Unmanned aerial vehicle control method, system and device based on nonlinear model prediction and medium

Abstract

The invention relates to an unmanned aerial vehicle control method, system and device based on nonlinear model prediction and a medium. According to the non-linear model prediction-based unmanned aerial vehicle control method, a target flight path and a current flight state are input into a non-linear model prediction algorithm, and a flight control parameter output by the non-linear model prediction algorithm is utilized to control an unmanned aerial vehicle to fly according to the target flight path; it is ensured that the unmanned aerial vehicle effectively and stably tracks the predetermined trajectory when transporting power grid rescue materials, so that it is ensured that the unmanned aerial vehicle can conduct emergency repair operation in a complex environment in real time, and the safety and reliability of the unmanned aerial vehicle for rescuing a power grid in the complex environment are provided.

Description

Technical Field

[0001] The present disclosure relates to the technical field of unmanned aerial vehicle control, and in particular to a method, system, device and medium for unmanned aerial vehicle control based on nonlinear model prediction. Background Art

[0002] In recent years, multi-rotor UAVs, as simple and flexible small aerial devices, have incomparable advantages in disaster investigation and other emergency rescue in mountainous areas. They have been widely used in the investigation and design of power emergency repair, but have not yet been widely used in the field of emergency repair operations. At the same time, complex mountainous areas usually have steep mountains, canyons, cliffs and other complex terrains. The terrain is complex and changeable, and there are a large number of obstacles. The flight control system of the UAV needs to be able to adapt to these terrains and automatically adjust the flight altitude and path to avoid collisions. However, the altitude changes in mountainous areas are large. In high-altitude areas, the air pressure is low, which will cause the performance of the UAV's power system to decline, thereby affecting its flight speed and stability. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the present disclosure provides a nonlinear model predicted unmanned aerial vehicle control method, system, device and medium.

[0004] A first aspect of the present disclosure provides a nonlinear model prediction method for controlling a drone, the method comprising:

[0005] Obtain the current flight status and target flight trajectory of the drone during power grid rescue;

[0006] Based on the target flight trajectory and the current flight state, determining the flight control parameters of the UAV using a nonlinear model prediction algorithm;

[0007] Based on the flight control parameters, the UAV is controlled to fly according to the target flight trajectory.

[0008] Optionally, the target flight trajectory includes a target flight state corresponding to the current flight state, and the determining the flight control parameters of the UAV using a nonlinear model prediction algorithm based on the target flight trajectory and the current flight state includes:

[0009] Inputting the target flight state and the current flight state into a nonlinear model prediction algorithm to obtain a flight deviation between the target flight state and the current flight state;

[0010] Based on the flight deviation, the objective function of the nonlinear model prediction algorithm is solved by utilizing the constraint conditions of the nonlinear model prediction algorithm to obtain the flight control parameters of the UAV.

[0011] Optionally, the constraints include flight control parameter constraints, state constraints and pre-trained dynamics model constraints.

[0012] Optionally, the training process of the dynamic model includes:

[0013] Acquire multiple simulated flight states of the UAV under different disturbance parameters, and the simulated control parameters and generated flight states corresponding to each simulated flight state;

[0014] Calculating the deviation between each simulated flight state and each generated flight state to obtain a plurality of standby deviations;

[0015] Using the plurality of simulation control parameters and the plurality of standby deviations as a training set;

[0016] Inputting the training set into a preset disturbance initial model to obtain a disturbance model through training;

[0017] The disturbance model and the preset ideal dynamics model are integrated to obtain the dynamics model.

[0018] Optionally, the method for constructing the preset ideal kinetic model includes:

[0019] Based on the ideal flight state and dynamics of the UAV, a state transfer equation is established;

[0020] The transfer equation is approximately linearized to obtain the ideal kinetic model.

[0021] Optionally, the objective function is determined by:

[0022] Determining parameters of an objective function based on the plurality of standby deviations and the plurality of simulation control parameters;

[0023] Based on the kinetic model, optimizing the parameters of the objective function to obtain optimized parameters;

[0024] Based on the optimized parameters, the objective function is constructed.

[0025] Optionally, controlling the UAV to fly according to the target flight trajectory based on the flight control parameters includes:

[0026] Respectively obtaining a pitch deviation and a roll angular rate deviation between the flight control parameter and the current flight state;

[0027] Determining a target control parameter of the UAV based on the pitch deviation, the roll angular rate deviation and the thrust value;

[0028] Based on the target control parameters, the UAV is controlled to fly according to the target flight trajectory.

[0029] A second aspect of the present disclosure provides a nonlinear model predicted unmanned aerial vehicle control system, the system comprising:

[0030] an acquisition unit, configured to acquire a current flight state and a target flight trajectory of the UAV during power grid rescue;

[0031] a parameter determination unit configured to determine the flight control parameters of the UAV using a nonlinear model prediction algorithm based on the target flight trajectory and the current flight state;

[0032] The control unit is configured to control the UAV to fly according to the target flight trajectory based on the flight control parameters.

[0033] Optionally, the target flight trajectory includes a target flight state corresponding to the current flight state, and the parameter determination unit is configured to:

[0034] Inputting the target flight state and the current flight state into a nonlinear model prediction algorithm to obtain a flight deviation between the target flight state and the current flight state;

[0035] Based on the flight deviation, the objective function of the nonlinear model prediction algorithm is solved by utilizing the constraint conditions of the nonlinear model prediction algorithm to obtain the flight control parameters of the UAV.

[0036] Optionally, the constraints include flight control parameter constraints, state constraints and pre-trained dynamics model constraints.

[0037] Optionally, the training process of the dynamic model includes:

[0038] Acquire multiple simulated flight states of the UAV under different disturbance parameters, and the simulated control parameters and generated flight states corresponding to each simulated flight state;

[0039] Calculating the deviation between each simulated flight state and each generated flight state to obtain a plurality of standby deviations;

[0040] Using the plurality of simulation control parameters and the plurality of standby deviations as a training set;

[0041] Inputting the training set into a preset disturbance initial model to obtain a disturbance model through training;

[0042] The disturbance model and the preset ideal dynamics model are integrated to obtain the dynamics model.

[0043] Optionally, the method for constructing the preset ideal kinetic model includes:

[0044] Based on the ideal flight state and dynamics of the UAV, a state transfer equation is established;

[0045] The transfer equation is approximately linearized to obtain the ideal kinetic model.

[0046] Optionally, the objective function is determined by:

[0047] Determining parameters of an objective function based on the plurality of standby deviations and the plurality of simulation control parameters;

[0048] Based on the kinetic model, optimizing the parameters of the objective function to obtain optimized parameters;

[0049] Based on the optimized parameters, the objective function is constructed.

[0050] Optionally, the control unit is configured as:

[0051] Respectively obtaining a pitch deviation and a roll angular rate deviation between the flight control parameter and the current flight state;

[0052] Determining a target control parameter of the UAV based on the pitch deviation, the roll angular rate deviation and the thrust value;

[0053] Based on the target control parameters, the UAV is controlled to fly according to the target flight trajectory.

[0054] A third aspect of the present disclosure provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the steps of the drone control method predicted by the nonlinear model described in the first aspect of the present disclosure.

[0055] A fourth aspect of the present disclosure provides an electronic device, including:

[0056] processor;

[0057] a memory for storing processor-executable instructions;

[0058] Among them, the processor is configured to execute the executable instructions to implement the steps of the drone control method based on nonlinear model prediction described in the first aspect of the present disclosure.

[0059] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: by inputting the target flight trajectory and the current flight status into a nonlinear model prediction algorithm, the flight control parameters output by the nonlinear model prediction algorithm are used to control the UAV to fly according to the target flight trajectory, thereby ensuring that the UAV effectively and stably tracks the predetermined trajectory when transporting power grid rescue supplies, thereby ensuring that the UAV can perform real-time emergency repairs in complex environments, and providing the safety and reliability of UAVs in rescuing power grids in complex environments.

[0060] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0062] Figure 1 is a flow chart of a nonlinear model prediction method for controlling a UAV according to an exemplary embodiment;

[0063] Figure 2 is a flow chart of another nonlinear model prediction method for controlling a UAV according to an exemplary embodiment;

[0064] Figure 3 is a block diagram of a nonlinear model predicted UAV control system according to an exemplary embodiment;

[0065] Figure 4 is a block diagram of a device for a UAV control system for nonlinear model prediction according to an exemplary embodiment;

[0066] Figure 5 It is a block diagram of a device for a UAV control system for nonlinear model prediction according to an exemplary embodiment. DETAILED DESCRIPTION

[0067] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present disclosure. Instead, they are merely examples of systems and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0068] Figure 1 is a flowchart of a nonlinear model prediction method for controlling a UAV according to an exemplary embodiment. Figure 1As shown, the UAV control method predicted by the nonlinear model may include the following steps:

[0069] In step 101, the current flight state and target flight trajectory of the UAV during power grid rescue are obtained.

[0070] The target flight trajectory includes the target flight state corresponding to the current flight state, and the target flight trajectory may be a flight trajectory planned with the power grid rescue location as the end point and the mountain environment that the UAV is to pass through. The current flight state may include the current position, current attitude, current speed (e.g., linear speed and / or angular speed) and current flight control parameters of the UAV.

[0071] It should be noted that the drone can obtain the current status in real time through IMU (Inertial Measurement Unit) data and other sensors (such as GPS, lidar, visual sensors and gyroscopes).

[0072] In step 102, based on the target flight trajectory and the current flight state, a nonlinear model prediction algorithm is used to determine the flight control parameters of the UAV.

[0073] Among them, flight control parameters may include pitch, roll, thrust and torque, etc.

[0074] It should be noted that the target flight trajectory and the current flight state are input into the nonlinear model prediction algorithm, and the flight control parameters of the UAV are output through the nonlinear model prediction algorithm.

[0075] For example, the current position, current attitude and current speed of the UAV and the target position corresponding to the current position, the target attitude corresponding to the current attitude and the target speed corresponding to the current speed are input into the nonlinear model prediction algorithm, and the current position, current attitude and current speed and the target position corresponding to the current position, the target attitude corresponding to the current attitude and the target speed corresponding to the current speed are processed by the nonlinear model prediction algorithm to obtain the pitch, roll and thrust of the UAV.

[0076] In step 103, based on the flight control parameters, the UAV is controlled to fly according to the target flight trajectory.

[0077] A possible implementation method of this step is to respectively obtain the pitch deviation and roll angular rate deviation of the flight control parameters and the current flight state; determine the target control parameters of the UAV based on the pitch deviation, the roll angular rate deviation and the thrust value; and control the UAV to fly according to the target flight trajectory based on the target control parameters.

[0078] It should be noted that, unlike the traditional PID-controlled quadcopter drone, the drone control architecture disclosed in the present invention is logically divided into two layers. The bottom layer is a fast and lightweight PID control (i.e., PID controller), which runs on the lower computer to achieve high-frequency attitude control. The flight control parameters output by the nonlinear model prediction algorithm can be transmitted to the PID (Proportion Integration Differentiation) controller, and the PID control controls the flight of the drone through the flight control parameters.

[0079] The above technical scheme, by inputting the target flight trajectory and the current flight status into the nonlinear model prediction algorithm, uses the flight control parameters output by the nonlinear model prediction algorithm to control the UAV to fly according to the target flight trajectory, thereby ensuring that the UAV effectively and stably tracks the predetermined trajectory when transporting power grid rescue materials, thereby ensuring that the UAV can perform real-time emergency repair operations in complex environments, and providing the safety and reliability of UAVs in rescuing power grids in complex environments.

[0080] Figure 2 is a flow chart of another nonlinear model prediction method for controlling a UAV according to an exemplary embodiment. Figure 2 As shown above Figure 1 The specific implementation of step 102 may include the following steps:

[0081] In step 1021, the target flight state and the current flight state are input into a nonlinear model prediction algorithm to obtain a flight deviation between the target flight state and the current flight state.

[0082] The flight deviation may include a deviation between the current position and the target position corresponding to the current position, a deviation between the current attitude and the target attitude corresponding to the current attitude, and a deviation between the current speed and the target speed corresponding to the current speed.

[0083] In step 1022, based on the flight deviation and using the constraints of the nonlinear model prediction algorithm, the objective function of the nonlinear model prediction algorithm is solved to obtain the flight control parameters of the UAV.

[0084] The constraints include flight control parameter constraints, state constraints and pre-trained dynamic model constraints. The objective function can be a function of state tracking error, ensuring that the predicted flight state of the drone is as close to the target flight state as possible.

[0085] It should be noted that the flight control parameter constraint can be that the thrust (and / or torque) cannot exceed the range of the drone motor change, especially the maximum change value of the drone motor. The state constraint can be a limit on position, speed or attitude. The pre-trained dynamic model constraint can be to ensure that the current flight state and the output flight control parameters conform to the dynamic equation.

[0086] For example, multiple standby flight control parameters that meet the constraints of the nonlinear model prediction algorithm are predicted through flight deviation, and the state tracking error value corresponding to each standby flight control parameter is calculated through the multiple standby flight control parameters and the objective function of the nonlinear model prediction algorithm, and the standby flight control parameter corresponding to the state tracking error value is used as the flight control parameter of the UAV.

[0087] Optionally, the training process of the dynamic model may include the following steps:

[0088] In step S1, a plurality of simulated flight states of the UAV under different disturbance parameters, and simulation control parameters and generated flight states corresponding to each simulated flight state are obtained.

[0089] The simulated flight state can be obtained by simulating the flight state of the UAV under different external environmental interferences (such as wind force) when the UAV is loaded through simulation software. The generated flight state can be generated for the UAV through an ideal dynamics model.

[0090] In step S2, the deviation between each simulated flight state and each generated flight state is calculated to obtain a plurality of standby deviations.

[0091] In step S3, the plurality of simulation control parameters and the plurality of standby deviations are used as a training set.

[0092] In step S4, the training set is input into a preset disturbance initial model to obtain a disturbance model through training.

[0093] Among them, the preset disturbance initial model can be a neural network model (for example, a feedforward neural network, a convolutional neural network or a recurrent neural network, etc.), a deep learning model or a meta-learning model, etc.

[0094] In step S5, the disturbance model and the preset ideal dynamics model are integrated to obtain the dynamics model.

[0095] Among them, the method of constructing the preset ideal dynamics model may include: establishing a state transfer equation based on the ideal flight state and dynamics of the drone; and approximately linearizing the transfer equation to obtain an ideal dynamics model.

[0096] It should be noted that the present disclosure also uses a method combined with meta-learning to observe the interference of the hoisting load on the UAV, and models the system by combining a neural network with a nominal dynamics model.

[0097] The above technical solution uses a trained dynamic model to offset the interference caused by the load traction on the drone, so that the drone will be able to handle the load more smoothly. At the same time, the observer and the robust controller are effectively combined to ensure that the drone can effectively and stably track the predetermined trajectory while transporting materials.

[0098] Optionally, the objective function may be determined by:

[0099] Based on the multiple standby deviations and multiple simulation control parameters, the parameters of the objective function are determined; based on the dynamic model, the parameters of the objective function are optimized to obtain optimized parameters; based on the optimized parameters, the objective function is constructed.

[0100] Figure 3 is a block diagram of a nonlinear model prediction UAV control system according to an exemplary embodiment, such as Figure 3 As shown, the system comprises:

[0101] An acquisition unit 301 is configured to acquire the current flight state and target flight trajectory of the UAV during power grid rescue;

[0102] A parameter determination unit 302 is configured to determine the flight control parameters of the UAV using a nonlinear model prediction algorithm based on the target flight trajectory and the current flight state;

[0103] The control unit 303 is configured to control the UAV to fly according to the target flight trajectory based on the flight control parameters.

[0104] Optionally, the target flight trajectory includes a target flight state corresponding to the current flight state, and the parameter determination unit 302 is configured to:

[0105] Inputting the target flight state and the current flight state into a nonlinear model prediction algorithm to obtain a flight deviation between the target flight state and the current flight state;

[0106] Based on the flight deviation, the objective function of the nonlinear model prediction algorithm is solved by utilizing the constraint conditions of the nonlinear model prediction algorithm to obtain the flight control parameters of the UAV.

[0107] Optionally, the constraints include flight control parameter constraints, state constraints and pre-trained dynamics model constraints.

[0108] Optionally, the training process of the dynamic model includes:

[0109] Acquire multiple simulated flight states of the UAV under different disturbance parameters, and the simulated control parameters and generated flight states corresponding to each simulated flight state;

[0110] Calculating the deviation between each simulated flight state and each generated flight state to obtain a plurality of standby deviations;

[0111] Using the plurality of simulation control parameters and the plurality of standby deviations as a training set;

[0112] Inputting the training set into a preset disturbance initial model to obtain a disturbance model through training;

[0113] The disturbance model and the preset ideal dynamics model are integrated to obtain the dynamics model.

[0114] Optionally, the method for constructing the preset ideal kinetic model includes:

[0115] Based on the ideal flight state and dynamics of the UAV, a state transfer equation is established;

[0116] The transfer equation is approximately linearized to obtain the ideal kinetic model.

[0117] Optionally, the objective function is determined by:

[0118] Determining parameters of an objective function based on the plurality of standby deviations and the plurality of simulation control parameters;

[0119] Based on the kinetic model, optimizing the parameters of the objective function to obtain optimized parameters;

[0120] Based on the optimized parameters, the objective function is constructed.

[0121] Optionally, the control unit 303 is configured to:

[0122] Respectively obtaining a pitch deviation and a roll angular rate deviation between the flight control parameter and the current flight state;

[0123] Determining a target control parameter of the UAV based on the pitch deviation, the roll angular rate deviation and the thrust value;

[0124] Based on the target control parameters, the UAV is controlled to fly according to the target flight trajectory.

[0125] A third aspect of the present disclosure provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the steps of the drone control method predicted by the nonlinear model described in the first aspect of the present disclosure.

[0126] A fourth aspect of the present disclosure provides an electronic device, including:

[0127] processor;

[0128] a memory for storing processor-executable instructions;

[0129] Among them, the processor is configured to execute the executable instructions to implement the steps of the drone control method based on nonlinear model prediction described in the first aspect of the present disclosure.

[0130] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0131] The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the steps of the nonlinear model predicted drone control method provided by the present disclosure.

[0132] Figure 4 4 is a block diagram of a device for a drone control system for nonlinear model prediction according to an exemplary embodiment. For example, the device 400 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0133] Reference Figure 4 , the device 400 may include one or more of the following components: a first processing component 402 , a first memory 404 , a first power component 406 , a multimedia component 408 , an audio component 410 , a first input / output interface 412 , a sensor component 414 , and a communication component 416 .

[0134] The first processing component 402 generally controls the overall operation of the device 400, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The first processing component 402 may include one or more first processors 420 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the first processing component 402 may include one or more modules to facilitate the interaction between the first processing component 402 and other components. For example, the first processing component 402 may include a multimedia module to facilitate the interaction between the multimedia component 408 and the first processing component 402.

[0135] The first memory 404 is configured to store various types of data to support operations on the device 400. Examples of such data include instructions for any application or method operating on the device 400, contact data, phone book data, messages, pictures, videos, etc. The first memory 404 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0136] The first power source component 406 provides power to various components of the device 400. The first power source component 406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 400.

[0137] The multimedia component 408 includes a screen that provides an output interface between the device 400 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 408 includes a front camera and / or a rear camera. When the device 400 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0138] The audio component 410 is configured to output and / or input audio signals. For example, the audio component 410 includes a microphone (MIC), and when the device 400 is in an operation mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the first memory 404 or sent via the communication component 416. In some embodiments, the audio component 410 also includes a speaker for outputting audio signals.

[0139] The first input / output interface 412 provides an interface between the first processing component 402 and a peripheral interface module, which may be a keyboard, a click wheel, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0140] The sensor assembly 414 includes one or more sensors for providing various aspects of the status assessment of the device 400. For example, the sensor assembly 414 can detect the open / closed state of the device 400, the relative positioning of components, such as the display and keypad of the device 400, and the sensor assembly 414 can also detect the position change of the device 400 or a component of the device 400, the presence or absence of user contact with the device 400, the orientation or acceleration / deceleration of the device 400, and the temperature change of the device 400. The sensor assembly 414 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 414 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 414 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0141] The communication component 416 is configured to facilitate wired or wireless communication between the device 400 and other devices. The device 400 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 416 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 416 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0142] In an exemplary embodiment, the apparatus 400 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0143] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a first memory 404 including instructions, and the instructions can be executed by a first processor 420 of the device 400 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0144] In addition to being an independent electronic device, the above-mentioned device can also be a part of an independent electronic device. For example, in one embodiment, the device can be an integrated circuit (IC) or a chip, wherein the integrated circuit can be an IC or a collection of multiple ICs; the chip can include but is not limited to the following types: GPU (Graphics Processing Unit), CPU (Central Processing Unit), FPGA (Field Programmable Gate Array), DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), SOC (System on Chip, SoC), etc. The above-mentioned integrated circuit or chip can be used to execute executable instructions (or codes) to implement the above-mentioned nonlinear model prediction method for unmanned aerial vehicle control. The executable instructions can be stored in the integrated circuit or chip, or can be obtained from other devices or equipment, such as the integrated circuit or chip including a processor, a memory, and an interface for communicating with other devices. The executable instruction can be stored in the memory, and when the executable instruction is executed by the processor, the above-mentioned drone control method based on nonlinear model prediction can be implemented; alternatively, the integrated circuit or chip can receive the executable instruction through the interface and transmit it to the processor for execution, so as to implement the above-mentioned drone control method based on nonlinear model prediction.

[0145] Figure 5 5 is a block diagram of a device for a drone control system for nonlinear model prediction according to an exemplary embodiment. For example, the device 500 may be provided as a server. Figure 5 The apparatus 500 includes a second processing component 522, which further includes one or more processors, and a memory resource represented by a third memory 532 for storing instructions executable by the second processing component 522, such as an application. The application stored in the third memory 532 may include one or more modules, each corresponding to a set of instructions. In addition, the second processing component 522 is configured to execute instructions to perform the above-mentioned nonlinear model prediction method for controlling a drone.

[0146] The device 500 may further include a second power supply component 526 configured to perform power management of the device 500, a wired or wireless network interface 550 configured to connect the device 500 to a network, and a second input / output interface 558. The device 500 may operate based on an operating system stored in the third memory 532.

[0147] In another exemplary embodiment, a computer program product is also provided, which includes a computer program that can be executed by a programmable device, and the computer program has a code portion for executing the above-mentioned nonlinear model predictive drone control method when executed by the programmable device.

[0148] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the present disclosure. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0149] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A nonlinear model prediction method for controlling an unmanned aerial vehicle, characterized in that: The method comprises: Obtain the current flight status and target flight trajectory of the drone during power grid rescue; Based on the target flight trajectory and the current flight state, determining the flight control parameters of the UAV using a nonlinear model prediction algorithm; Based on the flight control parameters, the UAV is controlled to fly according to the target flight trajectory.

2. The method according to claim 1, characterized in that The target flight trajectory includes a target flight state corresponding to the current flight state, and the flight control parameters of the UAV are determined by using a nonlinear model prediction algorithm based on the target flight trajectory and the current flight state, including: Inputting the target flight state and the current flight state into a nonlinear model prediction algorithm to obtain a flight deviation between the target flight state and the current flight state; Based on the flight deviation, the objective function of the nonlinear model prediction algorithm is solved by utilizing the constraint conditions of the nonlinear model prediction algorithm to obtain the flight control parameters of the UAV.

3. The method according to claim 2, characterized in that The constraints include flight control parameter constraints, state constraints and pre-trained dynamics model constraints.

4. The method according to claim 3, characterized in that The training process of the dynamic model includes: Acquire multiple simulated flight states of the UAV under different disturbance parameters, and the simulated control parameters and generated flight states corresponding to each simulated flight state; Calculating the deviation between each simulated flight state and each generated flight state to obtain a plurality of standby deviations; Using the plurality of simulation control parameters and the plurality of standby deviations as a training set; Inputting the training set into a preset disturbance initial model to obtain a disturbance model through training; The disturbance model and the preset ideal dynamics model are integrated to obtain the dynamics model.

5. The method according to claim 4, characterized in that The method for constructing the preset ideal kinetic model includes: Based on the ideal flight state and dynamics of the UAV, a state transfer equation is established; The transfer equation is approximately linearized to obtain the ideal kinetic model.

6. The method according to claim 3, characterized in that The objective function is determined by: Determining parameters of an objective function based on the plurality of standby deviations and the plurality of simulation control parameters; Based on the kinetic model, optimizing the parameters of the objective function to obtain optimized parameters; Based on the optimized parameters, the objective function is constructed.

7. The method according to claim 1, characterized in that The step of controlling the UAV to fly according to the target flight trajectory based on the flight control parameters includes: Respectively obtaining a pitch deviation and a roll angular rate deviation between the flight control parameter and the current flight state; Determining a target control parameter of the UAV based on the pitch deviation, the roll angular rate deviation and the thrust value; Based on the target control parameters, the UAV is controlled to fly according to the target flight trajectory.

8. A nonlinear model-predicted UAV control system, characterized in that: The system comprises: an acquisition unit, configured to acquire a current flight state and a target flight trajectory of the UAV during power grid rescue; a parameter determination unit configured to determine the flight control parameters of the UAV using a nonlinear model prediction algorithm based on the target flight trajectory and the current flight state; The control unit is configured to control the UAV to fly according to the target flight trajectory based on the flight control parameters.

9. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to execute the executable instructions to implement the steps of the method according to any one of claims 1 to 7.

Images