Unmanned aerial vehicle tunnel environment detection system and variable structure method

Abstract

The invention discloses an unmanned aerial vehicle tunnel environment detection system and a variable structure method, and belongs to the technical field of machine vision, the unmanned aerial vehicle tunnel environment detection system comprises a variable structure unmanned aerial vehicle prototype platform, an environment information acquisition system, a robot operating system, a wireless communication system, a ground station and a monitoring upper computer, the variable-structure unmanned aerial vehicle prototype platform and the environment 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 upper computer. The position information of the obstacles is quickly obtained based on a clustering algorithm and a spatial index structure, the minimum distance between the obstacles is calculated, the autonomous adaptive capacity and robustness of the unmanned aerial vehicle in a complex environment are improved, meanwhile, key environment data such as harmful gas concentration, temperature and humidity can be accurately monitored in real time, and autonomous monitoring in a tunnel is achieved.

Description

Technical Field

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

[0002] In the face of collapsed urban tunnels with complex terrains, key technologies such as real-time acquisition of harmful gas concentration, temperature and humidity, and structural conditions can effectively monitor and warn of possible environmental risks, providing data support for tunnel maintenance and rescue.

[0003] Currently, domestic urban tunnel monitoring systems are still in the stage of building fixed tunnel monitoring systems using various expensive sensors. For environmental exploration in complex scenarios such as disaster environments, narrow tunnel environments, or collapsed caves, researchers mostly carry equipment manually.

[0004] How to ensure the long-term effective operation of the monitoring system in a harsh tunnel environment is a challenge faced by designers. Moreover, fixed tunnel monitoring equipment cannot cope with the damage caused by sudden tunnel environment collapses. At the same time, for the collapsed tunnel environment, the method of manually carrying detection equipment is inefficient and extremely dangerous. Therefore, the research on using intelligent robotic equipment for tunnel environment exploration is urgent. Based on this, the present invention proposes an unmanned aerial vehicle tunnel environment detection system and a variable structure method. Summary of the Invention

[0005] The purpose of the present invention is to provide an unmanned aerial vehicle tunnel environment detection system and a variable structure method. By using the processed depth image data, three-dimensional point cloud information is generated in real time, and based on the clustering algorithm and spatial index structure, the obstacle position information is quickly obtained, and the minimum distance between obstacles is calculated, which improves the autonomous adaptation ability and robustness of the unmanned aerial vehicle in a complex environment. At the same time, by integrating a variety of high-precision sensors, key environmental data such as harmful gas concentration, temperature and humidity are monitored in real time and accurately, and autonomous monitoring can be realized based on the unmanned aerial vehicle platform inside the tunnel.

[0006] To achieve the above purpose, the present invention provides an unmanned aerial vehicle tunnel environment detection system, including a variable structure unmanned aerial vehicle 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 unmanned aerial vehicle prototype platform. The variable structure unmanned aerial vehicle 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, an Intel NUC, intelligent bus servos, motors, and wings. The Intel NUC is arranged above the flight controller. There are four intelligent bus servos, which are symmetrically arranged around the flight controller. There are also four motors and four wings. The four motors are respectively arranged on the upper side of each intelligent 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 system, function monitoring mainly for setting UAV target points, path planning, and adaptive deformation, and environmental monitoring for monitoring and feedback of real-time environmental data information.

[0010] A UAV variable-structure method provided by the present invention adopts the above 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. Add a bounding box to the three-dimensional point cloud information;

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

[0015] S5. According to the minimum distance of the bounding box, the UAV performs variable structure.

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

[0017] S21. Use the high-precision sensor module to obtain the depth image information of the tunnel;

[0018] S22. Perform filtering processing on the depth image information of the tunnel to remove pixel-level noise;

[0019] S23. Map the depth image information after removing pixel-level noise combined with the camera parameters 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. Preprocess the 3D point cloud information to obtain point cloud data clustering;

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

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

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

[0025] S41. If no bounding box information is detected in the safety area, return to S2; if bounding box information is detected in the safety area, proceed to the next step;

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

[0027] S43. Use the R-Tree spatial index obstacle detection algorithm to organize the obstacle bounding box data;

[0028] S44. Input the obstacle bounding box data into the R-tree spatial index, combine the current position and attitude information of the UAV, and define a local search area for the 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 3D point cloud information, determine the two nearest obstacle bounding boxes through the spatial relationship, and calculate the minimum distance of the bounding box.

[0030] Preferably, the process of the UAV changing its 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 returns to S45; if the flight safety threshold of the UAV is greater than the minimum distance of the bounding box, the UAV changes its structure;

[0032] S52. The intelligent bus servo in the UAV prototype platform rotates according to the minimum distance of the bounding box, changes the flight safety threshold of the UAV, and makes it less than the minimum distance of the bounding box to complete the structure change of the UAV.

[0033] Therefore, the UAV tunnel environment detection system and structure change method adopting the above structure in the present invention have the following advantages:

[0034] 1. It can autonomously change its structure to pass through the complex and changeable environment or narrow space of the tunnel disaster site;

[0035] 2. Design a variable-structure unmanned aerial vehicle (UAV) with rotors that can fold around the X-axis, which can solve the problem that the rotation deformation around the Z-axis has certain angle limitations and cannot minimize the lateral size of the UAV to the greatest extent.

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

[0037] 4. Use an environmental information collection system. In current engineering operations, the disaster environment in urban tunnels usually faces various problems such as difficult maintenance, harsh environment, and high risks. Utilize the high mobility of the UAV to design and carry a set of advanced environmental information monitoring platforms. The variable-structure UAV has excellent environmental adaptability and flexibility, can fly freely in narrow or complex underground environments, and at the same time, the monitoring platform carried by it can collect key environmental data in real time, such as temperature, humidity, gas composition, and structural stability and other information.

[0038] 5. The present invention is provided with an intuitive and easy-to-use interaction interface, which simplifies the operation process, ensures the management operations of non-technical personnel, and thus improves the efficiency and safety of tunnel disaster response.

[0039] 6. There is no need for manual carrying of environmental information monitoring equipment, which maximally guarantees the safety of personnel and liberates the labor force.

[0040] The technical solutions of the present invention will be further described in detail below through the accompanying drawings and embodiments. Description of the Drawings

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

[0042] Figure 2 It is the UAV model structure diagram of an embodiment of a UAV tunnel environment detection system of the present invention;

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

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

[0045] Figure 5 It is the flow chart of a UAV variable-structure method of the present invention;

[0046] Figure 6 It is the obstacle clustering and variable-structure generation result diagram of a UAV variable-structure method of the present invention;

[0047] Figure 7 Schematic diagram of the local search area for a method of changing the structure of an unmanned aerial vehicle according to the present invention; Detailed implementation manners

[0048] Embodiment

[0049] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. Usually, the components of the embodiments of the present invention described and illustrated in the accompanying drawings here 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 claimed invention, but merely represents selected embodiments of the present invention. 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.

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

[0052] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "upper", "lower", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the product of the present invention is usually placed during use. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present invention.

[0053] In the description of the present invention, it should also be noted that unless otherwise clearly defined and limited, the terms "set", "installed", "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0054] The following will describe in detail some embodiments of the present invention with reference to the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0055] Such as Figures 1 - 4As shown in the figure, in the embodiment of the present invention, experiments are carried out using the flight controller of HolyBro Pixhawk 6c, the intelligent bus servo of Huaner LX-224 model, the KV1300 motor, and the 7-inch three-blade propeller. A drone tunnel environment detection system of the present invention includes a variable-structure drone 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 drone prototype platform. The variable-structure drone 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 drone prototype platform includes a flight controller, an Intel NUC, intelligent bus servos, motors, and wings. The Intel NUC is arranged above the flight controller. There are four intelligent bus servos, which are symmetrically arranged around the flight controller at the center. There are also four motors and four wings. The four motors are respectively arranged on the upper side of each intelligent bus servo, and the four wings are respectively arranged 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 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 drone 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 function of the system, mainly for function monitoring of setting the target point of the drone, path planning, and adaptive deformation, and environmental monitoring for monitoring and feedback of real-time environmental data information.

[0059] A drone variable-structure method of the present invention uses the above-mentioned drone tunnel environment detection system, as Figure 5 shown, and includes the following steps:

[0060] S1. Build a drone tunnel environment detection system and install a linear active disturbance rejection control system on it;

[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. Use the high-precision sensor module to obtain the depth image information of the tunnel;

[0063] S22. Perform filtering processing on the depth image information of the tunnel to remove pixel-level noise;

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

[0065] S3. As Figure 6 shown, add a bounding box to the three-dimensional point cloud information, and the process is as follows;

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

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

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

[0069] S4. As Figure 7 shown, calculate the minimum distance of the bounding box according to the bounding box, and the process is as follows;

[0070] S41. If no bounding box information is detected in the safe area, return to S2. If 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. Use the R-Tree spatial index obstacle detection algorithm to organize the obstacle bounding box data;

[0073] S44. Input the obstacle bounding box data into the R-tree space index, combine the current position and attitude information of the UAV, and define a local search area for the 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 nearest obstacle bounding boxes through the spatial relationship, and calculate the minimum distance of the bounding box.

[0075] S5. According to the minimum distance of the bounding box, the UAV performs variable structure, and 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 perform variable 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 performs variable structure;

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

[0078] Therefore, the drone tunnel environment detection system and variable structure method with the above structure of the present invention have the following advantages:

[0079] 1. It can autonomously change its structure to pass through the complex and changeable environment or narrow space at the tunnel disaster site;

[0080] 2. By using a variable structure drone with rotors folded around the X-axis, the problem that the rotation deformation around the Z-axis has a certain angle limit and cannot minimize the lateral size of the drone to the greatest extent can be solved;

[0081] 3. The LADRC control strategy is adopted for control. Compared with the traditional PID controller, it has stronger anti-interference ability, can actively identify and compensate for external disturbances, and return to the stable state faster, ensuring the robustness of the system;

[0082] 4. An environmental information acquisition system is used. In current engineering operations, the urban tunnel disaster environment usually faces various problems such as difficult maintenance, harsh environment, and high risks. By utilizing the high mobility of the drone, an advanced environmental information monitoring platform is designed and carried. The variable structure drone has excellent environmental adaptability and flexibility, can fly freely in narrow or complex underground environments, and at the same time, the monitoring platform carried by it can collect key environmental data in real time, such as temperature, humidity, gas composition, and structural stability and other information.

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

[0084] 6. There is no need for manual carrying of environmental information monitoring equipment, which maximally ensures personnel safety and liberates the labor force.

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

Claims

1. A UAV tunnel environment detection system, characterized by: It includes a variable structure UAV prototype platform, an environmental information collection system, a robot operating system, a wireless communication system, a ground station and a monitoring host computer. The environmental information collection system is arranged on the variable structure UAV prototype platform. The variable structure UAV prototype platform and the environmental information collection 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 UAV tunnel environment detection system according to claim 1 is characterized by: The variable structure UAV prototype platform includes a flight controller, IntelNUC, smart bus servos, motors and wings. The IntelNUC 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 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.

3. The UAV tunnel environment detection system according to claim 2 is characterized in that: 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 IntelNUC. 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 UAV tunnel environment detection system according to claim 3 is characterized by: 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, and adaptive deformation, and for environmental monitoring for monitoring and feedback of real-time environmental data information.

5. A method for changing the structure of an unmanned aerial vehicle, characterized in that: The unmanned aerial vehicle tunnel environment detection system according to any one of claims 1 to 4 above comprises the following steps: S1. Build a UAV tunnel environment detection system and equip it with a linear anti-disturbance control system; S2, using the detection system to collect depth image information and process it to obtain three-dimensional point cloud information; S3, adding a bounding box to the three-dimensional point cloud information; S4, calculating the minimum distance of the bounding box according to the bounding box; S5. According to the minimum distance of the bounding box, the drone performs a variable structure.

6. A method for changing the structure of a drone according to claim 5, 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.

7. A method for changing the structure of a drone according to claim 6, characterized in that: The process of adding a bounding box to 3D point cloud information in S3 is as follows: S31, preprocessing the three-dimensional point cloud information to obtain point cloud data clustering; S32, using a region growing algorithm to perform cluster segmentation on obstacles in the point cloud data clustering, and segmenting the obstacles from the environment; S33. Add a bounding box for each detected point cloud cluster, and store the coordinate information of the generated bounding box.

8. The method for changing the structure of a drone according to claim 7, characterized in that: The process of calculating the minimum distance of the bounding box based on the bounding box in S4 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, constructing R-Tree spatial index obstacle detection algorithm; S43, organizing obstacle bounding box data using an R-Tree spatial index obstacle detection algorithm; S44, input the obstacle bounding box data into the R-tree spatial index, combine the current position and attitude information of the UAV, and define 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 nearest obstacle bounding boxes through spatial relationship, and calculate the minimum distance between the bounding boxes.

9. The method for changing the structure of a drone according to claim 8, characterized in that: The process of changing the structure of the drone in S5 is as follows: S51, determining 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 returns to S45. If the flight safety threshold of the UAV is greater than the minimum distance of the bounding box, the UAV changes its 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 make it smaller than the minimum distance of the bounding box, thereby completing the variable structure of the UAV.

Images