Rotary fixed wing tilting type child-mother unmanned aerial vehicle cooperative autonomous investigation method and system
Through the coordinated independent reconnaissance method of rotary tilt-rotating mother-child drone, dynamic classification and execution of tasks, the problems of poor battery life and communication stability of the drone in complex terrain are solved, and efficient and accurate reconnaissance tasks are achieved.
Patent Information
- Application Number
- CN202410875991.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-02
- Publication Date
- 2024-11-08
AI Technical Summary
Existing drones have problems such as insufficient endurance, limited function, limited adaptability, low autonomy and poor communication stability in complex terrain or long-term continuous reconnaissance tasks, resulting in unsafe task execution and insufficient data transmission in complex environments. precise.
The rotary tilt-type child-male drone-type coordinated independent reconnaissance method is adopted to classify the reconnaissance tasks by receiving target reconnaissance tasks, and compare the reconnaissance efficiency of rotary sub-machine and parent base stations, and dynamically perform tasks, including dynamic release and recovery of sub-machines, and use The tilt locking device and multi-point communication mechanism ensure efficient completion of tasks.
It improves the reconnaissance efficiency and the accuracy of data transmission, enhances the mission execution capabilities and communication stability of the drone in complex environments, and achieves efficient and reliable reconnaissance tasks.
Smart Images

Figure CN118915778A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) target detection, and in particular to a method and system for coordinated autonomous detection of rotary-fixed-wing tilt-rotating mother-and-child UAVs. Background Art
[0002] With the development of drone technology, it has been widely used in the fields of geographic surveying and mapping, disaster monitoring, reconnaissance and search and rescue. However, in complex terrain or tasks that require long-term continuous reconnaissance, a single type of drone is often difficult to meet the mission requirements, especially in terms of endurance, operating efficiency and communication stability. Traditional drone reconnaissance technology relies on a single model or drones of the same type to perform a wide range of tasks, resulting in the limitation of the single performance of drones in complex or vast mission areas, resulting in insufficient endurance, functional limitations, limited adaptability, limited autonomy, insufficient flexibility, low redundancy and other problems. In addition, single communication technology is susceptible to interference in complex environments and there is no efficient escort mechanism, which affects the safety of mission execution and accurate data transmission. The existing drone clusters have a low degree of mission autonomy and rely on remote control communication channels and too much human operation, which limits the number of drone clusters in the air and their ability to perform complex tasks. Summary of the invention
[0003] In view of this, the main purpose of the embodiments of the present invention is to provide a method and system for collaborative autonomous reconnaissance of a rotary-fixed-wing tilt-rotating mother-and-child UAV to improve the reconnaissance efficiency and the accuracy of data transmission.
[0004] To achieve the above-mentioned purpose, an embodiment of the present invention provides a method for cooperative autonomous reconnaissance of a rotary-fixed-wing tilt-rotating mother-and-child UAV:
[0005] receiving a target reconnaissance task, classifying the target reconnaissance task, and obtaining a classification result;
[0006] According to the classification results, the efficiency of the multi-rotor sub-machine reconnaissance and the efficiency of the mother machine base station autonomous reconnaissance are compared to obtain a comparison result;
[0007] According to the comparison result, executing the target detection subtask;
[0008] Return to the designated landing point and end the target reconnaissance mission.
[0009] In some embodiments, receiving a target reconnaissance task, classifying the target reconnaissance task, and obtaining a classification result comprises the following steps:
[0010] According to the detection capability of the mother base station and the detection range of the mother base station, the target detection task is first classified to obtain a first detection type;
[0011] Based on the first reconnaissance type, performing a second classification on the target reconnaissance task to obtain a second reconnaissance type;
[0012] The first investigation type includes large-scale basic investigation, medium-scale basic investigation, small-scale basic investigation, large-scale detailed investigation, medium-scale detailed investigation and small-scale detailed investigation;
[0013] The second investigation type includes a simple investigation area and a complex investigation area.
[0014] In some embodiments, performing the target detection task according to the comparison result includes the following steps:
[0015] According to the comparison result, determine whether the mother machine base station meets the first preset condition, if the mother machine base station meets the first preset condition, perform a first investigation, if the mother machine base station does not meet the first preset condition, perform a second investigation;
[0016] Among them, the first preset condition is that without releasing the multi-rotor sub-machine, the efficiency of the autonomous detection of the mother machine base station is greater than the efficiency of the detection of the multi-rotor sub-machine.
[0017] In some embodiments, if the mother machine base station meets the first preset condition, performing a first reconnaissance includes the following steps:
[0018] Set a preset detection time;
[0019] If the current detection time is less than the preset detection time, the mother base station detects the target;
[0020] If the current detection time is greater than the preset detection time, the mother base station and the multi-rotor sub-machine detect the target.
[0021] In some embodiments, if the mother machine base station does not meet the first preset condition, performing a second reconnaissance includes the following steps:
[0022] Obtaining the target range and target time of the target reconnaissance mission;
[0023] According to the target range and the target time, determining whether the target reconnaissance task satisfies a second preset condition, if the target reconnaissance task satisfies the second preset condition, executing a first sub-reconnaissance, and if the target reconnaissance task does not satisfy the second preset condition, executing a second sub-reconnaissance;
[0024] Among them, the second preset condition is that the target range is greater than the sum of the detection ranges of all the multi-rotor sub-machines, and the target time is greater than the shortest endurance time of the mother base station.
[0025] In some embodiments, if the target reconnaissance task satisfies the second preset condition, performing the first sub-reconnaissance includes the following steps:
[0026] Obtaining the demand for each model of the multi-rotor aircraft;
[0027] Setting a disengagement rule for the multi-rotor aircraft;
[0028] According to the demand and the disengagement rule, the mother base station and the multi-rotor sub-machine detect the target.
[0029] In some embodiments, if the target reconnaissance task does not meet the second preset condition, performing a second sub-reconnaissance includes the following steps:
[0030] Obtaining the demand for each model of the multi-rotor aircraft;
[0031] Setting the disengagement rules of the multi-rotor sub-machine and setting the preset detection time;
[0032] Planning a preset path for the multi-rotor aircraft by means of a path planning algorithm;
[0033] According to the preset path, the demand and the disengagement rule, the multi-rotor drone detects the target;
[0034] When the power of the multi-rotor is less than a preset threshold, it returns to the mother base station;
[0035] According to the number of the multi-rotor sub-machines that return to the mother base station, releasing the substitute multi-rotor sub-machines;
[0036] According to the preset path and the disengagement rule, the substitute multi-rotor drone detects the target;
[0037] If the current detection time is greater than the preset detection time, the mother base station and the multi-rotor sub-machine detect the target.
[0038] To achieve the above-mentioned purpose, another aspect of the embodiment of the present invention provides a rotary-fixed-wing tilt-rotating type mother-and-child UAV cooperative autonomous reconnaissance system, the system comprising:
[0039] The mother machine base station is equipped with a built-in high-efficiency battery, the first detection equipment and a tilting locking device;
[0040] Multi-rotor sub-machines, including reconnaissance sub-machines and escort sub-machines;
[0041] The reconnaissance sub-machine is provided with a second reconnaissance device and a first locking device;
[0042] The escort type sub-machine is provided with a third detection device, a communication relay device, a second locking device and a third locking device;
[0043] Wherein, the first locking device of the reconnaissance sub-machine is connected to the tilting locking device of the mother base station;
[0044] The second locking device of the escort type sub-machine is connected to the tilting locking device of the mother machine base station;
[0045] The mother base station and the multi-rotor sub-machine are used to perform target reconnaissance tasks using the method described in any one of claims 1-7.
[0046] To achieve the above-mentioned purpose, another aspect of the embodiment of the present invention provides a rotary-fixed-wing tilt-rotating mother-and-child UAV cooperative autonomous reconnaissance device, the device comprising:
[0047] The first module is used to receive a target reconnaissance task, classify the target reconnaissance task, and obtain a classification result;
[0048] The second module is used to compare the efficiency of the multi-rotor sub-machine reconnaissance and the efficiency of the mother machine base station autonomous reconnaissance according to the classification results to obtain a comparison result;
[0049] The third module is used to execute the target detection task according to the comparison result;
[0050] The fourth module is used to return to the designated landing point and end the target reconnaissance mission.
[0051] To achieve the above-mentioned purpose, another aspect of an embodiment of the present invention provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the aforementioned method of collaborative autonomous reconnaissance of a rotary-fixed-wing tilt-rotor type mother-and-child UAV.
[0052] To achieve the above-mentioned purpose, another aspect of an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the aforementioned method of collaborative autonomous reconnaissance of a rotary-fixed-wing tilt-rotor type mother-and-child UAV.
[0053] To achieve the above-mentioned purpose, another aspect of an embodiment of the present invention provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the aforementioned method for cooperative autonomous reconnaissance of a rotary-fixed-wing tilt-rotating mother-and-child UAV.
[0054] The embodiments of the present invention include at least the following beneficial effects: the present invention provides a method and system for cooperative autonomous reconnaissance of a rotary-fixed-wing tilt-rotating mother-and-child UAV, which utilizes a rotary-fixed-wing tilt-rotating mother-and-child UAV cooperative autonomous reconnaissance system to receive a target reconnaissance mission, classify the target reconnaissance mission, and obtain a classification result; execute the target reconnaissance mission according to the classification result; execute the target reconnaissance subtask according to the target range and target time in the target reconnaissance mission; return to a designated landing point, and end the target reconnaissance mission. The embodiments of the present invention can improve the reconnaissance efficiency and the accuracy of data transmission. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0056] Figure 1 This is a flow chart of a method for cooperative autonomous reconnaissance of a rotary-fixed-wing tilt-rotating mother-and-child UAV provided by an embodiment of the present invention;
[0057] Figure 2 It is a schematic diagram of a flow chart of determining whether the independent and autonomous detection of a mother machine base station is optimal, provided by an embodiment of the present invention;
[0058] Figure 3 It is a flowchart of a chain and mesh communication mechanism for multi-point communication and multi-terminal collaboration provided by an embodiment of the present invention;
[0059] Figure 4 is a schematic structural diagram of a rotary-fixed-wing tilt-rotating mother-and-child UAV provided in an embodiment of the present invention;
[0060] Figure 5 It is a structural schematic diagram of a vertical take-off and landing fixed-wing endurance type mother aircraft base station provided by an embodiment of the present invention;
[0061] Figure 6 It is a schematic diagram of the structure of a multi-rotor reconnaissance sub-machine provided in an embodiment of the present invention;
[0062] Figure 7 It is a schematic diagram of the structure of a multi-rotor escort type sub-machine provided in an embodiment of the present invention;
[0063] Figure 8a-8b is a schematic diagram of the execution flow of the tilting locking device provided by an embodiment of the present invention;
[0064] Fig. 9It is a flow chart of a reconnaissance method of a rotary-fixed-wing tilt-rotating mother-and-child UAV provided in an embodiment of the present invention;
[0065] Fig.10 It is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention.
[0066] Reference numerals:
[0067] The mother machine base station 100, the built-in high-efficiency battery 101, the first reconnaissance equipment 102, the tilting locking device 103;
[0068] Multirotor 200;
[0069] A detection sub-machine 210, a second detection device 211, and a first locking device 212;
[0070] Escort submachine 220, third reconnaissance equipment 221, second locking device 222, third locking device 223; DETAILED DESCRIPTION
[0071] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present invention, and they are only examples of devices and methods consistent with some aspects of the embodiments of the present invention as detailed in the attached claims.
[0072] It should be noted that, although the functional modules are divided in the system schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in a different order than the module division in the system or the flow chart. The terms "first / S100" and "second / S200" in the specification and claims and the above-mentioned drawings may be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiment of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determination".
[0073] The terms "at least one", "multiple", "each", "any", etc. used in the present invention, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.
[0074] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein are only for the purpose of describing the embodiments of the present invention and are not intended to limit the present invention.
[0075] Currently, the mission autonomy of drone swarms is not high and they rely too much on remote control communication channels and human operations, which limits the number of drones in the air and their ability to perform complex tasks.
[0076] In view of this, if Figure 1 As shown, an embodiment of the present invention provides a method for cooperative autonomous reconnaissance of a rotary-fixed-wing tilt-rotating mother-and-child UAV. Figure 1 The method may include but is not limited to steps S100 to S400:
[0077] Step S100, receiving a target reconnaissance task, classifying the target reconnaissance task, and obtaining a classification result;
[0078] Step S200, comparing the efficiency of the multi-rotor sub-machine detection and the efficiency of the mother machine base station autonomous detection according to the classification result to obtain a comparison result;
[0079] Step S300, executing the target detection task according to the comparison result;
[0080] Step S400, returning to the designated landing point, and ending the target reconnaissance mission.
[0081] In some embodiments, step S100 may include but is not limited to steps S110 to S120:
[0082] Step S110, performing a first classification on the target reconnaissance task according to the reconnaissance capability of the mother base station and the reconnaissance range of the mother base station to obtain a first reconnaissance type;
[0083] Step S120, based on the first reconnaissance type, performing a second classification on the target reconnaissance task to obtain a second reconnaissance type;
[0084] In some embodiments, in steps S110 to S120, the mother base station receives the target detection task and evaluates its own capabilities to determine whether the mother base station can independently complete the target detection task and whether the mother base station is optimal in independently completing the target detection task. The mother base station's own capabilities include but are not limited to detection capability, detection range, and endurance; the detection range is the size of the detected environment area. Figure 2As shown, based on the detection capability of the mother machine base station and the detection range of the mother machine base station, the difficulty of the target detection task is judged, so as to perform a first classification on the target detection task to obtain a first detection type, which includes large-scale basic detection, medium-scale basic detection, small-scale basic detection, large-scale detailed detection, medium-scale detailed detection and small-scale detailed detection. And on the basis of the first detection type, the target detection task is further classified into a second detection type to obtain a second detection type, which includes a simple detection area and a complex detection area. Among them, a large range means that the target range of the target detection task is greater than the sum of the detection ranges of all multi-rotor sub-machines of each model; a small range means that the target range of the target detection task is less than or equal to the sum of the detection ranges of the escort sub-machines; a medium range means that the target range of the target detection task is less than or equal to the sum of the detection ranges of the detection sub-machines and the escort sub-machines, and is greater than the sum of the detection ranges of the escort sub-machines.
[0085] In step S200 of some embodiments, Figure 2 As shown, according to the classification results, the efficiency of multi-rotor sub-machine reconnaissance and the efficiency of the mother machine base station autonomous reconnaissance are compared.
[0086] According to the classification results, under the premise of not unlocking and releasing the multi-rotor sub-machine cluster reconnaissance, the efficiency of the multi-rotor sub-machine reconnaissance and the efficiency of the mother machine base station autonomous reconnaissance are compared to obtain a comparison result, so as to determine whether the independent and autonomous reconnaissance of the mother machine base station is optimal, so as to prepare for the subsequent execution of target reconnaissance tasks.
[0087] In some embodiments, step S300 may include but is not limited to step S310:
[0088] Step S310, judging whether the mother machine base station meets a first preset condition according to the comparison result, and performing a first investigation if the mother machine base station meets the first preset condition, and performing a second investigation if the mother machine base station does not meet the first preset condition;
[0089] Among them, the first preset condition is that without releasing the multi-rotor sub-machine, the efficiency of the autonomous detection of the mother machine base station is greater than the efficiency of the detection of the multi-rotor sub-machine.
[0090] In step S310 of some embodiments, according to the comparison result, if the efficiency of the autonomous reconnaissance of the mother base station is greater than the efficiency of the reconnaissance of the multi-rotor daughter machine, the first reconnaissance is performed; if the efficiency of the autonomous reconnaissance of the mother base station is less than the efficiency of the reconnaissance of the multi-rotor daughter machine, the second reconnaissance is performed. Specifically, based on the flight altitude, flight time, performance of the sensors and reconnaissance equipment carried by the mother base station and the multi-rotor daughter machine, the size of the geographical area that the mother base station and the multi-rotor daughter machine can cover in a single flight can be evaluated first, and then the speed at which the mother base station and the multi-rotor daughter machine complete the reconnaissance task can be evaluated, that is, the area that can be covered or the number of tasks completed in a unit time. Through the above evaluation, the efficiency of the autonomous reconnaissance of the mother base station and the efficiency of the multi-rotor daughter machine reconnaissance can be compared to obtain the optimal reconnaissance type.
[0091] Among them, when the mother base station conducts autonomous reconnaissance, the tilt-locking device can be used to obtain assistance and support functions from the multi-rotor sub-machines, so that the flight speed, flight altitude, etc. of the mother base station are assisted and supported. For example, when the tilt-locking device causes the multi-rotor sub-machine cluster to tilt forward, the multi-rotor sub-machine cluster starts lift, so that the mother base station can obtain auxiliary support for speed and lift; when the tilt-locking device causes the multi-rotor sub-machine cluster to tilt backward, the multi-rotor sub-machine cluster starts lift, so that the mother base station can obtain auxiliary support for deceleration and lift.
[0092] In some embodiments, if the mother machine base station meets the first preset condition, a first investigation is performed, which may include but is not limited to steps S311 to S313:
[0093] Step S311, setting a preset detection time;
[0094] Step S312, if the current detection time is less than the preset detection time, the mother base station detects the target;
[0095] Step S313, if the current detection time is greater than the preset detection time, the mother base station and the multi-rotor sub-machine detect the target.
[0096] In steps S311 to S313 of some embodiments, the mother base station carries the multi-rotor sub-machine cluster to perform a first reconnaissance, and conducts reconnaissance on the target within the specified preset reconnaissance time until all targets are reconnaissanced. If the mother base station has not completed the reconnaissance of all targets within the specified preset reconnaissance time, that is, when the current reconnaissance time is greater than the preset reconnaissance time, the multi-rotor sub-machine cluster and the mother base station cooperate to reconnaissance the target until all targets are reconnaissanced. When all targets have been reconnaissanced, the mother base station can plan the return path through the dragonfly algorithm, laying a good foundation for returning to the designated landing point and completing the target reconnaissance mission.
[0097] In some embodiments, if the mother machine base station does not meet the first preset condition, a second investigation is performed, which may include but is not limited to steps S314 to S315:
[0098] Step S314, obtaining the target range and target time of the target reconnaissance task;
[0099] Step S315, judging whether the target reconnaissance task satisfies a second preset condition according to the target range and the target time, and executing a first sub-reconnaissance if the target reconnaissance task satisfies the second preset condition; and executing a second sub-reconnaissance if the target reconnaissance task does not satisfy the second preset condition.
[0100] In steps S314 to S315 of some embodiments, if the target reconnaissance task meets the requirements of large range and short time, that is, the target range of the target reconnaissance task is greater than the preset range, and the target time of the target reconnaissance task is less than the preset time, then the target reconnaissance task meets the second preset condition and the first sub-reconnaissance is performed; if the target range of the target reconnaissance task is less than the preset range, or the target time of the target reconnaissance task is greater than the preset time, then the target reconnaissance task does not meet the second preset condition and the second sub-reconnaissance is performed. Among them, large range means that the target range of the target reconnaissance task is greater than the sum of the reconnaissance ranges of all multi-rotor sub-machines of each model; small range means that the target range of the target reconnaissance task is less than or equal to the sum of the reconnaissance ranges of the escort sub-machines; medium range means that the target range of the target reconnaissance task is less than or equal to the sum of the reconnaissance ranges of the reconnaissance sub-machines and the escort sub-machines, and is greater than the sum of the reconnaissance ranges of the escort sub-machines. Then, the duration of the reconnaissance mission is analyzed according to the reconnaissance type (detailed and basic) and area type (simple and complex) of the target reconnaissance mission to obtain the length of time. A short time means that the target time of the target reconnaissance mission is less than the shortest endurance time of the mother base station, and a long time means that the target time of the target reconnaissance mission is greater than the shortest endurance time of the mother base station.
[0101] In some embodiments, if the target reconnaissance task satisfies the second preset condition, the first sub-reconnaissance is performed, which may include but is not limited to steps S3151 to S3153:
[0102] Step S3151, obtaining the demand quantity corresponding to each model of the multi-rotor sub-machine;
[0103] Step S3152, setting the disengagement rule of the multi-rotor sub-machine;
[0104] Step S3153: According to the demand and the separation rule, the mother base station and the multi-rotor sub-machine detect the target.
[0105] In steps S3151 to S3153 of some embodiments, the mother base station analyzes the corresponding demand for multi-rotor sub-machines of various models according to the target reconnaissance mission, and sets the disengagement rules for the multi-rotor sub-machines to unlock and disengage from the mother base station. The disengagement rules follow the principle that the mother base station can recover the multi-rotor sub-machines in the optimal execution path, and follow the principle that the center of gravity of the rotary-fixed-wing tilt-rotating sub-mother-and-child UAV remains in a stable state. In addition, when the tilt locking device of the mother base station releases the multi-rotor sub-machine, it follows the principles of the maneuverability and endurance, safety and environmental adaptability of the multi-rotor sub-machine cluster, and reducing airflow interference.
[0106] According to the demand and the disengagement rules, the mother base station carries the multi-rotor sub-machine and releases the multi-rotor sub-machine after arriving at the optimal position. The multi-rotor sub-machine cluster and the mother base station cooperate to detect targets until all targets have been detected. When all targets have been detected, the mother base station can plan the return path through the dragonfly algorithm, laying a solid foundation for returning to the designated landing point and completing the target detection mission. Among them, after the selected reconnaissance sub-machine receives the corresponding reconnaissance task, the tilt-type locking device of the mother base station unlocks and releases the corresponding reconnaissance sub-machine, and the selected escort sub-machine ensures communication security and assists in detection according to the task situation. The mother base station obtains the reconnaissance information and working condition data of each model in real time to optimize task allocation.
[0107] In some embodiments, if the target reconnaissance task does not meet the second preset condition, a second sub-reconnaissance is performed, which may include but is not limited to steps S3154 to S315B:
[0108] Step S3154, obtaining the demand quantity corresponding to each model of the multi-rotor sub-machine;
[0109] Step S3155, setting the disengagement rule of the multi-rotor sub-machine and setting a preset detection time;
[0110] Step S3156, planning a preset path of the multi-rotor aircraft by using a path planning algorithm;
[0111] Step S3157, the multi-rotor drone detects the target according to the preset path, the demand and the disengagement rule;
[0112] Step S3158, when the power of the multi-rotor is less than a preset threshold, return to the mother machine base station;
[0113] Step S3159, releasing the substitute multi-rotor sub-machine according to the number of the multi-rotor sub-machines that have returned to the mother base station;
[0114] Step S315A, according to the preset path and the disengagement rule, the substitute multi-rotor drone detects the target;
[0115] Step S315B, if the current detection time is greater than the preset detection time, the mother base station and the multi-rotor sub-machine detect the target.
[0116] In steps S3154 to S315B of some embodiments, the mother machine base station analyzes the demand corresponding to each model of multi-rotor sub-machines according to the target detection task, and can plan and optimize the preset path of the multi-rotor sub-machines through the policy gradient algorithm and the dragonfly algorithm. According to the preset path, the demand corresponding to each model of multi-rotor sub-machines and the preset separation rules, the mother machine base station releases the multi-rotor sub-machine to detect the target. When the power of the multi-rotor sub-machine is less than the preset threshold, it automatically returns to the mother machine base station for charging. The mother machine base station automatically plans the optimal time period and releases the corresponding number of substitute multi-rotor sub-machines again according to the number of multi-rotor sub-machines returning. The substitute multi-rotor sub-machine detects the target according to the preset path. If the multi-rotor sub-machine has not completed the detection of all targets within the preset detection time, that is, when the current detection time is greater than the preset detection time, the multi-rotor sub-machine cluster and the mother machine base station cooperate to detect the target until all targets are detected. When all targets have been detected, the mother base station can use the dragonfly algorithm to plan the return route, laying a solid foundation for returning to the designated landing point and completing the target detection mission.
[0117] In step S400 of some embodiments, after the mother-child drone completes the reconnaissance mission, if the multi-rotor sub-machine is not released during the mission, the mother-child drone directly returns to the designated landing point to end the target reconnaissance mission. If the multi-rotor sub-machine is released during the mission, it will autonomously detect whether the multi-rotor sub-machine cluster has been recovered. If all the multi-rotor sub-machines have been recovered, the mother-child drone returns to the designated landing point to end the target reconnaissance mission. If there are still unrecovered multi-rotor sub-machines, the mother-child base station transmits the optimal recovery path instruction and execution path to the multi-rotor sub-machine cluster, coordinates the multi-rotor sub-machines to gather to the mother-child base station, and after the recovery is completed, the mother-child drone returns to the designated landing point to end the target reconnaissance mission.
[0118] like Figure 3 As shown, when the rotary-fixed-wing tilt-rotating mother-and-child UAV performs mission reconnaissance alone or in collaboration, efficient communication is maintained through multi-point communication, multi-terminal collaborative chain and mesh communication mechanisms. The communication process may include but is not limited to the following steps:
[0119] 1. Communication channel modeling: First, it is necessary to model the communication channel between the rotary-fixed-wing tilt-rotor mother-and-child UAVs, which involves considering the impact of environmental factors, distance, moving speed, etc. on signal transmission.
[0120] 2. Communication waveform design: Design a suitable communication waveform based on channel characteristics to improve the reliability and efficiency of UAV cluster communication.
[0121] 3. Network architecture and protocol: Establish a network architecture suitable for the UAV system and design communication protocols to ensure the correct transmission and processing of data.
[0122] 4. Drone intelligent collaboration: Drones share information and resources through intelligent collaboration mechanisms to improve overall work efficiency and response speed.
[0123] 5. Resource allocation optimization: In the time division multiplexing mode, the time resources and power resources of the UAV are allocated, and the trajectory is jointly optimized to maximize the efficiency of the system.
[0124] 6. Cross-domain heterogeneous collaboration: For systems composed of different types of drones, such as fixed-wing aerial drones and surface unmanned ships, fixed-wing tilt-rotor mother-and-child drones need to study the implementation methods of cross-domain heterogeneous collaboration to ensure effective communication and collaboration between different platforms.
[0125] 7. Simulation and verification: Verify the feasibility and effectiveness of the designed communication mechanism by building a semi-physical simulation platform or testing in an actual environment.
[0126] Among them, the chain and mesh communication mechanisms of multi-point communication and multi-terminal collaboration also include:
[0127] The escort sub-machine can maintain the security of the state information communication transmission between the other drones. In the initial state, the detective sub-machine and the escort sub-machine communicate directly with the mother base station in a chain, forming a mesh chain transmission communication. When the distance between the reconnaissance sub-machine and the mother base station is greater than the limit value of the wireless communication transmission distance, the mother base station will call the escort sub-machine as a relay communication point. When there is no idle escort sub-machine that can be used as a relay point, the idle reconnaissance sub-machine will be called as a relay communication node. The mother base station transmits and forwards detective communication instructions and tasks to the relay point, and forms a mesh communication through collaborative communication and relay point communication between multiple drones, thereby maintaining stable communication between the multi-rotor sub-machine and the mother base station.
[0128] When the escort sub-machine or the reconnaissance sub-machine is used as a relay point, the mother machine base station obtains the reconnaissance information and working condition data of each model, adjusts the direction of the multi-rotor sub-machine at the relay point to be consistent with the reconnaissance flight direction of the multi-rotor sub-machine at the required connection point, and coordinates the multi-rotor sub-machines at the connection point. With the support of the auxiliary communication of the multi-rotor sub-machine at the relay point, the transmission distance between the multi-rotor sub-machine at each transmission communication point and the mother machine is within the limit value range of safe wireless transmission.
[0129] When the distance between a multi-rotor drone performing a target reconnaissance mission and the mother base station exceeds the limit range of safe wireless transmission, the mother base station will coordinate and mobilize other multi-rotor drones to add relay points to assist in signal communication between the multi-rotor drone and the mother machine. The mother base station adjusts the number of multi-rotor drones at relay points according to mission requirements. If there are no multi-rotor drones that can be mobilized as relay points, the mother base station will adjust the multi-rotor drones that exceed the limit range back to within the limit range, and then optimize the collaborative path between the multi-rotor drone cluster and the mother base station, so that the required reconnaissance area can be effectively detected.
[0130] The embodiment of the present invention enables multiple drones to exchange information simultaneously through multi-point communication. Under this mechanism, the information communication of drones is no longer just point-to-point linear transmission, but can form a chain-like flow communication of information between multiple points, allowing drones of various models in different locations to communicate in real time, greatly improving the efficiency of cluster collaboration; through multi-terminal collaboration, multiple drones can realize data and resource sharing and synchronization on the platform. This cross-device collaborative working capability ensures the continuity and flexibility of collaborative reconnaissance between the sub-machine and the mother machine base station, making the reconnaissance more efficient; multi-point communication and multi-terminal collaboration are combined to construct a more complex chain and mesh communication mechanism for drone clusters. In chain communication, information is transmitted from a drone at one node to a drone at the next node in a certain order to form a chain of information transmission, while mesh communication is a more complex structure. In mesh communication, drones at any node are allowed to communicate directly with drones at any other node to form a complex network communication.
[0131] like Figure 4 , Figure 5 , Figure 6 and Figure 7 As shown, the embodiment of the present invention also provides a rotary-fixed-wing tilt-rotating mother-and-child UAV cooperative autonomous reconnaissance system, which may include but is not limited to:
[0132] The mother machine base station 100 is provided with a built-in high-efficiency battery 101, a first detection device 102 and a tilting locking device 103;
[0133] The multi-rotor sub-machine 200 includes a reconnaissance sub-machine 210 and an escort sub-machine 220;
[0134] The reconnaissance sub-machine 210 is provided with a second reconnaissance device 211 and a first locking device 212;
[0135] The escort submachine 220 is provided with a third detection device 221, a communication relay device, a second locking device 222 and a third locking device 223;
[0136] Wherein, the first locking device 212 of the reconnaissance sub-machine 210 is connected to the tilting locking device 103 of the mother base station 100;
[0137] The second locking device 222 of the escort type sub-machine 220 is connected to the tilting locking device 103 of the mother machine base station 100;
[0138] The mother base station and the multi-rotor sub-machine are used to perform target reconnaissance tasks using the method described in any one of claims 1-7.
[0139] Specifically, the mother base station is a vertical take-off and landing fixed-wing endurance mother base station, with a reconnaissance camera on the nose, which can carry a large number of multi-rotor sub-machines, undertake task allocation and large-area monitoring and reconnaissance, and the tilt-type locking device is installed under the fixed wing of the mother base station. When the multi-rotor sub-machine leaves the mother base station, it follows the principle that the center of gravity of the mother machine is within the stable axis distance safety range. The support brought by its tilt-type locking device to the mother base station follows the balance principle of the mother base station. This principle is that the mother base station supports the forward speed and lift according to the specific situation. When supporting, the number and position of the multi-rotor sub-machines on both sides of the ailerons activated by the mother base station are corresponding and symmetrical, thereby providing balanced auxiliary support to the mother base station. In addition, the tilt-type locking device has the function of realizing the tilting and charging endurance of the multi-rotor sub-machine, which can not only provide endurance and guarantee for the multi-rotor sub-machine cluster, but also effectively use the multi-rotor sub-machine to provide the mother base station with some forward acceleration, deceleration power and a certain degree of lift after tilting.
[0140] The reconnaissance sub-machine adopts a multi-rotor model, carries a reconnaissance camera on the nose, is equipped with high-precision reconnaissance equipment, and has a locking device installed on the fuselage. The reconnaissance sub-machine is used for detailed target reconnaissance analysis and data collection.
[0141] The escort-type sub-aircraft adopts a multi-rotor model, carries a reconnaissance camera on the nose, and is equipped with reconnaissance equipment. The escort-type sub-aircraft is equipped with communication relay equipment inside the fuselage, and locking devices are installed at the bottom and top of the fuselage. It can be used to carry multi-rotor sub-aircraft, provide escort for the multi-rotor sub-aircraft cluster and assist the mother base station and other multi-rotor sub-aircraft in performing tasks, and can also assist in the rescue and recovery of other multi-rotor sub-aircraft in the event of accidents.
[0142] In addition, the tilt-type locking device of the mother base station includes a tilt module and a locking module. When the multi-rotor sub-machine approaches the mother machine, it can connect the sub-mother drone through the locking module. Compared with the magnetic suction device, this docking method can effectively avoid the interference of the electromagnetic field or reduce the power consumption of the mother base station. The tilt-type locking device can automatically complete the locking and unlocking of the multi-rotor sub-machine cluster docking process within a certain distance, and can also ensure the accuracy of the multi-rotor sub-machine cluster positioning and adjustment of the docking in the process of approaching the mother machine by calling GPS positioning, visual assistance or other sensors. The locking device of the escort sub-machine also has a function similar to the tilt-type locking device, which can realize docking with other sub-machines or mother base stations, and rescue the aircraft when other sub-machines have accidents. When performing locking docking, the corresponding model drone will autonomously call the relative vision module, locking module, positioning module, and dragonfly algorithm to assist and support, and complete the locking docking of the relative positioning of the sub-machine and the mother-machine.
[0143] like Figure 8a As shown, when the mother base station conducts independent reconnaissance, the tilt-type locking device can be used to assist and support the sub-machine cluster. After determining that the mother base station does not need to unlock the sub-machine, and that the mother base station needs the assistance and support of the sub-machine cluster, the type of support required by the mother base station is determined. When the mother base station needs lift support and speed support, the tilt-type locking device tilts the multi-rotor sub-machine cluster forward, and the multi-rotor sub-machine cluster starts lift, so that the mother base station can obtain lift and speed assistance support; when the mother base station needs lift support and deceleration support, the tilt-type locking device tilts the multi-rotor sub-machine cluster backward, and the multi-rotor sub-machine cluster starts lift, so that the mother base station can obtain lift and deceleration assistance support.
[0144] like Figure 8b As shown, when the mother machine base station is mounted with a callable sub-machine, the mother machine base station can analyze through sensors whether it is necessary to tilt the rotor machine through the tilting locking device. If the rotor machine is not needed, the tilting locking device will be on standby; if the rotor machine is needed, the tilting locking device will perform corresponding operations according to the needs, and the corresponding sub-machine will start lift. The operation may include but is not limited to: the tilting locking device is tilted to make the corresponding sub-machine tilt forward, thereby obtaining lift and speed boost; the tilting locking device is tilted to make the corresponding sub-machine tilt backward, thereby obtaining lift and deceleration boost; the tilting locking device is tilted to make the corresponding sub-machine tilt left, thereby obtaining lift and right roll boost; the tilting locking device is tilted to make the corresponding sub-machine tilt right, thereby obtaining lift and left roll boost.
[0145] Fig. 9 is an optional flow chart of a reconnaissance method for a rotary-fixed-wing tilt-rotating mother-and-child UAV provided in an embodiment of the present invention. Fig. 9 Taking the example of a rotary-fixed-wing tilt-rotating mother-and-child UAV, the following are the steps for detecting the drone:
[0146] Step N1: The mother base station receives the target reconnaissance mission, and analyzes the target reconnaissance mission using the policy gradient method and the dragonfly algorithm before arriving at the target. After arriving at the target, the mother base station determines whether the endurance mother base station can independently and optimally complete the reconnaissance without releasing the multi-rotor sub-machine cluster based on its own capabilities, regional scope, and mission difficulty. If so, execute step N2; if not, execute step N3.
[0147] Step N2: The mother base station carries the multi-rotor sub-machine cluster to perform the reconnaissance mission until all targets are reconnaissanced, and then executes step A. If the mother base station does not complete the reconnaissance within the specified time, then execute step K.
[0148] Step N3: The mother machine base station analyzes the number of sub-machines of each type required for the target reconnaissance mission and specifies the rules for each sub-machine to unlock and detach from the mother machine; the selected reconnaissance sub-machine detaches from the mother machine after receiving the corresponding reconnaissance mission, and the selected escort sub-machine ensures communication security and assists in reconnaissance according to the mission situation. The mother machine base station obtains the patrol information and working condition data of each model in real time to optimize task allocation. The execution path of single or multi-target reconnaissance is realized and optimized through the multi-core FCM clustering analysis algorithm and the policy gradient method. If the reconnaissance mission is a large-scale short-term mission, step D1 is executed; if the reconnaissance mission is a small-scale long-term mission or other, step D2 is executed. If the sub-machine fails to complete the reconnaissance mission within the specified time, step K is executed.
[0149] Step D1: The mother base station releases the multi-rotor sub-machine after reaching the optimal position according to the reconnaissance mission. The sub-machine and the mother base station cooperate in reconnaissance until all reconnaissance targets are completed, and then execute step L.
[0150] Step D2: The mother base station optimizes the execution path of the slave allocation according to the reconnaissance task, releases the optimal number of slaves to perform the reconnaissance task, and automatically returns to the mother base station for charging when the released slaves are low on power. The mother base station automatically plans the optimal time period and releases the corresponding number of slaves again for replacement. When all reconnaissance targets are completed, execute step L.
[0151] Step K: The sub-machine cluster and the main machine cooperate to detect the target and charge and sustain battery life autonomously until all the detected targets are detected. After the detection is completed, execute step L.
[0152] Step A: The mother base station plans the return route, and after returning to the designated landing point, the reconnaissance mission is completed and ended.
[0153] Step L: The sub-machine cluster gathers towards the mother machine base station. The mother machine base station coordinates the drone cluster to transmit the optimal recovery path instruction and execution path. After the recovery is completed, it returns to the designated landing point, completing and ending the reconnaissance mission.
[0154] After the above-mentioned mother-child drone completes the reconnaissance mission, if the child drone is not released, it will return to the designated landing point to complete and end the reconnaissance mission. If the child drone has been released, it will autonomously detect whether all the child drone clusters have been recovered. If all have been recovered, it will return to the designated landing point to complete and end the reconnaissance mission; if not all have been recovered, execute step L.
[0155] In some embodiments, the process of using the policy gradient method to plan and allocate the execution paths of reconnaissance missions of various aircraft types and the number of drones in the reconnaissance area involves the steps of initializing reconnaissance data, reconnaissance strategy network, generating execution paths of reconnaissance missions, allocating the number of drones in the area, real-time execution and monitoring, evaluation and optimization, and real-time application. Specifically, it includes the following steps:
[0156] 1. Initialization of reconnaissance data:
[0157] 1.1. Define the problem and objectives: Determine the area scope, mission objectives, number of drones, etc. of the reconnaissance mission.
[0158] 1.2. Define state space and action space: Divide the reconnaissance area into discrete grids or other suitable state representations, where each state represents a position in the area. For each drone, define its feasible actions, such as moving to an adjacent position, staying in place, etc.
[0159] 1.3. Initialize the policy network: Build a policy network that receives the state as input, outputs the probability distribution of the action, and initializes the weights and biases of the neural network.
[0160] 1.4. Define the reward function: The reward function is used to evaluate the quality of each action. It is designed according to the task objectives. The reward function includes a combination of indicators such as task completion, energy consumption, and coverage. Among them, the coverage reward R c The expression is:
[0161]
[0162] Energy consumption penalty R e The expression is:
[0163] R e =-Energy consumption
[0164] Task Completion R t The expression is:
[0165] R t =Task Completion
[0166] 2. Reconnaissance Strategy Network:
[0167] 2.1、Sampling data:
[0168] Use the policy network to select actions based on the current state to perform the drone's path planning task in the environment and collect sample data.
[0169] 2.2. Calculate the gradient:
[0170] Use sampled data to calculate the policy gradient, that is, to estimate the gradient of the policy network parameters. This can be done by using the REINFORCE algorithm, whose gradient calculation formula is:
[0171]
[0172] Among them, θ represents the policy parameter; πθ(a t |s t ) represents the output of the policy network; b(s t ) represents the benchmark function; R t Represents the reward at the current moment, that is, the degree of task completion; a t represents the action selected at time step t; s t represents the state at time step t; represents the gradient vector of the policy gradient; t represents a single time step; T represents the final time step; J(θ) represents the expected return with respect to the policy parameters θ.
[0173] 2.3. Update parameters:
[0174] Use the gradient ascent method to update the parameters of the policy network, and use optimizers such as SGD or Adam to update so that the expected value of the reward function is maximized.
[0175] 2.4. Iterative training:
[0176] Repeat steps 2.1 to 2.3 until the policy network converges or reaches the preset number of training times.
[0177] 3. Generate the execution path of the reconnaissance task:
[0178] 3.1. Using the strategy network: Use the trained strategy network to generate the path of the mother-child drone according to the status of the reconnaissance area.
[0179] 3.2. Path planning: Based on the generated path, combined with Dijkstra’s path planning algorithm, the shortest path is assigned to each UAV.
[0180] 4. Number of drones in the allocation area:
[0181] According to the regional scope and number of drones of the reconnaissance mission, drones are reasonably allocated to different areas to ensure global reconnaissance coverage and efficiency.
[0182] 5. Real-time execution and monitoring:
[0183] 5.1. Implement reconnaissance missions: Implement reconnaissance missions of the mother-and-child drones according to the assigned paths and areas.
[0184] 5.2. Real-time monitoring: Monitor the execution of the UAV and adjust the strategy network parameters or path planning based on real-time feedback to adapt to the dynamically changing mission environment and requirements.
[0185] 6. Evaluation and optimization:
[0186] 6.1. Evaluate performance: Conduct performance evaluation on the implemented reconnaissance missions, including indicators such as coverage, energy consumption, and mission completion time.
[0187] 6.2. Tuning and improvement: Tune and improve the policy network and path planning algorithm based on the evaluation results to improve the efficiency and effectiveness of the reconnaissance mission.
[0188] 7. Real-time application:
[0189] 7.1. Real-time control: Apply the optimized policy network and path planning algorithm to the actual reconnaissance mission to control the execution of the mother-child UAV in real time.
[0190] 7.2. Dynamic Adjustment: Dynamically adjust the UAV task allocation and path according to the real-time situation to cope with changes in the mission environment and requirements.
[0191] Specifically, the policy gradient method is as follows:
[0192] Assume that there is a reconnaissance state space set S, where each state s corresponds to the execution path of a reconnaissance mission and the number of drones of various types. In the reconnaissance action space set A, each action a corresponds to the decision of a drone to perform a reconnaissance mission in a certain area. Then in the policy gradient method, a parameterized policy function πθ(a|s) is defined, which represents the probability of selecting action a under state s, and θ is the parameter of the policy function.
[0193] By using gradient ascent to update the parameters of the policy function, the expected return increases and the expected return J(θ) is maximized, that is, the overall utility of the reconnaissance task is maximized. The gradient of the policy gradient theorem can be calculated as follows:
[0194]
[0195] In the formula, Q πθ (s,a) represents the state-action value function, which indicates the expected return after selecting action a in state s; Represents the gradient of the expected return, which represents the gradient vector of the expected return with respect to the policy function parameter θ; E πθrepresents the expected action under the policy πθ, which is the expected value of the random variable generated from the policy; Represents the gradient operation on the policy parameter θ.
[0196] Among them, the algorithm formula for estimating the gradient is:
[0197]
[0198] In the formula, Q πθ (s i ,a i ) is the detection state-action pair generated according to the strategy πθ; N is the number of sampled trajectories.
[0199] The entire algorithm optimization process can be completed by the gradient ascent algorithm. The gradient of the policy function, represents the gradient of the policy function with respect to the parameter θ, where the parameter update formula is:
[0200]
[0201] Where α is the learning rate; θ t+1 represents the policy parameters updated at the t+1th iteration; θ t represents the updated policy parameters at the tth iteration; J(θ t ) represents the policy parameter θ t expected return.
[0202] By using the policy gradient method to plan and allocate the execution paths of reconnaissance missions of various models and the number of drones in the corresponding area, the execution efficiency, resource utilization efficiency and flexibility of the mission can be improved, and it can adapt to complex mission environments. In addition, the dragonfly algorithm and Dijkstra algorithm can be combined to jointly optimize the reconnaissance path and area and meet the needs of reconnaissance, thereby achieving high efficiency, accuracy and reliable execution of reconnaissance missions.
[0203] Specifically, the process of Dijkstra algorithm includes the steps of path initialization, execution of Dijkstra algorithm, backtracking the shortest path, and returning the shortest path:
[0204] 1. Path initialization:
[0205] 1.1. Define the graph structure: Based on the map of the reconnaissance area, construct a directed weighted graph. The nodes in the graph represent different locations in the area, the edges represent the connection relationship between the locations, and the weights represent the movement cost.
[0206] 1.2. Initialization distance and predecessor node: For each node, the initialization distance is infinite (except the starting node) and the predecessor node is empty.
[0207] The distance is initialized as:
[0208] distance[v] = ∞ (for all vertices v)
[0209] distance[source]=0
[0210] Where distance[v] is the current shortest distance from vertex v to the source vertex; distance[source] is the shortest distance from the source vertex to other nodes. Since the distance from the source vertex to itself is 0, the shortest distance from the source vertex to other nodes is initialized to 0.
[0211] The precursor is initialized as:
[0212] predecessor[v] = None (for all vertices v)
[0213] Where predecessor[v] is the previous vertex of vertex v in the shortest path.
[0214] 1.3. Initialize the starting node: set the distance of the starting node to 0.
[0215] 2. Execute Dijkstra algorithm:
[0216] 2.1. Select the nearest node: Among them, V unuisited is the set of unvisited vertices, v closest is the unvisited vertex that is currently closest to the source vertex. V is the set of unvisited vertices unuisited The vertex closest to the source vertex. The node with the smallest distance from the unprocessed nodes is selected as the current node.
[0217] 2.2. Update the distance between adjacent nodes:
[0218] distance[w]=min(distance[w],distance[v closest ]+weight(v closest ,w))
[0219] For each unvisited neighbor vertex w, weight(v closest ,w) is from v closest The weight of the edge to w;
[0220] Mark the vertex: v closestMark it as visited and add it to the set of vertices for which the shortest path has been found. For each adjacent vertex of the current vertex, calculate the distance from the starting vertex through the current vertex to this adjacent vertex to obtain the calculated distance. If this calculated distance is less than the current distance of the adjacent vertex, then update the current distance of the adjacent vertex to this calculated distance and set the current vertex as the predecessor vertex of the adjacent vertex.
[0221] 2.3. Mark the current vertex as processed: Mark the current vertex as processed and no longer consider the exploration path starting from it.
[0222] 2.4. Repeat steps 2.1 to 2.3: Repeatedly select the nearest vertex, update the distances of adjacent vertices, and mark the processed vertices until all vertices have been processed.
[0223] 3. Backtrack the shortest path:
[0224] 3.1. Start backtracking from the end vertex: Starting from the end vertex, backtrack along the predecessor vertex of each vertex until backtracking to the starting vertex.
[0225] 3.2. Record the exploration path: Record the path obtained by backtracking, which is the shortest exploration path from the starting vertex to the end vertex.
[0226] 4. Return the shortest path:
[0227] 4.1. Return the path: Return the shortest path recorded in step 3.2 as the shortest path for the mother-daughter UAV exploration. At this time, the process ends.
[0228] Exemplarily, the formulas, equations, and implementation system methods of Dijkstra's algorithm are as follows:
[0229] Suppose there is a directed exploration graph G=(V, E), where V is the set of vertices and E is the set of edges. Each edge consists of a starting vertex, a target vertex, and a weight. Initialize the shortest path of the exploration starting vertex to 0, and the shortest paths of other vertices to positive infinity. Mark all vertices as unvisited.
[0230] Iteratively update the shortest path: Repeat the following steps until all vertices are marked as visited:
[0231] Step 1. Select the vertex with the shortest path: Select the vertex with the current shortest path from the unvisited vertices as the current vertex.
[0232] Step 2. Update the shortest paths of adjacent vertices: For each adjacent vertex u' of the current vertex u, when distance[u]+weight(u, u')<distance[u'], update the shortest path of the adjacent vertex, then there is:
[0233] distance[u′]=distance[u]+weight(u,u′)
[0234] Where distance[u] represents the length of the current shortest reconnaissance path from the starting point to the current node u; weight(u,u′) represents the weight of the edge from the current node u to the adjacent node u′.
[0235] Step 3: Mark the current node as visited.
[0236] Repeat steps 1 to 3 above until all nodes are marked as visited. The shortest reconnaissance path can be obtained by backtracking from the target node to the starting node. If the specific path of the shortest reconnaissance path needs to be obtained, the predecessor node of each node is recorded during the iterative update of the shortest path.
[0237] By using the Dijkstra algorithm to plan the shortest path, the flight distance and time of the drone can be minimized, thereby saving energy and reducing mission execution time, improving reconnaissance efficiency, and allowing reconnaissance missions to be completed more quickly and accurately.
[0238] Specifically, the process of the multi-core FCM cluster analysis algorithm includes the following steps: obtaining reconnaissance mission target information, multi-core FCM cluster analysis, planning the paths of parent-child drones, collaborative path planning, path execution and adjustment:
[0239] 1. Obtaining reconnaissance mission target information: Collecting target information within the mission area, including the location and importance of single targets and multiple targets.
[0240] 2. Multi-core FCM cluster analysis: Use the multi-core FCM cluster analysis algorithm to cluster the targets in the task area, group similar targets into a group, and form multiple clusters. Cluster analysis can consider factors such as the spatial distance and importance between targets, so as to consider the correlation between targets when planning the path.
[0241] 3. Plan the paths of the mother-child drones: For a single target: Combine the Dijkstra algorithm and the dragonfly algorithm to plan the shortest path for the drone to reach a single target. For multiple targets: Take the center of each cluster as a virtual target point, and use the Dijkstra algorithm and the dragonfly algorithm to plan the shortest path for the child drone to reach the center of each cluster. For each cluster, select a child drone to cover all target points in the cluster, and then fully consider factors such as the number and flight capabilities of the child drones to plan the shortest path for the mother-child drones in the cluster.
[0242] 4. Collaborative path planning: The path of the child drone is collaboratively planned with the path of the mother drone to maximize the coverage and efficiency of the mission area. Combined with the communication and collaboration mechanism between the child and mother drones, it is ensured that the child and mother drones can cooperate and support each other when performing tasks, thereby coordinating the execution of reconnaissance missions.
[0243] 5. Path execution and adjustment: Apply the planned path to the mother-child UAV system and let the UAV execute the task according to the path. Then monitor the task execution in real time, and adjust and optimize the path and the allocation of various types of mother-child UAVs as needed to adapt to the actual situation during the task execution.
[0244] By using the multi-core FCM cluster analysis algorithm to perform rapid convergence of a single target and regional collaborative flight paths for multiple targets, local optimal reconnaissance can be made to emerge as the global optimal reconnaissance in the cluster, thereby improving collaborative efficiency. It can improve the initiative of the UAV system in executing the mission environment, planning paths, and allocating tasks, and improve the efficiency and accuracy of task execution, so that each model of the mother-child UAV can effectively execute and efficiently detect.
[0245] Specifically, the dragonfly algorithm can be used to plan the mother-child drones, solve the separation, alignment and aggregation of the mother-child drones, plan the shortest trajectory, recover the optimal execution path of the child drones and strengthen the regional allocation, and update the position, speed, status, and reconnaissance data of each model. In the application of drone cluster collaborative control, the dragonfly algorithm is an intelligent optimization algorithm that simulates the behavior of dragonfly groups in nature. This algorithm is mainly used to solve complex optimization problems, especially path planning and task allocation problems in dynamic environments. The following is the process of the dragonfly optimization algorithm in drone clusters:
[0246] 1. Population initialization: Define the reconnaissance space: In drone swarm applications, the search space is usually defined as a mission space or physical space, where each point represents a potential mission execution location or flight path node.
[0247] 2. Set boundary conditions: According to the performance and mission requirements of the drone, set reasonable boundary conditions such as flight altitude, speed and operating range to ensure that all operations are carried out under the premise of safety and compliance. Initialization position: The initial position and state (such as speed and direction) of each drone needs to be set according to the actual mission scenario, which can be preset or randomly generated by the ground control system.
[0248] 3. Role allocation and position update: Optimize the allocation of tasks for each model and update the reconnaissance position in real time.
[0249] 4. Separation behavior: In a drone swarm, separation behavior can help drones maintain a certain distance and avoid mid-air collisions. The mathematical model of this behavior can be used to adjust the relative positions between drones to maintain a safe flight interval.
[0250] 5. Queuing behavior: Queuing behavior simulates the speed matching of dragonflies when flying, which can be used to synchronize flight speeds in drone clusters to ensure coordination of formation flight. By adjusting flight speeds, drones can effectively form formations and adjust formations.
[0251] 6. Collaborative behavior: Coalition behavior helps drones form a specific cluster when performing tasks, which is very useful for performing certain specific tasks (such as regional monitoring, terrain mapping, etc.). This behavior model can enable drone clusters to form an effective search or coverage pattern around the target area.
[0252] 7. Target detection and position adjustment: Optimize the detection and position of single targets and multiple targets.
[0253] 8. Prey-seeking behavior: In a drone swarm, the behavior of detecting a target can be considered as the behavior of detecting a target mission. The drone optimizes its flight path to find and lock on to the target mission, such as search and rescue, target tracking, etc. This behavior pattern improves the execution efficiency and success rate of the mission.
[0254] 9. Avoidance behavior: In military applications, avoidance behavior can be used to avoid enemy threats, such as radar detection, air defense systems, etc. The drone avoids potential threat areas by adjusting the flight path in real time, thereby improving survivability and mission completion rate.
[0255] In addition, in order to better improve the application and effect of the dragonfly optimization algorithm in drone clusters, the following aspects need to be considered:
[0256] 10. Parameter adjustment: The performance of the algorithm depends largely on the parameter settings. Therefore, how to choose appropriate parameters is an important issue to consider when using the Dragonfly Optimization Algorithm.
[0257] 11. Adaptability analysis: Different optimization problems may require different algorithm variants or parameter settings. Understanding the adaptability of the algorithm and adjusting it according to the specific problem is the key to achieving the optimization goal.
[0258] 12. Comparative Study: Comparing the Dragonfly Optimization Algorithm with other optimization algorithms (such as genetic algorithms, particle swarm optimization, etc.) can better highlight its advantages and limitations.
[0259] The dragonfly optimization algorithm is used to simulate the group predation behavior of dragonflies in nature to solve the optimization problem. The algorithm process includes three main steps: cluster initialization, role allocation and position update, and target search and position adjustment. It can be used to solve the separation, alignment and aggregation of mother-child drones, plan the shortest trajectory, recover the optimal execution path of the child drone, strengthen regional allocation, and update the position, speed, status, and reconnaissance data of each model. The dragonfly algorithm can effectively solve the problem of trajectory area planning of mother-child drones in complex environments and improve the efficiency and safety of mission execution.
[0260] Exemplarily, the specific formula, equation, and implementation system method of the Dragonfly algorithm are as follows:
[0261] The Dragonfly algorithm involves multiple aspects in planning the execution path of the mother-child UAV area allocation, the shortest route path, and the path for recovering the child UAV, including key elements such as fitness function, state update equation, and selection strategy. The Dragonfly algorithm includes:
[0262] 1. Separation, which means avoiding the distance between individual drones from being too close to reduce the efficiency of reconnaissance and optimization:
[0263]
[0264] Among them, E k is the separation degree of UAV k; D represents the current position of the UAV; D j represents the position of the jth neighboring drone; J represents the number of neighboring drones of the kth drone in the group.
[0265] 2. Alignment, which indicates the degree to which a drone has the same individual speed as its neighboring drones:
[0266]
[0267] Among them, U k is the alignment degree of UAV k; V j Represents the flight speed of the jth neighboring UAV.
[0268] 3. Aggregation, which means that a drone has a tendency to move closer to nearby better drones:
[0269]
[0270] Among them, B k is the aggregation degree of drone k.
[0271] 4. Target source detection, indicating the position of the optimal drone individual in a certain iterative calculation.
[0272] S k =D + -D
[0273] Among them, S k is the target source detection degree of UAV k; D + Represents the optimal drone position in the current calculation.
[0274] 5. Danger dispersal aims to keep individuals as far away from the worst drone individuals as possible and improve the efficiency of optimization calculation:
[0275] T k =D - +D
[0276] Among them, T k D is the danger dispersal degree of drone k; - Represents the worst drone position in the current calculation.
[0277] Then the expression for updating the flight range of individual UAV k is:
[0278] ΔD k+1 =(eE i +uU i +bB i +sS i +tT i )+βD k
[0279] The expression for updating the UAV flight position is:
[0280] D i+1 =D i +ΔD k+1
[0281] Among them, e, u, b, and s represent the influence coefficient of separation, the influence coefficient of alignment, the influence coefficient of aggregation, and the influence coefficient of target source detection degree respectively; E i represents the separation degree of UAV k when the iteration count is i; U i represents the alignment degree of UAV k when the iteration count is i; B i represents the aggregation degree of drone k when the iteration count is i; S i represents the target source detection degree of UAV k when the iteration count is i; T i represents the iteration count i; β represents the inertia coefficient; i represents the subscript of the iteration count; ΔD k+1 Represents the flight position update range of UAV k; D k represents the currently calculated position of UAV k; D i Represents the current position of the drone when the iteration count is i; D i+1 Represents the current position of the drone when the iteration count is i+1.
[0282] The calculation process of the adaptively adjusted dragonfly algorithm includes the following 12 steps:
[0283] Step 1: Initialize the calculation parameters, consider the scale of solving the short-term optimization scheduling model of cascade UAVs, set the number of dragonfly algorithm populations N = 40, and the number of iterative calculations iter MAX =200.
[0284] Step 2: Use the dragonfly algorithm to take the state parameter positions of the mother base station and the multi-rotor sub-machine as decision variables, and calculate the upper limit Z of the position motion area. MAX(i,t) and the lower limit Z MIN(i,t) , according to the formula X r =Z MIN(i,t) +e×(Z MAX(i,t) -Z MIN(i,t) ) generates the initial cluster, where e is a random number between 0 and 1; X r Represents the set of initial clusters.
[0285] Step 3: Randomly select an initial drone individual, use the POA algorithm, based on the single drone optimization principle, to perform optimization calculations on the selected drone individual to ensure that at least one drone individual in the initial cluster is a feasible solution. Set the number of iterations iter = 1 and the drone dimension r = 0.
[0286] Step 4: Determine whether the drone has neighbors. If so, proceed to Step 5, otherwise proceed to Step 6.
[0287] Step 5: Perform population evolution calculation to obtain the separation degree E r , Alignment U r , Aggregation B r , Target source detection level S r And the danger dispersal T r . And calculate the individual position of the drone to update the range, and enter Step 7.
[0288] Step 6: The drone has no neighbors, according to formula X r =e×(Z MAX(i,t) -Z MIN(i,t) ) Carry out individual drone random flight and proceed to Step 7.
[0289] Step 7: Calculate the new individual after the current dimension position update, calculate the drone individual objective function value func2 before the current dimension update and the drone individual objective function value func1 after the update. If func2>func1, it means that the position change of this dimension is beneficial to the objective function calculation, then keep the position update of the current dimension, ΔX k,t+1 =ΔX k,t+1If func2 < func1, it indicates that the change in the current dimensional position is unfavorable to the objective function, then ΔX k,t+1 = 0, where ΔX k,t+1 represents the change in the position of the k-th drone at the (t + 1)-th iteration in a specific dimension.
[0290] Step8: Increment the calculation dimension of the drone individual by 1, i.e., r = r + 1. Determine whether the update of all dimensions of the drone individual is completed. If all dimensions are updated and r = r ,ax , then proceed to Step9; otherwise, return to Step5.
[0291] Step9: Update the position change amount ΔX k of the drone X t at time step t. The position update is X k,t+1 = X k,t + ΔX k,t+1 , where X k represents the position of the k-th drone; X t represents the current position of the drone at the t-th iteration; ΔX t represents the change in the drone's position at time step t; X k,t+1 represents the new position of the k-th drone at time step t + 1.
[0292] Step10: Let k = k + 1 and enter the optimization calculation of a new drone individual. If k ≥ N, the position update calculation of all drone individuals ends, and proceed to Step11. If k < N, return to Step4.
[0293] Step11: In the current iteration, find the optimal drone individual, compare it with the target position, and update the target position according to whether it is better than the objective function value of the target position. Let iter = iter + 1. If iter ≥ iter MAX , then proceed to Step12; otherwise, return to Step4.
[0294] Step12: Return the target position in the current loop iteration as the optimal calculation result, and the calculation ends.
[0295] In practical applications, the formulas involved in the above dragonfly algorithm need to be adjusted and parameterized according to specific problem scenarios and constraints. In addition, path planning also needs to consider factors such as the environmental constraints, self-constraints of the drones, and the constraints within the swarm to enable the drones to efficiently and safely complete tasks such as area allocation, reconnaissance, and recovery.
[0296] The embodiment of the present invention further provides a rotary-fixed-wing tilt-rotating type mother-and-child UAV cooperative autonomous reconnaissance device, which can implement the above-mentioned rotary-fixed-wing tilt-rotating type mother-and-child UAV cooperative autonomous reconnaissance method, and the device includes:
[0297] The first module is used to receive a target reconnaissance task, classify the target reconnaissance task, and obtain a classification result;
[0298] The second module is used to compare the efficiency of the multi-rotor sub-machine reconnaissance and the efficiency of the mother machine base station autonomous reconnaissance according to the classification results to obtain a comparison result;
[0299] The third module is used to execute the target detection task according to the comparison result;
[0300] The fourth module is used to return to the designated landing point and end the target reconnaissance mission.
[0301] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0302] The embodiment of the present invention further provides an electronic device, which includes a processor and a memory, wherein the memory stores a computer program, and when the processor executes the computer program, the above-mentioned method of cooperative autonomous reconnaissance of a rotary-fixed-wing tilt-rotating mother-and-child UAV is implemented. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.
[0303] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0304] refer to Fig.10 , Fig.10 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:
[0305] The processor 501 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present invention;
[0306] The memory 502 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 502 can store an operating system and other application programs. When the technical solution provided in the embodiments of this specification is implemented by software or firmware, the relevant program code is stored in the memory 502, and the processor 501 calls and executes a method for cooperative autonomous reconnaissance of a rotary-fixed-wing tilt-rotating mother-and-child UAV in an embodiment of the present invention;
[0307] Input / output interface 503, used to implement information input and output;
[0308] Communication interface 504, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);
[0309] A bus 505 that transmits information between the various components of the device (e.g., the processor 501, the memory 502, the input / output interface 503, and the communication interface 504);
[0310] The processor 501 , the memory 502 , the input / output interface 503 and the communication interface 504 are connected to each other in communication within the device via the bus 505 .
[0311] An embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned method of coordinated autonomous reconnaissance of a rotary-fixed-wing tilt-rotating mother-and-child UAV.
[0312] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0313] The embodiment of the present invention also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. The processor of the computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the aforementioned method for cooperative autonomous reconnaissance of a rotary-fixed-wing tilt-rotating type mother-and-child UAV.
[0314] In summary, the method and device for cooperative autonomous reconnaissance of a rotary-fixed-wing tilt-rotating mother-and-child UAV according to the embodiment of the present invention has the following advantages:
[0315] 1. The vertical take-off and landing fixed-wing endurance mother base station of the embodiment of the present invention is responsible for task allocation and large-area monitoring and reconnaissance. It is equipped with high-efficiency batteries, high-precision mapping and reconnaissance equipment, and a tilting locking device for recovering the sub-machine. The locking device has the function of realizing the tilting of the sub-machine and charging and endurance. It can not only provide endurance and protection for the sub-machine cluster as a base station, but also effectively use the sub-machine after tilting to provide some forward acceleration, deceleration power and a certain degree of lift for the mother base station.
[0316] 2. The multi-rotor reconnaissance sub-machine of the embodiment of the present invention is equipped with high-precision reconnaissance equipment and a locking device, which can perform detailed reconnaissance analysis and data collection; the multi-rotor escort sub-machine is equipped with reconnaissance equipment, communication relay equipment and rescue aircraft locking device, which is responsible for basic reconnaissance, ensuring communication security, and also providing escort functions for drone clusters, and assisting the mother machine and other sub-machines in executing tasks.
[0317] 3. When the mother-and-child drones of the embodiments of the present invention perform mission reconnaissance alone or in collaboration, they maintain efficient communication through multi-point communication, multi-terminal collaborative chain and mesh communication mechanisms, providing high scalability and robustness for drone communication. When a problem occurs with a drone at one node, information can be transmitted through the paths of other drones to ensure that communication is not interrupted. In addition, the communication mechanism also supports a variety of communication protocols and technical standards, so that different child devices and the mother base station can be seamlessly connected. This mechanism enables real-time collaboration between drones of various models distributed nearby to jointly advance the progress of reconnaissance, ensure that key information can be quickly conveyed, and respond in a timely manner, thereby improving the autonomy of the mother-and-child drone system, the flexibility of communication, and the execution capability of mission reconnaissance.
[0318] 4. The embodiment of the present invention uses the policy gradient method to allocate the execution path of the reconnaissance mission of each model and the number of corresponding drones in the region, uses the Dijkstra algorithm to plan the shortest path, uses the multi-core FCM clustering analysis algorithm to perform rapid convergence of a single target and regional collaborative flight paths of multiple targets, so that the local optimal reconnaissance emerges from the global optimal reconnaissance in the cluster, improves the drone coordination efficiency, uses the dragonfly algorithm to optimize the separation, alignment and aggregation of parent and child drones, optimizes the shortest track, recovers the optimal execution path of the sub-machine and strengthens regional allocation, and updates the position, speed, status, and reconnaissance data of each model.
[0319] 5. The embodiments of the present invention can improve the detection efficiency and the accuracy of data transmission, optimize the operation efficiency, endurance time, and communication stability of the UAV, and can achieve efficient and reliable single or multi-target detection in complex environment areas. It is suitable for efficient mapping of complex terrain, environmental monitoring, disaster area assessment, early warning, detection, urban planning and efficient operations in wide areas.
[0320] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.
[0321] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features described may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions, and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.
[0322] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.
[0323] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.
[0324] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.
[0325] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0326] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.
[0327] Although the 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 claims and their equivalents.
[0328] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the described embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.
Claims
1. A method for cooperative autonomous reconnaissance of a rotary-fixed-wing tilt-rotating mother-and-child UAV, characterized in that: The following steps are involved: receiving a target reconnaissance task, classifying the target reconnaissance task, and obtaining a classification result; According to the classification results, the efficiency of the multi-rotor sub-machine reconnaissance and the efficiency of the mother machine base station autonomous reconnaissance are compared to obtain a comparison result; According to the comparison result, executing the target reconnaissance task; Return to the designated landing point and end the target reconnaissance mission.
2. The method for cooperative autonomous reconnaissance of a rotary-fixed-wing tilt-rotating mother-and-child UAV according to claim 1 is characterized in that: The receiving of the target reconnaissance task, classifying the target reconnaissance task, and obtaining the classification result comprises the following steps: According to the detection capability of the mother base station and the detection range of the mother base station, the target detection task is first classified to obtain a first detection type; Based on the first reconnaissance type, performing a second classification on the target reconnaissance task to obtain a second reconnaissance type; The first investigation type includes large-scale basic investigation, medium-scale basic investigation, small-scale basic investigation, large-scale detailed investigation, medium-scale detailed investigation and small-scale detailed investigation; The second investigation type includes a simple investigation area and a complex investigation area.
3. The method for cooperative autonomous reconnaissance of a rotary-fixed-wing tilt-rotating mother-and-child UAV according to claim 1 is characterized in that: The step of executing the target detection task according to the comparison result includes the following steps: According to the comparison result, determine whether the mother machine base station meets the first preset condition, if the mother machine base station meets the first preset condition, perform a first investigation, if the mother machine base station does not meet the first preset condition, perform a second investigation; Among them, the first preset condition is that without releasing the multi-rotor sub-machine, the efficiency of the autonomous detection of the mother machine base station is greater than the efficiency of the detection of the multi-rotor sub-machine.
4. The method for cooperative autonomous reconnaissance of a rotary-fixed-wing tilt-rotating mother-and-child UAV according to claim 3 is characterized in that: If the mother machine base station meets the first preset condition, performing a first investigation includes the following steps: Set a preset detection time; If the current detection time is less than the preset detection time, the mother base station detects the target; If the current detection time is greater than the preset detection time, the mother base station and the multi-rotor sub-machine detect the target.
5. The method for cooperative autonomous reconnaissance of a rotary-fixed-wing tilt-rotating mother-and-child UAV according to claim 3 is characterized in that: If the mother machine base station does not meet the first preset condition, performing a second investigation includes the following steps: Obtaining the target range and target time of the target reconnaissance mission; According to the target range and the target time, determining whether the target reconnaissance task satisfies a second preset condition, if the target reconnaissance task satisfies the second preset condition, executing a first sub-reconnaissance, and if the target reconnaissance task does not satisfy the second preset condition, executing a second sub-reconnaissance; Among them, the second preset condition is that the target range is greater than the sum of the detection ranges of all the multi-rotor sub-machines, and the target time is greater than the shortest endurance time of the mother base station.
6. The method for cooperative autonomous reconnaissance of a rotary-fixed-wing tilt-rotating mother-and-child UAV according to claim 5 is characterized in that: If the target reconnaissance task satisfies the second preset condition, the first sub-reconnaissance is performed, including the following steps: Obtaining the demand for each model of the multi-rotor aircraft; Setting a disengagement rule for the multi-rotor aircraft; According to the demand and the disengagement rule, the mother base station and the multi-rotor sub-machine detect the target.
7. The method for cooperative autonomous reconnaissance of a rotary-fixed-wing tilt-rotating mother-and-child UAV according to claim 5 is characterized in that: If the target reconnaissance task does not meet the second preset condition, performing a second sub-reconnaissance includes the following steps: Obtaining the demand for each model of the multi-rotor aircraft; Setting the disengagement rules of the multi-rotor sub-machine and setting the preset detection time; Planning a preset path for the multi-rotor aircraft by means of a path planning algorithm; According to the preset path, the demand and the disengagement rule, the multi-rotor drone detects the target; When the power of the multi-rotor is less than a preset threshold, it returns to the mother base station; According to the number of the multi-rotor sub-machines that return to the mother base station, releasing the substitute multi-rotor sub-machines; According to the preset path and the disengagement rule, the substitute multi-rotor drone detects the target; If the current detection time is greater than the preset detection time, the mother base station and the multi-rotor sub-machine detect the target.
8. A rotary-fixed-wing tilt-rotating mother-and-child UAV cooperative autonomous reconnaissance system, characterized in that: include: The mother machine base station is equipped with a built-in high-efficiency battery, the first detection equipment and a tilting locking device; Multi-rotor sub-machines, including reconnaissance sub-machines and escort sub-machines; The reconnaissance sub-machine is provided with a second reconnaissance device and a first locking device; The escort type sub-machine is provided with a third detection device, a communication relay device, a second locking device and a third locking device; Wherein, the first locking device of the reconnaissance sub-machine is connected to the tilting locking device of the mother base station; The second locking device of the escort type sub-machine is connected to the tilting locking device of the mother machine base station; The mother base station and the multi-rotor sub-machine are used to perform target reconnaissance tasks using the method described in any one of claims 1-7.
9. A rotary-fixed-wing tilt-rotating mother-and-child UAV cooperative autonomous reconnaissance device, characterized in that: include: The first module is used to receive a target reconnaissance task, classify the target reconnaissance task, and obtain a classification result; The second module is used to compare the efficiency of the multi-rotor sub-machine reconnaissance and the efficiency of the mother machine base station autonomous reconnaissance according to the classification results to obtain a comparison result; The third module is used to execute the target detection task according to the comparison result; The fourth module is used to return to the designated landing point and end the target reconnaissance mission.
10. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 7.
Citation Information
Cited By
Method, device and medium for guiding slave aircraft to intercept target based on master aircraft of unmanned aerial vehicle
CN119270917A
Unmanned aerial vehicle detection equipment efficiency calculation method and device based on airspace grid
CN121328936A
Wide-area reconnaissance and hovering fine investigation cooperation method and system for putting multiple rotors on fixed wing
CN121523391A
Wide-area reconnaissance and hovering pinpointing coordination method and system for fixed-wing multi-rotor drop
CN121523391B
