Unmanned aerial vehicle inspection trajectory planning system

Abstract

The invention relates to the technical field of unmanned aerial vehicle inspection, and discloses an unmanned aerial vehicle inspection trajectory planning system. According to the unmanned aerial vehicle inspection trajectory planning system, terrain, weather and unmanned aerial vehicle state information is acquired in real time through the data acquisition unit, the data processing unit performs denoising and feature extraction on the acquired information to ensure the accuracy of the used data, and the trajectory planning unit applies a shortest path algorithm to perform trajectory planning according to environment parameters and obstacle information which are calculated in real time. The flight path is dynamically optimized, the process not only improves the inspection accuracy, but also reduces the risk that the unmanned aerial vehicle deviates from the track due to obstacle interference, the monitoring feedback unit continuously monitors the state of the unmanned aerial vehicle in the flight process, the flight path can be adjusted in time, and it is ensured that the unmanned aerial vehicle flies along the optimal path all the time. Therefore, the system greatly improves the operation capability and safety of the unmanned aerial vehicle in the inspection task.

Description

Technical Field

[0001] The present invention relates to the technical field of drone inspection, and particularly to a drone inspection trajectory planning system. Background Art

[0002] A drone is an aircraft that can fly autonomously or remotely and is widely used in multiple fields, including agricultural monitoring, environmental protection, logistics transportation, mapping, and infrastructure inspection. Especially in infrastructure inspection, drones can quickly obtain data in difficult-to-reach areas with their high efficiency and flexibility, significantly improving inspection efficiency and reducing labor costs. Drone inspection has gradually become an important monitoring method in industries such as power, communication, and transportation, being able to detect equipment failures in real time, reduce potential safety hazards, and provide data support for subsequent maintenance decisions.

[0003] Existing drone inspection systems often have difficulty in real-time optimizing flight trajectories to cope with unexpected situations when facing complex terrains and changing weather conditions. This limitation may cause drones to be unable to effectively avoid obstacles, thus reducing inspection efficiency and even facing safety risks. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the present invention provides a drone inspection trajectory planning system. The data acquisition unit obtains terrain, meteorological, and drone status information in real time. The data processing unit denoises and extracts features from the collected information to ensure the accuracy of the data used. The trajectory planning unit applies the shortest path algorithm and dynamically optimizes the flight route according to the real-time calculated environmental parameters and obstacle information. This process not only improves the accuracy of inspection but also reduces the risk of the drone deviating from the trajectory due to obstacle interference. The monitoring and feedback unit continuously monitors the drone status during flight and can adjust the flight trajectory in a timely manner to ensure that the drone always flies along the optimal path, greatly enhancing the operation ability and safety of the drone in the inspection task.

[0005] To achieve the above object, the present invention provides the following technical solution: A drone inspection trajectory planning system, including a data acquisition unit, a data processing unit, a trajectory planning unit, a flight control unit, and a monitoring and feedback unit;

[0006] The data acquisition unit is used to obtain terrain data, meteorological data, drone status data, and information of the inspection area, and the obtained data is sent to the data processing unit through a wireless network;

[0007] After denoising the data transmitted by the data acquisition unit, the data processing unit extracts the flight slope feature and the flight obstacle distance feature, and calculates the wind speed influence factor, the priority of the inspection target area, the flight path length, the estimated shortest flight time, and the flight energy consumption. The above calculated values are transmitted to the trajectory planning unit for UAV flight trajectory planning;

[0008] The trajectory planning unit calculates the optimal flight path of the UAV by applying the shortest path algorithm according to the data transmitted by the data processing unit and sends it to the flight control unit;

[0009] The flight control unit generates a UAV inspection instruction based on the optimal flight path of the UAV to control the UAV to perform inspection according to the predetermined optimal flight path;

[0010] The monitoring and feedback unit is used to monitor the state of the UAV flight inspection process in real time, and through the built-in monitoring algorithm, when there is a risk that the UAV deviates from the flight trajectory, the UAV flight trajectory is adjusted to the predetermined flight direction in real time.

[0011] Preferably, the formula for data denoising is as follows:

[0012]

[0013] In the formula, represents the th denoised data point, represents the th collected original data point, represents the window size of the filter, represents the index subscript.

[0014] Preferably, the formula for extracting the flight slope feature is as follows:

[0015]

[0016] In the formula, represents the flight slope, represents the height of point 1,[[ID=4)]] represents the height of point 2, represents the horizontal distance between point 1 and point 2.

[0017] Preferably, the formula for extracting the flight obstacle distance feature is as follows:

[0018] [[ID=5)]]

[0019] In the formula, represents the flight obstacle distance, represents the three-dimensional coordinates of the UAV, Represents the three-dimensional coordinates of the obstacle.

[0020] Preferably, the formula for calculating the wind speed influence factor is as follows:

[0021]

[0022] In the formula, Represents the wind speed influence factor, Represents the actual speed of the drone when flying in the wind, Represents the flying speed of the drone under windless conditions.

[0023] Preferably, the formula for calculating the priority of the inspection target area is as follows:

[0024]

[0025] In the formula, Represents the priority of the inspection target area, , , Represents the various attributes affecting the priority, , , Are the weight coefficients of the various attributes, which are intelligently assigned by the system.

[0026] Preferably, the formula for calculating the flight path length is as follows:

[0027]

[0028] In the formula, Represents the flight path length, Represents the coordinates of the Represents the index subscript, Represents the total number of points on the inspection path.

[0029] Preferably, the formula for calculating the expected shortest flight time is as follows:

[0030]

[0031] In the formula, Represents the expected shortest flight time, Represents the flight path length, Represents the flying speed of the drone.

[0032] Preferably, the formula for calculating the flight energy consumption is as follows:

[0033]

[0034] In the formula, Indicates the flight energy consumption, Indicates the flight path length, Indicates the energy consumed by the drone per kilometer.

[0035] Preferably, the formula for calculating the optimal flight path of the drone is as follows:

[0036]

[0037] In the formula, Indicates the shortest known distance to reach node , Indicates the shortest known distance to reach node , Indicates from node to node edge weight.

[0038] Compared with the prior art, the present invention provides a drone inspection trajectory planning system, which has the following beneficial effects:

[0039] The present invention obtains terrain, meteorological and drone status information in real time through the data acquisition unit. The data processing unit denoises and extracts features from the collected information to ensure the accuracy of the data used. The trajectory planning unit applies the shortest path algorithm and dynamically optimizes the flight route according to the real-time calculated environmental parameters and obstacle information. This process not only improves the accuracy of inspection, but also reduces the risk of the drone deviating from the trajectory due to obstacle interference. The monitoring and feedback unit continuously monitors the drone status during flight and can adjust the flight trajectory in a timely manner to ensure that the drone always flies along the optimal path, making the system greatly improve the operation ability and safety of the drone in the inspection task. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0041] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0042] In view of the problem that existing UAV inspection systems often struggle to optimize flight trajectories in real time to handle emergencies when faced with complex terrains and changing meteorological conditions, which may lead to the UAV's inability to effectively avoid obstacles, thereby reducing inspection efficiency and even posing safety risks, a UAV inspection trajectory planning system is proposed. Please refer to Figure 1 , which includes a data acquisition unit, a data processing unit, a trajectory planning unit, a flight control unit, and a monitoring and feedback unit;

[0043] The data acquisition unit uses a variety of high-precision sensors and advanced communication technologies to be responsible for obtaining terrain data, meteorological data, UAV status data, and information on the inspection area required for inspection. Specifically, it can capture terrain features through lidar (LiDAR) and optical cameras, collect meteorological parameters such as wind speed, temperature, and humidity using meteorological sensors, and simultaneously monitor the flight status of the UAV in real time through the built-in IMU (inertial measurement unit) and GPS module of the UAV. The collected data is transmitted to the data processing unit in real time through an efficient and stable wireless network (such as 4G / 5G or Wi-Fi) to ensure the immediacy and accuracy of the data, thereby providing a reliable information basis for subsequent trajectory planning and monitoring control. This data exchange process uses encryption technology to ensure data security and avoid information leakage or loss during transmission. Through this comprehensive technical means, the data acquisition unit can achieve a comprehensive monitoring of the inspection environment and lay the foundation for the efficient and autonomous inspection of the UAV;

[0044] The main task of the data processing unit is to perform denoising processing on the data received from the data acquisition unit to improve the accuracy and reliability of the data. After denoising, the system uses signal processing technology to extract the flight slope feature and the flight obstacle distance feature. During this process, the flight slope Pd is calculated by the following formula:

[0045]

[0046] where and are the heights of adjacent terrain points respectively, d is the horizontal distance between the two points, and the slope feature can reflect the undulation of the terrain, helping the UAV adjust its flight path to avoid steep areas and ensure flight safety;

[0047] For the distance feature of flight obstacles, the following formula is used for calculation:

[0048]

[0049] Here represents the UAV position, Indicates the position of the obstacle. This feature is used to monitor the distance between the drone and the obstacle in real time, ensuring that the drone can fly safely and avoid obstacles;

[0050] In addition, the data processing unit also calculates the wind speed influence factor, and its formula is:

[0051]

[0052] This formula is used to evaluate the impact of wind speed on the flight ability of the drone. is the speed in flight in the wind, is the speed in the non-windy state. By calculating the wind speed influence factor, it can help the system make corresponding speed adjustments during trajectory planning to adapt to different wind speed conditions;

[0053] The priority of the inspection target area is calculated by the following formula:

[0054]

[0055] In this formula, , , represent the various features affecting the priority (for example, the importance of the area, potential risks, etc.), while , , are their corresponding weights. By comprehensively evaluating these features, the system can determine which areas to inspect first, thus effectively optimizing resource allocation;

[0056] The calculation formula for the flight path length is:

[0057]

[0058] This formula is used to calculate the total distance of the entire inspection path. is the number of points on the path. Accurate measurement of the path length is crucial for trajectory planning because it directly affects the flight time and energy consumption of the drone;

[0059] The estimated shortest flight time is calculated by the following formula:

[0060]

[0061] Among them, is the flight path length, is the flight speed of the drone. This supports the system to estimate the completion time in advance during the trajectory planning stage, thus better arranging the inspection plan;

[0062] Finally, the calculation formula for the flight energy consumption is:

[0063]

[0064] Here, is the energy consumption per unit path length. By accurately calculating the energy consumption, the system can timely adjust the flight plan to avoid flight interruption due to insufficient power;

[0065] The results of all these calculations will be transmitted to the trajectory planning unit for detailed planning of the UAV flight trajectory to ensure the efficient and high-quality completion of the inspection task. Through the above technical means, the data processing unit not only improves the value of data usage but also provides a solid theoretical basis and data support for the safe flight and task execution of the UAV;

[0066] The trajectory planning unit is a key component in the UAV inspection system. It is responsible for calculating the optimal flight path of the UAV according to the important parameters transmitted by the data processing unit. This process involves multiple steps to ensure that the UAV can execute the inspection task in the most efficient way, reducing flight time and energy consumption, and at the same time avoiding risks brought by obstacles and terrain changes;

[0067] First of all, the data received by the trajectory planning unit includes flight slope characteristics, flight obstacle distance characteristics, wind speed influence factor, inspection target area priority, flight path length, and expected shortest flight time, etc. These data provide the necessary background information for the shortest path algorithm, enabling it to more accurately evaluate the feasibility and efficiency of different paths. During the path planning process, the shortest path algorithm, such as Dijkstra's algorithm, will be applied to ensure that the UAV selects the best inspection route;

[0068] The general formula of Dijkstra's algorithm is:

[0069]

[0070] In this formula, represents the shortest known distance to reach node , is the known shortest distance of node , and is the edge weight from node to node . This algorithm finds the shortest path from the starting point to all nodes by gradually expanding the shortest path tree. In the context of UAV path planning, nodes can represent different flight path points, and the edge weights can be comprehensively evaluated according to factors such as distance, terrain characteristics, and wind speed influence;

[0071] In this way, the trajectory planning unit can not only optimize the path but also improve flight safety. For example, based on the distance feature of flight obstacles, it can avoid approaching dangerous areas when planning the flight route, thus reducing the risk of collision with obstacles. At the same time, considering the flight slope feature can ensure that the attitude of the UAV remains stable when flying over undulating terrain, reducing the probability of falling;

[0072] The flight control unit is one of the core components of the UAV inspection system. Its main responsibility is to generate inspection instructions based on the calculated optimal flight path of the UAV and precisely control the flight state of the UAV to ensure that it performs the inspection task according to the predetermined flight path. In this process, the flight control unit not only needs to handle the basic flight control of the UAV but also comprehensively consider environmental factors, flight states, and task requirements. Specifically, the flight control unit will use advanced PID control algorithms and multi-input multi-output (MIMO) control strategies to adjust the attitude, speed, and altitude of the UAV in real time to ensure its stability and safety during inspection;

[0073] The process of generating flight control instructions usually relies on the real-time state feedback of the UAV, including data such as position, speed, and acceleration. These data are collected in real time by the inertial measurement unit (IMU), GPS, and other sensors built into the UAV. Through data fusion technology, the flight control unit can more accurately judge the current flight state of the UAV and generate corresponding control instructions accordingly. These instructions include heading adjustment, climb or descent instructions, so as to ensure that the UAV always flies along the optimal path and avoids conflicts and deviations;

[0074] Meanwhile, the role of the monitoring and feedback unit is also crucial. It is responsible for monitoring the flight state of the UAV in real time to ensure that it does not deviate from the set flight trajectory when performing the inspection task. By combining sensor input with real-time data analysis, the monitoring and feedback unit can quickly identify potential flight deviations and, in combination with built-in monitoring algorithms (such as Kalman filtering, fuzzy control, etc.), efficiently judge whether the UAV is at risk of deviating from its heading. When the monitoring and feedback unit detects that the UAV has deviated from the predetermined trajectory or is approaching an obstacle, it will promptly generate corrective measures and send new instructions through the flight control unit to adjust the heading and attitude of the UAV;

[0075] In addition, the monitoring and feedback unit can also integrate learning algorithms based on artificial intelligence. As the flight tasks are continuously executed, the system can self-learn and optimize. This adaptive ability can significantly improve the adaptability and safety of the UAV in complex environments. For example, in the face of sudden weather changes or unforeseen obstacles, the system will be able to respond more flexibly and quickly;

[0076] Through the close cooperation between the flight control unit and the monitoring and feedback unit, the intelligence and precision of the inspection task are achieved. This technical framework not only improves the autonomous flight ability of the UAV but also ensures the overall safety and efficiency of the inspection process. Whether it is in the inspection of power lines, pipeline monitoring, or other infrastructure, the combination of the flight control and monitoring and feedback systems can effectively improve the operation quality of the UAV, ultimately realizing the concept of efficient, accurate, and safe UAV inspection.

[0077] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An unmanned aerial vehicle inspection trajectory planning system, characterized in that: It includes a data acquisition unit, a data processing unit, a trajectory planning unit, a flight control unit, and a monitoring and feedback unit; The data acquisition unit is used to obtain terrain data, meteorological data, UAV status data, and information on the inspection area, and the acquired data is sent to the data processing unit through a wireless network; After denoising the data transmitted by the data acquisition unit, the data processing unit extracts the flight slope feature and the flight obstacle distance feature, and calculates the wind speed influence factor, the priority of the inspection target area, the flight path length, the estimated shortest flight time, and the flight energy consumption. The above calculated values are transmitted to the trajectory planning unit for UAV flight trajectory planning; The trajectory planning unit calculates the optimal UAV flight path by applying the shortest path algorithm according to the data transmitted by the data processing unit and sends it to the flight control unit; The flight control unit generates a UAV inspection instruction based on the optimal UAV flight path to control the UAV to perform inspections according to the predetermined optimal flight path; The monitoring and feedback unit is used to monitor the status of the UAV during the flight inspection in real time, and through the built-in monitoring algorithm, when there is a risk of the UAV deviating from the flight trajectory, the UAV flight trajectory is adjusted to the predetermined flight direction in real time.

2. The UAV inspection trajectory planning system according to claim 1, wherein: The formula for data denoising is as follows: , in the formula, represents the th denoised data point, represents the th originally collected data point, represents the window size of the filter, represents the index subscript.

3. The UAV inspection trajectory planning system according to claim 2, characterized in that: The formula for extracting the flight slope feature is as follows: , in the formula, represents the flight slope, represents the height of point 1, represents the height of point 2, represents the horizontal distance between point 1 and point 2.

4. The UAV inspection trajectory planning system according to claim 3, wherein: The formula for extracting the distance feature of the flight obstacle is as follows: , in the formula, represents the distance of the flight obstacle, represents the three-dimensional coordinates of the UAV, represents the three-dimensional coordinates of the obstacle.

5. The UAV inspection trajectory planning system according to claim 4, characterized in that: The formula for calculating the wind speed influence factor is as follows: , in the formula, represents the wind speed influence factor, represents the actual speed of the drone when flying in the wind, represents the flying speed of the drone under windless conditions.

6. The UAV inspection trajectory planning system according to claim 5, wherein: The formula for calculating the priority of the inspection target area is as follows: , in the formula, represents the priority of the inspection target area, , , represent the various attributes affecting the priority, , , are the weight coefficients of the various attributes, respectively assigned by the system intelligence.

7. The UAV inspection trajectory planning system according to claim 6, characterized in that: The formula for calculating the flight path length is as follows: , in the formula, represents the flight path length, represents the coordinates of the index subscript, represents the total number of points on the inspection path.

8. The UAV inspection trajectory planning system according to claim 7, wherein: The formula for calculating the estimated shortest flight time is as follows: , in the formula, represents the estimated shortest flight time, represents the flight path length, represents the flight speed of the drone.

9. The UAV inspection trajectory planning system according to claim 8, wherein: The formula for calculating the flight energy consumption is as follows: , in the formula, represents the flight energy consumption, represents the flight path length, represents the energy consumed by the UAV per kilometer.

10. The UAV inspection trajectory planning system according to claim 9, characterized in that: The formula for calculating the optimal flight path of the drone is as follows: , in the formula, represents the shortest known distance to reach node . represents the shortest known distance to reach node . represents the edge weight from node to node .

Images