An Unmanned Aerial Vehicle Tunnel Environment Detection System and a Variable Structure Method

Abstract

The present invention discloses an unmanned aerial vehicle (UAV) tunnel environment detection system and a variable structure method, belonging to the field of machine vision technology. The system includes a variable structure UAV prototype platform, an environmental information acquisition system, a robot operating system, a wireless communication system, a ground station and a monitoring host computer. The environmental information acquisition system is arranged on the variable structure UAV prototype platform. The variable structure UAV prototype platform and the environmental information acquisition system communicate with the ground station through the wireless communication system. The ground station communicates with the robot operating system, and the robot operating system communicates with the monitoring host computer. The present invention adopts the above system and the corresponding method, and quickly obtains obstacle position information based on a clustering algorithm and a spatial index structure, calculates the minimum distance between obstacles, improves the autonomous adaptability and robustness of the UAV in complex environments, and can also accurately monitor key environmental data such as harmful gas concentration, temperature and humidity in real time, thereby realizing autonomous monitoring inside the tunnel.

Description

Technical Field

[0001] The present invention relates to the field of machine vision technology, and in particular to an unmanned aerial vehicle (UAV) tunnel environment detection system and a variable structure method. Background Art

[0002] In the case of collapsed urban tunnels in complex terrain, real-time acquisition of key technologies such as hazardous gas concentrations, temperature and humidity, and structural conditions can effectively monitor and warn of potential environmental risks, providing data support for tunnel maintenance and rescue efforts.

[0003] Currently, China's urban tunnel monitoring systems are still based on the use of various expensive sensors to build fixed tunnel monitoring systems. Researchers often use human-carried equipment to conduct environmental surveys in complex scenarios such as disaster environments, confined tunnels, and collapsed caves.

[0004] Ensuring the long-term effectiveness of monitoring systems in harsh tunnel environments is a challenge for designers. Fixed tunnel monitoring equipment is unable to cope with the damage caused by sudden tunnel collapses. Furthermore, for collapsed tunnels, the inefficient and highly dangerous method of carrying monitoring equipment manually is crucial. Therefore, research on the application of intelligent robotic equipment for tunnel environmental exploration is urgent. Based on this, this paper proposes an unmanned aerial vehicle (UAV) tunnel environmental monitoring system and a variable structure method. Summary of the Invention

[0005] The purpose of the present invention is to provide a UAV tunnel environment detection system and variable structure method, which utilizes processed depth image data to generate three-dimensional point cloud information in real time, and quickly obtains obstacle position information based on clustering algorithm and spatial index structure, and calculates the minimum distance between obstacles, thereby improving the autonomous adaptability and robustness of the UAV in complex environments. At the same time, by integrating multiple high-precision sensors, key environmental data such as harmful gas concentration, temperature and humidity can be monitored in real time and accurately, and autonomous monitoring can be achieved inside the tunnel based on the UAV platform.

[0006] To achieve the above-mentioned objectives, the present invention provides a UAV tunnel environment detection system, comprising a variable-structure UAV prototype platform, an environmental information acquisition system, a robot operating system, a wireless communication system, a ground station and a monitoring host computer. The environmental information acquisition system is arranged on the variable-structure UAV prototype platform, the variable-structure UAV prototype platform and the environmental information acquisition system communicate with the ground station through the wireless communication system, the ground station communicates with the robot operating system, and the robot operating system communicates with the monitoring host computer.

[0007] Preferably, the variable structure UAV prototype platform includes a flight controller, Intel NUC, smart bus servos, motors and wings. The Intel NUC is arranged above the flight controller. There are four smart bus servos, which are centrally symmetrically arranged around the flight controller. There are also four motors and wings. The four motors are respectively arranged on the upper side of each smart bus servo, and the four wings are respectively arranged on the upper side of each motor.

[0008] Preferably, the environmental information acquisition system includes an environmental information acquisition board, a high-precision sensor module and an information acquisition camera. The environmental information acquisition board is arranged above the Intel NUC. There are several high-precision sensor modules, all of which are arranged on the environmental information acquisition board. The information acquisition camera is arranged on one side of the variable structure UAV prototype platform.

[0009] Preferably, the monitoring host computer includes a computer and an environmental monitoring UI. The environmental monitoring UI is installed in the computer. The environmental monitoring UI includes status monitoring for monitoring the power, speed, and communication functions of the monitoring system. It is mainly used for function monitoring of drone target point setting, path planning, adaptive deformation, and environmental monitoring for monitoring and feedback of real-time environmental data information.

[0010] The present invention provides a method for changing the structure of a UAV, which uses the above-mentioned UAV tunnel environment detection system, and includes the following steps:

[0011] S1. Build a UAV tunnel environment detection system and equip it with a linear active disturbance rejection control system;

[0012] S2. Use the detection system to collect depth image information and process it to obtain three-dimensional point cloud information;

[0013] S3, adding a bounding box to the 3D point cloud information;

[0014] S4. Calculate the minimum distance of the bounding box according to the bounding box;

[0015] S5. Based on the minimum distance of the bounding box, the drone performs structure change.

[0016] Preferably, the process of obtaining the three-dimensional point cloud information in S2 is as follows:

[0017] S21, using a high-precision sensor module to obtain depth image information of the tunnel;

[0018] S22, filtering the depth image information of the tunnel to remove pixel-level noise;

[0019] S23. Combining the depth image information with pixel-level noise removed with the camera parameter mapping of the information acquisition camera to generate three-dimensional point cloud information.

[0020] Preferably, the process of adding a bounding box to the 3D point cloud information in S3 is as follows:

[0021] S31, preprocessing the three-dimensional point cloud information to obtain point cloud data clustering;

[0022] S32. Use a region growing algorithm to cluster and segment obstacles in the point cloud data clustering, and separate the obstacles from the environment;

[0023] S33. Add a bounding box for each detected point cloud cluster and store the coordinate information of the generated bounding box.

[0024] Preferably, the process of calculating the minimum distance of the bounding box according to the bounding box in S4 is as follows:

[0025] S41: If the bounding box information is not detected in the safe area, return to S2; if the bounding box information is detected in the safe area, proceed to the next step;

[0026] S42. Construct an R-Tree spatial index obstacle detection algorithm;

[0027] S43. Organize obstacle bounding box data using the R-Tree spatial index obstacle detection algorithm;

[0028] S44, inputting the obstacle bounding box data into the R-tree spatial index, combining the current position and attitude information of the UAV, and defining a local search area for point cloud data clustering with the current position of the UAV as the center;

[0029] S45. Quickly retrieve the required obstacle bounding box in the three-dimensional point cloud information, determine the two closest obstacle bounding boxes through spatial relationships, and calculate the minimum distance between the bounding boxes.

[0030] Preferably, the process of the drone changing structure in S5 is as follows:

[0031] S51. Determine the flight safety threshold of the UAV. If the flight safety threshold of the UAV is less than the minimum distance of the bounding box, the UAV does not need to change its structure, and return to S45. If the flight safety threshold of the UAV is greater than the minimum distance of the bounding box, the UAV undergoes a change of structure.

[0032] S52. The intelligent bus servo in the UAV prototype platform rotates according to the minimum distance of the bounding box, changing the flight safety threshold of the UAV to be less than the minimum distance of the bounding box, thereby completing the variable structure of the UAV.

[0033] Therefore, the present invention adopts a UAV tunnel environment detection system and variable structure method of the above structure, which has the following advantages:

[0034] 1. Ability to autonomously change structure to pass through complex and changing environments or narrow spaces at tunnel disaster sites;

[0035] 2. Designing a variable-structure drone with foldable rotors around the X-axis can solve the problem of limited rotational deformation around the Z-axis, which prevents the drone from minimizing its lateral size.

[0036] 3. The LADRC control strategy is used for control, which has stronger anti-interference ability than the traditional PID controller. It can actively identify and compensate for external disturbances, return to a stable state faster, and ensure the robustness of the system.

[0037] 4. Utilizing an environmental information collection system. This system addresses the challenges often faced in current urban tunnel disaster operations, including difficult maintenance, harsh environments, and high risks. Leveraging the high maneuverability of drones, an advanced environmental information monitoring platform was designed and deployed. The variable-structure drone boasts exceptional adaptability and flexibility, enabling it to navigate confined and complex underground environments. Its onboard monitoring platform collects critical environmental data in real time, including temperature, humidity, gas composition, and structural stability.

[0038] 5. The present invention is equipped with an intuitive and easy-to-use interactive interface, which simplifies the operation process and ensures management and operation by non-technical personnel, thereby improving the efficiency and safety of tunnel disaster response;

[0039] 6. There is no need for people to carry environmental information monitoring equipment, which ensures personnel safety to the greatest extent and liberates labor.

[0040] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a system flow chart of a UAV tunnel environment detection system of the present invention;

[0042] Figure 2 This is a structural diagram of a drone model of an embodiment of a drone tunnel environment detection system of the present invention;

[0043] Figure 3 This is a schematic diagram of the UAV control system of a UAV tunnel environment detection system of the present invention;

[0044] Figure 4 This is an environmental monitoring UI interface diagram of a UAV tunnel environment detection system of the present invention;

[0045] Figure 5 This is a flow chart of a method for changing the structure of a UAV according to the present invention;

[0046] Figure 6 This is a diagram showing the obstacle clustering and variable structure generation results of a variable structure method for a UAV according to the present invention;

[0047] Figure 7 Schematic diagram of a local search area of a UAV variable structure method of the present invention; DETAILED DESCRIPTION

[0048] Example

[0049] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of 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. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0050] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort shall fall within the scope of protection of the present invention.

[0051] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0052] In the description of the present invention, it should be noted that the terms "upper", "lower", "inside", "outside", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, or are the orientations or positional relationships in which the inventive product is usually placed when in use. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they should not be understood as limiting the present invention.

[0053] In the description of the present invention, it should also be noted that, unless otherwise expressly specified or limited, the terms "disposed," "installed," and "connected" should be understood broadly. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0054] The following embodiments of the present invention are described in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments may be combined with each other.

[0055] like Figures 1-4As shown, an embodiment of the present invention uses a HolyBro Pixhawk 6c flight controller, a Huaner LX-224 model intelligent bus servo, a KV1300 motor and a 7-inch three-blade propeller for experiments. A UAV tunnel environment detection system of the present invention includes a variable structure UAV prototype platform, an environmental information acquisition system, a robot operating system, a wireless communication system, a ground station and a monitoring host computer. The environmental information acquisition system is arranged on the variable structure UAV prototype platform. The variable structure UAV prototype platform and the environmental information acquisition system communicate with the ground station through the wireless communication system. The ground station communicates with the robot operating system, and the robot operating system communicates with the monitoring host computer.

[0056] The variable structure UAV prototype platform includes a flight controller, Intel NUC, smart bus servos, motors and wings. The Intel NUC is set above the flight controller. There are four smart bus servos, which are symmetrically arranged around the flight controller. There are also four motors and wings. The four motors are set on the upper side of each smart bus servo, and the four wings are set on the upper side of each motor.

[0057] The environmental information acquisition system includes an environmental information acquisition board, a high-precision sensor module and an information acquisition camera. The environmental information acquisition board is set above the Intel NUC. There are several high-precision sensor modules, all of which are set on the environmental information acquisition board. The information acquisition camera is set on one side of the variable structure UAV prototype platform.

[0058] The monitoring host computer includes a computer and an environmental monitoring UI. The environmental monitoring UI is installed in the computer. The environmental monitoring UI includes status monitoring for monitoring the power, speed, and communication functions of the monitoring system. It is mainly used for drone target point setting, path planning, adaptive deformation function monitoring, and environmental monitoring for monitoring and feedback of real-time environmental data information.

[0059] The present invention provides a method for changing the structure of a UAV, using the above-mentioned UAV tunnel environment detection system, such as Figure 5 The following steps are shown:

[0060] S1. Build a UAV tunnel environment detection system and equip it with a linear active disturbance rejection control system;

[0061] S2. Use the detection system to collect depth image information and process it to obtain three-dimensional point cloud information. The process is as follows;

[0062] S21, using a high-precision sensor module to obtain depth image information of the tunnel;

[0063] S22, filtering the depth image information of the tunnel to remove pixel-level noise;

[0064] S23. Combining the depth image information with pixel-level noise removed with the camera parameter mapping of the information acquisition camera to generate three-dimensional point cloud information.

[0065] S3, such as Figure 6 As shown, the process of adding a bounding box to the 3D point cloud information is as follows;

[0066] S31, preprocessing the three-dimensional point cloud information to obtain point cloud data clustering;

[0067] S32. Use a region growing algorithm to cluster and segment obstacles in the point cloud data clustering, and separate the obstacles from the environment;

[0068] S33. Add a bounding box for each detected point cloud cluster and store the coordinate information of the generated bounding box.

[0069] S4, such as Figure 7 As shown, the minimum distance of the bounding box is calculated based on the bounding box. The process is as follows;

[0070] S41: If the bounding box information is not detected in the safe area, return to S2; if the bounding box information is detected in the safe area, proceed to the next step;

[0071] S42. Construct an R-Tree spatial index obstacle detection algorithm;

[0072] S43. Organize obstacle bounding box data using the R-Tree spatial index obstacle detection algorithm;

[0073] S44, inputting the obstacle bounding box data into the R-tree spatial index, combining the current position and attitude information of the UAV, and defining a local search area for point cloud data clustering with the current position of the UAV as the center;

[0074] S45. Quickly retrieve the required obstacle bounding box in the three-dimensional point cloud information, determine the two closest obstacle bounding boxes through spatial relationships, and calculate the minimum distance between the bounding boxes.

[0075] S5. Based on the minimum distance of the bounding box, the drone performs a variable structure. The process is as follows.

[0076] S51. Determine the flight safety threshold of the UAV. If the flight safety threshold of the UAV is less than the minimum distance of the bounding box, the UAV does not need to change its structure, and return to S45. If the flight safety threshold of the UAV is greater than the minimum distance of the bounding box, the UAV undergoes a change of structure.

[0077] S52. The intelligent bus servo in the UAV prototype platform rotates according to the minimum distance of the bounding box, changing the flight safety threshold of the UAV to be less than the minimum distance of the bounding box, thereby completing the variable structure of the UAV.

[0078] Therefore, the present invention adopts a UAV tunnel environment detection system and variable structure method of the above structure, which has the following advantages:

[0079] 1. Ability to autonomously change structure to pass through complex and changing environments or narrow spaces at tunnel disaster sites;

[0080] 2. Using a variable-structure drone with foldable rotors around the X-axis can solve the problem of limited angles of rotation around the Z-axis, which prevents the drone from minimizing its lateral size.

[0081] 3. The LADRC control strategy is used for control, which has stronger anti-interference ability than the traditional PID controller. It can actively identify and compensate for external disturbances, return to a stable state faster, and ensure the robustness of the system.

[0082] 4. Utilizing an environmental information collection system. This system addresses the challenges often faced in current urban tunnel disaster operations, including difficult maintenance, harsh environments, and high risks. Leveraging the high maneuverability of drones, an advanced environmental information monitoring platform was designed and deployed. The variable-structure drone boasts exceptional adaptability and flexibility, enabling it to navigate confined and complex underground environments. Its onboard monitoring platform collects critical environmental data in real time, including temperature, humidity, gas composition, and structural stability.

[0083] 5. The present invention is equipped with an intuitive and easy-to-use interactive interface, which simplifies the operation process and ensures management and operation by non-technical personnel, thereby improving the efficiency and safety of tunnel disaster response;

[0084] 6. There is no need for people to carry environmental information monitoring equipment, which ensures personnel safety to the greatest extent and liberates labor.

[0085] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the same. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solutions of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for detecting an environment in a variable structure tunnel using an unmanned aerial vehicle, characterized in that: The following steps are involved: S1. Build a UAV tunnel environment detection system and equip it with a linear active disturbance rejection control system; S2. Use the detection system to collect depth image information and process it to obtain three-dimensional point cloud information; S3. Add a bounding box to the 3D point cloud information. The process of adding a bounding box is as follows: S31, preprocessing the three-dimensional point cloud information to obtain point cloud data clustering; S32. Use a region growing algorithm to cluster and segment obstacles in the point cloud data clustering, and separate the obstacles from the environment; S33, adding a bounding box for each detected point cloud cluster, and storing the coordinate information of the generated bounding box; S4. Calculate the minimum distance of the bounding box according to the bounding box. The calculation process is as follows: S41: If the bounding box information is not detected in the safe area, return to S2; if the bounding box information is detected in the safe area, proceed to the next step; S42. Construct an R-Tree spatial index obstacle detection algorithm; S43. Organize obstacle bounding box data using the R-Tree spatial index obstacle detection algorithm; S44, inputting the obstacle bounding box data into the R-Tree spatial index, combining the current position and attitude information of the UAV, and defining a local search area for point cloud data clustering with the current position of the UAV as the center; S45. Quickly retrieve the required obstacle bounding box in the three-dimensional point cloud information, determine the two closest obstacle bounding boxes through spatial relationships, and calculate the minimum distance between the bounding boxes; S5. Based on the minimum distance of the bounding box, the drone performs a variable structure. The process is as follows: S51. Determine the flight safety threshold of the UAV. If the flight safety threshold of the UAV is less than the minimum distance of the bounding box, the UAV does not need to change its structure, and return to S45. If the flight safety threshold of the UAV is greater than the minimum distance of the bounding box, the UAV undergoes a change of structure. S52, the intelligent bus servo in the UAV prototype platform rotates according to the minimum distance of the bounding box, changing the flight safety threshold of the UAV to be less than the minimum distance of the bounding box, thereby completing the variable structure of the UAV; The UAV tunnel environment detection system includes a variable structure UAV prototype platform, an environmental information acquisition system, a robot operating system, a wireless communication system, a ground station and a monitoring host computer. The environmental information acquisition system is set on the variable structure UAV prototype platform. The variable structure UAV prototype platform and the environmental information acquisition system communicate with the ground station through the wireless communication system. The ground station communicates with the robot operating system, and the robot operating system communicates with the monitoring host computer.

2. The method for detecting a variable structure tunnel environment using an unmanned aerial vehicle according to claim 1, wherein: The variable structure UAV prototype platform includes a flight controller, Intel NUC, smart bus servos, motors and wings. The Intel NUC is set above the flight controller. There are four smart bus servos, which are symmetrically arranged around the flight controller. There are also four motors and wings. The four motors are set on the upper side of each smart bus servo, and the four wings are set on the upper side of each motor.

3. The method for detecting a variable structure tunnel environment using an unmanned aerial vehicle according to claim 2, wherein: The environmental information acquisition system includes an environmental information acquisition board, a high-precision sensor module and an information acquisition camera. The environmental information acquisition board is set above the Intel NUC. There are several high-precision sensor modules, all of which are set on the environmental information acquisition board. The information acquisition camera is set on one side of the variable structure UAV prototype platform.

4. The method for detecting a variable structure tunnel environment using an unmanned aerial vehicle according to claim 3, wherein: The monitoring host computer includes a computer and an environmental monitoring UI. The environmental monitoring UI is installed in the computer. The environmental monitoring UI includes status monitoring for monitoring the power, speed, and communication functions of the monitoring system. It is mainly used for drone target point setting, path planning, adaptive deformation function monitoring, and environmental monitoring for monitoring and feedback of real-time environmental data information.

5. The method for detecting a variable structure tunnel environment by using a drone according to claim 4, characterized in that: The process of obtaining three-dimensional point cloud information in S2 is as follows: S21, using a high-precision sensor module to obtain depth image information of the tunnel; S22, filtering the depth image information of the tunnel to remove pixel-level noise; S23. Combining the depth image information with pixel-level noise removed with the camera parameter mapping of the information acquisition camera to generate three-dimensional point cloud information.

Images