Unmanned aerial vehicle automatic landing control method and device
By constructing a multi-objective fitness function and a particle swarm optimization algorithm, the problems of model dependence and insufficient robustness in the automatic landing control of UAVs were solved, and safe, accurate and efficient landing in complex environments was achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- INST OF AUTOMATION CHINESE ACAD OF SCI
- Filing Date
- 2026-01-29
- Publication Date
- 2026-06-02
AI Technical Summary
Existing automatic landing control methods for unmanned aerial vehicles (UAVs) are difficult to model accurately in complex environments, resulting in poor robustness, poor real-time performance, and high algorithm complexity, which limits their engineering applications.
By collecting UAV operational status parameters and environmental interference data, a multi-objective fitness function is constructed, and a particle swarm optimization algorithm is used for global optimization to determine the target landing control parameters, thereby enabling the UAV to land safely and accurately in complex environments.
It significantly improves the landing accuracy and attitude stability of UAVs in interference environments, enhances the robustness and environmental adaptability of the system, and achieves safe, accurate and efficient autonomous landing.
Smart Images
Figure CN122131646A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of unmanned aerial vehicle (UAV) control technology, and in particular to an automatic landing control method and device for UAVs. Background Technology
[0002] Automatic landing of unmanned aerial vehicles (UAVs) is a crucial step in UAV flight missions, directly impacting flight safety and mission success. In civilian (e.g., logistics and power line inspection) and military (e.g., reconnaissance and recovery, and supply delivery) fields, UAVs often need to complete automatic landings in complex environments (e.g., strong winds, uneven terrain, and positioning errors), placing extremely high demands on the accuracy, robustness, and adaptability of control algorithms.
[0003] In related technologies, existing automatic landing control methods for unmanned aerial vehicles (UAVs) mainly include two categories: traditional linear control and nonlinear control. Traditional linear control ignores the nonlinear characteristics of the UAV landing process, and the PID parameters mostly rely on manual tuning. It has poor robustness in complex scenarios such as wind speed disturbances and terrain deviations, and landing accuracy is difficult to guarantee. Nonlinear control relies on high-precision mathematical models. However, factors such as wind speed disturbances, sensor noise, and terrain uncertainties in the UAV landing process make it difficult to establish accurate models. In addition, the algorithm has high complexity and poor real-time performance, which limits engineering applications. Summary of the Invention
[0004] This application provides an automatic landing control method and apparatus for unmanned aerial vehicles (UAVs) to solve the technical problems in the prior art that exist in the UAV landing process, such as wind speed disturbance, sensor noise, and terrain uncertainty, which make it difficult to establish an accurate model, and the algorithm has high complexity and poor real-time performance, thus limiting the engineering application.
[0005] This application provides an automatic landing control method for unmanned aerial vehicles (UAVs), characterized by comprising: Collect operational status parameters and environmental interference data of the UAV during the automatic landing phase; Based on the operating status parameters and the environmental interference data, the dynamic model and landing constraints of the UAV landing process are determined. Based on the aforementioned landing constraints, a multi-objective fitness function is constructed to evaluate landing performance; With the goal of optimizing the multi-objective fitness function, the landing control parameters of the UAV are globally optimized based on the particle swarm optimization algorithm to determine the target landing control parameters; Based on the target landing control parameters, the UAV is controlled to complete an automatic landing.
[0006] According to the automatic landing control method for unmanned aerial vehicles provided in this application, the landing constraints include at least one of the following: Vertical landing speed is less than or equal to the landing speed threshold; Attitude angle is less than or equal to attitude angle threshold; The horizontal offset of the landing point is less than or equal to the horizontal offset threshold.
[0007] According to the automatic landing control method for unmanned aerial vehicles provided in this application, the operating status parameters include the position information, speed information, attitude angle information and altitude information of the unmanned aerial vehicle; The environmental interference data is generated through Monte Carlo simulation, and includes: dynamic wind speed and direction interference information, air pressure disturbance information, ground effect interference information, and random turbulence interference information.
[0008] According to the automatic landing control method for unmanned aerial vehicles (UAVs) provided in this application, the step of globally optimizing the landing control parameters of the UAV based on the particle swarm optimization algorithm to determine the target landing control parameters includes: The particle swarm is initialized, wherein each particle in the particle swarm corresponds to a set of candidate landing control parameters; In each iteration, the multi-objective fitness function value is determined based on the candidate landing control parameters and landing dynamics model corresponding to each particle. The individual optimal solution of each particle and the global optimal solution of the entire particle swarm are updated based on the multi-objective fitness function value. The velocity and position of the particle are updated based on the individual optimal solution and the global optimal solution; If the preset iteration termination condition is met, the iteration is stopped, and the landing control parameters corresponding to the global optimal solution are used as the target landing control parameters.
[0009] According to the automatic landing control method for unmanned aerial vehicles provided in this application, the determination of satisfying the preset iteration termination condition includes any one of the following: The number of iterations equals the iteration threshold; The fitness function corresponding to the global optimal solution changes less than a preset threshold for N consecutive rounds, where N is a positive integer.
[0010] According to the automatic landing control method for unmanned aerial vehicles provided in this application, the specific expression of the multi-objective fitness function is as follows: Fitness value = ω1 × landing accuracy index + ω2 × attitude stability index + ω3 × energy consumption index + ω4 × anti-interference index; Among them, ω1, ω2, ω3, and ω4 are dynamic weighting coefficients.
[0011] This application also provides an automatic landing control device for unmanned aerial vehicles, characterized in that it includes: The data acquisition module is used to collect the operating status parameters and environmental interference data of the UAV during the automatic landing phase. The determination module is used to determine the dynamic model and landing constraints of the UAV landing process based on the operating state parameters and the environmental interference data. A construction module is used to construct a multi-objective fitness function for evaluating landing performance based on the landing constraints. The optimization module is used to perform global optimization of the UAV's landing control parameters based on the particle swarm optimization algorithm with the goal of optimizing the multi-objective fitness function, so as to determine the target landing control parameters. The control module is used to control the UAV to complete an automatic landing based on the target landing control parameters.
[0012] According to the automatic landing control device for unmanned aerial vehicles provided in this application, the landing constraints include at least one of the following: Vertical landing speed is less than or equal to the landing speed threshold; Attitude angle is less than or equal to attitude angle threshold; The horizontal offset of the landing point is less than or equal to the horizontal offset threshold.
[0013] According to the automatic landing control device for unmanned aerial vehicles provided in this application, the operating status parameters include the position information, speed information, attitude angle information and altitude information of the unmanned aerial vehicle; The environmental interference data is generated through Monte Carlo simulation, and includes: dynamic wind speed and direction interference information, air pressure disturbance information, ground effect interference information, and random turbulence interference information.
[0014] According to the automatic landing control device for unmanned aerial vehicles provided in this application, the optimization module is specifically used for: The particle swarm is initialized, wherein each particle in the particle swarm corresponds to a set of candidate landing control parameters; In each iteration, the multi-objective fitness function value is determined based on the candidate landing control parameters and landing dynamics model corresponding to each particle. The individual optimal solution of each particle and the global optimal solution of the entire particle swarm are updated based on the multi-objective fitness function value. The velocity and position of the particle are updated based on the individual optimal solution and the global optimal solution; If the preset iteration termination condition is met, the iteration is stopped, and the landing control parameters corresponding to the global optimal solution are used as the target landing control parameters.
[0015] According to the automatic landing control device for unmanned aerial vehicles provided in this application, the determination that the preset iteration termination condition is met includes any one of the following: The number of iterations equals the iteration threshold; The fitness function corresponding to the global optimal solution changes less than a preset threshold for N consecutive rounds, where N is a positive integer.
[0016] According to the automatic landing control device for unmanned aerial vehicles provided in this application, the specific expression of the multi-target fitness function is as follows: Fitness value = ω1 × landing accuracy index + ω2 × attitude stability index + ω3 × energy consumption index + ω4 × anti-interference index; Among them, ω1, ω2, ω3, and ω4 are dynamic weighting coefficients.
[0017] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the automatic landing control method for unmanned aerial vehicles as described above.
[0018] This application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the automatic landing control method for unmanned aerial vehicles as described above.
[0019] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the automatic landing control method for unmanned aerial vehicles as described above.
[0020] The UAV automatic landing control method and apparatus of this application establish a realistic dynamic model and safety constraints by collecting flight status and environmental disturbance data in real time. It constructs a multi-objective fitness function that comprehensively evaluates landing accuracy, attitude stability, energy consumption, and anti-interference capability, and utilizes the global optimization capability of the particle swarm optimization algorithm to efficiently search for the optimal combination of control parameters in a complex parameter space. This method not only significantly improves the landing accuracy and attitude stability of the UAV in disturbed environments but also enhances its endurance adaptability by optimizing energy consumption. Furthermore, its independence from precise mathematical models greatly enhances the system's robustness and environmental adaptability, ultimately achieving safe, accurate, and efficient autonomous landing of the UAV in complex scenarios such as strong winds and turbulence. This effectively solves the technical bottlenecks of traditional methods in terms of model dependence, insufficient robustness, and multi-objective trade-offs. Attached Figure Description
[0021] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0022] Figure 1This is a flowchart illustrating the automatic landing control method for unmanned aerial vehicles provided in this application.
[0023] Figure 2 This is a schematic diagram of the structure of the unmanned aerial vehicle automatic landing control device provided in this application.
[0024] Figure 3 A schematic diagram of the physical structure of an electronic device is provided. Detailed Implementation
[0025] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0026] The following is combined with Figure 1 This application describes the automatic landing control method for unmanned aerial vehicles.
[0027] Figure 1 This is a flowchart illustrating the automatic landing control method for unmanned aerial vehicles provided in this application, as shown below. Figure 1 As shown, the method includes the following: Step 101: Collect the operating status parameters and environmental interference data of the UAV during the automatic landing phase.
[0028] Among them, the operational status parameters refer to the set of motion status parameters of the UAV measured in real time by airborne sensors during the landing process, which reflect the UAV's current spatial position, speed and attitude information.
[0029] In this embodiment of the application, the operating status parameters include the UAV's position information, speed information, attitude angle information, and altitude information.
[0030] The location information of the drone refers to its position relative to the ground coordinate system, and there are no restrictions on this.
[0031] Among them, the speed of movement refers to the speed of movement of the drone in three directions.
[0032] Attitude information is used to describe the spatial orientation of the UAV body, such as roll angle, pitch angle, yaw angle, etc., and there are no restrictions on it.
[0033] The altitude information of the drone can be, for example, the actual vertical distance between the drone and the ground, and there are no restrictions on this.
[0034] In this embodiment of the application, the operational status parameters of the UAV during the automatic landing phase can be collected by obtaining position information based on Global Positioning System (GPS) / Real-time Kinematic (RTK) technology, attitude information based on Inertial Measurement Unit (IMU), altitude information based on barometer, and velocity based on airspeed meter. There are no restrictions on this.
[0035] The environmental disturbance data is generated through Monte Carlo simulation. It includes dynamic wind speed and direction disturbance information, air pressure disturbance information, ground effect disturbance information, and random turbulence disturbance information.
[0036] Among them, environmental interference data refers to data that will affect the landing of the drone during the landing phase.
[0037] Among them, dynamic wind speed and direction interference information refers to the natural phenomenon that wind speed and direction change over time during the landing process of the drone, which is the main external factor affecting the stability of the drone.
[0038] Among them, atmospheric pressure disturbance information refers to unexpected changes in atmospheric pressure, mainly caused by weather system movement, thermal convection, terrain effects, etc., which can interfere with the aerodynamic performance and force system efficiency of UAVs during the landing phase.
[0039] Ground effect interference information refers to the aerodynamic phenomena generated by the interaction between the rotor downwash airflow and the ground when the UAV approaches the ground (usually at a height less than 1-2 times the rotor diameter).
[0040] Among them, random turbulence disturbance information refers to information used to describe random fluctuations in airflow velocity and direction caused by irregular atmospheric motion.
[0041] In some embodiments, environmental disturbance data of the UAV during the automatic landing phase can be collected, for example, by real-time measurement using an onboard anemometer and barometer, and by combining the data with a terrain database to assess the ground effect, in order to determine the environmental disturbance data of the UAV during the automatic landing phase.
[0042] In this embodiment, the environmental interference data is generated through Monte Carlo simulation. That is, the Monte Carlo simulation method can be used to simulate the landing of drones in different landing scenarios to construct environmental interference data covering both normal and extreme scenarios.
[0043] Step 102: Based on the operating status parameters and environmental disturbance data, determine the dynamic model and landing constraints of the UAV landing process.
[0044] The dynamic model is a set of equations that describe the relationship between the UAV's motion state (position, velocity, attitude) and control inputs (such as thrust and torque).
[0045] Landing constraints refer to the safety and performance limitations that the UAV must meet during landing, such as thresholds for speed, attitude, and position. For example, the vertical landing speed must be controlled within a safe threshold to avoid the risk of a hard landing; the roll, pitch, and yaw attitude angles must be kept within a small range to ensure stable landing attitude; and the horizontal offset of the landing point must be controlled within a preset accuracy to ensure accurate landing position. No restrictions are imposed on these.
[0046] Optionally, in some embodiments, the landing constraints include at least one of the following: Vertical landing speed is less than or equal to the landing speed threshold; Attitude angle is less than or equal to attitude angle threshold; The horizontal offset of the landing point is less than or equal to the horizontal offset threshold.
[0047] In this embodiment of the application, the constraints are set according to the physical limits and safety standards of the UAV, such as vertical landing speed ≤ 0.5 m / s, roll and pitch angles ≤ 5°, yaw angle ≤ 3°, and horizontal offset of landing point ≤ 0.3 m. Alternatively, the constraints can be determined through statistical analysis of historical landing data, for example, based on 1000 landing data, the 99th percentile is taken as the threshold, and no restrictions are imposed on this.
[0048] Step 103: Based on landing constraints, construct a multi-objective fitness function to evaluate landing performance.
[0049] Among them, the multi-objective fitness function can be used to comprehensively optimize landing performance. That is, it can be optimized based on the multi-objective fitness function, which is an evaluation function that comprehensively considers multiple performance indicators. It is used to quantify the overall performance of UAV landing control. The multiple performance indicators may include: the deviation between the landing position and the target point as the landing accuracy indicator, the fluctuation range of the attitude angle as the attitude stability indicator, and the energy consumption of the control command as the energy consumption indicator. There are no restrictions on these.
[0050] Among them, the landing accuracy index refers to the index that quantifies the deviation between the actual landing point of the UAV and the target landing point. It can be used to reflect the accuracy of control and the position tracking capability.
[0051] Among them, the attitude stability index quantifies the smoothness of attitude angle changes during the landing process of the UAV, and can be used to reflect the flight stability and anti-interference capability of the UAV.
[0052] Among them, the energy consumption index quantifies the energy or control cost consumed by the drone during the landing process, and it can be used to reflect control efficiency.
[0053] Among them, the anti-interference index is an indicator that quantifies the stability and robustness of UAVs in interference environments. It can be used to reflect the control system's ability to suppress external interference.
[0054] Optionally, in some embodiments, the specific expression of the multi-objective fitness function is: Fitness value = ω1 × landing accuracy index + ω2 × attitude stability index + ω3 × energy consumption index + ω4 × anti-interference index; Among them, ω1, ω2, ω3, and ω4 are dynamic weighting coefficients.
[0055] Among them, the dynamic weighting coefficient can be dynamically adjusted in conjunction with the landing phase and performance requirements. For example, in the early stage of drone landing, the attitude stability index and energy consumption index have higher weights. In the middle stage of drone landing, the weights of landing accuracy index and anti-interference index gradually increase. In the late stage of drone landing, the weight of landing accuracy index is the highest, thereby ensuring accurate drone landing.
[0056] In this embodiment, the multi-objective fitness function for evaluating landing performance based on landing constraints can be implemented as follows: First, for the four core performance objectives of landing accuracy, attitude stability, energy efficiency, and anti-interference capability, corresponding quantitative index functions are designed respectively. The landing accuracy index is characterized by the weighted sum of the horizontal distance deviation and vertical height error between the actual landing point and the target point of the UAV; the attitude stability index is evaluated by the integral attitude angle fluctuation amplitude and angular velocity change rate; the energy consumption index is measured by the total energy consumption of statistical control commands and the smoothness of change; and the anti-interference index quantifies the robustness of the system by comparing the performance differences under conditions with and without interference. Subsequently, these independent performance indices are integrated into a unified fitness function value through a linear weighted combination, where each weight coefficient can be dynamically adjusted according to the landing stage: in the early stage of landing, attitude stability and energy consumption are given higher weights to ensure safety and economy, while in the late stage of landing, the landing accuracy weight is significantly increased to ensure accurate landing. At the same time, the landing constraints are rigidly embedded into the fitness function by introducing constraint violation penalties (such as penalty coefficients for vertical overspeed, attitude over-limit, or position deviation exceeding the threshold).
[0057] Step 104: With the goal of optimizing the multi-objective fitness function, the landing control parameters of the UAV are globally optimized based on the particle swarm optimization algorithm to determine the target landing control parameters.
[0058] Optimizing the multi-objective fitness function refers to the process of finding the combination of control parameters that minimizes (or optimizes) the value of the multi-objective fitness function.
[0059] Among them, the particle swarm optimization algorithm is a stochastic optimization algorithm based on swarm intelligence. The concepts involved in this algorithm include: a particle is a candidate solution in the search space, corresponding to a set of candidate control parameters; position is the coordinate of the particle in the parameter space, representing the specific parameter value; velocity is the direction and step size of the particle's movement in the parameter space; the individual optimal solution is the optimal position found by the particle itself, and the global optimal solution is the optimal position found in the entire swarm.
[0060] Among them, the target landing control parameters are the final combination of control parameters determined after optimization. The target control parameters can be, for example, proportional-integral-derivative (PID) controller parameters, which satisfy the fitness function to reach the optimal or suboptimal state and meet all landing constraints.
[0061] Optionally, in some embodiments, the landing control parameters of the UAV are globally optimized based on the particle swarm optimization algorithm to determine the target landing control parameters, including: The particle swarm is initialized, where each particle in the swarm corresponds to a set of candidate landing control parameters; In each iteration, the multi-objective fitness function value is determined based on the candidate landing control parameters and landing dynamics model corresponding to each particle. The individual optimal solution of each particle and the global optimal solution of the entire particle swarm are updated based on the multi-objective fitness function value. Update the particle's velocity and position based on the individual optimal solution and the global optimal solution; If the preset iteration termination condition is met, the iteration stops, and the landing control parameters corresponding to the global optimal solution are taken as the target landing control parameters.
[0062] Optionally, in some embodiments, a preset iteration termination condition is determined, including any one of the following: The number of iterations equals the iteration threshold; The fitness function value corresponding to the global optimal solution for N consecutive rounds changes less than a preset threshold, where N is a positive integer.
[0063] The number of iterations is the number of complete optimization loops executed in the particle swarm optimization algorithm. It can be used to control the maximum running time of the algorithm and prevent infinite loops.
[0064] Among them, the iteration number threshold is a preset maximum upper limit of the number of iterations. The preset threshold is a pre-set very small positive number used to determine convergence.
[0065] The change in fitness function is the difference in fitness value between adjacent iterations corresponding to the global optimal solution, which can be used to reflect the speed and convergence of optimization progress.
[0066] In other words, in this embodiment of the application, the specific implementation process of global optimization of UAV landing control parameters based on particle swarm optimization is as follows: First, the particle swarm is initialized, where each particle corresponds to a set of candidate landing control parameters (such as PID control parameters). An initial particle swarm is created within a preset parameter range through random generation, and an initial velocity and position are assigned to each particle. During each iteration, the system performs simulation calculations based on the candidate landing control parameters corresponding to each particle, combined with the UAV landing dynamics model, to determine the multi-objective fitness function value under the parameter configuration (comprehensively evaluating landing accuracy, attitude stability, energy consumption, and anti-interference performance). Based on the calculated fitness value, the individual optimal solution of each particle (i.e., the best parameter combination in the particle's history) and the global optimal solution of the entire particle swarm (i.e., the best parameter combination among all current particles) are updated.
[0067] Then, based on the updated individual optimal solution and the global optimal solution, the velocity and position of each particle are adjusted according to the velocity update formula of the particle swarm optimization algorithm. The velocity update comprehensively considers the inertial component, the individual cognitive component (moving towards the individual optimal solution), and the social learning component (moving towards the global optimal solution), while the position update calculates a new parameter combination based on the current velocity and position. This iterative process continues, and after each iteration, the system determines whether the preset iteration termination conditions are met (such as reaching the maximum number of iterations, the global optimal solution showing no significant improvement for several consecutive iterations, the fitness value converging to a preset threshold, or the computation time reaching the upper limit). Once any termination condition is met, the iteration stops, and the landing control parameters corresponding to the current global optimal solution are output as the final determined target landing control parameters.
[0068] For example, set the particle swarm size to 40 particles (each particle corresponds to a set of control parameters for three channels: x, y, and z); set the initial values for inertial weights and learning factors; set the maximum number of iterations; then substitute the control parameters corresponding to each particle into the UAV landing process model, calculate its corresponding fitness function value, and record the optimal fitness value of each particle (individual optimal) and the optimal fitness value of the entire swarm (global optimal). Iterate and update the velocity and position of each particle (within a reasonable range to avoid parameter deviation). When the iteration reaches 80 times, or when the change in the global optimal fitness value is less than 0.0001 for 5 consecutive iterations, stop the iteration, and output the control parameters corresponding to the global optimal as the target control parameters.
[0069] Step 105: Based on the target landing control parameters, control the UAV to complete the automatic landing.
[0070] In this embodiment, taking the optimized PID controller parameters [Kp=2.5, Ki=0.12, Kd=0.8] as an example, the UAV is controlled to complete automatic landing based on the target landing control parameters. For example, these parameters can be injected into the attitude and position control loop of the UAV flight control system in real time. When the UAV enters the landing phase, the flight control system continuously collects the current altitude, speed and attitude information, and combines it with the preset landing trajectory (such as an exponential descent curve). The optimized control parameters are used to calculate the speed adjustment of each motor in real time. When encountering crosswind interference, the anti-interference compensation parameters will automatically adjust the control output to offset the wind disturbance. At the same time, the monitoring system verifies the constraints such as vertical speed not exceeding 0.5m / s and roll angle less than 5° in real time. If an abnormal deviation is detected, the parameter fine-tuning mechanism is triggered. Through such closed-loop control, the UAV descends smoothly along the predetermined trajectory and finally executes the slow descent procedure 0.5 meters above the target point, accurately touching the ground with a vertical speed of 0.2m / s, completing the entire automatic landing process.
[0071] The UAV automatic landing control method of this application establishes a realistic dynamic model and safety constraints by collecting flight status and environmental disturbance data in real time. It constructs a multi-objective fitness function that comprehensively evaluates landing accuracy, attitude stability, energy consumption, and anti-interference capability. Utilizing the global optimization capability of the particle swarm optimization algorithm, it efficiently searches for the optimal combination of control parameters in a complex parameter space. This method not only significantly improves the landing accuracy and attitude stability of the UAV in disturbed environments but also enhances its endurance adaptability by optimizing energy consumption. Furthermore, its independence from precise mathematical models greatly enhances the system's robustness and environmental adaptability. Ultimately, it achieves safe, accurate, and efficient autonomous landing of the UAV in complex scenarios such as strong winds and turbulence, effectively solving the technical bottlenecks of traditional methods in terms of model dependence, insufficient robustness, and multi-objective trade-offs.
[0072] The automatic landing control device for unmanned aerial vehicles (UAVs) provided in this application is described below. The automatic landing control device for UAVs described below can be referred to in correspondence with the automatic landing control method for UAVs described above.
[0073] Figure 2 This is a schematic diagram of the structure of the unmanned aerial vehicle automatic landing control device provided in this application, as shown below. Figure 2 As shown, the device includes the following: The data acquisition module 201 is used to collect the operating status parameters and environmental interference data of the UAV during the automatic landing phase. The determination module 202 is used to determine the dynamic model and landing constraints of the UAV landing process based on the operating status parameters and environmental disturbance data. Module 203 is used to construct a multi-objective fitness function for evaluating landing performance based on landing constraints. The optimization module 204 is used to perform global optimization of the landing control parameters of the UAV based on the particle swarm algorithm with the goal of optimizing the multi-objective fitness function, so as to determine the target landing control parameters. The control module 205 is used to control the UAV to complete the automatic landing based on the target landing control parameters.
[0074] According to the automatic landing control device for unmanned aerial vehicles provided in this application, the landing constraints include at least one of the following: Vertical landing speed is less than or equal to the landing speed threshold; Attitude angle is less than or equal to attitude angle threshold; The horizontal offset of the landing point is less than or equal to the horizontal offset threshold.
[0075] According to the automatic landing control device for unmanned aerial vehicles provided in this application, the operating status parameters include the position information, speed information, attitude angle information and altitude information of the unmanned aerial vehicle; The environmental disturbance data is generated through Monte Carlo simulation. It includes dynamic wind speed and direction disturbance information, air pressure disturbance information, ground effect disturbance information, and random turbulence disturbance information.
[0076] According to the automatic landing control device for unmanned aerial vehicles provided in this application, the optimization module 204 is specifically used for: The particle swarm is initialized, where each particle in the swarm corresponds to a set of candidate landing control parameters; In each iteration, the multi-objective fitness function value is determined based on the candidate landing control parameters and landing dynamics model corresponding to each particle. The individual optimal solution of each particle and the global optimal solution of the entire particle swarm are updated based on the multi-objective fitness function value. Update the particle's velocity and position based on the individual optimal solution and the global optimal solution; If the preset iteration termination condition is met, the iteration stops, and the landing control parameters corresponding to the global optimal solution are taken as the target landing control parameters.
[0077] According to the automatic landing control device for unmanned aerial vehicles provided in this application, a preset iteration termination condition is determined, including any one of the following: The number of iterations equals the iteration threshold; The fitness function value corresponding to the global optimal solution for N consecutive rounds changes less than a preset threshold, where N is a positive integer.
[0078] According to the automatic landing control device for unmanned aerial vehicles provided in this application, the specific expression of the multi-target fitness function is as follows: Fitness value = ω1 × landing accuracy index + ω2 × attitude stability index + ω3 × energy consumption index + ω4 × anti-interference index; Among them, ω1, ω2, ω3, and ω4 are dynamic weighting coefficients.
[0079] The UAV automatic landing control device of this application establishes a realistic dynamic model and safety constraints by collecting real-time flight status and environmental disturbance data. It constructs a multi-objective fitness function that comprehensively evaluates landing accuracy, attitude stability, energy consumption, and anti-interference capability. Utilizing the global optimization capability of the particle swarm optimization algorithm, it efficiently searches for the optimal combination of control parameters in a complex parameter space. This method not only significantly improves the landing accuracy and attitude stability of the UAV in disturbed environments but also enhances its endurance adaptability by optimizing energy consumption. Furthermore, its independence from precise mathematical models greatly enhances the system's robustness and environmental adaptability. Ultimately, it achieves safe, accurate, and efficient autonomous landing of the UAV in complex scenarios such as strong winds and turbulence, effectively solving the technical bottlenecks of traditional methods in terms of model dependence, insufficient robustness, and multi-objective trade-offs.
[0080] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communications interface 320, and the memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute an automatic landing control method for the unmanned aerial vehicle, the method including: Collect operational status parameters and environmental interference data of the UAV during the automatic landing phase; Based on operational status parameters and environmental disturbance data, the dynamic model and landing constraints of the UAV landing process are determined. Based on landing constraints, a multi-objective fitness function is constructed to evaluate landing performance. With the goal of optimizing the multi-objective fitness function, the landing control parameters of the UAV are globally optimized based on the particle swarm optimization algorithm to determine the target landing control parameters; Based on the target landing control parameters, the UAV is controlled to complete an automatic landing.
[0081] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0082] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the UAV automatic landing control method provided by the above methods, the method including: Collect operational status parameters and environmental interference data of the UAV during the automatic landing phase; Based on operational status parameters and environmental disturbance data, the dynamic model and landing constraints of the UAV landing process are determined. Based on landing constraints, a multi-objective fitness function is constructed to evaluate landing performance. With the goal of optimizing the multi-objective fitness function, the landing control parameters of the UAV are globally optimized based on the particle swarm optimization algorithm to determine the target landing control parameters; Based on the target landing control parameters, the UAV is controlled to complete an automatic landing.
[0083] In another aspect, this application also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, is implemented to perform the unmanned aerial vehicle (UAV) automatic landing control method provided by the above methods, the method comprising: Collect operational status parameters and environmental interference data of the UAV during the automatic landing phase; Based on operational status parameters and environmental disturbance data, the dynamic model and landing constraints of the UAV landing process are determined. Based on landing constraints, a multi-objective fitness function is constructed to evaluate landing performance. With the goal of optimizing the multi-objective fitness function, the landing control parameters of the UAV are globally optimized based on the particle swarm optimization algorithm to determine the target landing control parameters; Based on the target landing control parameters, the UAV is controlled to complete an automatic landing.
[0084] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0085] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.
Claims
1. A method for automatic landing control of an unmanned aerial vehicle (UAV), characterized in that, include: Collect operational status parameters and environmental interference data of the UAV during the automatic landing phase; Based on the operating status parameters and the environmental interference data, the dynamic model and landing constraints of the UAV landing process are determined. Based on the aforementioned landing constraints, a multi-objective fitness function is constructed to evaluate landing performance; With the goal of optimizing the multi-objective fitness function, the landing control parameters of the UAV are globally optimized based on the particle swarm optimization algorithm to determine the target landing control parameters; Based on the target landing control parameters, the UAV is controlled to complete an automatic landing.
2. The method according to claim 1, characterized in that, The landing constraints include at least one of the following: Vertical landing speed is less than or equal to the landing speed threshold; Attitude angle is less than or equal to attitude angle threshold; The horizontal offset of the landing point is less than or equal to the horizontal offset threshold.
3. The method according to claim 1, characterized in that, The operating status parameters include the UAV's position information, speed information, attitude angle information, and altitude information; The environmental interference data is generated through Monte Carlo simulation, and includes: dynamic wind speed and direction interference information, air pressure disturbance information, ground effect interference information, and random turbulence interference information.
4. The method according to claim 1, characterized in that, The global optimization of the UAV landing control parameters based on the particle swarm optimization algorithm to determine the target landing control parameters includes: The particle swarm is initialized, wherein each particle in the particle swarm corresponds to a set of candidate landing control parameters; In each iteration, the multi-objective fitness function value is determined based on the candidate landing control parameters and landing dynamics model corresponding to each particle. The individual optimal solution of each particle and the global optimal solution of the entire particle swarm are updated based on the multi-objective fitness function value. The velocity and position of the particle are updated based on the individual optimal solution and the global optimal solution; If the preset iteration termination condition is met, the iteration is stopped, and the landing control parameters corresponding to the global optimal solution are used as the target landing control parameters.
5. The method according to claim 4, characterized in that, The determination that the preset iteration termination condition is met includes any one of the following: The number of iterations equals the iteration threshold; The fitness function corresponding to the global optimal solution changes less than a preset threshold for N consecutive rounds, where N is a positive integer.
6. The method according to claim 1, characterized in that, The specific expression for the multi-objective fitness function is as follows: Fitness value = ω1 × landing accuracy index + ω2 × attitude stability index + ω3 × energy consumption index + ω4 × anti-interference index; Among them, ω1, ω2, ω3, and ω4 are dynamic weighting coefficients.
7. An automatic landing control device for unmanned aerial vehicles (UAVs), characterized in that, include: The data acquisition module is used to collect the operating status parameters and environmental interference data of the UAV during the automatic landing phase. The determination module is used to determine the dynamic model and landing constraints of the UAV landing process based on the operating state parameters and the environmental interference data. A construction module is used to construct a multi-objective fitness function for evaluating landing performance based on the landing constraints. The optimization module is used to perform global optimization of the UAV's landing control parameters based on the particle swarm optimization algorithm with the goal of optimizing the multi-objective fitness function, so as to determine the target landing control parameters. The control module is used to control the UAV to complete an automatic landing based on the target landing control parameters.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the automatic landing control method for unmanned aerial vehicles as described in any one of claims 1 to 6.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the automatic landing control method for unmanned aerial vehicles as described in any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the automatic landing control method for unmanned aerial vehicles as described in any one of claims 1 to 6.