Near space putting method, device and equipment based on digital twinning and storage medium

Abstract

The invention discloses a near space launching method, device and equipment based on digital twinning, and a storage medium. The method comprises the following steps: constructing a digital twinning model of an unmanned aerial vehicle and an environment where the unmanned aerial vehicle is located; according to a predetermined task target, simulating delivery results under different delivery strategies by using a digital twin model, and calculating a target delivery path and a target delivery time point; collecting state data of the unmanned aerial vehicle in the actual flight process in real time, and transmitting the state data to a ground control center, so that the ground control center updates the digital twin model by using the received state data and feeds back; and based on the updated digital twin model, the target delivery path and the target delivery time point, the flight path and delivery time of the unmanned aerial vehicle are adjusted in real time until the delivery task is completed. Through the digital twin model, the high simulation of the parameters of the unmanned aerial vehicle can be realized, the flight path and the delivery time of the unmanned aerial vehicle are adjusted in real time based on the updated digital twin model, and the delivery accuracy is improved.

Description

Technical Field

[0001] The present application relates to the field of drone technology, and in particular to near-space delivery methods, devices, equipment, and storage media based on digital twins. Background Art

[0002] In current drone applications, especially those involving precision delivery missions, existing technical solutions primarily rely on pre-defined flight paths and delivery strategies. These approaches are typically based on preliminary assessments of environmental conditions, drone performance, and the characteristics of the delivered objects. However, as application scenarios become increasingly complex, traditional approaches are increasingly revealing their limitations and shortcomings.

[0003] Most existing systems use static path planning, which determines the flight route and drop point based on known information before the mission begins. This approach cannot cope with dynamic changes that occur during flight, such as sudden weather changes, unexpected obstacles, and other unexpected situations. As a result, when actual execution deviates from the plan, delivery accuracy is insufficient. Summary of the Invention

[0004] The main purpose of this application is to provide a near-space delivery method, device, equipment and storage medium based on digital twins, aiming to solve the current technical problem of low accuracy of drone near-space delivery.

[0005] To achieve the above objectives, this application proposes a near-space delivery method based on digital twins, which includes:

[0006] Constructing a digital twin model of the drone and its environment, the model including at least the drone's physical characteristics, flight parameters, environmental conditions, and properties of the droplet;

[0007] According to the predetermined task objectives, the digital twin model is used to simulate the delivery results under different delivery strategies, and the target delivery path and target delivery time point are calculated;

[0008] Collect the status data of the UAV in real time during the actual flight process, and transmit the status data to the ground control center, so that the ground control center uses the received status data to update the digital twin model and provide feedback;

[0009] Based on the updated digital twin model, the target delivery path and the target delivery time point, the flight trajectory and delivery timing of the drone are adjusted in real time until the delivery mission is completed.

[0010] In one embodiment, the step of simulating delivery results under different delivery strategies using the digital twin model according to a predetermined task objective and calculating a target delivery path and a target delivery time point includes:

[0011] According to the predetermined mission objectives, the physical characteristics, flight parameters, and environmental parameters of the UAV are input into the digital twin model, and the motion equations are solved using numerical methods to obtain the predicted trajectory of the UAV.

[0012] For different delivery strategies, the corresponding delivery errors are calculated based on the predicted trajectory. The formula for calculating the delivery error is:

[0013]

[0014] Where x0, y0, z0 are the target location coordinates, and x, y, z are the actual delivery point coordinates calculated based on the predicted trajectory;

[0015] Select the target delivery path and target delivery time point based on the principle of minimum error.

[0016] In one embodiment, the step of adjusting the flight trajectory and delivery timing of the drone in real time based on the updated digital twin model, the target delivery path, and the target delivery time point includes:

[0017] Feeding back status data from the ground control center to the digital twin model in real time to update the predicted trajectory;

[0018] The shortest distance is obtained by combining the updated predicted trajectory with the actual position of the current UAV and the target drop position;

[0019] When the current flight time approaches the target delivery time point, the target delivery timing is recalculated according to the shortest distance and the current speed, so as to complete the delivery task according to the target delivery timing and the updated predicted trajectory. The target delivery timing is calculated as follows:

[0020]

[0021] Among them, t 投放 is the target delivery time, d 最短 is the shortest distance, v 当前 is the current speed of the drone, a 当前 is the current acceleration of the UAV, t 当前 is the current time, v 目标 is the target speed.

[0022] In one embodiment, the step of adjusting the flight trajectory and delivery timing of the drone in real time based on the updated digital twin model, the target delivery path, and the target delivery time point until the delivery mission is completed includes:

[0023] Controlling the UAV according to the target delivery path and collecting real-time flight parameters;

[0024] Based on the real-time flight parameters, a state transition model of a Kalman filter and an updated digital twin model are used to predict the state of the drone at the next moment to obtain a predicted state, where the predicted state includes position, velocity, and acceleration;

[0025] adjusting the flight trajectory of the UAV according to the predicted state, and controlling the UAV according to the adjusted flight trajectory;

[0026] Acquiring a current flight environment, and updating the target delivery time point using a Kalman filter according to the current flight environment to obtain an updated target delivery time point;

[0027] The drone is controlled to deliver the delivery according to the updated target delivery time point.

[0028] In one embodiment, the step of constructing a digital twin model of the drone and the environment in which the drone is located includes:

[0029] Determine the types of data needed to build the digital twin model;

[0030] Collecting the physical characteristics, flight parameters, environmental conditions, and properties of the dropped objects of the drone based on the data types;

[0031] defining an initial physical model, wherein the initial physical model is used to describe the behavior of the UAV in different flight states;

[0032] The physical characteristics of the drone, the flight parameters, the environmental conditions, and the properties of the droplets are integrated into the initial physical model to construct a digital twin model of the drone and the environment in which the drone is located.

[0033] In one embodiment, the step of collecting status data of the drone in real time during actual flight and transmitting the status data to a ground control center so that the ground control center uses the received status data to update the digital twin model and provide feedback includes:

[0034] Collect initial flight data of the drone during actual flight through multiple sensors;

[0035] Preprocessing the initial flight data to obtain status data;

[0036] The status data is transmitted to a ground control center so that the ground control center uses the received status data to update the digital twin model and provide feedback.

[0037] In one embodiment, the step of preprocessing the initial flight data to obtain status data includes:

[0038] Obtaining a preset smoothing coefficient, and preprocessing the initial flight data using the preset smoothing coefficient to obtain reference flight data;

[0039] Obtaining a timestamp corresponding to each data in the reference flight data;

[0040] Determining an offset of the timestamp relative to a reference time;

[0041] Time alignment is performed on the reference flight data according to the offset to obtain status data.

[0042] In addition, to achieve the above objectives, the present application also proposes a near-space delivery device based on digital twins, which includes:

[0043] A construction module for constructing a digital twin model of the drone and its environment, the model including at least the drone's physical characteristics, flight parameters, environmental conditions, and properties of the droplet;

[0044] A calculation module is used to simulate the delivery results under different delivery strategies using the digital twin model according to the predetermined task objectives, and calculate the target delivery path and target delivery time point;

[0045] The acquisition module is used to collect the status data of the UAV in real time during the actual flight process and transmit the status data to the ground control center so that the ground control center can use the received status data to update the digital twin model and provide feedback;

[0046] The adjustment module is used to adjust the flight trajectory and delivery timing of the drone in real time based on the updated digital twin model, the target delivery path, and the target delivery time point until the delivery mission is completed.

[0047] In addition, to achieve the above-mentioned purpose, the present application also proposes a near-space delivery device based on digital twins, which includes: a memory, a processor, and a computer program stored on the memory and runnable on the processor, and the computer program is configured to implement the steps of the near-space delivery method based on digital twins as described above.

[0048] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the near-space delivery method based on digital twins as described above are implemented.

[0049] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the near-space delivery method based on digital twins as described above.

[0050] One or more technical solutions proposed in this application construct a digital twin model of the drone and its environment; based on the predetermined mission objectives, use the digital twin model to simulate the delivery results under different delivery strategies and calculate the target delivery path and target delivery time point; collect the drone's status data in real time during actual flight and transmit the status data to the ground control center so that the ground control center can use the received status data to update the digital twin model and provide feedback; based on the updated digital twin model, the target delivery path and target delivery time point, adjust the drone's flight trajectory and delivery timing in real time until the delivery mission is completed. Through the digital twin model, a high degree of simulation of the drone's parameters can be achieved, so that when planning the delivery strategy, the delivery results under different conditions can be more accurately predicted, thereby improving the accuracy of determining the target delivery path and time point. The drone's flight trajectory and delivery timing can be adjusted in real time based on the updated digital twin model to improve the delivery accuracy. Using the digital twin model for virtual simulation, the effectiveness of various delivery strategies can be tested without actually operating the drone, identifying potential problems and optimizing solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0053] Figure 1 A flowchart of the first embodiment of the near-space delivery method based on digital twins provided in this application;

[0054] Figure 2 A flowchart of the second embodiment of the near-space delivery method based on digital twins provided in this application;

[0055] Figure 3 This is a schematic diagram of the module structure of a near-space delivery device based on digital twins in an embodiment of the present application;

[0056] Figure 4This is a schematic diagram of the device structure of the hardware operating environment involved in the near-space delivery method based on digital twins in the embodiment of the present application.

[0057] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0058] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0059] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0060] The main solution of the embodiment of the present application is: constructing a digital twin model of the UAV and the environment in which the UAV is located, the model including at least the physical characteristics, flight parameters, environmental conditions and properties of the delivery object of the UAV; according to the predetermined mission objectives, using the digital twin model to simulate the delivery results under different delivery strategies, and calculate the target delivery path and target delivery time point; collecting the status data of the UAV during the actual flight in real time, and transmitting the status data to the ground control center, so that the ground control center uses the received status data to update the digital twin model and provide feedback; based on the updated digital twin model, the target delivery path and the target delivery time point, adjusting the flight trajectory and delivery timing of the UAV in real time until the delivery mission is completed.

[0061] Existing technologies use static path planning, which determines the flight route and drop point based on known information before the mission begins. This approach cannot cope with dynamic changes during flight, such as sudden weather changes, unexpected obstacles, and other unexpected situations. As a result, when actual execution deviates from the plan, delivery accuracy is insufficient.

[0062] This application provides a solution that, by constructing a digital twin model of a drone and its environment, can achieve a high degree of simulation of key factors such as drone flight parameters, physical characteristics, and properties of the objects being delivered. This enables more accurate prediction of delivery results under different conditions when planning delivery strategies, thereby improving the accuracy of determining the target delivery path and time points. By using a digital twin model for virtual simulation, it is possible to test the effects of various delivery strategies without actually operating the drone, identify potential problems, and optimize solutions. This not only reduces the risk of actual operational failure due to trial and error, but also avoids possible property losses or safety hazards.

[0063] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of implementing the above functions, a near-space delivery device based on digital twins, etc. The following uses the near-space delivery device based on digital twins as an example to illustrate this embodiment and the following embodiments.

[0064] Based on this, the embodiment of the present application provides a near-space delivery method based on digital twins, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the near-space delivery method based on digital twins of this application.

[0065] In this embodiment, the near-space delivery method based on digital twins includes steps S10 to S40:

[0066] Step S10: Construct a digital twin model of the drone and the environment in which the drone is located, wherein the model at least includes the physical characteristics, flight parameters, environmental conditions, and properties of the dropped objects of the drone.

[0067] It's important to note that the physical characteristics of a drone include its size, weight, and propulsion system. Flight parameters include altitude, speed, and heading. Environmental conditions include factors like wind speed, temperature, and air density, which influence flight trajectory and delivery outcomes. The properties of the delivered object include its size, shape, weight, and delivery method.

[0068] A digital twin is a virtual model built based on real-time data and physical properties, used to accurately simulate the actual physical object. By collecting this data, a digital model can be created that accurately reflects the changes in the drone and its surroundings.

[0069] In a feasible implementation, step S10 may include steps A11 to A14:

[0070] Step A11: Determine the data types required to build the digital twin model.

[0071] It's understandable that in the initial stages of building a digital twin model, it's important to first identify the types of data that need to be collected. This data will form the foundation of the model, ensuring it accurately describes the drone's flight characteristics and environment. Specific data types include:

[0072] Physical characteristics of the drone: Dimensions and mass: such as the drone's length, width, height, center of gravity, and weight. Powertrain: such as engine type, thrust, and power efficiency. Aerodynamic characteristics: such as wingspan, lift coefficient, and drag coefficient.

[0073] Flight parameters: Flight speed: such as cruising speed, maximum speed, climb rate, etc. Flight altitude: such as normal flight altitude, maximum flight altitude, etc. Heading and attitude: such as pitch angle, roll angle, yaw angle, etc.

[0074] Environmental conditions: Meteorological data: such as wind speed, wind direction, temperature, and humidity. Air density: A key factor affecting flight, closely related to altitude and meteorological conditions. Geographic information: such as terrain, altitude, and obstacle distribution.

[0075] Object properties: The object's size and mass affect the object's gravity and air resistance. The method of release determines how the object is released from the drone (e.g., through a hatch, hanging, etc.). The object's shape and material affect its aerodynamic properties during flight.

[0076] Step A12: Collect the physical characteristics, flight parameters, environmental conditions and properties of the dropped object of the UAV according to the data type.

[0077] Specific data collection can begin based on the data types determined in the above steps. Data sources can be diverse, such as the drone's own sensor data, weather service data, and drone specifications. For example, the drone's IMU (Inertial Measurement Unit), GPS, air pressure sensor, speed sensor, and other sensors provide real-time flight parameters during flight. If the drop is a pre-determined item, relevant parameters can be obtained from the item's specifications and design documents.

[0078] Step A13: Define an initial physical model, which is used to describe the behavior of the UAV in different flight states.

[0079] After data collection is complete, an initial physical model can be defined based on the collected data. This initial physical model is a mathematical model that describes the interaction between the drone and its environment. Its purpose is to accurately simulate the drone's behavior under different flight conditions. This model typically includes: flight mechanics model, dynamics model, environmental impact model, and droplet behavior model.

[0080] The flight dynamics model uses flight dynamics formulas, such as Newton's second law and dynamic equations, to describe how a drone is affected by factors such as aerodynamics and gravity during flight. The dynamics model describes the drone's kinematic behavior, such as its speed, position, and acceleration. This may include feedback from ground control commands and control algorithms (such as PID controllers). Environmental impact models can be constructed based on wind tunnel test data, meteorological data, and other factors. The droplet behavior model describes the trajectory of the droplet after it is released from the drone, taking into account factors such as its mass, shape, and air resistance.

[0081] Step A14: Integrate the physical characteristics of the drone, the flight parameters, the environmental conditions, and the properties of the droplets into the initial physical model to construct a digital twin model of the drone and the environment in which the drone is located.

[0082] In practice, state variables (such as position, velocity, and attitude) can be defined and their temporal variations described by equations of motion (e.g., Newton-Euler and Lagrange equations). These physical models can simulate the drone's motion under different flight conditions, specifically how it is affected by external forces such as airflow, gravity, and thrust.

[0083] The final digital twin model is constructed by integrating all previously collected data (such as the physical characteristics of the drone, flight parameters, environmental conditions, properties of the dropped objects, etc.) into the model.

[0084] Collected data, such as flight parameters and environmental conditions, is input into the physical model to ensure it dynamically reflects the actual flight state. For different flight states (e.g., takeoff, cruising, landing), the model is ensured to accurately calculate the drone's motion state (position, speed, attitude, etc.). Environmental factors (e.g., wind speed, terrain, temperature, etc.) are incorporated into the digital twin model to ensure the model accurately responds to the drone's interaction with the environment. The model also incorporates the trajectory and behavior simulation of the droplet to ensure that the droplet's landing point can be accurately predicted in different environments, meeting the predetermined mission objectives.

[0085] Ultimately, after data integration and model adjustments, a digital twin model is generated that accurately reflects the state of the drone and its environment. This model not only simulates the drone's physical behavior but also provides real-time updates and feedback during mission execution, helping ground control centers adjust flight strategies and launch timing in real time.

[0086] Step S20: According to the predetermined task objectives, the digital twin model is used to simulate the delivery results under different delivery strategies, and the target delivery path and target delivery time point are calculated.

[0087] In specific implementation, the digital twin model can be used to simulate the delivery results under different delivery strategies based on the predetermined task objectives. The predetermined task objectives can be the delivery targets issued by the user, for example, delivering objects to a certain area in City A between 8:00 and 9:00.

[0088] It should be understood that the digital twin model can be used to simulate the delivery results under different delivery strategies according to the predetermined mission objectives, so as to calculate the target delivery path and target delivery time point. Specifically, the flight parameters, environmental conditions, etc. of the drone can be input into the digital twin model according to the mission objectives, so as to predict the flight trajectory of the drone and obtain the optimal delivery path and delivery time point.

[0089] Step S30: Collect the status data of the UAV during the actual flight in real time, and transmit the status data to the ground control center, so that the ground control center uses the received status data to update the digital twin model and provide feedback.

[0090] It's understandable that during actual flight, the drone's flight status data, including position, speed, acceleration, and more, is collected in real time and transmitted to a ground control center via sensors. The ground control center updates the digital twin model based on the received data, thereby obtaining the current flight status and providing timely feedback to the drone.

[0091] In a feasible implementation, step S30 may include steps B11 to B13:

[0092] Step B11: Collect initial flight data of the UAV during the actual flight process through multiple sensors.

[0093] It should be noted that the initial flight data of the drone during actual flight can be collected through multiple sensors at different locations on the drone. These sensors will provide various flight data in real time, including but not limited to: location data: the drone's longitude, latitude, and altitude (GPS data); speed data: the drone's flight speed, climb rate, and acceleration; flight attitude data: pitch angle, roll angle, and yaw angle (IMU data); environmental data: wind speed, air pressure, temperature, humidity, etc.; power system data: battery power, engine thrust, power consumption, etc. This data will provide the basis for real-time monitoring of the flight process and updating the digital twin model.

[0094] Step B12: Preprocess the initial flight data to obtain status data.

[0095] It should be understood that the initial flight data collected may contain noise, errors, or redundant information. Therefore, data preprocessing is required to extract valid information that accurately reflects the drone's flight status. Preprocessing can include data cleaning, data denoising, and normalization.

[0096] Understandably, some sensors may be subject to interference, resulting in abnormal or unreasonable flight data (such as extreme temperatures or wind speeds), which needs to be eliminated. Filtering algorithms (such as Kalman filtering and low-pass filtering) can be used to smooth sensor data and reduce the impact of noise on the data.

[0097] Since the data collected by different sensors may be collected at different times, the preprocessing also includes time alignment of the collected data.

[0098] In a feasible embodiment, step B12 may include: obtaining a preset smoothing coefficient, preprocessing the initial flight data using the preset smoothing coefficient to obtain reference flight data; obtaining the timestamp corresponding to each data in the reference flight data; determining the offset of the timestamp relative to the reference time; and time-aligning the reference flight data according to the offset to obtain status data.

[0099] It should be noted that the smoothing coefficient is a parameter used to smooth sensor data during data processing. Its function is to reduce random noise in the data, making it more representative and preventing errors caused by transient noise from affecting flight status analysis. The preset smoothing coefficient refers to the smoothing parameter pre-set during system design. For example, if the preset smoothing coefficient is set to 0.8, the initial flight data is pre-processed according to the preset smoothing coefficient as follows:

[0100] y[n]=αx[n]+(1-α)y[n-1]

[0101] x[n] is the initial flight data, y[n] is the reference flight data, and α is the smoothing coefficient, which is 0.8.

[0102] During flight, drones continuously collect sensor data, and each data point is assigned a corresponding timestamp. The timestamp refers to the precise time each data point was collected, typically in seconds or milliseconds. Referencing the timestamps in flight data provides a basis for subsequent time alignment and data synchronization. Through timestamps, the system knows when each data point was collected, enabling synchronization of data from different sensors. During flight, multiple sensors operate simultaneously, and they may have varying time synchronization errors. This means that each sensor's timestamp may not be completely consistent with a reference time (such as system startup time). To ensure proper alignment of individual data, the offset between these timestamps and the reference time must be determined.

[0103] The base time is usually the time when the system starts, or a unified time reference set by the system in advance. The time offset is calculated by comparing the timestamp with the base time.

[0104] Assuming the base time is T0 and the timestamp of a data is T1, the offset is T1-T0. The offset is used to adjust the timestamps of the sensor data so that they are consistent with the base time.

[0105] In a specific implementation, the timestamp of each sensor data may be adjusted according to the calculated offset, and the data of all sensors may be synchronized based on the same time point through time alignment.

[0106] Data smoothing and time alignment ensure the accuracy and consistency of drone flight data, providing high-quality input data for updating and optimizing the digital twin model. This process reduces noise interference and corrects time deviations in flight data, enabling ground control centers to obtain the most accurate flight status information in real time.

[0107] Step B13: Transmit the status data to the ground control center, so that the ground control center uses the received status data to update the digital twin model and provide feedback.

[0108] It's important to note that preprocessed status data must be promptly transmitted to the ground control center for real-time updates of the digital twin model and feedback to the flight control system. This status data must be transmitted to the ground control center via a reliable communication network. Wireless communication technologies (such as 5G, satellite communications, and Wi-Fi) can be used for data transmission to ensure stable data transmission during flight. To ensure efficient and secure data transmission, data compression and encryption are typically required to protect confidentiality and integrity. The ground control center updates the digital twin model based on the received status data. This includes: Updating position and flight status: Adjusting state variables in the model, such as the drone's position, velocity, and attitude. Adjusting the environmental simulation: Updating environmental conditions in the model based on the latest environmental data (such as air pressure and wind speed). Updating powertrain status: If the drone's battery power decreases or the engine status changes, the ground control center must reflect these changes in the digital twin model. The updated digital twin model is fed back to the device, and based on the model's feedback, the flight control system can optimize its flight strategy.

[0109] Step S40: Based on the updated digital twin model, the target delivery path, and the target delivery time point, the flight trajectory and delivery timing of the drone are adjusted in real time until the delivery mission is completed.

[0110] With the support of the digital twin model, the drone can be controlled according to the target delivery path and the target delivery time point, and the drone's flight trajectory and delivery timing can be adjusted in real time, so that the delivery can be accurately carried out according to the flight status and environment, thereby improving the accuracy of the delivery.

[0111] In a feasible implementation, step S40 may include steps C11 to C15:

[0112] Step C11: Control the UAV according to the target delivery path and collect real-time flight parameters.

[0113] In specific implementation, the drone can be controlled to fly according to the target delivery path, and during the flight, real-time flight data such as the current drone position, speed, acceleration, attitude, etc. can be collected through sensors (such as GPS, accelerometer, gyroscope, etc.).

[0114] Step C12: Based on the real-time flight parameters, the state transition model of the Kalman filter and the updated digital twin model are used to predict the state of the UAV at the next moment to obtain a predicted state, which includes position, speed and acceleration.

[0115] The Kalman filter is a mathematical tool used to estimate system states (such as position, velocity, and acceleration) from measurements. It effectively combines predictive models (physical models) with sensor measurements to estimate a drone's true state. Based on the drone's flight dynamics (e.g., the equations of motion in physics), the Kalman filter uses state transition models to predict the drone's state at the next moment. For example, based on the current velocity and acceleration, it can predict the next moment's position and velocity.

[0116] Combining the Kalman filter and the digital twin model allows us to predict the drone’s state (position, velocity, acceleration) at the next moment, known as the predicted state. This prediction helps identify possible deviations in advance and adjust the trajectory.

[0117] Step C13: adjusting the flight trajectory of the UAV according to the predicted state, and controlling the UAV according to the adjusted flight trajectory.

[0118] Based on the deviation between the predicted drone state and the target trajectory, the flight control system calculates how to correct the flight path. For example, if there is a discrepancy between the predicted position and the target path, the control system needs to adjust the drone's direction, speed, or altitude to correct the trajectory. This adjustment can be achieved using trajectory tracking control algorithms (such as PID control and model predictive control), ensuring that the drone will fly along the desired trajectory at the next moment.

[0119] After adjusting the flight trajectory, the control system will send new control instructions to the drone to ensure that the drone is adjusted to the correct position. For example, it will increase or decrease the thrust, adjust the heading or tilt angle, etc. to ensure the drone's stable flight.

[0120] Step C14: Acquire the current flight environment, and use a Kalman filter to update the target delivery time point according to the current flight environment to obtain an updated target delivery time point.

[0121] During flight, the flight environment (such as wind speed, air pressure, temperature, and weather changes) can affect the drone's flight state. Due to these environmental factors, the actual release time may need to be adjusted. For example, if wind speeds are too high or the drone's flight path deviates, the release time needs to be updated accordingly to ensure the target arrives at the intended location at the correct time. Therefore, a Kalman filter can be used to update the target release time based on the flight environment and recalculate the optimal release time.

[0122] Step C15: Control the UAV to deliver the payload according to the updated target delivery time point.

[0123] When the target delivery time is updated, the flight control system will adjust the drone's movements according to the new delivery time to ensure that the drone delivers the target at the exact time and location.

[0124] This embodiment provides a near-space delivery method based on digital twins. It constructs a digital twin model of a drone and its environment. Based on predetermined mission objectives, the digital twin model is used to simulate delivery results under different delivery strategies, calculating the target delivery path and target delivery time. The drone's status data during actual flight is collected in real time and transmitted to a ground control center, allowing the ground control center to update the digital twin model and provide feedback using the received status data. Based on the updated digital twin model, the target delivery path, and target delivery time, the drone's flight trajectory and delivery timing are adjusted in real time until the delivery mission is completed. The digital twin model allows for a high degree of simulation of drone parameters, enabling more accurate prediction of delivery results under different conditions when planning delivery strategies, thereby improving the accuracy of determining the target delivery path and time. The updated digital twin model is used to adjust the drone's flight trajectory and delivery timing in real time, improving delivery accuracy. Using the digital twin model for virtual simulation, the effectiveness of various delivery strategies can be tested without actually operating the drone, identifying potential problems and optimizing solutions.

[0125] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 2 , step S20 includes steps S201 to S203:

[0126] Step S201: The physical characteristics, flight parameters, and environmental parameters of the UAV are input into the digital twin model according to the predetermined mission objectives, and the motion equations are solved using numerical methods to obtain the predicted trajectory of the UAV.

[0127] In practice, all physical characteristics, flight parameters, and environmental parameters are input into the digital twin model. The model then solves the drone's equations of motion using numerical methods (such as the Euler method and the Runge-Kutta method) to determine the drone's expected flight trajectory during the mission. The predicted trajectory is the trajectory the drone is expected to follow during the mission, ultimately reaching the target drop point.

[0128] By obtaining the initial position x(0), initial velocity v(0) and initial acceleration a(0), the state of the drone at each time step is calculated step by step using the Euler method.

[0129] Define initial conditions: initial position: x(0), initial velocity: v(0), initial acceleration: a(0), time step: Δt, maximum time: T;

[0130] Set up the external force model: Calculate the drone's acceleration at each time step. Acceleration is typically determined by external forces (such as thrust, gravity, and air resistance). Based on the drone's physical model, calculate the acceleration: a(t) = F(t)m, where F(t) is the total external force acting on the drone at time t and m is the drone's mass.

[0131] Iterative calculation: For each time step: calculate the new velocity: v(t+Δt)=v(t)+a(t)Δt;

[0132] Calculate the new position: x(t+Δt)=x(t)+v(t)Δt;

[0133] Repeat the above steps until the maximum time T is reached.

[0134] Calculate the flight trajectory of a drone using the Euler method: Assume that the drone is flying on a simple two-dimensional plane. We ignore air resistance and only consider the effect of gravity. The motion equation of the drone can be simplified to: Fg = mg, where g is the acceleration due to gravity (assumed to be a constant), and the acceleration is: a = (0, -g) where g is the acceleration due to gravity (9.81m / s 2 ).

[0135] Step S202: For different delivery strategies, the corresponding delivery errors are calculated based on the predicted trajectory.

[0136] A delivery strategy is the flight path and timing chosen by a drone during a delivery mission. Different delivery strategies affect the drone's flight trajectory, and thus the accuracy of the delivery. Common delivery strategies may include: Direct delivery: The drone flies along a straight trajectory, dropping items at a predetermined location. Curved delivery: The drone chooses a non-straight trajectory to drop items based on factors like wind speed and flight stability. Speed ​​control: The drone adjusts flight speed based on altitude or time of day to control the timing and accuracy of the delivery.

[0137] The delivery error is the deviation between the predicted trajectory and the actual delivery point. In order to evaluate the effectiveness of different delivery strategies, it is necessary to calculate the error for each delivery strategy. The formula is as follows:

[0138]

[0139] Where x0, y0, z0 are the target location coordinates, and x, y, z are the actual delivery point coordinates calculated based on the predicted trajectory;

[0140] By calculating the delivery error corresponding to each delivery strategy, we can evaluate the accuracy of each strategy and provide a basis for selecting the best strategy.

[0141] Step S203: Select the target delivery path and target delivery time point according to the principle of minimum error.

[0142] The principle of minimum error is the basis for selecting the delivery path and timing. Based on the calculation results of different delivery strategies, the path and time point that can minimize the delivery error are selected.

[0143] In practice, the principle of minimizing delivery error means the system evaluates all possible flight paths and delivery times and selects the strategy that minimizes the distance between the target delivery point and the actual delivery point. This distance is typically the Euclidean distance, or the straight-line distance in three-dimensional space. For example, suppose there are three different delivery strategies, each with the following calculated delivery errors: Strategy A: 2 meters; Strategy B: 1.5 meters; Strategy C: 3 meters.

[0144] According to the principle of minimum error, the system will select strategy B because its delivery error is the smallest (1.5 meters), that is, the deviation between the target and the actual delivery point is the smallest.

[0145] By calculating the delivery error for different time points and path combinations, the system can find the optimal combination of flight path and delivery timing.

[0146] In a feasible implementation, step S40 may further include steps D11 to D14:

[0147] Step D11: Feedback the status data fed back by the ground control center to the digital twin model in real time to update the predicted trajectory.

[0148] It's important to note that feedback data from the ground control center (such as current position, speed, and attitude) is transmitted to the digital twin model in real time, updating the model's status information. This data helps the digital twin more accurately describe the current flight status and predict future trajectories. This reduces system errors and improves the precision and accuracy of predictions.

[0149] In the specific implementation, the numerical method was used to solve the UAV motion equation and obtain the UAV's motion trajectory. After the digital twin model was updated, the updated predicted trajectory was obtained.

[0150] Step D12: The shortest distance is obtained by combining the updated predicted trajectory with the actual position of the current UAV and the target placement position.

[0151] The digital twin model is updated with the feedback data to produce a more accurate prediction of the drone’s flight trajectory, which reflects the drone’s future flight path.

[0152] In the updated trajectory, the shortest distance under the current flight state can be calculated by combining the drone's actual position and the target drop location. The shortest distance is the straight-line distance between the drone's current position and the target drop location, or the shortest flight path along the predicted trajectory. Δd = |Ptarget - Pcurrent|, where Ptarget is the target drop location and Pcurrent is the actual position.

[0153] Step D13: When the current flight time approaches the target delivery time point, the target delivery timing is recalculated based on the shortest distance and the current speed, so as to complete the delivery task based on the target delivery timing and the updated predicted trajectory. The target delivery timing is calculated as follows:

[0154]

[0155] Among them, t 投放 is the target delivery time, d 最短 is the shortest distance, v 当前 is the current speed of the drone, a 当前 is the current acceleration of the drone. 当前 is the current time, v 目标 is the target speed.

[0156] In practice, when the flight time approaches the predetermined target release time, the drone needs to reassess whether the release timing needs to be adjusted. This is because the real-time status during flight (such as speed, acceleration, environmental changes, etc.) may affect the initially preset release timing. Therefore, the target release timing can be recalculated based on the calculated shortest distance and the current flight speed. The speed and shortest distance of the drone jointly affect the accuracy of the release. The calculation of the target release timing needs to take these factors into account. If the drone is close to the target location and the flight speed is fast, the release may need to be carried out in advance; if the drone is slow or the distance is far, the release may need to be delayed. The target release time is calculated using the above formula. Based on the shortest distance and speed, the time required for the drone to reach the target release location is predicted, thereby determining the optimal time for the release. Based on the target release timing, the drone will perform the release operation at the predetermined time. The release process usually includes a series of control steps such as opening the release cabin and releasing the target object to ensure the correct release of the target object.

[0157] In this embodiment, the physical characteristics, flight parameters, and environmental parameters of the UAV are input into the digital twin model according to the predetermined mission objectives. The motion equation is solved using a numerical method to obtain the predicted trajectory of the UAV. For different delivery strategies, the corresponding delivery errors are calculated based on the predicted trajectory. The formula for calculating the delivery error is: Where x0, y0, and z0 are the target location coordinates, and x, y, and z are the actual delivery point coordinates calculated based on the predicted trajectory. The target delivery path and time are selected based on the principle of minimizing error. This helps ensure that the drone can accurately deliver items to the target location within the shortest possible error range during mission execution, improving delivery accuracy.

[0158] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the near-space delivery method based on digital twins of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0159] This application also provides a near-space delivery device based on digital twins, please refer to Figure 3 , the near-space delivery device based on digital twins includes:

[0160] The construction module 10 is used to construct a digital twin model of the UAV and the environment in which the UAV is located. The model at least includes the physical characteristics, flight parameters, environmental conditions and properties of the droplet of the UAV.

[0161] The calculation module 20 is used to simulate the delivery results under different delivery strategies using the digital twin model according to the predetermined task objectives, and calculate the target delivery path and target delivery time point.

[0162] The acquisition module 30 is used to collect the status data of the UAV during the actual flight in real time and transmit the status data to the ground control center so that the ground control center uses the received status data to update the digital twin model and provide feedback.

[0163] The adjustment module 40 is used to adjust the flight trajectory and delivery timing of the drone in real time based on the updated digital twin model, the target delivery path and the target delivery time point until the delivery mission is completed.

[0164] The digital twin-based near-space delivery device provided in this application, which employs the digital twin-based near-space delivery method described in the aforementioned embodiment, can resolve the current technical issue of low accuracy in drone near-space delivery. Compared to the prior art, the beneficial effects of the digital twin-based near-space delivery device provided in this application are the same as those of the digital twin-based near-space delivery method described in the aforementioned embodiment, and the other technical features of the digital twin-based near-space delivery device are the same as those disclosed in the aforementioned embodiment method, and are not further elaborated here.

[0165] In one embodiment, the computing module 20 is further configured to input the physical characteristics, flight parameters, and environmental parameters of the UAV into the digital twin model according to predetermined mission objectives, and solve the equation of motion using a numerical method to obtain a predicted trajectory of the UAV;

[0166] For different delivery strategies, the corresponding delivery errors are calculated based on the predicted trajectory. The formula for calculating the delivery error is:

[0167]

[0168] Where x0, y0, z0 are the target location coordinates, and x, y, z are the actual delivery point coordinates calculated based on the predicted trajectory;

[0169] Select the target delivery path and target delivery time point based on the principle of minimum error.

[0170] In one embodiment, the computing module 20 is further configured to feed back status data fed back by the ground control center to the digital twin model in real time to update the predicted trajectory;

[0171] The shortest distance is obtained by combining the updated predicted trajectory with the actual position of the current UAV and the target drop position;

[0172] When the current flight time approaches the target delivery time point, the target delivery timing is recalculated according to the shortest distance and the current speed, so as to complete the delivery task according to the target delivery timing and the updated predicted trajectory. The target delivery timing is calculated as follows:

[0173]

[0174] Among them, t 投放 is the target delivery time, d 最短 is the shortest distance, v 当前 is the current speed of the drone, a 当前 is the current acceleration of the UAV, t 当前 is the current time, v 目标 is the target speed.

[0175] In one embodiment, the adjustment module 40 is further configured to control the UAV according to the target delivery path and collect real-time flight parameters;

[0176] Based on the real-time flight parameters, a state transition model of a Kalman filter and an updated digital twin model are used to predict the state of the drone at the next moment to obtain a predicted state, where the predicted state includes position, velocity, and acceleration;

[0177] adjusting the flight trajectory of the UAV according to the predicted state, and controlling the UAV according to the adjusted flight trajectory;

[0178] Acquiring a current flight environment, and updating the target delivery time point using a Kalman filter according to the current flight environment to obtain an updated target delivery time point;

[0179] The drone is controlled to deliver the delivery according to the updated target delivery time point.

[0180] In one embodiment, the construction module 10 is further used to determine the data type required to construct the digital twin model;

[0181] Collecting the physical characteristics, flight parameters, environmental conditions, and properties of the dropped objects of the drone based on the data types;

[0182] defining an initial physical model, wherein the initial physical model is used to describe the behavior of the UAV in different flight states;

[0183] The physical characteristics of the drone, the flight parameters, the environmental conditions, and the properties of the droplets are integrated into the initial physical model to construct a digital twin model of the drone and the environment in which the drone is located.

[0184] In one embodiment, the acquisition module 30 is further configured to collect initial flight data of the UAV during actual flight through a plurality of sensors;

[0185] Preprocessing the initial flight data to obtain status data;

[0186] The status data is transmitted to a ground control center so that the ground control center uses the received status data to update the digital twin model and provide feedback.

[0187] In one embodiment, the acquisition module 30 is further configured to obtain a preset smoothing coefficient, and pre-process the initial flight data using the preset smoothing coefficient to obtain reference flight data;

[0188] Obtaining a timestamp corresponding to each data in the reference flight data;

[0189] Determining an offset of the timestamp relative to a reference time;

[0190] Time alignment is performed on the reference flight data according to the offset to obtain status data.

[0191] The present application provides a near-space delivery device based on digital twins, and the near-space delivery device based on digital twins includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the near-space delivery method based on digital twins in the above-mentioned embodiment one.

[0192] Reference below Figure 4 , which shows a schematic structural diagram of a near-space delivery device based on digital twins suitable for implementing the embodiments of the present application. The near-space delivery device based on digital twins in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The digital twin-based near-space delivery device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0193] like Figure 4As shown, the near-space delivery device based on digital twins may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in ROM (Read Only Memory) 1002 or the program loaded from the storage device 1003 to RAM (Random Access Memory) 1004. Various programs and data required for the operation of the near-space delivery device based on digital twins are also stored in RAM 1004. The processing device 1001, ROM 1002 and RAM 1004 are connected to each other via a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, an LCD (Liquid Crystal Display), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the near-space delivery device based on the digital twin to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a near-space delivery device based on the digital twin with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0194] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0195] The digital twin-based near-space delivery device provided in this application, which employs the digital twin-based near-space delivery method described in the aforementioned embodiment, can resolve the current technical issue of low accuracy in drone near-space delivery. Compared to the prior art, the beneficial effects of the digital twin-based near-space delivery device provided in this application are the same as those of the digital twin-based near-space delivery method described in the aforementioned embodiment, and the other technical features of the digital twin-based near-space delivery device are the same as those disclosed in the previous embodiment, and are not further elaborated here.

[0196] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0197] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0198] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the near-space delivery method based on digital twins in the above-mentioned embodiment.

[0199] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or Flash memory), an optical fiber, a CD-ROM (CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0200] The above-mentioned computer-readable storage medium may be included in the near-space delivery device based on digital twins; or it may exist independently without being assembled into the near-space delivery device based on digital twins.

[0201] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the near-space delivery device based on digital twin, the near-space delivery device based on digital twin: constructs a digital twin model of the UAV and the environment in which the UAV is located, and the model at least includes the physical characteristics, flight parameters, environmental conditions and properties of the delivery object of the UAV; according to the predetermined mission objectives, uses the digital twin model to simulate the delivery results under different delivery strategies, and calculates the target delivery path and target delivery time point; collects the status data of the UAV during the actual flight in real time, and transmits the status data to the ground control center, so that the ground control center uses the received status data to update the digital twin model and feedback; based on the updated digital twin model, the target delivery path and the target delivery time point, adjusts the flight trajectory and delivery timing of the UAV in real time until the delivery mission is completed.

[0202] The computer program code for performing the operations of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a LAN (Local Area Network) or a WAN (Wide Area Network), or can be connected to an external computer (e.g., using an Internet service provider to connect via the Internet).

[0203] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0204] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0205] The computer-readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned near-space delivery method based on digital twins. This computer-readable storage medium can address the current technical issue of low accuracy in near-space delivery of drones. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the near-space delivery method based on digital twins provided in the aforementioned embodiments, and are not further elaborated here.

[0206] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned digital twin-based near-space delivery method.

[0207] The computer program product provided in this application can solve the current technical problem of low accuracy in near-space drone delivery. Compared with the existing technology, the beneficial effects of the computer program product provided in this application are the same as those of the near-space delivery method based on digital twins provided in the above embodiments, and will not be elaborated here.

[0208] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A near-space deployment method based on digital twins, comprising the following steps: Constructing a digital twin model of the drone and its environment, the model including at least the drone's physical characteristics, flight parameters, environmental conditions, and properties of the droplet; According to the predetermined task objectives, the digital twin model is used to simulate the delivery results under different delivery strategies, and the target delivery path and target delivery time point are calculated; Collect the status data of the UAV in real time during the actual flight process, and transmit the status data to the ground control center, so that the ground control center uses the received status data to update the digital twin model and provide feedback; Based on the updated digital twin model, the target delivery path and the target delivery time point, the flight trajectory and delivery timing of the drone are adjusted in real time until the delivery mission is completed.

2. The method according to claim 1, wherein The steps of simulating the delivery results under different delivery strategies using the digital twin model according to the predetermined task objectives and calculating the target delivery path and target delivery time point include: According to the predetermined mission objectives, the physical characteristics, flight parameters, and environmental parameters of the UAV are input into the digital twin model, and the motion equations are solved using numerical methods to obtain the predicted trajectory of the UAV. For different delivery strategies, the corresponding delivery errors are calculated based on the predicted trajectory. The formula for calculating the delivery error is: Where x0, y0, z0 are the target location coordinates, and x, y, z are the actual delivery point coordinates calculated based on the predicted trajectory; Select the target delivery path and target delivery time point based on the principle of minimum error.

3. The method according to claim 2, wherein The step of adjusting the flight trajectory and delivery timing of the drone in real time based on the updated digital twin model, the target delivery path, and the target delivery time point includes: Feeding back status data from the ground control center to the digital twin model in real time to update the predicted trajectory; The shortest distance is obtained by combining the updated predicted trajectory with the actual position of the current UAV and the target drop position; When the current flight time approaches the target delivery time point, the target delivery timing is recalculated according to the shortest distance and the current speed, so as to complete the delivery task according to the target delivery timing and the updated predicted trajectory. The target delivery timing is calculated as follows: Among them, t 投放 is the target delivery time, d 最短 is the shortest distance, v 当前 is the current speed of the drone, a 当前 is the current acceleration of the UAV, t 当前 is the current time, v 目标 is the target speed.

4. The method according to claim 1, wherein The step of adjusting the flight trajectory and delivery timing of the drone in real time based on the updated digital twin model, the target delivery path, and the target delivery time point until the delivery task is completed includes: Controlling the UAV according to the target delivery path and collecting real-time flight parameters; Based on the real-time flight parameters, a state transition model of a Kalman filter and an updated digital twin model are used to predict the state of the drone at the next moment to obtain a predicted state, where the predicted state includes position, velocity, and acceleration; adjusting the flight trajectory of the UAV according to the predicted state, and controlling the UAV according to the adjusted flight trajectory; Acquiring a current flight environment, and updating the target delivery time point using a Kalman filter according to the current flight environment to obtain an updated target delivery time point; The drone is controlled to deliver the delivery according to the updated target delivery time point.

5. The method according to claim 1, wherein The steps of constructing a digital twin model of the drone and the environment in which the drone is located include: Determine the types of data needed to build the digital twin model; Collecting the physical characteristics, flight parameters, environmental conditions, and properties of the dropped objects of the drone based on the data types; defining an initial physical model, wherein the initial physical model is used to describe the behavior of the UAV in different flight states; The physical characteristics of the drone, the flight parameters, the environmental conditions, and the properties of the droplets are integrated into the initial physical model to construct a digital twin model of the drone and the environment in which the drone is located.

6. The method according to claim 1, wherein The step of collecting the status data of the UAV in real time during the actual flight process and transmitting the status data to the ground control center so that the ground control center uses the received status data to update the digital twin model and provide feedback includes: Collect initial flight data of the drone during actual flight through multiple sensors; Preprocessing the initial flight data to obtain status data; The status data is transmitted to a ground control center so that the ground control center uses the received status data to update the digital twin model and provide feedback.

7. The method according to claim 6, wherein The step of preprocessing the initial flight data to obtain status data includes: Obtaining a preset smoothing coefficient, and preprocessing the initial flight data using the preset smoothing coefficient to obtain reference flight data; Obtaining a timestamp corresponding to each data in the reference flight data; Determining an offset of the timestamp relative to a reference time; Time alignment is performed on the reference flight data according to the offset to obtain status data.

8. A near-space delivery device based on digital twins, characterized in that: The device comprises: A construction module for constructing a digital twin model of the drone and its environment, the model including at least the drone's physical characteristics, flight parameters, environmental conditions, and properties of the droplet; A calculation module is used to simulate the delivery results under different delivery strategies using the digital twin model according to the predetermined task objectives, and calculate the target delivery path and target delivery time point; The acquisition module is used to collect the status data of the UAV in real time during the actual flight process and transmit the status data to the ground control center so that the ground control center can use the received status data to update the digital twin model and provide feedback; The adjustment module is used to adjust the flight trajectory and delivery timing of the drone in real time based on the updated digital twin model, the target delivery path, and the target delivery time point until the delivery mission is completed.

9. A near-space delivery device based on digital twins, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the near-space delivery method based on digital twins as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the near-space delivery method based on digital twins are implemented as described in any one of claims 1 to 7.

Images