Unmanned aerial vehicle and manned vehicle combined search and rescue path planning method under airspace layering

Abstract

The invention discloses an unmanned aerial vehicle and manned vehicle combined search and rescue path planning method under airspace layering, and belongs to the technical field of unmanned aerial vehicles, and the method comprises the steps: carrying out the airspace layering according to a target search and rescue area, and building an airspace layering model; based on the airspace layering model, performing joint search and rescue path planning on the plurality of unmanned aerial vehicles and the plurality of manned vehicles; performing path conflict simulation optimization on the plurality of unmanned aerial vehicles and the plurality of manned vehicles based on a joint search and rescue path planning result; the optimized search and rescue path planning result is encrypted and sent to the multiple unmanned aerial vehicles and the multiple manned vehicles, and the multiple unmanned aerial vehicles and the multiple manned vehicles search and rescue the target search and rescue area according to the optimized search and rescue path planning result. The technical problems of low search and rescue efficiency and high aircraft conflict risk caused by lack of systematic path planning and airspace management during joint search and rescue of an unmanned aerial vehicle and a manned vehicle in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles (UAVs), and in particular to a method for joint search and rescue path planning of unmanned aerial vehicles (UAVs) and manned aircraft under airspace stratification. Background Art

[0002] In recent years, drone technology and manned aircraft flight technology have developed rapidly and are widely used in agriculture, monitoring, logistics and other fields. Especially in the field of rescue, the combination of drones and manned aircraft has shown unique advantages. Drones can quickly reach remote or dangerous areas due to their flexibility, low cost and wide coverage, while manned aircraft have higher load capacity and long-term flight capabilities. Therefore, in emergency rescue missions in complex terrain or extreme weather, the use of drones and manned aircraft to work together can improve the efficiency and success rate of search and rescue, and minimize casualties and property losses.

[0003] However, the existing UAV and manned aircraft collaborative search and rescue methods still have many shortcomings. Traditional search and rescue modes often rely on manual scheduling and lack systematic path planning and airspace management, resulting in insufficient coverage of the search and rescue area and even the risk of conflict between aircraft. At the same time, due to the limited autonomous navigation capabilities of UAVs, the existing search and rescue paths are mostly based on static planning, which makes it difficult to cope with sudden terrain changes or dynamic rescue needs. In addition, there is a lack of efficient information transmission methods between UAVs and manned aircraft, resulting in poor coordination in complex search and rescue environments. Therefore, an airspace-layered UAV and manned aircraft joint search and rescue path planning method is proposed to solve the technical problems in the prior art that UAVs and manned aircraft lack systematic path planning and airspace management during joint search and rescue, resulting in low search and rescue efficiency and high risk of aircraft conflict. Summary of the invention

[0004] This application provides a joint search and rescue path planning method for UAVs and manned aircraft under airspace stratification, aiming to solve the technical problems in the prior art that UAVs and manned aircraft lack systematic path planning and airspace management during joint search and rescue, resulting in low search and rescue efficiency and high risk of aircraft conflict.

[0005] In view of the above problems, this application provides a joint search and rescue path planning method for UAVs and manned aircraft under airspace stratification.

[0006] The present application provides a method for joint search and rescue path planning for unmanned aerial vehicles and manned aircraft under airspace stratification, the method comprising performing airspace stratification according to a target search and rescue area and establishing an airspace stratification model; performing joint search and rescue path planning for multiple unmanned aerial vehicles and multiple manned aircraft based on the airspace stratification model to obtain a joint search and rescue path planning result; performing path conflict simulation optimization for the multiple unmanned aerial vehicles and the multiple manned aircraft based on the joint search and rescue path planning result to obtain an optimized search and rescue path planning result; encrypting the optimized search and rescue path planning result and sending it to the multiple unmanned aerial vehicles and the multiple manned aircraft, and the multiple unmanned aerial vehicles and the multiple manned aircraft perform search and rescue in the target search and rescue area according to the optimized search and rescue path planning result.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The technical solution of joint search and rescue path planning between UAVs and manned aircraft based on the airspace layering model is adopted to solve the technical problems of low search and rescue efficiency and high risk of aircraft conflict caused by the lack of systematic path planning and airspace management in the existing technology during joint search and rescue between UAVs and manned aircraft, thus achieving the technical effect of improving search and rescue efficiency and success rate. Through clear airspace division and task allocation, the solution realizes effective collaboration between multiple aircraft types, reduces the probability of path conflicts, ensures the safety and effectiveness of search and rescue operations, and thus provides a more efficient solution in emergency rescue scenarios.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flow chart of a method for joint search and rescue path planning between UAVs and manned aircraft under airspace stratification is provided for an embodiment of the present application.

[0011] Figure 2 A flow chart of obtaining a joint search and rescue path planning result in a joint search and rescue path planning method for UAVs and manned aircraft under airspace stratification is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0012] The overall idea of ​​the technical solution provided by this application is as follows:

[0013] The embodiment of the present application provides a method for joint search and rescue path planning of unmanned aerial vehicles and manned aircraft under airspace stratification. By constructing an airspace stratification model, joint search and rescue path planning of unmanned aerial vehicles and manned aircraft is realized. First, the airspace is divided according to the characteristics of the target search and rescue area, and a model is established to optimize the allocation of task areas. Then, the model is used for path planning to ensure coordinated operations between multiple aircraft types and reduce path conflicts. Finally, the optimized path planning results are encrypted and sent to each aircraft to ensure efficient and safe execution of search and rescue missions in complex environments, thereby improving the overall search and rescue effect.

[0014] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0015] Examples, such as Figure 1 As shown, the embodiment of the present application provides a method for joint search and rescue path planning of unmanned aerial vehicles and manned aircraft under airspace layering, the method comprising:

[0016] Step S100: Perform airspace stratification according to the target search and rescue area and establish an airspace stratification model.

[0017] Specifically, the target search and rescue area refers to the specific area where drones and manned aircraft need to perform search and rescue missions, including complex terrain, buildings or other obstacles. The target search and rescue area will be determined according to the rescue needs, such as mountainous areas, sea areas or urban buildings. Airspace stratification refers to dividing the airspace of the target area into multiple levels according to altitude, regional characteristics or mission requirements. Each level can be covered by different types of aircraft or different task divisions. The purpose of airspace stratification is to avoid conflicts between aircraft and improve the efficiency of airspace use. The airspace stratification model refers to a structured model after airspace stratification, which contains information such as the area range, altitude range, and task allocation between levels after stratification, providing data support for subsequent path planning. This model is used in search and rescue missions to clearly define the responsibilities and rules of each layer of airspace.

[0018] In the process of establishing the airspace hierarchical model, it is first necessary to collect the airspace and regional data of the target search and rescue area, including flight restrictions, altitude ranges, terrain obstacles, etc., to form a regional basic data set. This can be collected through GPS, remote sensing or geographic information system (GIS), and data cleaning is performed to remove redundant information. Based on the cleaned regional data set, a three-dimensional target search and rescue area model is generated using modeling tools (such as MATLAB, ArcGIS). This model intuitively reflects the geographical characteristics and airspace information of the search and rescue area.

[0019] Next, based on the preset airspace division rules, the regional model is airspace layered. The airspace division rules are usually set according to the rescue mission requirements. For example, the low-altitude layer is used for low-speed search by drones, the mid-altitude layer is used for manned aircraft search that quickly covers the area, and the high-altitude layer is used for data relay and signal transmission. Taking maritime search and rescue as an example, drones are responsible for detailed searches for floating objects in the low-altitude layer, helicopters patrol the mid-altitude layer, and drones are used to relay image information in the high-altitude layer. After the layering is completed, the resulting airspace layering model includes the altitude range and task assignments of each airspace layer, laying the foundation for joint search and rescue path planning.

[0020] This step can effectively coordinate the task allocation of UAVs and manned aircraft, reduce flight conflicts, and improve the coverage and response speed of search and rescue by stratifying the airspace of the target search and rescue area and establishing an airspace stratification model. In practical applications, this airspace stratification model not only improves the efficiency of airspace utilization, but also enhances the dynamic scheduling capability in complex environments, greatly improving the success rate of joint search and rescue missions.

[0021] Step S200: Based on the airspace layering model, joint search and rescue path planning is performed on multiple unmanned aerial vehicles and multiple manned aircraft to obtain a joint search and rescue path planning result.

[0022] Specifically, joint search and rescue path planning refers to the integrated planning of the paths of UAVs and manned aircraft based on the airspace hierarchical model to maximize the coverage of the search and rescue area and reduce path conflicts. The flight path generated by this plan assigns tasks to UAVs and manned aircraft at different altitudes and areas, allowing each aircraft to efficiently complete the search and rescue mission. The joint search and rescue path planning result refers to the final output of the path planning, which includes the detailed flight routes and time schedules of UAVs and manned aircraft, ensuring that each aircraft can work together efficiently without path conflicts.

[0023] When planning the joint search and rescue path, the tasks of UAVs and manned aircraft are first divided based on the airspace layering model. Since the airspace layering model has divided the target search and rescue area into different altitude levels, mission areas and other information, the mission areas can be reasonably allocated to different aircraft based on this layering information during path planning. Generally, UAVs are suitable for performing low-altitude precision search tasks, such as close-range observation of building ruins or complex terrain, while manned aircraft are suitable for wide-area patrol tasks at medium and high altitudes.

[0024] Specifically, the mission area is first allocated using a planning algorithm (such as the A algorithm or the Dijkstra algorithm) based on the mission requirements and flight capabilities of each aircraft (such as endurance, flight speed, obstacle avoidance, etc.). For example, the A algorithm can be used to calculate the shortest path for a drone in complex terrain, while the Dijkstra algorithm is more suitable for planning long-distance flight routes for manned aircraft in open areas. To improve the adaptability of path planning, deep learning models can also be used to train historical search and rescue data to optimize the path generation process. In mountain search and rescue, drones can be assigned to low-altitude areas to search hillsides and forests, while manned aircraft fly at medium and high altitudes to quickly patrol the entire mountain area.

[0025] After completing the path planning of each UAV and manned aircraft, these paths are fused to generate the final joint search and rescue path planning result. This fusion result contains detailed information such as the specific flight route, take-off and landing time, and flight altitude of each UAV and manned aircraft to ensure that there will be no conflict between UAVs and manned aircraft in space and time. Simulation software (such as MATLAB or ROS simulation platform) can be further used to detect conflicts on the paths to ensure that UAVs and manned aircraft will not interfere with each other in actual flight.

[0026] Through joint search and rescue path planning based on the airspace hierarchical model, UAVs and manned aircraft can work together in the same search and rescue area, significantly improving the coverage efficiency of search and rescue missions. The path planning results reduce the risk of conflict between aircraft in the airspace through reasonable path allocation, and make the search and rescue system achieve optimal utilization in time and space. Ultimately, this planning method can significantly improve the success rate and completion speed of search and rescue missions, providing safe and efficient technical guarantees for emergency search and rescue in complex environments.

[0027] Step S300: performing path conflict simulation optimization on the multiple UAVs and the multiple manned aircraft based on the joint search and rescue path planning result to obtain an optimized search and rescue path planning result.

[0028] Specifically, path conflict simulation optimization refers to simulating the paths of aircraft, detecting and eliminating potential conflicts between aircraft, such as intersections and overlaps. Through optimization, the flight path of each aircraft is made safer and more efficient. The optimized search and rescue path planning result refers to the final path planning result after path conflict simulation and optimization, including the specific routes and time arrangements of each aircraft in the mission to ensure that there will be no interference or conflict.

[0029] First, the joint search and rescue path planning results are imported into the simulation platform (such as MATLAB, ROS or AnyLogic simulation tools) for path conflict detection. The simulation platform can accurately simulate the intersection, overlap or mutual interference of different aircraft during flight by modeling the flight characteristics, path routes and airspace layering models of each UAV and manned aircraft. For example, if the paths of two UAVs overlap at a certain point, the simulation will detect the conflict point and mark its location and time.

[0030] Once the conflict detection is completed, the path will be optimized according to the detection results. During the optimization process, heuristic algorithms (such as genetic algorithms, particle swarm optimization algorithms, etc.) or path avoidance algorithms (such as collision avoidance algorithms) can be used to adjust the path. On the premise of keeping the general direction and target area of ​​the original mission path of the aircraft unchanged, the path conflict is resolved by adjusting the flight altitude, detour or time sequence. For example, if the paths of drone A and manned aircraft B overlap in a certain airspace, the optimization algorithm will guide drone A to slightly increase the flight altitude before the conflict point, or detour at this location to ensure that the two do not meet at the same airspace level.

[0031] In addition, the characteristics of the aircraft are also taken into account during the path optimization process. For example, manned aircraft prioritize flying in a straight line to save fuel, while drones can flexibly adjust their routes. Taking the valley search and rescue mission as an example, if a drone is searching the valley at low altitude and a manned aircraft is flying over it, the simulation results show that the possibility of conflict is high. The optimization plan will arrange for the drone to enter the valley low-altitude area after the manned aircraft passes, or guide the drone to enter from the side to avoid the manned aircraft's route.

[0032] Through path conflict simulation optimization, the results of joint search and rescue path planning can be further improved, which not only eliminates flight conflicts between drones and manned aircraft, but also effectively improves the safety and execution efficiency of search and rescue. The optimized path planning makes the search and rescue process smoother and more coordinated, which helps to complete the search and rescue mission quickly and without interference. This conflict optimization technology is particularly important in complex and multi-level search and rescue environments, ensuring the path safety when multiple aircraft types are coordinated, and improving the search and rescue success rate and time efficiency.

[0033] Step S400: encrypting the optimized search and rescue path planning result and sending it to the multiple unmanned aerial vehicles and the multiple manned aircraft, and the multiple unmanned aerial vehicles and the multiple manned aircraft perform search and rescue in the target search and rescue area according to the optimized search and rescue path planning result.

[0034] Specifically, encrypted transmission means that in order to ensure the security of communication, the optimized search and rescue path planning results will be encrypted and transmitted to each aircraft through a secure communication link to prevent the path information from being tampered with or intercepted.

[0035] First, the optimized search and rescue path planning results need to be encrypted to prevent the data from being maliciously attacked or intercepted during transmission. Common encryption methods include symmetric encryption (such as AES) or asymmetric encryption (such as RSA). Taking AES as an example, the encryption algorithm will encrypt the path data and generate encrypted ciphertext. Only the aircraft holding the key can decrypt and obtain the data. For example, a unique encryption key can be assigned to each drone and manned aircraft, and the optimized path data can be sent to the receiving module of each aircraft in an encrypted manner.

[0036] Next, the optimized path planning results are sent from the ground command center to each aircraft in an encrypted form through the wireless communication modules (such as LoRa, 4G / 5G communication modules, etc.) equipped on each aircraft. In order to ensure the stability and efficiency of the transmission process, communication protocols (such as TCP / IP, MQTT) will be used to ensure the complete transmission of data. Taking mountain search and rescue as an example, the signal strength in mountainous areas is uneven. The path planning results can be transmitted in shards through the 4G / 5G network, and stable communication links are given priority in areas with poor signals to ensure that the data successfully reaches each aircraft.

[0037] After receiving and decrypting the path data, the UAV and manned aircraft will each enter the target area according to the guidance of the path planning results to carry out the search and rescue mission. The UAV usually conducts detailed area scans at lower airspace, such as searching for traces of missing persons and detecting obstacles, while the manned aircraft will conduct wide-area coverage cruises at high altitudes to ensure support in a larger range. For example, in a maritime search and rescue mission, the UAV will be arranged to fly low along the sea surface to search for floating objects and life-saving signals, while the helicopter will observe the panoramic view of the sea surface from above to quickly respond to unexpected discoveries.

[0038] This step significantly improves the safety and efficiency of the entire search and rescue process by encrypting the transmission and accurately executing the optimized search and rescue path planning results. Encryption processing ensures the privacy and security of the search and rescue path, protecting the aircraft from external interference or path leakage. Each aircraft can seamlessly receive and strictly execute the path planning, avoid path deviation, improve the accuracy of search and rescue area coverage and the search and rescue success rate, thereby significantly improving the overall efficiency and safety of the search and rescue mission.

[0039] Furthermore, airspace stratification is performed according to the target search and rescue area, and an airspace stratification model is established, including: collecting airspace parameters and geographical parameters of the target search and rescue area to obtain a regional basic data set; modeling is performed based on the regional basic data set to obtain a target search and rescue area model; and airspace division is performed on the target search and rescue area model according to predetermined airspace division rules to generate the airspace stratification model.

[0040] Specifically, airspace parameters describe the parameters of flight conditions in the target search and rescue area, such as flight altitude, airspace restrictions, weather conditions, etc. These parameters are used to evaluate whether the aircraft can fly safely and effectively in the area. Regional parameters describe the parameters of the geographical characteristics of the target search and rescue area, such as terrain, landforms, obstacles and surface structures. These parameters affect the path planning of the aircraft and the execution of the search and rescue mission. The regional basic data set refers to the data set obtained by collecting airspace parameters and regional parameters, which contains the basic information of the target search and rescue area as a reference for subsequent modeling and path planning. The airspace division rules are rules used to stratify the airspace according to search and rescue needs, usually including altitude division, task allocation basis, etc., to reasonably allocate tasks for different aircraft at different airspace levels.

[0041] When establishing an airspace stratification model, it is first necessary to collect the airspace parameters and regional parameters of the target search and rescue area to form a regional basic data set. Airspace parameters include flight altitude, airspace restrictions, weather conditions, etc., which can be obtained through meteorological radar, satellite remote sensing data, etc. For example, in mountain search and rescue missions, it is necessary to understand the wind speed and cloud layer at different altitudes to ensure that the drone can fly safely in the low-altitude layer. At the same time, regional parameters such as terrain undulations and obstacle distribution can be collected through geographic information systems (GIS) and laser radar (LiDAR) scanning. After data cleaning and preprocessing, this information forms a consistent regional basic data set, providing accurate data support for subsequent modeling.

[0042] Based on this data set, a modeling tool (such as MATLAB or ArcGIS) is used to build a target search and rescue area model that reflects the three-dimensional geographical structure, climate, and ground features of the target search and rescue area. For example, the three-dimensional terrain model generated by ArcGIS can clearly show the ups and downs of the mountainous area, which is helpful for planning the search path of the aircraft in the low-altitude area.

[0043] After the modeling is completed, the target search and rescue area model is divided according to the preset airspace division rules to generate an airspace hierarchical model. The airspace division rules can be set according to the mission requirements. For example, it can be divided into three layers: low altitude, medium altitude, and high altitude according to the type of aircraft and mission requirements. Taking maritime search and rescue as an example, the low altitude layer can be used by drones for low-altitude fine searches, the medium altitude layer can be used by manned helicopters for large-scale searches, and the high altitude layer is used for signal relay and information transmission. After the division is completed, the airspace hierarchical model contains specific information such as the altitude range and task allocation of each layer, providing a clear structured framework for joint search and rescue path planning.

[0044] By establishing an airspace hierarchical model, hierarchical management of target search and rescue areas is achieved, enabling drones and manned aircraft to work together efficiently in different airspace levels. This hierarchical model can not only effectively reduce path conflicts between aircraft, but also improve the comprehensive coverage and resource utilization of search and rescue missions. With the help of the airspace hierarchical model, the search and rescue system can dynamically allocate tasks, improve the response speed and accuracy of search and rescue missions, and provide greater reliability and safety for search and rescue operations.

[0045] Furthermore, airspace parameters and regional parameters of the target search and rescue area are collected to obtain a regional basic data set, including: collecting the airspace parameters of the target search and rescue area to obtain airspace parameter collection results; collecting regional parameters of the target search and rescue area to generate regional parameter collection results; performing data cleaning according to the airspace parameter collection results and the regional parameter collection results to generate the regional basic data set.

[0046] Specifically, the airspace parameter collection results refer to the specific data of airspace parameters obtained through collection means, such as flight altitude range, wind speed and other data. These data reflect the flight conditions of the target area and guide the operation of the aircraft in the area. The regional parameter collection results refer to the specific data of regional parameters obtained through collection means, which show the geographical characteristics of the target area and provide terrain reference for path planning. Data cleaning refers to filtering, denoising, processing and converting the collected airspace and regional parameter data to remove redundant data and erroneous data to ensure the accuracy and consistency of the data.

[0047] In the process of collecting the airspace and regional parameters of the target search and rescue area, it is necessary to first obtain the airspace parameters and regional parameters respectively. For airspace parameters, tools such as meteorological radar, satellite remote sensing, and air traffic control systems can be used to obtain flight altitude ranges, meteorological information (such as wind speed, cloud cover, visibility), etc. For example, in mountain search and rescue missions, the collected airspace parameters include the cloud height, low-altitude wind speed, and visibility restrictions in the area to ensure that the drone can fly stably in the appropriate airspace.

[0048] For regional parameters, geographic information systems (GIS), laser radar (LiDAR), remote sensing technology and other means can be used to collect data on terrain, landforms and obstacle distribution. For example, in search and rescue missions in urban areas, LiDAR scanning can obtain regional parameters such as the three-dimensional position of buildings and ground undulations, and clearly identify obstacles that drones need to avoid or locations that need to be searched. These collection results form airspace parameter collection results and regional parameter collection results respectively, and these raw data often contain noise, redundant information or outliers.

[0049] Next, the airspace and regional collection results are cleaned, and data processing software (such as Pandas and NumPy libraries in Python, or dedicated data cleaning tools such as OpenRefine) is used to denoise the data, complete missing data, and remove outliers. For example, if some values ​​in the collected wind speed data are obviously too high or too low, it is an error during collection, and the outliers need to be removed or corrected through data cleaning to ensure the accuracy of the data. The cleaned data forms a regional basic data set, which contains structured airspace and regional information, and becomes an accurate basis for subsequent path planning and model building.

[0050] By collecting airspace and regional parameters and cleaning the data to form a regional basic data set, the airspace and geographic information of the search and rescue area can be ensured to be accurate and complete, providing solid data support for subsequent airspace stratification modeling. After data cleaning, the regional basic data set avoids the interference of noise and erroneous information, thereby improving the accuracy of the airspace stratification model and ensuring the accuracy and effectiveness of the search and rescue mission.

[0051] Further, such as Figure 2 As shown, based on the airspace hierarchical model, joint search and rescue path planning is performed for multiple UAVs and multiple manned aircraft to obtain a joint search and rescue path planning result, including: based on the airspace hierarchical model, search and rescue mission areas are allocated to the multiple UAVs and the multiple manned aircraft to obtain UAV search and rescue mission areas and manned aircraft search and rescue mission areas; based on the UAV search and rescue mission areas, search and rescue path planning is performed for the multiple UAVs to generate UAV search and rescue path planning results; based on the manned aircraft search and rescue mission areas, search and rescue path planning is performed for the multiple manned aircraft to generate manned aircraft search and rescue path planning results; and the UAV search and rescue path planning results and the manned aircraft search and rescue path planning results are integrated to generate the joint search and rescue path planning result.

[0052] Specifically, the allocation of search and rescue mission areas refers to the division of search and rescue areas into areas that are responsible for UAVs and manned aircraft, respectively, based on the airspace stratification model, to ensure that each aircraft performs its mission in an appropriate area to maximize mission efficiency. The UAV search and rescue mission area refers to the search and rescue area that the UAV is specifically responsible for, usually allocated in lower air layers or difficult-to-access complex terrain to take advantage of the UAV's flexibility and low-altitude detailed search capabilities. The manned search and rescue mission area refers to the search and rescue area that manned aircraft are responsible for, usually in higher air layers to cover a larger search and rescue range and achieve rapid patrols.

[0053] First, the mission areas of multiple drones and manned aircraft are allocated based on the airspace stratification model. Since the airspace stratification model has divided the search and rescue airspace into different altitudes and regional levels, the areas can be reasonably allocated according to the performance characteristics of the aircraft and mission requirements. Drones are usually responsible for lower altitude areas and are suitable for detailed searches in complex terrain or small spaces.

[0054] Next, the paths of the search and rescue mission areas of UAVs and manned aircraft are planned separately. For UAV path planning, a path planning algorithm (such as A algorithm) can be combined with a deep learning model to train UAVs to select the optimal path in complex terrain. After the UAV regional path planning is completed, the UAV search and rescue path planning results are generated, which include the detailed flight route, flight altitude and search strategy of each UAV in its mission area.

[0055] At the same time, for manned aircraft path planning, the shortest path algorithm such as Dijkstra algorithm is used to generate manned aircraft search and rescue path planning results. Manned aircraft are responsible for large-scale patrols in the middle and high altitude layers. The speed and endurance of the aircraft are taken into account during path planning to ensure that it can complete wide-area coverage in the shortest time.

[0056] Finally, the path planning results of the UAV and manned aircraft are fused to generate a joint search and rescue path planning result. During the path fusion process, simulation software (such as MATLAB or ROS simulation environment) can be used to detect spatial and temporal conflicts of the path to ensure that the UAV and manned aircraft will not interfere at the intersection. The fusion result includes the detailed flight routes, mission sequences, and altitude levels of the UAV and manned aircraft, enabling them to collaborate efficiently within the search and rescue area.

[0057] This step can maximize the use of the characteristics of UAVs and manned aircraft through joint search and rescue path planning, achieving more efficient search and rescue area coverage and more detailed target search. The task area allocation and path fusion of UAVs and manned aircraft enable search and rescue missions to be synchronized at multiple airspace levels, improving search and rescue speed and comprehensive coverage. The final joint search and rescue path planning results effectively avoid path conflicts between aircraft and ensure the efficiency, safety and coordination of search and rescue missions.

[0058] Furthermore, search and rescue paths are planned for the multiple drones based on the drone search and rescue mission area to generate drone search and rescue path planning results, including: collecting basic characteristic parameters of the multiple drones to obtain a drone characteristic data set; performing deep learning based on the drone search and rescue path planning set of the multiple drones to build a drone search and rescue path planning model; based on the drone search and rescue mission area and the drone characteristic data set, search and rescue paths are planned for the multiple drones according to the drone search and rescue path planning model to obtain the drone search and rescue path planning results.

[0059] Specifically, the basic characteristic parameters describe the set of parameters of the drone performance, such as flight speed, maximum endurance, obstacle avoidance, load capacity, etc. These parameters determine the actual flight capability and mission execution effect of the drone in the search and rescue mission. The drone characteristic data set is a data set composed of the characteristic parameters of multiple drones. It contains the performance data of all drones involved in the search and rescue mission and is used to guide the path planning process. The drone search and rescue path planning set stores the drone path planning data in historical search and rescue missions for the training of deep learning models. By learning these path data, the model can optimize the path planning effect of the drone in different tasks. The drone search and rescue path planning model is based on a model trained by deep learning, which is used to predict and optimize the path selection of the drone to ensure that the drone can perform tasks efficiently in the search and rescue area.

[0060] First, we need to collect the basic characteristic parameters of each drone, such as flight speed, range, obstacle avoidance sensor performance, etc., to form a drone characteristic data set. For example, in mountain search and rescue missions, some drones have long flight times and are suitable for long-distance missions, while other drones are equipped with precise obstacle avoidance sensors and are suitable for complex terrain. Therefore, through the drone characteristic data set, personalized path planning solutions can be formulated based on the performance characteristics of different drones.

[0061] Next, the deep learning model is trained using the UAV search and rescue path planning set to build a UAV search and rescue path planning model. This path planning set usually contains the best path data of the UAV under different terrain, weather and airspace conditions in previous search and rescue missions. The planning set can be trained using deep learning frameworks such as TensorFlow and PyTorch, so that the model can automatically identify and generate the optimal path under similar mission conditions.

[0062] Finally, based on the mission area and characteristic data set of the drone, the path planning model is applied to the actual search and rescue path planning to generate the drone search and rescue path planning results. This result includes the specific flight route, flight altitude, obstacle avoidance strategy and time schedule of each drone in the mission area. The planning model predicts and generates a path based on the characteristic data of the drone and the terrain characteristics of the search and rescue area. For example, in a valley search and rescue mission, the path planning results will allow drones with precise obstacle avoidance functions to fly low along the valley, while long-endurance drones will cruise long distances outside the valley.

[0063] In this step, the UAV search and rescue path planning results generated by the application of UAV characteristic data sets and deep learning path planning models can be highly adapted to the performance of specific UAVs and the complexity of the mission area. This path planning method can optimize the search coverage and safety of UAVs in complex search and rescue environments, improve the search and rescue efficiency and mission completion of UAVs, and make the entire search and rescue process more intelligent and efficient.

[0064] Furthermore, based on the joint search and rescue path planning result, path conflict simulation optimization is performed on the multiple UAVs and the multiple manned aircraft to obtain an optimized search and rescue path planning result, including: modeling based on the multiple UAVs and the multiple manned aircraft to construct a man-machine integration model; based on the joint search and rescue path planning result, search and rescue simulation is performed according to the airspace layered model and the man-machine integration model to obtain a search and rescue simulation result; path conflict identification is performed based on the search and rescue simulation result to obtain a search and rescue path conflict identification result; path optimization is performed on the joint search and rescue path planning result according to the search and rescue path conflict identification result to generate the optimized search and rescue path planning result.

[0065] Specifically, the human-machine integration model refers to a model used to simulate the collaborative operation of UAVs and manned aircraft in the airspace, combining the flight characteristics, communication features and mission requirements of UAVs and manned aircraft to achieve efficient coordination of multiple aircraft types in the same airspace. Search and rescue simulation refers to simulating the flight paths of various UAVs and manned aircraft in a simulation environment based on existing path planning and human-machine models, observing the interactive behaviors between them, and predicting the occurrence of path conflicts or mission interference. Path conflict identification refers to identifying the intersection, overlap or conflict areas of the flight paths between UAVs and manned aircraft by analyzing the flight trajectories in the simulation to determine the path nodes that need to be optimized. Path optimization refers to replanning or fine-tuning the paths of some aircraft based on the results of path conflict identification to eliminate conflicts and optimize the execution efficiency of search and rescue missions.

[0066] First, it is necessary to build models for UAVs and manned aircraft to form a human-machine integration model. This model integrates the physical characteristics, flight restrictions and communication characteristics of each aircraft. For example, UAVs have high maneuverability and are suitable for low-altitude missions, while manned aircraft usually have higher flight altitude restrictions and longer endurance, and are suitable for high-altitude area missions. The tools for building human-machine integration models can use professional simulation platforms such as MATLAB Simulink and Gazebo to facilitate simulation and testing. Specifically, the characteristic data of each UAV and manned aircraft (such as flight altitude, speed, turning radius, etc.) are collected, and then these parameters are input into the simulation platform (such as MATLAB Simulink or Gazebo) to simulate the flight behavior of the aircraft. Then, through system modeling and dynamic simulation technology, the flight characteristics and path requirements of UAVs and manned aircraft are integrated to achieve collaborative simulation of aircraft in multi-layer airspace, providing support for subsequent search and rescue path planning.

[0067] Next, the search and rescue simulation was carried out through the human-machine integration model using the joint search and rescue path planning results and the airspace layering model. During the simulation, the path data of the UAV and manned aircraft were loaded into the simulation environment and monitored in real time through virtual operation. This simulation can detect intersections or overlapping paths generated by aircraft on the path.

[0068] Subsequently, based on the results of the search and rescue simulation, path conflict identification is performed to detect whether there are path conflicts between aircraft, including areas of intersection, overlap or potential collision. For the identified conflict areas, further analysis will be performed to determine the specific optimization requirements. For each conflict area, the specific time node, path overlap location and conflict type are marked to generate the search and rescue path conflict identification results.

[0069] Finally, based on the path conflict identification results, the joint search and rescue path planning results are optimized. The optimization algorithm uses particle swarm optimization algorithm or obstacle avoidance algorithm to replan the path according to the characteristics of each aircraft.

[0070] Through the path conflict simulation optimization steps, path conflicts between different aircraft during the search and rescue process can be effectively avoided, thereby improving the safety and execution efficiency of the overall search and rescue mission. The optimized search and rescue path planning results ensure the coordination and cooperation between drones and manned aircraft, and significantly reduce mission interruptions or reduced efficiency caused by path conflicts. This human-machine integrated path optimization technology is particularly important in complex terrain or airspace, providing strong support for the rapid response and high coverage of search and rescue missions.

[0071] Furthermore, the multiple unmanned aerial vehicles and the multiple manned aircraft perform search and rescue in the target search and rescue area according to the optimized search and rescue path planning results, including: establishing search and rescue path planning grids for each man-machine based on the optimized search and rescue path planning results; performing real-time monitoring based on the multiple unmanned aerial vehicles and the multiple manned aircraft to obtain real-time flight monitoring data of each man-machine; performing path deviation detection on the real-time flight monitoring data of each man-machine based on the search and rescue path planning grids for each man-machine, and generating a man-machine path deviation warning signal.

[0072] Specifically, the search and rescue path planning grid refers to dividing the target search and rescue area into grids to facilitate refined management and allocation of search and rescue tasks. Each grid area corresponds to a specific UAV or manned aircraft to perform a mission, ensuring that the mission area is clearly divided and evenly covered. Real-time flight monitoring data refers to aircraft data collected in real time through wireless transmission, including the aircraft's current coordinates, speed, altitude and other status information, which is used to monitor whether it is performing tasks according to the planned route. Path deviation detection is used to identify the deviation between the actual flight path of the aircraft and the planned path, ensuring that the aircraft moves along the established route within the specified grid area. If the deviation exceeds the preset value, an early warning signal will be triggered.

[0073] First, based on the optimized search and rescue path planning results, the target search and rescue area is gridded to form a search and rescue path planning grid. This gridding process divides a large area into multiple small areas, and each grid is assigned to a specific UAV or manned aircraft to perform a mission.

[0074] Next, each drone and manned aircraft will be monitored in real time, and real-time flight status data such as location, speed, flight altitude, etc. will be obtained through the GPS and communication modules (such as 4G / 5G) configured on the aircraft. These data will be transmitted to the command center regularly to understand the execution status of the aircraft in real time.

[0075] Path deviation detection is performed based on real-time collected flight data and search and rescue path planning grids. Specifically, the actual flight data of each aircraft will be compared with the planned path. Once a deviation from the planned path is found and the deviation value exceeds the preset threshold (such as more than 10 meters), an offset warning signal will be automatically generated and the information will be fed back to the aircraft control end. For example, in maritime search and rescue, if the drone deviates from the route due to wind and waves, the offset warning signal will promptly remind the drone to make adjustments to avoid the creation of search and rescue blank areas.

[0076] Through path planning grid, real-time monitoring and deviation detection, this step ensures the path accuracy and real-time adjustment capability of each drone and manned aircraft when performing search and rescue missions. The deviation warning signal can quickly respond to path deviations, allowing the aircraft to automatically adjust the flight path or the control end to remotely adjust the flight path, ensuring efficient search and rescue, reducing coverage blind spots, and improving the success rate and response speed of search and rescue.

[0077] Furthermore, a wireless communication module is included between the multiple unmanned aerial vehicles and the multiple manned aircraft, and the wireless communication module is used for communication connection between the multiple unmanned aerial vehicles and the multiple manned aircraft.

[0078] Specifically, the wireless communication module refers to the communication equipment used for data transmission between drones and manned aircraft, usually including Wi-Fi, 4G / 5G, dedicated radio stations and other modules, which can realize the real-time transmission of data, instructions and status information. Communication connection refers to the data sharing between multiple aircraft through wireless signals, so that drones and manned aircraft can communicate mission status, location, speed and other information to coordinate actions.

[0079] Wireless communication modules are configured between multiple drones and manned aircraft to build a real-time and stable communication network. Usually, multiple communication technologies are included, such as 5G, LoRa or satellite communication, to ensure stable signal transmission in different search and rescue scenarios. For example, in urban environments, high-bandwidth 5G modules can be used to achieve fast data transmission; in areas with weak networks such as mountainous areas or at sea, satellite communication or LoRa can be used to ensure long-distance communication.

[0080] The establishment of communication connections must ensure that each aircraft can share key data in real time, such as location, flight status, and mission progress. Through this real-time data exchange, drones and manned aircraft can work together in missions. For example, when a drone finds a target in a forest search and rescue and sends back location information, other aircraft can adjust their paths based on the location and quickly approach the area. Communication protocols such as MAVLink or RTPS are usually used to achieve standardized transmission of data between devices, so that different types of aircraft can communicate compatiblely.

[0081] The use of wireless communication modules has greatly improved the efficiency of collaboration between drones and manned aircraft, enabling multiple aircraft types to respond quickly and adjust flexibly in complex search and rescue missions. Through real-time communication, search and rescue teams can quickly share and process on-site information, reduce redundant search and rescue, shorten response time, and effectively improve search and rescue coverage and success rate. This technology is particularly suitable for high-risk search and rescue environments such as complex terrain or at sea, and achieves efficient data interaction and real-time decision-making.

[0082] In summary, the method for joint search and rescue path planning of UAVs and manned aircraft under airspace stratification provided by the embodiment of the present application has the following technical effects:

[0083] 1. Through airspace stratification and joint search and rescue path planning, the collaboration efficiency between drones and manned aircraft in search and rescue missions is optimized. Through clear task allocation and planning, path conflicts can be reduced in complex environments, resource utilization can be improved, and comprehensive coverage of search and rescue missions can be ensured, ultimately improving the success rate and speed of search and rescue and reducing the uncertainty caused by human intervention.

[0084] 2. By collecting the airspace parameters and regional parameters of the target search and rescue area, an airspace stratification model is established, which can effectively identify the characteristics and risks of different airspaces. This model lays a scientific foundation for subsequent path planning, enables search and rescue operations to be optimized according to specific environmental conditions, and improves the pertinence and efficiency of search and rescue missions.

[0085] 3. Through joint search and rescue path planning for multiple UAVs and manned aircraft, reasonable allocation of mission areas and optimal allocation of resources can be achieved. This method ensures the coordinated operation of different aircraft, reduces conflicts in mission execution, improves the efficiency of multi-aircraft collaboration, and thus improves the overall effect of the search and rescue operation.

[0086] 4. Through path conflict simulation optimization, potential conflicts between UAVs and manned aircraft can be identified and handled in a timely manner. This measure ensures that aircraft can perform tasks safely during the search and rescue process, reduces resource waste and accident risks caused by conflicts, and significantly improves the safety and effectiveness of search and rescue operations.

[0087] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0088] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A joint search and rescue path planning method for UAVs and manned aircraft under airspace stratification, characterized in that: The method comprises: Conduct airspace stratification according to the target search and rescue area and establish an airspace stratification model; Based on the airspace hierarchical model, joint search and rescue path planning is performed for multiple unmanned aerial vehicles and multiple manned aircraft to obtain a joint search and rescue path planning result; Based on the joint search and rescue path planning result, path conflict simulation optimization is performed on the multiple unmanned aerial vehicles and the multiple manned aircraft to obtain an optimized search and rescue path planning result; The optimized search and rescue path planning result is encrypted and sent to the multiple unmanned aerial vehicles and the multiple manned aircraft, and the multiple unmanned aerial vehicles and the multiple manned aircraft perform search and rescue in the target search and rescue area according to the optimized search and rescue path planning result.

2. The method according to claim 1, characterized in that Airspace stratification is performed according to the target search and rescue area, and an airspace stratification model is established, including: Collecting airspace parameters and geographical parameters of the target search and rescue area to obtain a regional basic data set; Modeling is performed based on the regional basic data set to obtain a target search and rescue area model; The target search and rescue area model is airspace divided according to a predetermined airspace division rule to generate the airspace hierarchical model.

3. The method according to claim 2, characterized in that Collect the airspace parameters and regional parameters of the target search and rescue area to obtain a regional basic data set, including: Collecting airspace parameters of the target search and rescue area to obtain airspace parameter collection results; Collecting geographical parameters of the target search and rescue area and generating geographical parameter collection results; Data cleaning is performed according to the spatial parameter collection results and the regional parameter collection results to generate the regional basic data set.

4. The method according to claim 1, characterized in that Based on the airspace hierarchical model, joint search and rescue path planning is performed for multiple UAVs and multiple manned aircraft to obtain joint search and rescue path planning results, including: Based on the airspace hierarchical model, the multiple unmanned aerial vehicles and the multiple manned aircraft are allocated search and rescue mission areas to obtain unmanned aerial vehicle search and rescue mission areas and manned aircraft search and rescue mission areas; Performing search and rescue path planning for the multiple drones based on the drone search and rescue mission area, and generating drone search and rescue path planning results; Performing search and rescue path planning for the multiple manned aircraft based on the manned aircraft search and rescue mission area, and generating a manned aircraft search and rescue path planning result; The unmanned aerial vehicle search and rescue path planning result and the manned aircraft search and rescue path planning result are integrated to generate the joint search and rescue path planning result.

5. The method according to claim 4, characterized in that Performing search and rescue path planning for the multiple drones based on the drone search and rescue mission area, and generating drone search and rescue path planning results, including: Collecting basic characteristic parameters of the plurality of drones to obtain a drone characteristic data set; Performing deep learning based on the drone search and rescue path planning set of the multiple drones to build a drone search and rescue path planning model; Based on the UAV search and rescue mission area and the UAV characteristic data set, search and rescue paths are planned for the multiple UAVs according to the UAV search and rescue path planning model to obtain the UAV search and rescue path planning result.

6. The method according to claim 1, characterized in that Based on the joint search and rescue path planning result, path conflict simulation optimization is performed on the multiple unmanned aerial vehicles and the multiple manned aircraft to obtain an optimized search and rescue path planning result, including: Perform modeling based on the multiple unmanned aerial vehicles and the multiple manned aircraft to construct a human-machine integration model; Based on the joint search and rescue path planning result, performing search and rescue simulation according to the airspace layered model and the human-machine integration model to obtain a search and rescue simulation result; Performing path conflict identification based on the search and rescue simulation result to obtain a search and rescue path conflict identification result; The combined search and rescue path planning result is optimized according to the search and rescue path conflict identification result to generate the optimized search and rescue path planning result.

7. The method according to claim 1, characterized in that The multiple unmanned aerial vehicles and the multiple manned aircraft perform search and rescue in the target search and rescue area according to the optimized search and rescue path planning result, including: Based on the optimized search and rescue path planning results, establishing search and rescue path planning grids for each man and machine; Based on the real-time monitoring of the multiple unmanned aerial vehicles and the multiple manned aircraft, real-time flight monitoring data of each manned aircraft is obtained; Based on the man-machine search and rescue path planning grids, path deviation detection is performed on the real-time flight monitoring data of each man-machine, and a man-machine path deviation warning signal is generated.

8. The method according to claim 1, characterized in that A wireless communication module is included between the multiple unmanned aerial vehicles and the multiple manned aircraft, and the wireless communication module is used for communication connection between the multiple unmanned aerial vehicles and the multiple manned aircraft.

Images