A method and system for dynamic adjustment of UAV route and autonomous obstacle avoidance

Abstract

The present invention discloses a method and system for dynamically adjusting the route of a UAV and autonomous obstacle avoidance, which specifically relates to navigation monitoring of a UAV, wherein a preset route is obtained before the UAV takes off, flight hazards in the surrounding environment are monitored in real time after takeoff, and it is determined whether autonomous obstacle avoidance needs to be triggered; after autonomous obstacle avoidance is triggered, the energy consumption of the UAV is evaluated and it is determined whether the route needs to be adjusted immediately; if the route is not adjusted immediately, historical obstacle avoidance events and the remaining operating capability of the UAV are analyzed, and the risk and maneuverability margin of the future route are evaluated; after a comprehensive analysis of the risk and maneuverability margin of the future route, it is determined again whether the route needs to be adjusted, which can significantly improve the autonomous adaptability of the UAV in an unpredictable environment and the accuracy of task execution.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle navigation monitoring, and more specifically, to a method and system for dynamically adjusting a route of an unmanned aerial vehicle and autonomously avoiding obstacles. Background Art

[0002] In the existing technology, drones mainly rely on preset routes for flight, which are usually determined before the flight mission is planned, and it is difficult to make real-time adjustments during execution. However, due to the uncertainty of the drone flight environment, such as weather changes, unmapped obstacles or other air traffic factors, it is impossible to determine when to adjust the drone route in a timely and accurate manner, which may encounter a series of problems such as safety risks, low mission execution efficiency and success rate, which limits the effectiveness and reliability of drones in a wider range of application scenarios.

[0003] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method and system for dynamically adjusting the route of a UAV and autonomously avoiding obstacles to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for dynamically adjusting a UAV route and autonomously avoiding obstacles comprises the following steps:

[0007] S1: Before the drone takes off, obtain the preset flight route of the drone;

[0008] S2: After the drone takes off, monitor the flight hazards in the drone's surrounding environment in real time to determine whether to trigger autonomous obstacle avoidance;

[0009] S3: After the UAV triggers autonomous obstacle avoidance, the energy consumption of the UAV after autonomous obstacle avoidance is evaluated, and according to the evaluation result of the energy consumption of the UAV, it is determined whether to immediately adjust the preset flight route of the UAV;

[0010] S4: When the route is not adjusted immediately, the future route risk of the UAV is evaluated by analyzing historical obstacle avoidance events; the rear obstacle avoidance maneuver margin of the UAV is evaluated by analyzing the remaining operational capability of the UAV after completing the obstacle avoidance action;

[0011] S5: Comprehensively analyze the future flight route risk of the UAV and the rear obstacle avoidance maneuver margin of the UAV, and determine whether to adjust the preset flight route of the UAV.

[0012] In a preferred embodiment, in S1, specifically:

[0013] Define the mission objectives and requirements of the UAV;

[0014] Based on mission requirements, plan routes and determine route data;

[0015] Upload the route data to the drone’s navigation system.

[0016] In a preferred embodiment, in S2, specifically:

[0017] Obstacle detection using a deep learning model: O = f(I; θ); where O is the output obstacle information; I is the input sensor image, f is the deep learning model, and θ is the parameter of the deep learning model;

[0018] Predict whether a collision will occur based on the location and size of the obstacle and the speed and heading of the drone;

[0019] The collision prediction is calculated using the following formula: c =1-exp(-λ*t impact ), where P c is the probability of collision, λ is the collision risk coefficient, t impact is the estimated time of collision;

[0020] Based on the results of collision prediction, determine whether to trigger autonomous obstacle avoidance:

[0021] When P c >P threshold , then autonomous obstacle avoidance is triggered; when P c ≤P threshold , then autonomous obstacle avoidance will not be triggered;

[0022] Among them, P threshold is the preset collision probability threshold.

[0023] In a preferred embodiment, in S3, specifically:

[0024] After the drone triggers autonomous obstacle avoidance, collect energy consumption data during the obstacle avoidance action;

[0025] Obtain the remaining battery power before and after obstacle avoidance, as well as the duration of the obstacle avoidance action;

[0026] Calculate the energy consumed by the drone during obstacle avoidance. The calculation formula is: ΔE = E start -E end ; where ΔE is the energy consumed in the process of obstacle avoidance, E start 、E end They are the remaining battery power before and after obstacle avoidance;

[0027] Obstacle avoidance efficiency formula: E efficiency is the obstacle avoidance efficiency, t is the duration of the obstacle avoidance action;

[0028] Predict the energy consumption required for the drone to complete the remaining tasks on the current route; the energy consumption prediction model is expressed as: E required =d*E efficiency ; Where d is the distance from the current location to the destination; E required is the estimated energy consumption required to complete the remaining flight distance;

[0029] Compare the remaining power with the predicted energy consumption to determine whether the route needs to be adjusted immediately;

[0030] If E end <E required , then adjust the route immediately; if E end ≥E required , the route will not be adjusted immediately.

[0031] In a preferred embodiment, in S4, the future route risk of the UAV is evaluated by analyzing historical obstacle avoidance events; specifically:

[0032] Collect data on all relevant obstacle avoidance events in the drone's past flights, identify key risk factors that affect drone flight safety based on the collected data, and assign a quantitative value to each identified risk factor;

[0033] Calculate the quantitative value of the risk factor, the expression is: Among them, F i is the quantitative value of the ith risk factor, n events,i is the number of times the risk factor appears in the historical data, and T is the total flight time recorded in the historical data;

[0034] Calculate the total risk score of the future route, the expression is: Where R is the total risk score of the future route, n is the total number of risk factors, k is the slope adjustment factor, and C i is the center point.

[0035] In a preferred embodiment, the rear obstacle avoidance maneuver margin of the UAV is evaluated by analyzing the remaining operational capability of the UAV after completing the obstacle avoidance action, specifically:

[0036] Collect relevant performance data of the drone after completing the obstacle avoidance action; specific data includes:

[0037] E rem : remaining power after obstacle avoidance; v avg : average speed in obstacle avoidance action; d maneuver: The actual distance the drone moves during obstacle avoidance; θ response : Reaction time of posture adjustment during obstacle avoidance;

[0038] Define the drone obstacle avoidance performance degradation function, its expression is: Among them, D CZ is the degradation function of the obstacle avoidance performance of the UAV, E full It is the power of the drone when it is fully charged;

[0039] Calculate the dynamic redundancy index, the expression is: Among them, M YZ is the maneuver margin index, h is the adjustment coefficient, and c is the offset constant.

[0040] In a preferred embodiment, in S5, the future route risk of the drone and the rear obstacle avoidance maneuver margin of the drone are comprehensively analyzed to determine whether to adjust the preset route of the drone flight, specifically:

[0041] The total risk score and maneuver margin index of the future route are normalized, and the normalized total risk score and maneuver margin index of the future route are assigned preset proportional coefficients respectively, and the route adjustment evaluation coefficient is calculated to determine whether to adjust the preset route of the UAV flight again according to the route adjustment evaluation coefficient;

[0042] Set the route adjustment assessment threshold; compare the route adjustment assessment coefficient with the route adjustment assessment threshold:

[0043] When the route adjustment evaluation coefficient is greater than the route adjustment evaluation threshold, the route of the drone is adjusted;

[0044] When the route adjustment evaluation coefficient is less than or equal to the route adjustment evaluation threshold, it is determined that the route of the drone will not be adjusted.

[0045] On the other hand, the present invention provides a UAV route dynamic adjustment and autonomous obstacle avoidance system, including a preset route acquisition module, an obstacle avoidance trigger judgment module, an obstacle avoidance energy consumption evaluation module, a route information collection module, and a route adjustment judgment module;

[0046] Before the drone takes off, the preset route acquisition module acquires the preset route for the drone to fly;

[0047] After the drone takes off, the obstacle avoidance trigger judgment module monitors the flight hazards in the drone's surrounding environment in real time and determines whether to trigger autonomous obstacle avoidance;

[0048] After the UAV triggers autonomous obstacle avoidance, the obstacle avoidance energy consumption assessment module assesses the energy consumption of the UAV after autonomous obstacle avoidance, and determines whether to immediately adjust the preset flight route of the UAV based on the assessment result of the UAV's energy consumption;

[0049] When the route is not adjusted immediately, the route information collection module evaluates the future route risk of the drone by analyzing historical obstacle avoidance events; it evaluates the drone's post-obstacle avoidance maneuver margin by analyzing the drone's remaining operational capabilities after completing the obstacle avoidance action;

[0050] The route adjustment judgment module comprehensively analyzes the future route risk of the UAV and the rear obstacle avoidance maneuver margin of the UAV, and determines whether to adjust the preset route of the UAV flight.

[0051] Technical effects and advantages of a method and system for dynamically adjusting the route of a drone and autonomously avoiding obstacles provided by the present invention:

[0052] By monitoring the flight hazards of the drone's surrounding environment in real time and dynamically adjusting the route based on the monitoring results, the safety of the drone in complex environments is significantly improved. By analyzing the energy consumption after obstacle avoidance, historical obstacle avoidance events, and maneuver margin, the drone can decide whether to further adjust the route based on the current status. This adaptive adjustment strategy enables the drone to maximize the completion of complex tasks while maintaining efficiency, such as long-distance flights across different geographical or meteorological conditions. By integrating real-time environmental monitoring, intelligent decision-making algorithms, and historical data analysis, the drone's operational safety, energy efficiency, and mission adaptability are significantly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 A schematic diagram of a method for dynamically adjusting a UAV route and autonomously avoiding obstacles according to the present invention;

[0054] Figure 2 The present invention is a schematic structural diagram of a UAV route dynamic adjustment and autonomous obstacle avoidance system. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] Example 1

[0057] Figure 1 The present invention provides a method for dynamically adjusting the route of a UAV and autonomously avoiding obstacles, which comprises the following steps:

[0058] S1: Before the drone takes off, obtain the preset flight route of the drone.

[0059] S2: After the drone takes off, monitor the flight hazards in the drone's surrounding environment in real time to determine whether to trigger autonomous obstacle avoidance.

[0060] S3: After the UAV triggers autonomous obstacle avoidance, the energy consumption of the UAV after autonomous obstacle avoidance is evaluated, and according to the evaluation result of the energy consumption of the UAV, it is determined whether to immediately adjust the preset flight route of the UAV.

[0061] S4: When the route is not adjusted immediately, the future route risk of the UAV is evaluated by analyzing historical obstacle avoidance events; the post-obstacle avoidance maneuver margin of the UAV is evaluated by analyzing the remaining operating capability of the UAV after completing the obstacle avoidance action.

[0062] S5: Comprehensively analyze the future flight route risk of the UAV and the rear obstacle avoidance maneuver margin of the UAV, and determine whether to adjust the preset flight route of the UAV.

[0063] In S1, before the drone takes off, the preset flight route of the drone is obtained, specifically:

[0064] Obtaining a preset route is an important part of pre-flight preparation, ensuring that the drone can perform its mission on a safe and predetermined path.

[0065] Before a drone takes off, it is first necessary to define the mission objectives and requirements of the drone. This includes determining the purpose of the flight, the target area, the type of mission (such as monitoring, photography, logistics distribution, etc.) and any specific customer needs.

[0066] Based on mission requirements, route planning is carried out and route data is determined:

[0067] This usually involves choosing a take-off point and a destination point, as well as determining the approximate path of the flight.

[0068] When designing a route, you must consider local laws and regulations regarding drone flights. This includes flight altitude restrictions, no-fly zones, time limits, etc. You must ensure that route planning complies with all relevant laws and regulations to avoid entering no-fly zones or exceeding flight altitudes.

[0069] Use maps and terrain data to analyze the terrain and obstacles that may be encountered on the preset route. Especially in complex terrain or urban environments, obstacles such as buildings, high-voltage wires, and trees need to be considered to ensure the safety of the route.

[0070] If the drone operation involves direct input from the end user, such as in agricultural monitoring or logistics delivery, the route input needs to be made on the user interface. This may include specific locations or areas specified by the user.

[0071] The finalized route data is uploaded to the drone’s navigation system.

[0072] Perform a final check before the drone takes off to confirm that the drone's hardware, software, and route data are correct. Check the drone's communication system, GPS positioning system, battery status, etc. to ensure that all equipment is working properly.

[0073] In S2, after the drone takes off, the flight hazards in the drone's surrounding environment are monitored in real time to determine whether to trigger autonomous obstacle avoidance. Specifically:

[0074] When a drone is performing a flight mission, real-time monitoring of the surrounding environment and determining whether to trigger autonomous obstacle avoidance are key steps to ensure flight safety.

[0075] Drones are equipped with a variety of sensors, including cameras, radars (such as lidar), infrared sensors and sonar, which are used to capture detailed information about the surrounding environment in real time.

[0076] The main functions of the sensor and the parameters monitored include:

[0077] Camera: Obtain visual images to identify obstacles such as trees, buildings, etc.

[0078] Radar: Measures the distance and speed of objects and is used to detect moving and static obstacles.

[0079] Infrared sensors: Detect heat sources, especially at night or in low visibility conditions.

[0080] Sonar: Detect obstacles in water or high humidity environments.

[0081] After collecting data from various sensors, data fusion technology is used to integrate this information to obtain an accurate and comprehensive view of the surrounding environment.

[0082] Use the fused data to perform obstacle detection and localization. This typically involves image recognition techniques and machine learning models to identify and localize obstacles from the sensor data.

[0083] Obstacle detection can use deep learning models, such as convolutional neural networks (CNN), and the model can be expressed as: O = f(I; θ); where O is the output obstacle information, including type, location, size, etc.; I is the input sensor image or data, f is the deep learning model, and θ is the parameter of the deep learning model.

[0084] Predict whether a collision will occur based on the location and size of the obstacle and the speed and heading of the drone.

[0085] The collision prediction can be calculated using the following formula: c =1-exp(-λ*t impact ), where P cis the probability of collision, λ is the collision risk factor adjusted according to the dynamics of the environment, and t impact is the estimated time to collision, which is the distance to the obstacle divided by the speed of the drone.

[0086] Based on the results of collision prediction, determine whether to trigger autonomous obstacle avoidance.

[0087] The decision criteria for determining whether to trigger autonomous obstacle avoidance can be set as follows:

[0088] When P c >P threshold , then autonomous obstacle avoidance is triggered; when P c ≤P threshold , autonomous obstacle avoidance will not be triggered.

[0089] Among them, P threshold is the preset collision probability threshold, exceeding which the obstacle avoidance procedure will be initiated.

[0090] If autonomous obstacle avoidance is triggered, the drone will adjust its heading or flight altitude according to the preset obstacle avoidance strategy to avoid obstacles.

[0091] After executing the obstacle avoidance action, data on the obstacle avoidance effect is collected to optimize future obstacle avoidance decisions.

[0092] In S3, after the UAV triggers autonomous obstacle avoidance, the energy consumption of the UAV after autonomous obstacle avoidance is evaluated, and according to the evaluation result of the energy consumption of the UAV, it is determined whether to immediately adjust the preset flight route of the UAV, specifically:

[0093] After the drone triggers autonomous obstacle avoidance, the first thing to do is to collect energy consumption data during the obstacle avoidance process. This includes data such as the drone’s battery power, flight speed, flight altitude, and sensor type used before and after obstacle avoidance.

[0094] Get the remaining battery power before and after obstacle avoidance, as well as the duration of the obstacle avoidance action.

[0095] Calculate the energy consumed by the drone during obstacle avoidance. The calculation formula is: ΔE = E start -E end ; where ΔE is the energy consumed in the process of obstacle avoidance, E start 、E end They are the remaining battery power before obstacle avoidance and the remaining battery power after obstacle avoidance.

[0096] In order to evaluate the efficiency of the obstacle avoidance action, it is necessary to calculate the energy consumption per unit time.

[0097] Obstacle avoidance efficiency formula: E efficiencyis the obstacle avoidance efficiency, which is used to measure the energy efficiency of the obstacle avoidance action; t is the duration of the obstacle avoidance action.

[0098] Based on the current energy consumption and remaining power, predict the energy consumption required for the drone to complete the remaining tasks on the current route.

[0099] The energy consumption prediction model can be expressed as: E required =d*E efficiency ; Where d is the distance from the current location to the destination; E required is the estimated energy required to complete the remaining flight distance.

[0100] Compare remaining power with predicted energy consumption to determine if you need to immediately adjust your flight path to save energy or find a safe landing spot close by.

[0101] If E end <E required , then adjust the route immediately.

[0102] If E end ≥E required , the route will not be adjusted immediately.

[0103] If it is determined that a change in route is necessary, the best route is chosen based on the remaining battery and estimated energy consumption. This may involve finding a shorter route or a flight mode that uses less energy.

[0104] The route adjustment strategy can be: choose the route with the lowest energy consumption. Consider possible charging points or battery replacement locations along the way.

[0105] In S4, when the route is not adjusted immediately, the risk of the drone's future route is evaluated by analyzing historical obstacle avoidance events; specifically:

[0106] First, collect data on all relevant obstacle avoidance events in the drone's past flights. This data includes the date, time, location, environmental factors involved (such as weather conditions, visibility, etc.), the drone's state during obstacle avoidance (speed, altitude, battery level, etc.), and the results of the obstacle avoidance.

[0107] Based on the collected data, key risk factors that affect drone flight safety are identified. These risk factors may include changes in weather conditions, low battery power, obstacle avoidance during high-speed flight, etc.

[0108] Each identified risk factor is assigned a quantitative value based on the severity of each risk factor's impact on flight safety in historical data.

[0109] Calculate the quantitative value of the risk factor, the expression is: Among them, F iis the quantitative value of the ith risk factor, n events,i is the number of times the risk factor appears in the historical data, and T is the total flight time recorded in the historical data. Logarithmic transformation is used to balance the influence of each risk factor.

[0110] Combining the quantitative values ​​of each risk factor, the total risk score of the future route is calculated, and the expression is: Where R is the total risk score of the future route, n is the total number of risk factors, k is the slope adjustment factor, and C i is the center point.

[0111] k: controls the slope of the logistic function, that is, the "growth rate" of the function. In the example, the increase of k will make the function have a horizontal axis value of C i It becomes steeper near , which means that the response is more sensitive to changes in the input value.

[0112] C i : Defines the input value in the logic function (here is the quantitative value of the risk factor F i ). At this point, the output of the logistic function is 0.5, the middle value of the function.

[0113] The greater the total risk score of a future route, the higher the risk that may exist on the future route, and the route adjustment needs to be considered.

[0114] By analyzing the remaining operational capability of the UAV after completing the obstacle avoidance action, the UAV's post-obstacle avoidance maneuver margin is evaluated, specifically:

[0115] Collect relevant performance data of the drone after completing the obstacle avoidance action. Specific data includes:

[0116] Erem: remaining battery power after obstacle avoidance; vavg: average speed during obstacle avoidance; dmaneuver: actual distance the drone moves during obstacle avoidance; θresponse: reaction time for attitude adjustment during obstacle avoidance.

[0117] Define the drone obstacle avoidance performance degradation function, its expression is: Among them, DCZ is the degradation function of the obstacle avoidance performance of the drone, and Efull is the power of the drone when it is fully charged, which is used to standardize the remaining power.

[0118] This part calculates the power consumption ratio, which is used to reflect the power loss during the obstacle avoidance process. The higher the value, the greater the loss. The relationship between the moving distance of the drone and its speed and reaction time when avoiding obstacles is considered. Longer reaction time and slower speed for the same distance indicate that the drone is less efficient.

[0119] Calculate the dynamic redundancy index, the expression is: Among them, MYZ is the maneuver margin index, ranging from 0 to 1. The closer the value is to 1, the higher the maneuver margin is, that is, the performance degradation of the UAV is less, and the ability to continue to perform the mission is stronger; h is the adjustment coefficient, which is used to adjust The sensitivity of M affects the steepness of the curve. YZ The change of D CZ The more sensitive it is to changes in the CZ The center point determines which point D CZ Make M YZ Equal to 0.5, the value of c is set according to the expected normal operating threshold.

[0120] That is, the lower the maneuverability margin index is, the lower the UAV's rear obstacle avoidance maneuverability margin is, which means that after the UAV completes the obstacle avoidance action, the remaining operating capabilities and resources (such as power, mechanical performance, etc.) are relatively low, and its ability to continue to perform subsequent tasks or deal with additional flight obstacles is limited.

[0121] In S5, the future route risk of the UAV and the rear obstacle avoidance maneuver margin of the UAV are comprehensively analyzed to determine whether to adjust the preset route of the UAV flight. Specifically:

[0122] The total risk score and maneuverability margin index of the future route are normalized, and the normalized total risk score and maneuverability margin index of the future route are respectively assigned preset proportional coefficients, and the route adjustment evaluation coefficient is calculated to determine whether to adjust the preset route of the drone flight.

[0123] The expression of route adjustment evaluation coefficient is: Among them, JP is the route adjustment assessment coefficient, δ and ζ are the preset proportional coefficients of the total risk score and maneuverability margin index of the future route, respectively, and both δ and ζ are greater than 0.

[0124] It can be seen from the calculation formula of the route adjustment evaluation coefficient that the larger the route adjustment evaluation coefficient is, the more necessary it is to adjust the route of the drone.

[0125] The route adjustment assessment threshold is set by professional and technical personnel in this field based on the size of the route adjustment assessment coefficient calculated above and other actual conditions such as the actual route safety requirements for drone navigation, and will not be repeated here.

[0126] Compare the route adjustment assessment factor with the route adjustment assessment threshold:

[0127] When the route adjustment evaluation coefficient is greater than the route adjustment evaluation threshold, the route of the drone is adjusted;

[0128] When the route adjustment evaluation coefficient is less than or equal to the route adjustment evaluation threshold, it is determined that the route of the drone will not be adjusted.

[0129] Systematically evaluate the drone's condition after obstacle avoidance and the risk of future flight, and make decisions on whether to adjust the route. This process ensures the safety of drone flight and the smooth execution of the mission.

[0130] Example 2

[0131] The difference between Example 2 of the present invention and Example 1 is that this example introduces a system for dynamic adjustment of the route of an unmanned aerial vehicle and autonomous obstacle avoidance.

[0132] Figure 2 A structural schematic diagram of a UAV route dynamic adjustment and autonomous obstacle avoidance system of the present invention is given, which includes a preset route acquisition module, an obstacle avoidance trigger judgment module, an obstacle avoidance energy consumption evaluation module, a route information collection module and a route adjustment judgment module.

[0133] Before the drone takes off, the preset route acquisition module acquires the preset route for the drone to fly.

[0134] After the drone takes off, the obstacle avoidance trigger judgment module monitors the flight hazards in the drone's surrounding environment in real time and determines whether to trigger autonomous obstacle avoidance.

[0135] After the UAV triggers autonomous obstacle avoidance, the obstacle avoidance energy consumption assessment module assesses the energy consumption of the UAV after autonomous obstacle avoidance, and determines whether to immediately adjust the preset flight route of the UAV based on the assessment results of the UAV's energy consumption.

[0136] When the route is not adjusted immediately, the route information collection module evaluates the UAV's future route risk by analyzing historical obstacle avoidance events; and evaluates the UAV's post-obstacle avoidance maneuver margin by analyzing the UAV's remaining operating capabilities after completing the obstacle avoidance action.

[0137] The route adjustment judgment module comprehensively analyzes the future route risk of the UAV and the rear obstacle avoidance maneuver margin of the UAV, and determines whether to adjust the preset route of the UAV flight.

[0138] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0139] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0140] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0141] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0142] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0143] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0144] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0145] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0146] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0147] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for dynamically adjusting the route of a drone and autonomously avoiding obstacles, characterized in that: The steps include: S1: Before the drone takes off, obtain the preset flight route of the drone; S2: After the drone takes off, monitor the flight hazards in the drone's surrounding environment in real time to determine whether to trigger autonomous obstacle avoidance; S3: After the UAV triggers autonomous obstacle avoidance, the energy consumption of the UAV after autonomous obstacle avoidance is evaluated, and according to the evaluation result of the energy consumption of the UAV, it is determined whether to immediately adjust the preset flight route of the UAV; S4: When the route is not adjusted immediately, the future route risk of the UAV is evaluated by analyzing historical obstacle avoidance events; the rear obstacle avoidance maneuver margin of the UAV is evaluated by analyzing the remaining operational capability of the UAV after completing the obstacle avoidance action; S5: Comprehensively analyze the future flight route risk of the UAV and the rear obstacle avoidance maneuver margin of the UAV, and determine whether to adjust the preset flight route of the UAV; By analyzing the remaining operational capability of the UAV after completing the obstacle avoidance action, the UAV's post-obstacle avoidance maneuver margin is evaluated, specifically: Collect relevant performance data of the drone after completing the obstacle avoidance action; specific data includes: Erem: remaining battery after obstacle avoidance; vavg: average speed during obstacle avoidance; dmaneuver: actual distance the drone moves during obstacle avoidance; θresponse: reaction time for attitude adjustment during obstacle avoidance; Define the drone obstacle avoidance performance degradation function, its expression is: Among them, DCZ is the degradation function of the obstacle avoidance performance of the drone, and Efull is the power of the drone when it is fully charged; Calculate the dynamic redundancy index, the expression is: Among them, MYZ is the maneuver margin index, h is the adjustment coefficient, and c is the offset constant; In S5, the future route risk of the UAV and the rear obstacle avoidance maneuver margin of the UAV are comprehensively analyzed to determine whether to adjust the preset route of the UAV flight. Specifically: The total risk score and maneuver margin index of the future route are normalized, and the normalized total risk score and maneuver margin index of the future route are assigned preset proportional coefficients respectively, and the route adjustment evaluation coefficient is calculated to determine whether to adjust the preset route of the UAV flight again according to the route adjustment evaluation coefficient; Set the route adjustment assessment threshold; compare the route adjustment assessment coefficient with the route adjustment assessment threshold: When the route adjustment evaluation coefficient is greater than the route adjustment evaluation threshold, the route of the drone is adjusted; When the route adjustment evaluation coefficient is less than or equal to the route adjustment evaluation threshold, it is determined that the route of the drone will not be adjusted.

2. The method for dynamic adjustment of the route of an unmanned aerial vehicle and autonomous obstacle avoidance according to claim 1, characterized in that: In S1, specifically: Define the mission objectives and mission requirements of the drone; the mission objectives include the purpose of the flight, the target area and the mission type, and the mission requirements include customer needs; Based on mission requirements, plan routes and determine route data; Upload the route data to the drone’s navigation system.

3. The method for dynamic adjustment of the route of a UAV and autonomous obstacle avoidance according to claim 2, characterized in that: In S2, specifically: Obstacle detection using a deep learning model: O = f(I; θ); where O is the output obstacle information; I is the input sensor image, f is the deep learning model, and θ is the parameter of the deep learning model; Predict whether a collision will occur based on the location and size of the obstacle and the speed and heading of the drone; The collision prediction is calculated using the following formula: c =1-exp(-λ*t impact ), where P c is the probability of collision, λ is the collision risk coefficient, t impact is the estimated time of collision; Based on the results of collision prediction, determine whether to trigger autonomous obstacle avoidance: When P c >P threshold , then autonomous obstacle avoidance is triggered; when P c ≤P threshold , then autonomous obstacle avoidance will not be triggered; Among them, P threshold is the preset collision probability threshold.

4. The method for dynamic adjustment of the route and autonomous obstacle avoidance of a UAV according to claim 3, characterized in that: In S3, specifically: After the drone triggers autonomous obstacle avoidance, collect energy consumption data during the obstacle avoidance action; Obtain the remaining battery power before and after obstacle avoidance, as well as the duration of the obstacle avoidance action; Calculate the energy consumed by the drone during obstacle avoidance. The calculation formula is: ΔE = E start -E end ; where ΔE is the energy consumed in the process of obstacle avoidance, E start 、E end They are the remaining battery power before and after obstacle avoidance; Obstacle avoidance efficiency formula: E efficiency is the obstacle avoidance efficiency, t is the duration of the obstacle avoidance action; Predict the energy consumption required for the drone to complete the remaining tasks on the current route; the energy consumption prediction model is expressed as: E required =d*E efficiency ; Where d is the distance from the current location to the destination; E required is the estimated energy consumption required to complete the remaining flight distance; Compare the remaining power with the predicted energy consumption to determine whether the route needs to be adjusted immediately; If E end <E required , then adjust the route immediately; if E end ≥E required , the route will not be adjusted immediately.

5. The method for dynamic adjustment of the route of a UAV and autonomous obstacle avoidance according to claim 4, characterized in that: In S4, the future route risk of the drone is evaluated by analyzing historical obstacle avoidance events; specifically: Collect data on all relevant obstacle avoidance events in the drone's past flights, identify key risk factors that affect drone flight safety based on the collected data, and assign a quantitative value to each identified risk factor; Calculate the quantitative value of the risk factor, the expression is: Among them, Fi is the quantitative value of the i-th risk factor, nevents,i is the number of times the risk factor appears in the historical data, and T is the total flight time recorded in the historical data; Calculate the total risk score of the future route, the expression is: Where R is the total risk score of the future route, n is the total number of risk factors, k is the slope adjustment factor, and Ci is the center point.

6. A UAV route dynamic adjustment and autonomous obstacle avoidance system, used to implement a UAV route dynamic adjustment and autonomous obstacle avoidance method as described in any one of claims 1 to 5, characterized in that: It includes a preset route acquisition module, an obstacle avoidance trigger judgment module, an obstacle avoidance energy consumption evaluation module, a route information collection module, and a route adjustment judgment module; Before the drone takes off, the preset route acquisition module acquires the preset route for the drone to fly; After the drone takes off, the obstacle avoidance trigger judgment module monitors the flight hazards in the drone's surrounding environment in real time and determines whether to trigger autonomous obstacle avoidance; After the UAV triggers autonomous obstacle avoidance, the obstacle avoidance energy consumption assessment module assesses the energy consumption of the UAV after autonomous obstacle avoidance, and determines whether to immediately adjust the preset flight route of the UAV based on the assessment result of the UAV's energy consumption; When the route is not adjusted immediately, the route information collection module evaluates the future route risk of the drone by analyzing historical obstacle avoidance events; By analyzing the remaining operational capability of the UAV after completing the obstacle avoidance action, the UAV's post-obstacle avoidance maneuver margin is evaluated; The route adjustment judgment module comprehensively analyzes the future route risk of the UAV and the rear obstacle avoidance maneuver margin of the UAV, and determines whether to adjust the preset route of the UAV flight.

Images