including: The cloud server constructs an airspace constraint model based on the ground situational awareness map, which includes ground pedestrian flow safety threshold, traffic flow impact threshold, and building avoidance distance threshold. The cloud server performs airspace planning for the target area based on the airspace constraint model to determine the airspace in the target area where flight missions can currently be carried out, and marks it as the airspace to be released.

3. The airspace planning method based on ground-based multi-source situational awareness according to claim 1, characterized in that, The flight controller controls the aircraft to perform flight missions according to a preferred flight path, including: During the process of the flight controller controlling the aircraft to perform flight missions according to the preferred flight path, the cloud server monitors and acquires the multi-source fusion data in real time, and obtains the real-time changes in the multi-source fusion data; When the real-time change of the multi-source fusion data exceeds a preset threshold, the cloud server performs preprocessing on the multi-source fusion data, and uses a multi-source data fusion algorithm to extract and fuse features from the preprocessed multi-source fusion data to generate a unified ground situational awareness map, and then proceeds with the following steps.

4. The airspace planning method based on ground-based multi-source situational awareness according to claim 2, characterized in that, The obstacles include mountains, trees, signal towers, utility poles, and buildings; the data acquisition module includes: a video surveillance camera for collecting ground pedestrian traffic data; a traffic monitoring radar for collecting traffic flow data; and a laser scanner and total station for collecting static distribution data of buildings.

5. The airspace planning method based on ground multi-source situational awareness according to claim 4, characterized in that, The airspace constraint model includes a ground pedestrian flow constraint sub-model, a traffic flow constraint sub-model, and a building avoidance constraint sub-model. The cloud server preprocesses the multi-source fusion data and uses a multi-source data fusion algorithm to extract and fuse features from the preprocessed multi-source fusion data, generating a unified ground situational awareness map, including... The cloud server performs data format standardization and time and space dimension alignment preprocessing on the multi-source fused data; The cloud server constructs a multi-source data fusion algorithm model, which adopts a hierarchical fusion architecture. The multi-source data fusion algorithm model includes a data fusion layer, a feature fusion layer, and a decision fusion layer. The data fusion layer is used to eliminate noise in the multi-source fused data using a Kalman filter algorithm. The feature fusion layer is used to extract common and difference features of the multi-source fused data using a convolutional neural network. The decision fusion layer is used to generate a ground situational awareness map using a weighted voting method.

6. The airspace planning method based on ground multi-source situational awareness according to claim 2, characterized in that, The performance parameters include maximum range and maximum flight speed; the improved path search algorithm includes a genetic algorithm and an improved A* algorithm; the cloud server obtains the aircraft's starting point, ending point, and performance parameters, combines them with the released airspace, uses the improved path search algorithm to generate a preferred flight path, and sends the preferred flight path to the aircraft's flight controller, including: The cloud server uses a genetic algorithm to perform a global path search on the release airspace based on the aircraft's starting point, ending point, and maximum range, in order to generate multiple candidate paths; The cloud server determines the weights of each optimization objective in the local optimization by weighted summation, and uses an improved A* algorithm to perform local optimization on each candidate path to select the preferred flight path for the final output. The optimization objectives of the local optimization include the shortest path, the lowest flight energy consumption, and the lowest ground risk value. The ground risk value is quantified and calculated from the ground situational awareness map, and the ground risk value has the highest weight.

7. The airspace planning method based on ground-based multi-source situational awareness according to claim 1, characterized in that, The data acquisition module also includes building surveillance cameras installed within the target area; the cloud server acquires the aircraft's starting point, ending point, and performance parameters, combines this with the released airspace, uses an improved path search algorithm to generate a preferred flight path, and sends the preferred flight path to the aircraft's flight controller, and then further includes: The building surveillance camera captures real-time video of the buildings within the target area and sends it to the cloud server. The cloud server performs image recognition on the real-time video of the buildings to identify each building within the target area and marks it as the target building; The cloud server determines the secure containment three-dimensional area of ​​the target building, wherein the secure containment three-dimensional area is larger than the area occupied by the target building itself, and the secure containment three-dimensional area is a three-dimensional area. The cloud server marks the aircraft currently performing a flight mission as the first target aircraft and traverses the preferred flight paths of each first target aircraft to determine whether there is a first target aircraft whose preferred flight path intersects with the safe containment three-dimensional area. If so, the cloud server will mark the first target aircraft whose preferred flight path intersects with the safe containment three-dimensional area as the second target aircraft; The cloud server modifies the preferred flight path of the second target aircraft to generate a corresponding modified path, and sends the modified path to the flight controller of the second target aircraft. The flight controller of the second target aircraft controls the second target aircraft to perform a flight mission according to the changed path.

8. The airspace planning method based on ground multi-source situational awareness according to claim 7, characterized in that, The cloud server modifies the preferred flight path of the second target aircraft to generate a corresponding modified path, and sends the modified path to the flight controller of the second target aircraft, including: The cloud server obtains the first intersection point where the preferred flight path of the second target aircraft enters the safe containment three-dimensional area, and the second intersection point where it exits the safe containment three-dimensional area. The cloud server obtains the avoidance distance value and generates a modified path based on the avoidance distance value, the first intersection point, and the second intersection point. The modified path includes a first path from the first intersection point to the second intersection point and a second path from the second intersection point to the endpoint. The first path and the second path are on the same plane. The distance between each point in the first path and the nearest point in the safe containment three-dimensional area is a preset value, which is greater than the avoidance distance value. The cloud server will send the changed path to the flight controller of the second target aircraft.

9. A spatial planning method based on ground-based multi-source situational awareness according to claim 1, characterized in that, The system further includes a management terminal that is communicatively connected to the cloud server; the method further includes: The flight controller acquires the flight status data of the aircraft in real time, including real-time flight speed, real-time flight altitude, real-time remaining range, and real-time distance to the destination. The flight controller sends the flight status data of the aircraft to the cloud server in real time. The cloud server sends the acquired flight status data of each aircraft to the management terminal; The management terminal displays the flight status data of each aircraft in real time via a screen.

10. A space planning system based on ground-based multi-source situational awareness, characterized in that, The airspace planning method based on ground multi-source situational awareness as described in any one of claims 1-9 is applied; the system includes a data acquisition module, a cloud server, and an aircraft; the aircraft is equipped with a flight controller; the flight controller and the data acquisition module are both communicatively connected to the cloud server.

Images