UAV control system and method based on information collaboration

Abstract

The present invention provides a UAV control system and method based on information collaboration, the system includes processing the multi-source perception data of the UAV based on real-time data fusion and intelligent decision-making algorithm, and then adopting a collaborative control strategy to plan the flight path to obtain the flight trajectory of the UAV; determining key control points in the flight trajectory of the UAV, building a collaborative control framework based on the key control points, collaboratively controlling the UAV in the target direction, and obtaining collaborative control data; setting control parameters according to the collaborative control data to limit the decision range of the intelligent decision-making algorithm; searching for the optimal flight path and energy allocation scheme based on the optimization algorithm and energy management strategy under the criteria of meeting the mission requirements and minimizing energy consumption, and collaboratively optimizing the flight state of the UAV. The present invention can improve the autonomy and energy efficiency of the UAV in complex environments, while ensuring the safety of flight and the flexibility of tasks.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle automatic control, and more specifically, to an unmanned aerial vehicle control system and method based on information collaboration. Background Art

[0002] Existing drone control systems mainly rely on a single data source and control algorithm, which often has limitations when handling tasks in complex environments. Due to the lack of real-time data fusion and intelligent decision-making algorithms, these systems have difficulty responding quickly and accurately when faced with changing environmental conditions. In addition, traditional drone flight path planning often ignores the importance of collaborative control, resulting in the inability to effectively coordinate the actions of each drone when performing multi-drone missions, thus affecting the overall operational efficiency and safety.

[0003] In terms of flight path planning, many existing technologies fail to fully consider the balance between mission requirements and energy consumption, resulting in the drone not being able to achieve optimal energy efficiency when performing tasks. At the same time, existing technologies often lack precise algorithm support for determining key control points and building collaborative control frameworks, making it difficult for drones to achieve efficient collaborative operations when performing complex tasks.

[0004] In terms of mission planning and execution, existing UAV systems usually use serial processing, which is inefficient when processing multiple tasks and difficult to meet the requirements of real-time and parallel processing. In addition, the lack of adaptability of the task allocation algorithm makes it difficult for the UAV system to flexibly adjust the task allocation strategy when facing dynamically changing task requirements, affecting the timeliness and accuracy of task execution.

[0005] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the prior art: the existing UAV control systems have problems of low efficiency, poor adaptability and insufficient real-time performance in data processing, flight path planning, collaborative control and mission planning. These problems limit the autonomy of UAVs in complex environments and the flexibility of mission execution. Summary of the invention

[0006] The present invention provides an unmanned aerial vehicle control system and method based on information collaboration.

[0007] In a first aspect of the present invention, there is provided a drone control system based on information collaboration, comprising:

[0008] Based on real-time data fusion and intelligent decision-making algorithms, the multi-source perception data of the UAV is processed, and then the flight path is planned using a collaborative control strategy to obtain the flight trajectory of the UAV;

[0009] Determine the key control points in the flight trajectory of the UAV, build a collaborative control framework based on the key control points, collaboratively control the UAVs in the target direction, and obtain collaborative control data; set control parameters based on the collaborative control data to limit the decision range of the intelligent decision-making algorithm;

[0010] Under the principle of meeting mission requirements and minimizing energy consumption, based on optimization algorithms and energy management strategies, the optimal flight path and energy allocation scheme are searched to collaboratively optimize the flight status of the UAV.

[0011] Furthermore, the real-time data fusion is a Kalman filter algorithm; the mathematical model of the intelligent decision-making algorithm is:

[0012]

[0013] in, is the state estimation vector, is the control input vector, A is the state transfer matrix, B is the control input matrix, is the process noise, is the measurement output vector, H is the measurement matrix, is the measurement noise, K is the Kalman gain, is the time step.

[0014] Furthermore, the processing of multi-source perception data of the drone includes:

[0015] The sensor data carried by the drone is used as input, and the environmental state of the current stage is estimated according to the flight state of the previous stage. The optimal data fusion algorithm is selected according to the environmental state and the characteristics of the sensor data.

[0016] Obtain the corresponding fusion strategy based on the optimal data fusion algorithm, and obtain the state estimation based on the fusion strategy;

[0017] Based on state estimation, a control algorithm is used to design the flight control law of the UAV; the flight state of the UAV is controlled by the flight control law, and then the collaborative control coefficient of the corresponding data fusion algorithm is used to collaboratively optimize the flight state of the UAV.

[0018] Furthermore, the optimal data fusion algorithm is a data fusion algorithm corresponding to the minimum error under different environmental conditions.

[0019] Further, determining the key control points in the flight trajectory of the drone includes:

[0020] The UAV's perception data is sequentially processed through data processing, state estimation, and flight path planning to obtain the UAV's flight path;

[0021] Search for key control points in the flight path as the flight targets of the UAV, perform collaborative control on the flight targets of multiple adjacent control points in segments, and count the relative deviation of each control point in the collaborative control results and the average deviation of the control points in the segment;

[0022] The control segment with the smallest average deviation is taken as the target segment, and the control points are selected according to the relative deviation threshold, the flight path information of each selected control point is extracted, and the optimized control point is selected as the key control point.

[0023] Furthermore, the parameter range of the collaborative control framework is:

[0024]

[0025]

[0026] Among them, P is the control point number, Q is the control parameter number; W is the collaborative control width in the direction of the control point number, and H is the collaborative control height in the direction of the control parameter number. The construction model of the collaborative control framework is:

[0027]

[0028] in, is the collaborative control input, is the collaborative control gain, To coordinate the control output, is the output matrix, is the system state, J is the performance index, and are the adjustment values ​​of the collaborative control framework parameters P and Q respectively.

[0029] Furthermore, the collaborative optimization of the flight status of the UAV includes: dividing the flight path of the UAV along the heading into multiple segments according to the mission requirements, first obtaining the flight status of the central flight path before and after adjustment according to the mission requirements at the edge of the path and the adjacent paths, and then obtaining the flight status and lateral distance of other flight paths before and after adjustment.

[0030] In a second aspect of the present invention, a method for controlling a drone based on information collaboration is provided, comprising:

[0031] Acquiring flight data obtained according to the UAV control system based on information collaboration;

[0032] Based on the adaptive task allocation algorithm, the flight data is divided into multiple task modules; according to the task requirements, the CPU is used to allocate the corresponding task modules to the UAV in real time, and the task modules to be executed are allocated to the control unit of the UAV;

[0033] Based on the parallel computing platform, the computing resources of the UAV are used to parallelly process multi-task modules to execute the UAV's tasks.

[0034] Furthermore, based on the adaptive task allocation algorithm, the flight data is divided into multiple task modules, including: according to a preset task requirement threshold, a task allocation algorithm is used to allocate the flight data layer by layer to obtain each task module, and according to the task requirements of adjacent task modules, adjacent task modules are merged until the total task requirement threshold of the task module is reached to obtain multiple task modules.

[0035] Furthermore, the CPU is used to allocate corresponding task modules to the UAV in real time according to the task requirements, and the task modules to be executed are allocated to the control unit of the UAV, including:

[0036] Calculate the task module data to be assigned to the drone according to the current task requirements; use the priority queue data structure to build task allocation and initialize the task module data assigned to the drone;

[0037] When the mission requirements change, determine the type of mission requirement change and update the mission modules in the UAV; calculate the update threshold of task allocation, determine whether it is necessary to clear useless mission modules in the UAV and whether to allocate new mission modules to the UAV, and perform the required clearing or allocation operations.

[0038] The above-mentioned embodiments of the present invention have at least the following beneficial effects: The drone control system of the present invention can efficiently process the multi-source perception data of the drone through real-time data fusion and intelligent decision-making algorithms, and realize accurate flight path planning. The system adopts a collaborative control strategy, which can determine the key control points in the flight trajectory and build a collaborative control framework based on this, thereby optimizing the flight state of the drone. In addition, the system can minimize energy consumption while meeting mission requirements through optimization algorithms and energy management strategies, search for the optimal flight path and energy allocation plan, and improve the flight efficiency of the drone and the flexibility of mission execution.

[0039] Furthermore, the UAV task planning method of the present invention utilizes an adaptive task allocation algorithm to divide flight data into multiple task modules and allocate them to UAVs in real time according to task requirements. The method is based on a parallel computing platform, which enables the UAV to process multiple task modules in parallel, thereby improving the efficiency and response speed of task execution. In this way, the UAV can quickly adapt to changes in task requirements in a complex and changing environment, ensuring the smooth completion of the task and the safety of the UAV operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which:

[0041] Figure 1 A schematic diagram of a process flow of a UAV mission planning system based on information collaboration provided by an embodiment of the present invention;

[0042] Figure 2 A schematic diagram of a flow chart of a method for UAV mission planning based on information collaboration provided by an embodiment of the present invention;

[0043] Figure 3 The schematic diagram schematically shows the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0045] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, apparatus, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0046] It should be noted that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0047] Reference below Figure 1 , Figure 1 The following is a flow chart of a UAV control system based on information collaboration provided by an embodiment of the present invention. Figure 1 As shown, a UAV control system 100 based on information collaboration includes:

[0048] Step 101, based on real-time data fusion and intelligent decision-making algorithms, multi-source perception data of the UAV is processed, and then a collaborative control strategy is used to plan the flight path to obtain the flight trajectory of the UAV;

[0049] Step 102, determining key control points in the flight trajectory of the UAV, constructing a collaborative control framework based on the key control points, collaboratively controlling the UAVs in target directions, and acquiring collaborative control data; setting control parameters based on the collaborative control data, and limiting the decision range of the intelligent decision algorithm;

[0050] Step 103, under the principle of meeting mission requirements and minimizing energy consumption, based on the optimization algorithm and energy management strategy, search for the optimal flight path and energy allocation solution, and coordinately optimize the flight status of the UAV.

[0051] It should be noted that processing the multi-source perception data of drones based on real-time data fusion and intelligent decision-making algorithms means that the system needs to be able to receive and integrate data from different sensors on drones, such as GPS, cameras, radars, etc., and then use algorithms to analyze and process them in order to make decisions. This requires the system to have a high degree of data compatibility and processing capabilities.

[0052] Specifically, real-time data fusion can use the Kalman filter algorithm, which is a commonly used data fusion technology that can estimate the state of a dynamic system. Intelligent decision-making algorithms may include but are not limited to genetic algorithms, neural networks, or reinforcement learning, which are used to make decisions on flight path planning based on the fused data. When implementing, it is necessary to set the parameters of the algorithm, such as the initial state estimation of the Kalman filter, the covariance of the process noise and the measurement noise, etc.

[0053] Preferably, in order to improve the accuracy and efficiency of data processing, a distributed computing architecture can be used to distribute the computing tasks of data fusion and intelligent decision-making algorithms to multiple processing units. In addition, the mathematical model of the intelligent decision-making algorithm can be further refined. For example, the state transfer matrix and the control input matrix can be customized according to the dynamic model and mission requirements of the UAV to adapt to different flight environments and mission requirements.

[0054] In some embodiments, the real-time data fusion is a Kalman filter algorithm; the mathematical model of the intelligent decision algorithm is:

[0055]

[0056] in, is the state estimation vector, is the control input vector, A is the state transfer matrix, B is the control input matrix, is the process noise, is the measurement output vector, H is the measurement matrix, is the measurement noise, K is the Kalman gain, is the time step.

[0057] It should be noted that the real-time data fusion is a Kalman filter algorithm, which means that when implemented, the system will use the Kalman filter algorithm to process and fuse the multi-source perception data of the drone. Kalman filtering is an effective recursive filter that can estimate the state of a dynamic system from a series of noisy measurements.

[0058] Specifically, the implementation of the Kalman filter algorithm requires the definition of parameters such as the state estimation vector, control input vector, state transfer matrix, control input matrix, process noise, measurement output vector, measurement matrix, measurement noise, and Kalman gain. These parameters need to be accurately set according to the specific flight characteristics of the UAV and the performance of the sensor. For example, the state estimation vector may include the position, velocity, and acceleration of the UAV, while the control input vector may include instructions from a remote control or automatic control system.

[0059] Preferably, in order to improve the accuracy and robustness of the Kalman filter algorithm, variants such as extended Kalman filter EKF or unscented Kalman filter UKF can be used, which can better handle nonlinear systems. In addition, the parameters of the Kalman filter, such as the covariance of process noise and measurement noise, can be dynamically adjusted according to real-time data through machine learning methods such as online learning or adaptive filtering technology to adapt to environmental changes and fluctuations in sensor performance.

[0060] In some embodiments, the processing of multi-source perception data of the drone includes:

[0061] The sensor data carried by the drone is used as input, and the environmental state of the current stage is estimated according to the flight state of the previous stage. The optimal data fusion algorithm is selected according to the environmental state and the characteristics of the sensor data.

[0062] Obtain the corresponding fusion strategy based on the optimal data fusion algorithm, and obtain the state estimation based on the fusion strategy;

[0063] Based on state estimation, a control algorithm is used to design the flight control law of the UAV; the flight state of the UAV is controlled by the flight control law, and then the collaborative control coefficient of the corresponding data fusion algorithm is used to collaboratively optimize the flight state of the UAV.

[0064] It should be noted that the processing of the multi-source perception data of the UAV includes: taking the sensor data carried by the UAV as input, estimating the environmental state of the current stage according to the flight state of the previous stage, and selecting the optimal data fusion algorithm according to the environmental state and sensor data characteristics. It emphasizes that the UAV system needs to consider multiple aspects when processing multi-source data, including data input, environmental state estimation and data fusion algorithm selection.

[0065] Specifically, the sensors carried by the drone may include but are not limited to GPS, IMU inertial measurement unit, visual sensor, radar, etc., and the data provided by these sensors will be used as input. Environmental state estimation may involve the positioning, speed, location of surrounding obstacles, etc. of the drone. The selection of the optimal data fusion algorithm will be based on the current environmental state and the characteristics of the sensor data. For example, if the environment is changing dynamically, it may be necessary to select an algorithm that can respond to changes quickly.

[0066] Preferably, in order to more effectively process multi-source sensor data, a machine learning algorithm can be used to automatically identify and select the most appropriate data fusion algorithm. In addition, an adaptive system can be designed that can adjust the parameters of the data fusion algorithm based on real-time feedback to optimize performance. For example, the system can monitor the quality of sensor data and environmental changes in real time, and adjust the noise covariance parameters of the Kalman filter accordingly, or introduce a weight adjustment mechanism in the fusion algorithm to improve the accuracy and robustness of the fusion result.

[0067] In some embodiments, the optimal data fusion algorithm is a data fusion algorithm corresponding to the minimum error under different environmental conditions.

[0068] It should be noted that the optimal data fusion algorithm is the data fusion algorithm corresponding to the minimum error under different environmental conditions, which emphasizes that the selection of data fusion algorithm should be based on the current environmental conditions and the principle of minimizing errors. This means that the system needs to be able to evaluate the performance of different data fusion algorithms in a specific environment and select the algorithm with the minimum error to process the perception data of the drone.

[0069] Specifically, the selection of the optimal data fusion algorithm may involve the comparison of multiple algorithms, such as Kalman filtering, particle filtering, Gaussian mixture model, etc. Each algorithm has its specific application scenarios and performance characteristics. For example, Kalman filtering is suitable for linear systems, while particle filtering is suitable for nonlinear systems. The system needs to evaluate the performance of each algorithm based on real-time environmental data and historical data, including its performance in estimation accuracy, computational complexity, and robustness.

[0070] Preferably, in order to achieve the selection of the optimal data fusion algorithm, an adaptive mechanism can be adopted, which can dynamically adjust the algorithm selection according to real-time feedback and environmental changes. For example, an algorithm selector based on reinforcement learning can be designed, which learns and predicts which algorithm will provide the smallest error by evaluating the historical performance of each algorithm under different environmental conditions. In addition, a multi-model fusion strategy can be introduced, that is, combining the advantages of multiple algorithms to improve the overall data fusion performance through a weighted or voting mechanism. This approach can further improve the adaptability and accuracy of the system.

[0071] In some embodiments, determining the critical control points in the flight trajectory of the drone includes:

[0072] The UAV's perception data is sequentially processed through data processing, state estimation, and flight path planning to obtain the UAV's flight path;

[0073] Search for key control points in the flight path as the flight targets of the UAV, perform collaborative control on the flight targets of multiple adjacent control points in segments, and count the relative deviation of each control point in the collaborative control results and the average deviation of the control points in the segment;

[0074] The control segment with the smallest average deviation is taken as the target segment, and the control points are selected according to the relative deviation threshold, the flight path information of each selected control point is extracted, and the optimized control point is selected as the key control point.

[0075] Specifically, the determination of critical control points involves a series of processing steps for the drone perception data, including data fusion, state estimation, and flight path planning. These steps require setting specific parameters, such as the selection of data fusion algorithms, parameters of state estimation models, such as the initial state and covariance matrix of the Kalman filter, and parameters of the flight path planning algorithm (such as the distance between waypoints, speed, and time constraints. The collaborative control of control points may involve the design of control algorithms, such as PID controllers or model predictive control MPC, and collaborative control strategies, such as communication protocols and coordination mechanisms between multiple drones.

[0076] Preferably, in order to more accurately determine the critical control points, advanced data analysis and machine learning techniques can be used to analyze flight data and identify key features and potential risk points in the flight path. In addition, optimization algorithms, such as genetic algorithms or particle swarm optimization PSO, can be introduced to automatically adjust the positions of control points to minimize the total deviation of the flight path. In terms of collaborative control, more complex control strategies, such as model-based collaborative control or adaptive collaborative control, can be designed to adapt to changing environmental conditions and mission requirements. These methods can further improve the safety and efficiency of UAV flights.

[0077] In some embodiments, the parameter range of the collaborative control framework is:

[0078]

[0079]

[0080] Among them, P is the control point number, Q is the control parameter number; W is the collaborative control width in the direction of the control point number, and H is the collaborative control height in the direction of the control parameter number. The construction model of the collaborative control framework is:

[0081]

[0082] in, is the collaborative control input, is the collaborative control gain, To coordinate the control output, is the output matrix, is the system state, J is the performance index, and are the adjustment values ​​of the collaborative control framework parameters P and Q respectively.

[0083] Specifically, the parameter range of the collaborative control framework involves the setting of the minimum and maximum values ​​of the control point number P and the control parameter number Q. These parameters define the control range that the drone can adjust when performing a mission. is a key parameter that determines the degree of influence of the control input on the system state. Output matrix Used to set the system status Mapping to control output The performance index J can be used to evaluate the control effect, and the adjustment amount and It is used to fine-tune control parameters to optimize performance.

[0084] Preferably, in order to more accurately control the flight of the UAV, an adaptive control algorithm can be used to dynamically adjust the cooperative control gain For example, fuzzy logic or neural networks can be used to optimize the UAV’s real-time flight data and environmental feedback. In addition, the output matrix Customized design can be performed based on the mission requirements and flight environment of the drone to better map the system state to the control output. When adjusting the control parameters, a multi-objective optimization algorithm can be introduced to simultaneously consider flight stability, safety, and energy efficiency to achieve more comprehensive flight performance optimization.

[0085] In some embodiments, the collaborative optimization of the flight state of the UAV includes: dividing the flight path of the UAV along the heading into multiple segments according to mission requirements, first obtaining the flight state of the central flight path before and after adjustment according to the mission requirements at the edge of the path and the adjacent path, and then obtaining the flight state and lateral distance of other flight paths before and after adjustment.

[0086] Specifically, the collaborative optimization process involves dividing the UAV's flight path into multiple segments and optimizing each segment. This includes adjusting the flight path and evaluating the flight status. The mission requirements at the edge of the path and the adjacent path may involve adjusting parameters such as flight speed, altitude, and heading. The flight status before and after the adjustment of the central flight path may include the UAV's position, speed, acceleration, etc. Lateral distance refers to the lateral deviation of the UAV from the predetermined path during flight.

[0087] Preferably, in order to perform collaborative optimization more effectively, advanced optimization algorithms such as genetic algorithms, particle swarm optimization or simulated annealing algorithms can be used to automatically find the optimal flight path and state. In addition, real-time data analysis and prediction models can be introduced to predict the impact of environmental changes on flight status and adjust flight parameters accordingly. When implementing collaborative optimization, the energy consumption of the drone and the urgency of the mission can also be considered to optimize energy use and improve flight efficiency while meeting mission requirements. These methods can further improve the performance and reliability of drones in complex tasks.

[0088] The above-mentioned embodiments of the present invention have the following beneficial effects: the UAV control system based on information collaboration can process the multi-source perception data of the UAV in real time, and realize accurate planning and optimization of the flight path through intelligent decision-making algorithms and collaborative control strategies. The system can collaboratively optimize the flight state of the UAV based on real-time data fusion and intelligent decision-making algorithms to ensure that energy consumption is minimized while meeting mission requirements. In addition, by determining key control points in the flight trajectory and building a collaborative control framework, the system can effectively guide the collaborative control of the UAV and obtain collaborative control data, thereby improving the accuracy and safety of the flight.

[0089] Furthermore, the system can flexibly adjust the data fusion algorithm and control strategy according to different environmental conditions and mission requirements. Through the adaptive task allocation algorithm, the system can divide the flight data into multiple task modules and distribute them to the drones in real time to achieve efficient execution of tasks. This drone control system based on information collaboration can improve the autonomy of drones in complex environments and the flexibility of task execution, while reducing the complexity of operations and improving overall operational efficiency.

[0090] like Figure 2 As shown, in some embodiments, a method 200 for planning a UAV mission based on information collaboration includes:

[0091] Step 201, obtaining flight data obtained by the UAV control system based on information collaboration;

[0092] Step 202, based on the adaptive task allocation algorithm, the flight data is divided into multiple task modules; according to the task requirements, the CPU is used to allocate the corresponding task modules to the UAV in real time, and the task modules to be executed are allocated to the control unit of the UAV;

[0093] Step 203, based on the parallel computing platform, the computing resources of the drone are used to parallelly process the multi-task modules to execute the drone's tasks.

[0094] It is understandable that the modules recorded in the information collaboration-based UAV mission planning method 200 are similar to the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the UAV mission planning system based on information collaboration are also applicable to the UAV mission planning method 200 based on information collaboration and the modules contained therein, and will not be repeated here.

[0095] In some embodiments, the adaptive task allocation algorithm is used to divide the flight data into multiple task modules, including: according to a preset task requirement threshold, a task allocation algorithm is used to allocate the flight data layer by layer to obtain each task module, and adjacent task modules are merged according to the task requirements of adjacent task modules until the total task requirement threshold of the task module is reached to obtain multiple task modules.

[0096] It should be noted that the method of using the CPU to allocate corresponding task modules to the drone in real time according to task requirements, and allocating the task modules to be executed to the control unit of the drone describes an important step in the drone task planning method, namely, how to dynamically allocate task modules to the drone according to real-time task requirements, and ensure that these task modules can be executed by the control unit of the drone.

[0097] Specifically, a task module refers to a series of subtasks divided according to the mission requirements of the drone, which can be data collection, monitoring, transportation, etc. The real-time allocation of CPU task modules involves the management and scheduling of computing resources, and the allocation needs to be determined based on the performance of the drone, the current task load, and the urgency of the task. The assignment of task modules to the drone's control unit means that these task modules will be received by the drone's control system and perform corresponding operations according to preset instructions.

[0098] Preferably, in order to more efficiently allocate task modules in real time, a priority scheduling algorithm can be used to dynamically adjust the execution order of tasks according to the urgency and importance of the tasks. In addition, a machine learning algorithm can be introduced to predict the time and resource consumption of task execution, thereby optimizing the task allocation strategy. In the task allocation process, the energy status and current location of the drone can also be considered to ensure the feasibility and efficiency of the task. For example, if a task module needs to be completed within a specific time, and the energy status of the drone is not sufficient to support it, the system can prioritize the allocation of task modules with lower energy consumption, or adjust the flight path to optimize energy use. These methods can further improve the flexibility and responsiveness of drone task planning.

[0099] In some embodiments, the CPU is used to allocate corresponding task modules to the drone in real time according to the task requirements, and the task modules to be executed are allocated to the control unit of the drone, including:

[0100] Calculate the task module data to be assigned to the drone according to the current task requirements; use the priority queue data structure to build task allocation and initialize the task module data assigned to the drone;

[0101] When the mission requirements change, determine the type of mission requirement change and update the mission modules in the UAV; calculate the update threshold of task allocation, determine whether it is necessary to clear useless mission modules in the UAV and whether to allocate new mission modules to the UAV, and perform the required clearing or allocation operations.

[0102] Specifically, the calculation of mission module data involves the analysis of the current mission requirements of the drone and how to convert these requirements into specific mission modules. A priority queue is a data structure that organizes mission modules according to the priority of the tasks, ensuring that high-priority tasks are executed first. The types of changes in mission requirements may include the addition, deletion, or change of priority of tasks. The update threshold of task allocation is a parameter used to determine when the task allocation needs to be updated to adapt to changes in mission requirements.

[0103] Preferably, in order to more effectively manage the allocation and update of task modules, an adaptive algorithm can be used to dynamically adjust the task allocation strategy. For example, machine learning techniques can be used to predict the optimal order and time of task execution based on the historical task execution data of the UAV and the current task requirements. In addition, a multi-objective optimization algorithm can be introduced to simultaneously consider the task completion time, energy consumption, and task priority to achieve a more comprehensive optimization. When the task requirements change, an event-driven mechanism can be used to quickly respond to these changes and update the allocation of task modules in a timely manner. These methods can further improve the flexibility and efficiency of UAV task planning.

[0104] Reference below Figure 3 , which shows a schematic diagram of the structure of an electronic device 300 suitable for implementing some embodiments of the present invention. The electronic devices in some embodiments of the present invention may include but are not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0105] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 to a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0106] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0107] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0108] The above descriptions are only some preferred embodiments of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention.

Claims

1. A UAV control system based on information collaboration, characterized in that: The system performs the following steps: Based on real-time data fusion and intelligent decision-making algorithms, the multi-source perception data of the UAV is processed, and then the flight path is planned using a collaborative control strategy to obtain the flight trajectory of the UAV; Determine the key control points in the flight trajectory of the UAV, build a collaborative control framework based on the key control points, collaboratively control the UAVs in the target direction, and obtain collaborative control data; Set control parameters based on collaborative control data to limit the decision scope of the intelligent decision-making algorithm; Under the principle of meeting mission requirements and minimizing energy consumption, based on optimization algorithms and energy management strategies, the optimal flight path and energy allocation scheme are searched to collaboratively optimize the flight status of the UAV; Determining the key control points in the flight trajectory of the UAV includes: The UAV's perception data is sequentially processed through data processing, state estimation, and flight path planning to obtain the UAV's flight path; Search for key control points in the flight path as the flight targets of the UAV, perform collaborative control on the flight targets of multiple adjacent control points in segments, and count the relative deviation of each control point in the collaborative control results and the average deviation of the control points in the segment; The control segment with the smallest average deviation is taken as the target segment, and the control points are selected according to the relative deviation threshold, the flight path information of each selected control point is extracted, and the optimized control point is selected as the key control point; The parameter ranges of the collaborative control framework are: ； ； in, is the control point number, Q is the control parameter number; is the coordinated control width in the direction of the control point number, In order to control the collaborative control height in the direction of parameter sequence number, the construction model of the collaborative control framework is: ； in, is the collaborative control input, is the collaborative control gain, To coordinate the control output, is the output matrix, is the system status, is the performance indicator, and They are the collaborative control framework parameters and The amount of adjustment.

2. The UAV control system based on information collaboration according to claim 1 is characterized in that: The real-time data fusion is a Kalman filter algorithm; the mathematical model of the intelligent decision-making algorithm is: ； in, is the state estimation vector, is the control input vector, is the state transfer matrix, is the control input matrix, is the process noise, To measure the output vector, is the measurement matrix, To measure noise, is the Kalman gain, is the time step.

3. The information-coordinated UAV control system according to claim 2 is characterized in that: The processing of multi-source perception data of the UAV includes: The sensor data carried by the drone is used as input, and the environmental state of the current stage is estimated according to the flight state of the previous stage. The optimal data fusion algorithm is selected according to the environmental state and the characteristics of the sensor data. Obtain the corresponding fusion strategy based on the optimal data fusion algorithm, and obtain the state estimation based on the fusion strategy; Based on state estimation, a control algorithm is used to design the flight control law of the UAV; the flight state of the UAV is controlled by the flight control law, and then the collaborative control coefficient of the corresponding data fusion algorithm is used to collaboratively optimize the flight state of the UAV.

4. The information-coordinated UAV control system according to claim 3 is characterized in that: The optimal data fusion algorithm is a data fusion algorithm corresponding to the minimum error under different environmental conditions.

5. The information-coordinated UAV control system according to claim 1, characterized in that: The collaborative optimization of the flight state of the UAV includes: dividing the flight path of the UAV into multiple sections along the heading according to the mission requirements, first obtaining the flight state of the central flight path before and after adjustment according to the mission requirements at the edge of the path and the adjacent path, and then obtaining the flight state and lateral distance of other flight paths before and after adjustment.

6. A UAV mission planning method based on information collaboration, characterized in that: The steps include: Acquire flight data obtained by the information-coordinated UAV control system according to any one of claims 1 to 5; Based on the adaptive task allocation algorithm, the flight data is divided into multiple task modules; According to the task requirements, the CPU is used to allocate the corresponding task modules to the drone in real time, and the task modules to be executed are allocated to the control unit of the drone; Based on the parallel computing platform, the computing resources of the UAV are used to parallelly process multi-task modules to execute the UAV's tasks.

7. The method for UAV mission planning based on information collaboration according to claim 6 is characterized in that: The method divides the flight data into multiple task modules based on the adaptive task allocation algorithm, including: according to a preset task requirement threshold, using the task allocation algorithm to allocate the flight data layer by layer to obtain each task module, and merging adjacent task modules according to the task requirements of adjacent task modules until the total task requirement threshold of the task module is reached to obtain multiple task modules.

8. The method for UAV mission planning based on information collaboration according to claim 7 is characterized in that: The method of allocating corresponding task modules to the UAV in real time using the CPU according to the task requirements and allocating the task modules to be executed to the control unit of the UAV includes: Calculate the task module data to be assigned to the drone according to the current task requirements; use the priority queue data structure to build task allocation and initialize the task module data assigned to the drone; When the mission requirements change, determine the type of mission requirement change and update the mission modules in the UAV; calculate the update threshold of task allocation, determine whether it is necessary to clear useless mission modules in the UAV and whether to allocate new mission modules to the UAV, and perform the required clearing or allocation operations.

Images