CN117369512A - Unmanned aerial vehicle cooperated intelligent control and optimization system - Google Patents

Abstract

The invention discloses a collaborative intelligent control and optimization system for drones, which relates to the technical field of drone design. The main architecture of this collaborative control system includes the following technical modules: communication and instruction transmission module, environment perception and decision-making module , collaborative movement and task division module. The collaborative control system developed by the present invention in conjunction with multiple technical personnel is based on information exchange and instruction transmission between multiple drones to quickly respond and make decisions to the rapidly changing environment, realizing coordinated movement and control between multiple drones. Division of tasks can effectively ensure the maximization of overall collaborative efficiency and has important practical value.

Description

A collaborative intelligent control and optimization system for drones

Technical field

The invention relates to the technical field of UAV design, and in particular to a UAV collaborative intelligent control and optimization system.

Background technique

With the rapid development and application of drone technology, the development of drone technology has gone through multiple stages. The capabilities of a single drone can no longer meet the demand. From the initial reliance on the autonomous control of a single drone to complete tasks independently, Gradually evolved into collaborative work, communication and decision-making between multiple drones. In the early application stage, the development of wireless communications, satellite communications, mobile communications and other technologies has provided important support for the development of collaborative control of drones. Real-time communication between drones has become possible, and multiple drones can realize data processing. Transmission and command interaction. At the same time, artificial intelligence technology enables drones to realize intelligent decision-making, path planning and task allocation through learning and analysis of large amounts of data. It can make real-time decisions based on environmental changes and task requirements, improving the efficiency and adaptability of the overall system. . As time goes by, UAVs realize information sharing and exchange through communication networks. By integrating the sensor data and mission requirements of multiple UAVs, intelligent decision-making and task allocation are performed, so that UAVs can work together. Complete more complex tasks.

However, despite the widespread application of machine learning and artificial intelligence technology in UAV collaborative control, there are still many technical flaws, including at least the following prominent aspects: ① Unmanned aerial vehicles based on existing communication and network technologies Communication between drones will be affected by network bandwidth limitations, and the large amount of data transmitted between drones will cause delays, affecting real-time collaboration between drones. ② The sensor may fail or show poor performance in response to specific weather conditions or interference in the environment. The accuracy and stability may also be affected by factors such as mechanical vibration and temperature changes. ③Limitations of machine learning and artificial intelligence technology. Practical applications require a large amount of training data and computing resources to run machine learning algorithms, and greatly reduce the reliability and safety of the UAV control system. ④ The dynamic interaction and mutual influence between multiple UAVs poses new challenges to the formation control of UAVs. Further research on the design of collaborative methods is needed to improve the performance and stability of the formation control system. ⑤ In complex environments, UAV path planning may be restricted by various constraints such as airspace restrictions and obstacle avoidance, and efficient optimization algorithms need to be designed to solve this problem.

Contents of the invention

The technical problem to be solved by the present invention is to provide a collaborative intelligent control and optimization system for UAVs in view of the various deficiencies of the existing technology.

In order to solve the above technical problems, the technical solutions adopted by the present invention are as follows.

UAV collaborative intelligent control and optimization system. The collaborative control system quickly responds and makes decisions to the rapidly changing environment based on information exchange and instruction transmission between multiple UAVs, realizing collaboration between multiple UAVs. Division of movement and tasks ensures maximum overall collaborative efficiency.

As a preferred technical solution of the present invention, the collaborative control system includes the following technical modules: communication and instruction transmission module, environment perception and decision-making module, and collaborative movement and task division module.

As a preferred technical solution of the present invention, the communication and instruction transmission module uses binary coding to encode the UAV control instructions, and at the same time uses a decoding algorithm at the receiving end to convert the encoded instructions back to the original instructions; wireless local area network is used as the communication protocol, using standard frequency bands to establish hotspot networks between drones; automatically adjusts the data transmission rate according to channel quality and uses adaptive modulation methods and carrier-sensing multiple access protocols to adjust the time and frequency of data transmission between drones, with a maximum Reduce collisions and interference between drones to the greatest extent.

As a preferred technical solution of the present invention, the environment perception and decision-making module is equipped with a variety of sensors including high-definition cameras, laser radars, and ultrasonic sensors. By fusing the data of multiple sensors and using sensor fusion algorithms, the The accuracy and robustness of the drone's perception of the surrounding environment; at the same time, computer vision algorithms are used to detect and track the sensor data that has been preprocessed, feature extracted and data analyzed, and machine learning algorithms are used to model and predict the environment. And a planning algorithm and a task allocation algorithm are used to generate the adaptive path of each group of drones.

As a preferred technical solution of the present invention, the cooperative movement and task division module generates a smooth flight path for each drone through a path planning algorithm, and uses track prediction and dynamic obstacle avoidance algorithms to avoid obstacles. Detection and obstacle avoidance algorithms avoid collisions and avoid obstacles. At the same time, coordinated movement and task division among multiple UAVs are achieved through the design of collaborative control strategies based on distributed control algorithms and collective control algorithms.

As a preferred technical solution of the present invention, the data model and data process are constructed for the movement and task division module of the UAV intelligent system. The specific data process is: The construction process is:

(1) Construction of state and action model: Use vectors in finite-dimensional vector space to describe the state and action of the UAV. Let n-dimensional vector X_i=(x_1,x_2,...,x_n) represent UAV i The state of UAV i covers the information including position, speed, pitch angle, roll angle and yaw angle of UAV i in three-dimensional space; suppose m-dimensional vector U_i=(u_1,u_2,...,u_m) Represents the action of UAV i, including information including speed, angular velocity, and acceleration;

(2) Construction of motion model: Given the mapping relationship of F:R^n x R^m->R^n, the state change of the drone is X_i(t+1)=F(X_i(t),U_i( t))...(1), at time t+1, the state of drone i is determined by the state X_i(t) at time t and the action U_i(t);

(3) Objective function construction: By constructing the objective function, find an optimal path from the starting point to the end point that takes into account complex issues including risk and consumption and minimizes the path length and flight time. Let the objective function be Minimize the total moving distance, expressed as: min∑D(X_i(t+1),X_i(t))...(2), where D:R^n x R^n->R is the calculation between two states The function of moving distance, ∑ represents the sum of all positions; the state X_i of drone i needs to meet a certain range, X_i(t)∈S, where S is a finite-dimensional space, and the distance between two drones needs Maintain within a range;

(4) Construction of path planning algorithm: Project the position of the drone onto the coordinate system, and then independently find the optimal solution in each dimension. Specifically, during each iteration, for the k-th iteration: first Find the point x_1^ that minimizes the objective function under the coordinates of the first dimension, and then update x_1(k+1)=x_1^, and repeat this in each dimension (such as x_2, x_3,...,x_n) Operate until the convergence condition is met; define a continuously differentiable objective function to measure the degree of cooperation between drones, calculate the gradient of the objective function with respect to the drone position parameters, and then update the parameters in the direction of the negative gradient: for the kth iteration : First calculate the gradient of the objective function at the current UAV position x(k) Secondly update the drone position where α is the learning rate.

The invention also includes a device for supporting the execution of a UAV collaborative intelligent control and optimization system to implement the above data system. The device at least includes the following hardware technology modules: UAV body, flight control device, battery management Devices, load equipment devices.

As a preferred technical solution of the present invention, the drone body is equipped with a receiver and a control chip to enable hotspot network information transmission between drones to trigger corresponding programs.

As a preferred technical solution of the present invention, the flight control device uses a gyroscope and an accelerometer to measure the attitude and acceleration of the UAV through an inertial measurement unit, and controls the UAV according to the set control algorithm through the flight controller. It uses attitude control algorithms to adjust flight movements in real time based on sensor data to ensure the stability and accuracy of the drone.

As a preferred technical solution of the present invention, the load equipment device reserves load equipment slots and interfaces including cameras, sensors, and loads, and provides a stable platform and vibration isolation measures for the load equipment through the pan-tilt anti-shock system. , ensuring that the load equipment can work without interference.

The beneficial effect of adopting the above technical solution is that the UAV collaborative intelligent control and optimization system constructed by the present invention can quickly respond and make decisions to the rapidly changing environment based on information exchange and instruction transmission among multiple UAVs. Realize collaborative movement and task division among drones, maintain collaborative work and stable movement in a dynamic environment, and improve collaborative efficiency. The invention also helps to maximize the overall collaborative efficiency. Through the optimization algorithm and task allocation strategy, tasks are reasonably allocated and the task execution capability is expanded, so that each UAV can contribute to the overall collaboration to the greatest extent while completing its own tasks. The goal is to improve task execution efficiency, task coverage and response speed, and reduce resource waste. This invention realizes real-time collaborative decision-making and dynamic optimization through information exchange and instruction transmission between multiple UAVs, timely processing of abnormal situations and taking countermeasures, thereby improving the autonomy and adaptability of UAVs and enhancing task execution. safety and reliability. Generally speaking, the drone collaborative intelligent control and optimization system of the present invention can improve collaborative performance, quickly adapt to environmental changes, maximize overall collaborative efficiency, and improve task execution capabilities through collaborative control and optimization among multiple drones.

The following examples describe in detail the technical advantages and beneficial effects of various technical details of the present invention.

Detailed ways

The following examples illustrate the invention in detail. Various raw materials and various equipment used in the present invention are conventional commercially available products and can be directly obtained through market purchase.

In the description of the following embodiments, specific details such as specific system structures and technologies are provided for the purpose of explanation rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

It will be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements and/or components but does not exclude one or more other The presence or addition of features, integers, steps, operations, elements, components and/or collections thereof.

It will also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

As used in this specification and the appended claims, the term "if" may be interpreted as "when" or "once" or "in response to determining" or "in response to detecting" depending on the context. ". Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be interpreted, depending on the context, to mean "once determined" or "in response to a determination" or "once the [described condition or event] is detected ]" or "in response to detection of [the described condition or event]".

In addition, in the description of this application and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

Reference in this specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure or characteristic described in connection with the embodiment is included in one or more embodiments of the application. Therefore, the phrases "in one embodiment", "in some embodiments", "in other embodiments", "in other embodiments", etc. appearing in different places in this specification are not necessarily References are made to the same embodiment, but rather to "one or more but not all embodiments" unless specifically stated otherwise. The terms “including,” “includes,” “having,” and variations thereof all mean “including but not limited to,” unless otherwise specifically emphasized.

Example 1

The main body of the present invention has developed the following technical modules: communication and instruction transmission module, environment perception and decision-making module, collaborative movement and task division module, and based on the above modules, a data model is constructed to realize multiple groups of wireless Humans and machines work together stably, and minimize resource waste through optimized path planning algorithms to achieve coordinated movement and optimal task division among multiple drones.

Among them, the communication and instruction transmission module uses edge computing technology to place data processing and computing tasks on edge computing nodes closer to the drone, forming a distributed computing system to achieve distributed storage and collaborative processing of data. Establish communication links between drones, process and analyze the collected sensor data, generate control instructions and send them to the drones in time, thereby avoiding the performance bottleneck of a single node, making full use of the computing power of multiple computing nodes, and reducing the need for a single unmanned aerial vehicle. The dependence of humans and machines on communication network bandwidth improves the effect of real-time collaboration between drones.

Among them, the environment perception and decision-making module includes a variety of sensors such as high-definition cameras, lidar, and ultrasonic sensors. The high-definition camera can be used to collect video information, provide high-resolution and high-precision image information, and identify and track the ground and targets; lidar It can be used to generate point cloud data, conduct three-dimensional modeling and obstacle detection of the surrounding environment, which is crucial to improving the obstacle avoidance ability of drones; ultrasonic sensors can be used for short-range detection to provide the distance and speed of objects in the surrounding environment, etc. data. By fusing data from multiple sensors, a more complete and accurate environmental model is established, and data quality control, noise reduction and other optimizations are carried out. This can improve the perception effect of the drone, allowing the drone to better understand the surrounding environment and perform tasks more accurately. The sensor data that has undergone preprocessing, feature extraction and data analysis, such as image data collected by high-definition cameras, are used to extract features such as shape, size, color and texture of the target using traditional visual algorithms or deep learning methods. Carry out target detection and tracking, and then complete the perception of the surrounding environment, so that the drone can more clearly understand the conditions of pedestrians, vehicles, buildings and other objects in the surrounding environment, further improving the accuracy and reliability of drone control. Using a variety of data sources, such as historical data, sensor data and model data, you can build a model of the environment and then make predictions to improve the efficiency and flexibility of UAV collaborative control.

Among them, the collaborative motion and task division module generates a smooth flight path for each UAV through a path planning algorithm and calculates the target position, flight constraints, such as minimum turning radius, maximum speed and environmental information factors. The best path for the drone to reach the target point. Use the UAV's motion model and target track information to predict the UAV's position and speed in the future. In this way, possible conflicts can be discovered in time during the flight and corresponding avoidance strategies can be adopted. The dynamic obstacle avoidance algorithm uses machine learning or traditional obstacle avoidance algorithms to detect obstacles and adjust paths based on real-time perceived obstacle information to avoid collisions with obstacles and maintain high flight safety. Through the construction of data models and data processes, each drone can independently make decisions and adjustments based on environmental information and mission requirements, and through collaborative control among multiple drones, they can complete their missions. Cooperate and collaborate with each other at the same time.

On this basis, the project team jointly developed specific executable data processes with third-party manufacturers and university researchers, including:

(1) Construction of state and action model: Use vectors in finite-dimensional vector space to describe the state and action of the UAV. Let n-dimensional vector X_i=(x_1,x_2,...,x_n) represent UAV i The state of UAV i covers the information including position, speed, pitch angle, roll angle and yaw angle of UAV i in three-dimensional space; suppose m-dimensional vector U_i=(u_1,u_2,...,u_m) Represents the action of UAV i, including information including speed, angular velocity, and acceleration;

(2) Construction of motion model: Given the mapping relationship of F:R^nx R^m->R^n, the state change of the drone is X_i(t+1)=F(X_i(t),U_i( t))...(1), at time t+1, the state of drone i is jointly determined by the state X_i(t) at time t and the action U_i(t);

(3) Objective function construction: By constructing the objective function, find an optimal path from the starting point to the end point that takes into account complex issues including risk and consumption and minimizes the path length and flight time. Let the objective function be Minimize the total moving distance, expressed as: min∑D(X_i(t+1),X_i(t))...(2), where D:R^n x R^n->R is the calculation between two states The function of moving distance, ∑ represents the sum of all positions; the state X_i of drone i needs to meet a certain range, X_i(t)∈S, where S is a finite-dimensional space, and the distance between two drones needs Maintain within a range;

(4) Construction of path planning algorithm: Project the position of the drone onto the coordinate system, and then independently find the optimal solution in each dimension. Specifically, during each iteration, for the k-th iteration: first Find the point x_1^ that minimizes the objective function under the coordinates of the first dimension, and then update x_1(k+1)=x_1^, and repeat this in each dimension (such as x_2, x_3,...,x_n) Operate until the convergence condition is met; define a continuously differentiable objective function to measure the degree of cooperation between drones, calculate the gradient of the objective function with respect to the drone position parameters, and then update the parameters in the direction of the negative gradient: for the kth iteration : First calculate the gradient of the objective function at the current UAV position x(k) Secondly update the drone position where α is the learning rate.

Example 2

For the UAV collaborative intelligent control and optimization system, the present invention has developed a device for supporting the application of the above system. The device at least includes the following hardware technology modules: UAV body, flight control device, battery management device, load Equipment installation.

The receiver equipped on the drone body is used to receive wireless signals sent by the hotspot network. The receiver generally refers to a wireless communication module, such as a Wi-Fi module or a Bluetooth module. These modules have the function of receiving wireless signals and can receive wireless data sent by other drones within a specified range. The control chip is responsible for controlling the navigation, movement and mission of the drone. When the receiver receives the hotspot network information between drones, the control chip will analyze the information and trigger the corresponding program for processing based on preset rules and logical judgments. These programs can be pre-written or generated in real time, depending on the specific application scenario and task requirements.

The flight control devices include inertial measurement units, flight controllers, motor controllers, etc. The inertial measurement unit is a device that integrates sensors such as gyroscopes and accelerometers. It is used to measure the angular velocity and acceleration of the UAV. It measures the angular velocity of the UAV through the gyroscope, which is the rotation speed of the UAV. , and the accelerometer is used to measure the acceleration and attitude of the UAV; through the processing and calculation of the sensor measurement data, the attitude information of the UAV can be obtained, including pitch, roll, yaw angle, etc., as well as the UAV's attitude information. status parameters such as speed and position. The flight controller calculates the control amount required by the UAV by receiving sensor data and flight instructions, and sends the control signal to the flight control device to control the movement and attitude of the UAV, using embedded microcontrollers or FPGAs. A computer, combined with sensors such as gyroscopes, accelerometers, and magnetometers, performs data collection, signal processing, and control calculations. The flight control device refers to the hardware device in the UAV flight control system. The control device receives the control signal from the flight controller and controls the flight attitude and movement of the UAV by adjusting the speed and steering of the motor. Flight control devices usually need to respond quickly to instructions from the flight controller to ensure the stability and accuracy of the drone.

The load equipment device can provide stable power supply for load equipment such as cameras, sensors, and loads. This can be achieved through an integrated battery pack or an external power interface, ensuring continuous power support for the load device during flight. At the same time, corresponding data transmission and control interfaces are provided, allowing the drone to receive data collected by the load equipment in real time, and process and control it. This can be achieved through serial port, Ethernet or wireless communication to meet the data interaction needs between the payload device and the flight control device. Furthermore, the load equipment will generate a certain amount of heat during operation, and thermal management is required to ensure that the load equipment can work within a suitable temperature range. Load equipment devices can use components such as radiators, fans or temperature sensors to dissipate and monitor heat to prevent overheating from affecting equipment performance and life. Consider the need for rapid replacement and maintenance of load equipment. The design of the load equipment allows easy removal and installation of the load equipment, easy access and maintenance of equipment interfaces and cables. At the same time, the load equipment device is also equipped with a pluggable modular structure so that it can be quickly adapted when replacing different types of load equipment. The load equipment device can integrate fault detection and automatic alarm mechanisms to monitor and detect the working status of the load equipment in real time. When an equipment failure or abnormal situation is discovered, the device can automatically alarm and provide corresponding fault diagnosis information so that flight operators can take appropriate measures in a timely manner.

In the above embodiments, each embodiment is described with its own emphasis. For parts that are not detailed or documented in a certain embodiment, please refer to the relevant descriptions of other embodiments.

In various embodiments, the hardware implementation of the technology can directly use existing smart devices, including but not limited to industrial computers, PCs, smart phones, handheld stand-alone machines, floor-standing stand-alone machines, etc. Its input device preferably uses an on-screen keyboard, its data storage and calculation module uses existing memories, calculators, and controllers, its internal communication module uses existing communication ports and protocols, and its remote communication uses existing GPRS networks and Wanwan. Dimensional Internet, etc.

Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above functional units and modules is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs. Module completion means dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be hardware-based. It can also be implemented in the form of software functional units. In addition, the specific names of each functional unit and module are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present application. For the specific working processes of the units and modules in the above system, please refer to the corresponding processes in the foregoing method embodiments, and will not be described again here.

In the embodiments provided by the present invention, it should be understood that the disclosed apparatus/terminal equipment and methods can be implemented in other ways. For example, the apparatus/terminal equipment embodiments described above are only illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components. can be combined or can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, indirect coupling or communication connection of devices or units, which may be in electrical, mechanical or other forms. A unit described as a separate component may or may not be physically separate. A component shown as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Each functional unit in various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or software functional units. Integrated modules/units may be stored in a computer-readable storage medium if implemented in the form of software functional units and sold or used as independent products. Based on this understanding, the present invention can implement all or part of the processes in the methods of the above embodiments, and can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can be stored in a computer-readable storage medium. When executed by the processor, the steps of each of the above method embodiments can be implemented. . Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. Computer-readable media may include: any entity or device that can carry computer program code, recording media, USB flash drives, mobile hard drives, magnetic disks, optical disks, computer memory, read-only memory (Read-Only Memory, ROM), random access memory (RandomAcces Memory, RAM), electrical carrier signals, telecommunications signals, and software distribution media, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include Electrical carrier signals and telecommunications signals.

The above-described embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still implement the above-mentioned implementations. The technical solutions described in the examples are modified, or some of the technical features are equivalently replaced; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of the present invention, and should be included in within the protection scope of the present invention.

Claims (10)

1. UAV collaborative intelligent control and optimization system, characterized in that: the collaborative control system quickly responds and makes decisions to the rapidly changing environment based on information exchange and instruction transmission among multiple UAVs, realizing multiple autonomous drones. The collaborative movement and task division between humans and machines ensures that the overall collaborative efficiency is maximized. 2. The UAV collaborative intelligent control and optimization system according to claim 1, characterized in that: the collaborative control system includes the following technical modules: communication and instruction transmission module, environment perception and decision-making module, collaborative movement and task division module. 3. The UAV collaborative intelligent control and optimization system according to claim 2, characterized in that: the communication and instruction transmission module uses binary coding to encode the UAV control instructions, and at the same time uses a decoding algorithm at the receiving end. Convert the encoded instructions back to the original instructions; use wireless LAN as the communication protocol and use standard frequency bands to establish a hotspot network between drones; automatically adjust the data transmission rate according to the channel quality and adopt adaptive modulation methods and carrier sensing multiple access protocol adjustments The time and frequency of data transmission between drones minimizes collisions and interference between drones. 4. The UAV collaborative intelligent control and optimization system according to claim 2, characterized in that: the environment perception and decision-making module is equipped with a variety of sensors including high-definition cameras, lidar, and ultrasonic sensors. The data from multiple sensors are fused and sensor fusion algorithms are used to improve the accuracy and robustness of the drone's perception of the surrounding environment; at the same time, computer vision algorithms are used to perform target detection and For tracking, machine learning algorithms are used to model and predict the environment and planning algorithms and task allocation algorithms are used to generate adaptive paths for each group of drones. 5. The UAV collaborative intelligent control and optimization system according to claim 2, characterized in that: the collaborative movement and task division module generates a smooth flight path for each UAV through a path planning algorithm, and uses Track prediction and dynamic obstacle avoidance algorithm obstacle detection and obstacle avoidance algorithms to avoid collisions and obstacle avoidance. At the same time, coordinated movement and task division among multiple UAVs are achieved through the design of collaborative control strategies based on distributed control algorithms and collective control algorithms. 6. The UAV collaborative intelligent control and optimization system according to claim 5, characterized in that: the data model and data process are constructed for the motion and task division module of the UAV intelligent system, and the specific data process is for: (1) Construction of state and action model: Use vectors in finite-dimensional vector space to describe the state and action of the UAV. Let n-dimensional vector X_i=(x_1,x_2,...,x_n) represent UAV i The state of UAV i covers the information including position, speed, pitch angle, roll angle and yaw angle of UAV i in three-dimensional space; suppose m-dimensional vector U_i=(u_1,u_2,...,u_m) Represents the action of UAV i, including information including speed, angular velocity, and acceleration; (2) Construction of motion model: Given the mapping relationship of F:R^n x R^m->R^n, the state change of the drone is X_i(t+1)=F(X_i(t),U_i( t))...(1), at time t+1, the state of drone i is determined by the state X_i(t) at time t and the action U_i(t); (3) Objective function construction: By constructing the objective function, find an optimal path from the starting point to the end point that takes into account complex issues including risk and consumption and minimizes the path length and flight time. Let the objective function be Minimize the total moving distance, expressed as: min∑D(X_i(t+1),X_i(t))...(2), where D:R^n x R^n->R is the calculation between two states The function of moving distance, ∑ represents the sum of all positions; the state X_i of drone i needs to meet a certain range, X_i(t)∈S, where S is a finite-dimensional space, and the distance between two drones needs Maintain within a range; (4) Construction of path planning algorithm: Project the position of the drone onto the coordinate system, and then independently find the optimal solution in each dimension. Specifically, during each iteration, for the k-th iteration: first Find the point x_1^ that minimizes the objective function under the coordinates of the first dimension, and then update x_1(k+1)=x_1^, and repeat this in each dimension (such as x_2, x_3,...,x_n) Operate until the convergence condition is met; define a continuously differentiable objective function to measure the degree of cooperation between drones, calculate the gradient of the objective function with respect to the drone position parameters, and then update the parameters in the direction of the negative gradient: for the kth iteration : First calculate the gradient of the objective function at the current UAV position x(k) Secondly update the drone position where α is the learning rate. 7. A device for supporting the execution of a UAV collaborative intelligent control and optimization system, used to implement the system according to claim 1, characterized in that: the device at least includes the following hardware technology modules: UAV body, Flight control device, battery management device, payload equipment device. 8. A device for supporting the execution of a UAV collaborative intelligent control and optimization system according to claim 7, characterized in that: the UAV body is equipped with a receiver and a control chip to realize inter-UAV Hotspot network information transmission triggers corresponding procedures. 9. A device for executing a collaborative intelligent control and optimization system for drones according to claim 7, characterized in that: the flight control device uses a gyroscope and an accelerometer to measure the drone through an inertial measurement unit. The attitude and acceleration of the drone are controlled by the flight controller according to the set control algorithm. The attitude control algorithm is used to adjust the flight action in real time based on the sensor data to ensure the stability and accuracy of the drone. sex. 10. A device for supporting and executing a cooperative intelligent control and optimization system for drones according to claim 8, characterized in that: the load equipment device reserves load equipment slots including cameras, sensors, and loads. position and interface, and provides a stable platform and vibration isolation measures for the load equipment through the PTZ anti-shock system to ensure that the load equipment can work without interference.