Unmanned aerial vehicle flight path planning method based on infrastructure data

Abstract

The invention discloses an unmanned aerial vehicle route planning method based on capital construction data. The method comprises the following steps: step 1, data acquisition and arrangement; 2, performing three-dimensional modeling; step 3, preliminarily generating a route; 4, checking and optimizing the air route; and 5, simulating test flight. Through introduction of real-time dynamic data and application of an intelligent algorithm, the scheme effectively prevents the unmanned aerial vehicle from encountering obstacles and unsuitable areas in the flight process, significantly reduces the flight risk, can update the flight path plan in real time, ensures that the flight path of the unmanned aerial vehicle keeps adaptability under changing meteorological conditions and traffic flow, and improves the flight speed. The flight task is more flexible and efficient, and the flight time and energy consumption of the unmanned aerial vehicle can be reduced through an intelligent optimization algorithm and scheme, so that the task execution efficiency is improved, the operation cost is reduced, and higher economy and benefits are provided for the application of the unmanned aerial vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) trajectory planning, and in particular to an UAV trajectory planning method based on infrastructure data. Background Art

[0002] Unmanned aerial vehicle (UAV) technology has developed rapidly in recent years and is widely used in agricultural monitoring, environmental protection, traffic management and other fields. With the improvement of intelligence and automation, the UAV trajectory planning method based on infrastructure data has gradually become a research hotspot. Infrastructure data usually refers to information such as urban infrastructure, terrain, buildings, and traffic routes. These data provide important environmental background for UAV flight planning. Trajectory planning based on infrastructure data can make full use of high-precision maps and real-time sensor data to improve the navigation ability of UAVs in complex environments. It can realize real-time perception of static and dynamic obstacles, thereby dynamically adjusting the trajectory to ensure flight safety and efficiency. In addition, optimization algorithms based on machine learning are also gradually applied to trajectory planning. Through the analysis and learning of historical data, it helps UAVs predict and avoid potential obstacles and plan more efficient flight routes.

[0003] However, the existing technology still has major deficiencies, such as:

[0004] Existing drone trajectory planning often relies on static data and fails to take into account real-time environmental changes such as weather conditions, traffic flow, and flight restricted areas. Traditional route planning lacks an effective automatic verification mechanism, which may cause the drone route to cross obstacles or inappropriate flight areas. Summary of the invention

[0005] The purpose of the present invention is to provide a UAV trajectory planning method based on infrastructure data to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The UAV trajectory planning method based on infrastructure data includes the following steps:

[0008] Step 1: Data acquisition and organization;

[0009] Step 2: 3D modeling;

[0010] Step 3: Initial generation of routes;

[0011] Step 4: Route verification and optimization;

[0012] Step 5: Simulate test flight.

[0013] Preferably, the step 1: data acquisition and arrangement, specifically includes:

[0014] Get the infrastructure data model:

[0015] Using GIS technology, we can obtain detailed data of urban infrastructure, including buildings, bridges, roads, green spaces, etc., from relevant government departments and infrastructure databases, and ensure that the data format is standardized for subsequent processing;

[0016] Get real-time dynamic data:

[0017] Obtain dynamic data in real time through API interfaces, including real-time weather data, traffic flow information and no-fly zone information;

[0018] Data Fusion:

[0019] Use data fusion algorithms to integrate static infrastructure data with dynamic data to build a comprehensive environmental model. Use the Python programming language to implement data fusion to ensure real-time updating and accuracy of data.

[0020] Preferably, the step 2: three-dimensional modeling specifically includes:

[0021] Generate a 3D model:

[0022] Use 3D modeling software to generate a 3D model of the environment based on the acquired infrastructure data model. Ensure that the model has real spatial properties and is stored in a common format.

[0023] Model attribute storage

[0024] Store the properties of the 3D model into a database for later access and analysis.

[0025] Preferably, the step 3: initial generation of routes specifically includes:

[0026] Spatial location acquisition:

[0027] According to the spatial position of the equipment under different voltages and tower shapes in the infrastructure data model, the top and end positions of each equipment are extracted, and spatial queries are performed in the database to obtain the spatial coordinates of each equipment.

[0028] Shooting sequence connection:

[0029] In the order of shooting, all shooting points are connected to form a preliminary route, and the path is optimized to minimize flight time and energy consumption.

[0030] Obtain the starting and ending points of the drone:

[0031] Set the take-off and landing points of the drone, ensuring that these two points are connected to the initially generated route and meet flight safety requirements.

[0032] Preferably, the step 4: route verification and optimization specifically includes:

[0033] Route verification:

[0034] Use a custom algorithm to verify the initially generated route and check whether the spatial position of each point meets the flight conditions of the drone, including: ensuring that all route points are at a safe distance from obstacles and checking whether the weather conditions meet the flight requirements;

[0035] Intelligent algorithm optimization;

[0036] Deep learning algorithms are used to train historical flight data, identify potential flight risks, and optimize routes through models to ensure that drones can automatically avoid obstacles and unsuitable areas during flight.

[0037] Feedback and Correction

[0038] The optimized route data is output back to the infrastructure data model for real-time correction, and the route is adjusted based on real-time dynamic data to ensure the compliance and safety of drone flights.

[0039] Route planning completed

[0040] After all verification and optimization steps are completed, the final route planning scheme is generated and stored in the database for the UAV flight control system to call.

[0041] Preferably, the step 5: simulated flight test, specifically includes:

[0042] After confirming the flight plan, enter the route data into the simulated aircraft and conduct a simulated test flight.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] 1. Through the introduction of real-time dynamic data and the application of intelligent algorithms, the solution effectively avoids the drone from encountering obstacles and unsuitable areas during flight, significantly reducing flight risks;

[0045] 2. The solution can update the trajectory planning in real time to ensure that the UAV route remains adaptable under changing weather conditions and traffic flow, making the flight mission more flexible and efficient;

[0046] 3. Through intelligent optimization algorithms, the solution can reduce the flight time and energy consumption of drones, thereby improving mission execution efficiency, reducing operating costs, and providing higher economy and benefits for drone applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] See also Figure 1 , the present invention provides a technical solution:

[0050] The UAV trajectory planning method based on infrastructure data includes the following steps:

[0051] Step 1: Data acquisition and organization;

[0052] Step 2: 3D modeling;

[0053] Step 3: Initial generation of routes;

[0054] Step 4: Route verification and optimization;

[0055] Step 5: Simulate test flight.

[0056] Step 1: Data acquisition and organization, including:

[0057] Get the infrastructure data model:

[0058] Using GIS technology, we can obtain detailed data of urban infrastructure, including buildings, bridges, roads, green spaces, etc., from relevant government departments and infrastructure databases, and ensure that the data format is standardized for subsequent processing;

[0059] Contact relevant government departments to apply for access to GIS data of urban infrastructure, use GIS software such as ArcGIS or QGIS to export infrastructure data, ensure the format is Shapefile or GeoJSON, verify the integrity and accuracy of the data, clean up redundant data, and ensure data quality.

[0060] Get real-time dynamic data:

[0061] Obtain dynamic data in real time through API interfaces, including real-time weather data, traffic flow information and no-fly zone information;

[0062] Determine the required real-time data sources such as weather, traffic flow, no-fly zones, etc., and use the API interface to capture real-time data regularly. For example, use OpenWeatherAPI to obtain weather data, store the captured data in the local database, and update it regularly.

[0063] Data Fusion:

[0064] Use data fusion algorithms to integrate static infrastructure data with dynamic data to build a comprehensive environmental model. Use the Python programming language to implement data fusion to ensure real-time updating and accuracy of data.

[0065] Selecting appropriate algorithms such as Kalman filtering for data fusion, writing data fusion programs, and how to implement data fusion through the Python programming language are technologies well known to those skilled in the art and will not be publicly elaborated here. Input static and dynamic data, output the integrated environmental model, verify the merged data model, and ensure its accuracy in real-time applications.

[0066] By acquiring infrastructure data and real-time dynamic data, the solution can reflect changes in the urban environment in real time, providing a more accurate basis for drone trajectory planning. This real-time performance significantly improves the reliability of route planning, ensures that drones can fly safely in a dynamic environment, and solves the problem that traditional planning relies only on static data. The integration of real-time dynamic data enables drone route planning to quickly adapt to changes in weather and traffic, improving the flexibility of the overall flight mission. For example, if real-time meteorological data shows that the wind speed is too high, the system can automatically adjust the route and select a safer flight path. This effect directly corresponds to solving the technical problem of insufficient adaptability to dynamic environments. Through effective data acquisition and organization, a solid foundation is laid for subsequent three-dimensional modeling and route planning. Accurate infrastructure data and real-time dynamic data can ensure that the data models used in subsequent steps are more realistic and reliable, thereby improving the effectiveness and practicality of the entire solution. This systematic integration promotes the successful implementation of the entire trajectory planning solution.

[0067] Step 2: 3D modeling, including:

[0068] Generate a 3D model:

[0069] Use 3D modeling software to generate a 3D model of the environment based on the acquired infrastructure data model. Ensure that the model has real spatial properties and is stored in a common format.

[0070] Model attribute storage

[0071] Store the properties of the 3D model into a database for later access and analysis.

[0072] Use 3D modeling software such as Blender and SketchUp to import the infrastructure data models obtained in step 1, such as urban roads and buildings. Use modeling tools to create a real 3D environment model based on the imported data. For example, by adjusting the height, shape and material properties of the model, ensure that the model can accurately reflect the characteristics of the real environment. The generated 3D model needs to be exported in a common format such as OBJ or FBX for subsequent processing and application. These formats ensure that the model can be recognized and used by a variety of software.

[0073] Extract important attribute information from the generated 3D model, such as the building's height, coordinates, material characteristics, etc. These attributes are important bases for analysis and decision-making, and store the extracted 3D model attribute data in a database (such as PostgreSQL / PostGIS). This step ensures structured data storage, facilitates subsequent query, access, and management, and ensures that the 3D model can be associated with other data (such as real-time dynamic data, flight trajectory data, etc.) to form a complete data chain.

[0074] Compared with the existing technology, by generating a highly realistic three-dimensional model, the scheme can better simulate the real environment and provide accurate spatial information. This sense of reality is crucial for the flight of drones in complex urban environments. It can effectively improve the accuracy of trajectory planning, reduce errors and potential risks, and store the attributes of the three-dimensional model into a database, which can provide a convenient access channel for subsequent data analysis and decision-making. This organized data storage enables subsequent steps such as route planning and risk assessment to quickly retrieve the required information, improve overall work efficiency, and solve the problem of scattered data and difficult access in traditional methods. The attributes of the three-dimensional model after storage can be combined with real-time dynamic data to provide multi-dimensional support for drone trajectory planning. This integrated environmental model can provide a basis for automated decision-making, improve the intelligence level of autonomous flight of drones, and further promote the advancement and application of science and technology. For example, the system can automatically analyze the optimal route based on real-time data, reduce manual intervention, and improve flight efficiency and safety. Through the three-dimensional modeling in step two, the entire trajectory planning scheme can be managed efficiently, accurately and intelligently. The combination of realistic three-dimensional environmental models and structured data storage provides a solid foundation for the dynamic trajectory planning of drones, ensuring improved flight safety and adaptability, thereby promoting the widespread application of drone technology in urban environments.

[0075] Step 3: Initial generation of routes, including:

[0076] Spatial location acquisition:

[0077] According to the spatial position of the equipment under different voltages and tower shapes in the infrastructure data model, the top and end positions of each equipment are extracted, and spatial queries are performed in the database to obtain the spatial coordinates of each equipment.

[0078] According to the infrastructure data model, the equipment under different voltages and tower shapes are identified, and the top and end spatial positions of each equipment are extracted. This includes the spatial data of facilities such as utility poles, substations, and communication towers. Spatial queries are performed in databases (such as PostgreSQL / PostGIS) to obtain the accurate spatial coordinates of each device. These coordinates will serve as the basis for drone route planning.

[0079] Shooting sequence connection:

[0080] In the order of shooting, all shooting points are connected to form a preliminary route, and the path is optimized to minimize flight time and energy consumption.

[0081] According to the mission requirements, the specific points that the drone needs to shoot are determined. These points will form the key nodes of route planning. All shooting points are connected in the set shooting order to form a preliminary route. This process can be achieved through linear connection, and the preliminary generated route is optimized using a path optimization algorithm. The purpose is to minimize flight time and energy consumption while meeting the requirements of visiting all shooting points, thereby improving efficiency and reducing operating costs.

[0082] Obtain the starting and ending points of the drone:

[0083] Set the take-off and landing points of the drone, ensuring that these two points are connected to the initially generated route and meet flight safety requirements.

[0084] According to the mission requirements and actual site conditions, set the take-off and landing points of the drone to ensure that they are within a reasonable range and comply with flight rules and safety requirements. Ensure that the starting and ending points are connected to the initially generated route and follow safety restrictions throughout the flight path, including considering terrain, obstacles and legally required no-fly zones.

[0085] By accurately extracting the spatial location of the equipment from the database, the solution can achieve a comprehensive understanding of the key facilities in the environment. This precise spatial positioning improves the accuracy of route planning, reduces the error of the drone during flight, and ensures the smooth completion of the mission. Using efficient path optimization algorithms (such as A* or Dijkstra), the solution can quickly generate the optimal route in a complex environment. This enables the drone to complete the mission in the shortest flight time, thereby reducing battery consumption and operating costs. This efficiency improvement solves the problem of inefficient route planning in traditional methods. Setting the standard requirements for the starting and ending points helps to avoid safety hazards during flight. This safety improvement is an important advancement compared to existing technologies, ensuring that drones can take off and land safely in complex urban environments and reducing the risk of accidents. Through the preliminary generation of the route in step three, the entire drone trajectory planning scheme plays a key role in improving efficiency, ensuring flight safety, and optimizing resource utilization. The application of accurate spatial position acquisition and optimization algorithms provides a solid foundation for subsequent route adjustments and actual execution, making the application of drones in complex environments more feasible and promoting the widespread application and development of drone technology.

[0086] Step 4: Route verification and optimization, including:

[0087] Route verification:

[0088] Use a custom algorithm to verify the initially generated route and check whether the spatial position of each point meets the flight conditions of the drone, including: ensuring that all route points are at a safe distance from obstacles and checking whether the weather conditions meet the flight requirements;

[0089] Develop and apply custom algorithms to verify the initially generated routes to ensure that they meet the various conditions for drone flight, check the distance from each route point to surrounding obstacles such as buildings, trees, power lines, etc. Ensure that all route points maintain a safe distance from the nearest obstacles to reduce the risk of collision, analyze current meteorological data to ensure that meteorological conditions such as wind speed, rainfall, visibility, etc. meet the flight requirements of the drone. If the meteorological conditions are not suitable, mark the route as "infeasible" and consider replanning.

[0090] Intelligent algorithm optimization;

[0091] Deep learning algorithms are used to train historical flight data, identify potential flight risks, and optimize routes through models to ensure that drones can automatically avoid obstacles and unsuitable areas during flight.

[0092] Using historical flight data to train deep learning algorithms such as convolutional neural networks, the model can identify potential flight risks and obstacles. The trained model is applied to route optimization to automatically identify and mark obstacles and unsuitable areas that may be encountered on the route. The model will adjust the route in real time to ensure that the drone can avoid these risk areas during flight.

[0093] Feedback and Correction

[0094] The optimized route data is output back to the infrastructure data model for real-time correction, and the route is adjusted based on real-time dynamic data to ensure the compliance and safety of drone flights.

[0095] Import the optimized route data into the infrastructure data model for real-time correction. This process ensures that the model is consistent with the actual environment and dynamically adjusts the route based on real-time dynamic data (such as weather changes, traffic flow, no-fly zone changes, etc.). Ensure that the optimized route can adapt to changing environmental conditions and maintain flight compliance and safety.

[0096] Route planning completed

[0097] After all verification and optimization steps are completed, the final route planning plan is generated and stored in the database for use by the UAV flight control system.

[0098] After completing all verification and optimization steps, the final route planning scheme is generated. This scheme will cover all safety checks and optimization requirements, and the final route planning scheme will be stored in the database for the UAV flight control system to call, so as to achieve automation and efficiency of flight missions.

[0099] Step 5: Simulation test flight, including:

[0100] After confirming the flight plan, enter the route data into the simulated aircraft and conduct a simulated test flight.

[0101] After completing the route verification and optimization, confirm the final route planning scheme, and ensure that all flight parameters such as altitude, speed, flight time, etc. meet the technical specifications and mission requirements of the drone. Document the confirmed route and related parameters to form a standard flight plan to provide a basis for subsequent simulated flight tests. Select a suitable flight simulator such as X-Plane or develop a customized simulated aircraft software to facilitate the input of route data and real-time simulation. Enter the final route data including all key coordinates, flight altitude, speed and other parameters into the simulator. This process requires ensuring that the data format is consistent with the simulator to ensure accuracy. Start the simulated aircraft and perform the test flight according to the predetermined flight plan. During the simulation process, monitor the flight performance of the drone, including route tracking capability, response speed, obstacle avoidance capability, etc. Compared with existing technologies, simulated test flights, as a low-risk verification method, can discover potential problems before actual flight, reduce the risk of flight accidents or equipment damage caused by improper route design, and effectively reduce the cost expenditure caused by actual flight by testing in a simulated environment. Simulated test flights can be quickly adjusted when problems arise, without causing actual equipment losses or mission delays, thereby improving cost-effectiveness.

[0102] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A UAV trajectory planning method based on infrastructure data, characterized by: The steps include: Step 1: Data acquisition and organization; Step 2: 3D modeling; Step 3: Initial generation of routes; Step 4: Route verification and optimization; Step 5: Simulate test flight.

2. The method for UAV trajectory planning based on infrastructure data according to claim 1 is characterized in that: The step 1: data acquisition and arrangement, specifically includes: Get the infrastructure data model: Using GIS technology, we can obtain detailed data of urban infrastructure, including buildings, bridges, roads, green spaces, etc., from relevant government departments and infrastructure databases, and ensure that the data format is standardized for subsequent processing; Get real-time dynamic data: Get dynamic data in real time through API interface, including real-time weather data, traffic flow information and no-fly zone information; Data Fusion: Use data fusion algorithms to integrate static infrastructure data with dynamic data to build a comprehensive environmental model. Use the Python programming language to implement data fusion to ensure real-time updating and accuracy of data.

3. The method for UAV trajectory planning based on infrastructure data according to claim 2 is characterized in that: The step 2: 3D modeling, specifically includes: Generate a 3D model: Use 3D modeling software to generate a 3D model of the environment based on the acquired infrastructure data model; ensure that the model has real spatial properties and is stored in a common format; Model attribute storage Store the properties of the 3D model into a database for later access and analysis.

4. The method for UAV trajectory planning based on infrastructure data according to claim 3 is characterized in that: The step 3: initial generation of routes, specifically includes: Spatial location acquisition: According to the spatial position of equipment under different voltages and tower shapes in the infrastructure data model, the top and end positions of each equipment are extracted, and spatial queries are performed in the database to obtain the spatial coordinates of each equipment; Shooting sequence connection: Connect all shooting points in the order of shooting to form a preliminary route and optimize the path to minimize flight time and energy consumption; Obtain the starting and ending points of the drone: Set the take-off and landing points of the drone, ensuring that these two points are connected to the initially generated route and meet flight safety requirements.

5. The method for UAV trajectory planning based on infrastructure data according to claim 1 is characterized in that: The fourth step: route verification and optimization, specifically includes: Route verification: Use a custom algorithm to verify the initially generated route and check whether the spatial position of each point meets the flight conditions of the drone, including: ensuring that all route points are at a safe distance from obstacles and checking whether the weather conditions meet the flight requirements; Intelligent algorithm optimization; Use deep learning algorithms to train historical flight data, identify potential flight risks, and optimize routes through models to ensure that drones can automatically avoid obstacles and unsuitable areas during flight; Feedback and Correction The optimized route data is outputted back to the infrastructure data model for real-time correction, and the route is adjusted according to the real-time dynamic data to ensure the compliance and safety of the UAV flight; Route planning completed After all verification and optimization steps are completed, the final route planning plan is generated and stored in the database for use by the UAV flight control system.

6. The method for UAV trajectory planning based on infrastructure data according to claim 1, characterized in that: The step 5: simulated test flight, specifically includes: After confirming the flight plan, enter the route data into the simulated aircraft and conduct a simulated test flight.

Images