Data fusion intelligent inspection robot based on multiple sensors

Abstract

The invention relates to the technical field of robots, in particular to a multi-sensor-based data fusion intelligent inspection robot which comprises a driving assembly, a control assembly and a detection assembly. The driving assembly comprises a chassis. Front wheels and rear wheels are connected to the bottom of the chassis. The detection assembly comprises a holder, a first camera, a second camera and a detector, the control assembly comprises a control box, and an onboard computer and an encoder are fixed in an inner cavity of the control box. The system has the capability of executing various inspection tasks automatically or manually at a fixed point, the inspection tasks are completed at a time according to the requirements of task points, important nodes are subjected to manual intervention, inspection is completed, a temperature sensor and a dust sensor are carried, environment temperature and air quality are monitored in real time, and the environment temperature and the air quality are displayed on a terminal.

Description

Technical Field

[0001] The present invention relates to the technical field of robots, and in particular to a multi-sensor based data fusion intelligent inspection robot. Background Art

[0002] With the development of science and technology, factories around the world have begun to show a highly automated and intelligent production model, also known as "unmanned factories". Unmanned factories originated in the United States, but the first unmanned factory was established in Japan in 1984. At present, Tesla has six super factories around the world, which use a large amount of automation and robotics technology to greatly improve production efficiency. However, in unmanned factories, such as equipment maintenance, quality inspection, and material management, manual participation is still required. People are mainly responsible for monitoring and maintaining the correct operation of automated equipment. In the factory, major equipment supervision and other tasks still rely heavily on fixed cameras. However, since cameras are generally hung high, there are still deficiencies in the inspection of important equipment close to the ground, hidden corners, and important equipment. If manual inspection is used for inspection, due to the high degree of automation in the factory and the close coordination between various equipment, it is difficult for manual inspection to enter the gaps between the machines, which greatly increases the difficulty of inspection. In addition, during the operation of the machine, dust may be generated during production, and the machine may heat up due to long-term operation, causing changes in the production environment inside the factory. Although the factory will have detection devices, such as PM2.5 detectors, temperature sensors, humidity sensors and other detection elements, they are hung inside the factory and the changes in the environment cannot be observed at any time.

[0003] At present, due to the emergence of market demand and the improvement of scientific and technological levels, the role of inspection robots in the inspection field has become increasingly prominent. With its advantages such as high inspection efficiency, advanced editable functions and relatively low costs, inspection robots can bring considerable social and economic benefits compared to manual inspections. Especially in recent years, with the increasing probability of safety accidents, the production safety issues of unmanned factories have become extremely sensitive, and the society and the public are still waiting to see the development of unmanned factories. Therefore, using inspection robots for regular inspections has become an important way to solve such problems. At present, in the scenarios of substations, chemical plants, fire protection, and photovoltaic power stations, attempts have been made to use inspection robots instead of manual inspections, which also reflects the current mainstream development direction of inspection robots. Summary of the invention

[0004] The purpose of the present invention is to provide a multi-sensor based data fusion intelligent inspection robot, which solves the problems raised in the background technology.

[0005] To achieve the above-mentioned object, the present invention provides the following technical solutions: a multi-sensor based data fusion intelligent inspection robot, comprising: a driving component, a control component and a detection component;

[0006] The driving assembly comprises a chassis, power motors are fixed on both sides of the rear end of the bottom of the chassis, the outer end of the output shaft of the power motor is fixedly connected to the rear wheel, a steering motor is fixed to one side of the bottom of the chassis, the output end of the steering motor is connected to the steering member, the output end of the steering member is hinged to the carrier, the carrier is rotatably mounted on the bottom of the chassis, and the outer end of the carrier is rotatably connected to the front wheel;

[0007] The detection component includes a pan / tilt, a first camera, a second camera and a detector;

[0008] The pan / tilt is fixed to the top of the fixing frame on the top of the chassis, the top of the pan / tilt is fixedly connected to a first camera, the middle of the front end of the fixing frame is fixed to a second camera, and detectors are fixed to both sides of the front end of the fixing frame;

[0009] The control assembly comprises a control box, an onboard computer and an encoder are fixed in the inner cavity of the control box, and a display is fixed on the surface of the control box.

[0010] By adopting the above technical solution, the power motor drives the rear wheel to rotate, so that the driving device can be moved as a whole, and during the movement, the steering motor drives the steering member to move, so as to drive the front wheel to steer. The semi-loaded computer and encoder can accurately calculate the steering angle of the vehicle and convert it into an electrical signal, so as to use the onboard computer to control the steering motor to drive the steering member to steer accurately.

[0011] The first camera and the second camera can be used to capture images of the detection area, and the pan / tilt head can be used to capture images from multiple angles, ensuring a wide and accurate capture area.

[0012] As a preferred embodiment of the present invention, the control component also includes a laser radar and a detection camera, and the laser radar and the detection camera are fixed to the front side of the fixing frame at the top of the front end of the chassis.

[0013] The laser radar is Silan laser radar, and its working principle is to emit laser beams and receive reflected laser beams. According to the time difference and angle difference between the laser beam signal being sent and received, the distance and angle information between the radar and the target are calculated, which can help the inspection robot realize autonomous navigation, obstacle avoidance and positioning functions;

[0014] The detection camera is a high-precision camera, so it can capture images accurately.

[0015] As a preferred implementation manner of the present invention, the onboard computer includes a 4G communication module, a PWM signal driving module, an STM32 core module, and a Bluetooth module.

[0016] 4G communication module: realizes autonomous positioning and navigation of the inspection robot, receives instructions from the remote control center or plans routes on its own. The robot can complete inspection tasks autonomously, improving training efficiency and certainty.

[0017] PWM signal drive module: amplifies the PWM signal of the control chip to control the speed and torque of the motor and the speed and rotation angle of the servo.

[0018] STM32 core module: The core module of the entire inspection robot control system, composed of STM32 and its required peripheral circuits, is used to complete the processing of encoder signals and to allocate tasks such as the speed of the left and right wheels when turning.

[0019] Bluetooth module: connects the inspection robot to mobile phones, terminals and other devices, and sends instructions to the inspection robot through these devices, so that the inspection robot can inspect according to the preset route, and also allows functional personnel to re-inspect important nodes.

[0020] As a preferred embodiment of the present invention, the detector includes a temperature sensor and a dust sensor, which monitor the ambient temperature and air quality in real time and display them on the terminal. The staff can observe the corresponding parameters through the terminal device.

[0021] As a preferred embodiment of the present invention, a recharging seat is fixedly installed at the rear end of the chassis.

[0022] For the realization of the automatic recharging function: in terms of software operation, you first need to build a map for automatic recharging. After completing the map building and saving, close the relevant nodes, and then turn on the navigation nodes and automatic recharging functions by executing specific commands. Then modify the 2D Nav Goal topic in rvi z and mark the location and direction of the charging pile. After completing these operations, the automatic recharging function of the inspection robot can be realized, so that the inspection robot can autonomously find the charging pile and perform charging operations.

[0023] As a preferred embodiment of the present invention, emergency stop switches are fixed on both sides of the top of the control box.

[0024] As a preferred embodiment of the present invention, a front stopper is fixed to the front end of the chassis.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] (1) It has the ability to perform various inspection tasks at fixed points, automatically or manually, complete the inspection tasks in one go according to the requirements of the task points, and conduct manual intervention on important nodes to complete the inspection.

[0027] (2) Equipped with temperature sensors and dust sensors to monitor ambient temperature and air quality in real time and display them on the terminal.

[0028] (3) The current power level is displayed in real time on the monitor, and the battery is charged through a charging pile. The charging pile is connected by infrared to achieve automatic recharging. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0030] Figure 1 This is a schematic diagram of the overall structure of the multi-sensor data fusion intelligent inspection robot of the present invention;

[0031] Figure 2 It is a schematic diagram of the front structure of the multi-sensor data fusion intelligent inspection robot of the present invention;

[0032] Figure 3 This is a schematic diagram of the chassis structure of the multi-sensor data fusion intelligent inspection robot based on the present invention, viewed from above.

[0033] In the figure:

[0034] 1. Chassis; 2. First camera; 3. Second camera; 4. Control box; 5. Display; 6. Emergency stop switch; 7. Rear wheel; 8. Charging seat; 9. Front wheel; 10. Detection camera; 11. LiDAR; 12. Detector; 13. Front windshield; 14. Steering motor; 15. Steering parts; 16. Carrier; 17. Power motor; 18. Gimbal. DETAILED DESCRIPTION

[0035] See also Figure 1-3 ,The present invention provides a technical solution: a multi-sensor based data fusion intelligent inspection robot, including a driving component, a control component and a detection component;

[0036] The driving assembly includes a chassis 1, a power motor 17 is fixed on both sides of the rear end of the bottom of the chassis 1, the outer end of the output shaft of the power motor 17 is fixedly connected to the rear wheel 7, a steering motor 14 is fixed to one side of the bottom of the chassis 1, the output end of the steering motor 14 is connected to the steering member 15, the output end of the steering member 15 is hinged to the carrier 16, the carrier 16 is rotatably installed on the bottom of the chassis 1, and the outer end of the carrier 16 is rotatably connected to the front wheel 9;

[0037] It should be noted that the steering member 15 adopts a mature Ackerman steering structure design, using a slider instead of the middle cross bar design, and at the same time the slider is moved to reduce the rotation speed requirement during steering. Different from the Ackerman structure on the market, the Ackerman structure inspection robot adopts a crank slider mechanism instead of a crank connecting rod mechanism. The steering wheel is rotated by a servo, and the steering wheel is connected to the slider through a connecting rod. The rotation of the steering wheel is converted into a translational motion of the connecting rod. The connecting rod is used to connect the wheel to the slider. When the servo rotates, it drives the wheel to rotate, thereby realizing the steering of the inspection robot.

[0038] It should be understood that the power motor 17 drives the rear wheel 7 to rotate, thereby driving the entire device to move, and during the movement, the steering motor 14 drives the steering member 15 to move, thereby driving the front wheel 9 to turn.

[0039] Furthermore, a front baffle 13 is fixed to the front end of the chassis 1, and the arrangement of the front baffle 13 can protect the entire device.

[0040] Furthermore, emergency stop switches 6 are fixed on both sides of the top of the control box 4.

[0041] like Figure 1 The control component includes a control box 4, an onboard computer and an encoder are fixed in the inner cavity of the control box 4, a display 5 is fixed on the surface of the control box 4, and the onboard computer includes a 4G communication module, a PWM signal drive module, an STM32 core module, and a Bluetooth module;

[0042] It should be understood that the half-loaded computer and encoder can accurately calculate the steering angle of the vehicle and convert it into an electrical signal, so as to use the onboard computer to control the steering motor 14 to drive the steering member 15 to steer accurately.

[0043] in:

[0044] 4G communication module: realizes autonomous positioning and navigation of the inspection robot, receives instructions from the remote control center or plans routes on its own. The robot can complete inspection tasks autonomously, improving training efficiency and certainty.

[0045] PWM signal drive module: amplifies the PWM signal of the control chip to control the speed and torque of the motor and the speed and rotation angle of the servo.

[0046] STM32 core module: The core module of the entire inspection robot control system, composed of STM32 and its required peripheral circuits, is used to complete the processing of encoder signals and to allocate tasks such as the speed of the left and right wheels when turning.

[0047] Bluetooth module: connects the inspection robot to mobile phones, terminals and other devices, and sends instructions to the inspection robot through these devices, so that the inspection robot can inspect according to the preset route, and also allows functional personnel to re-inspect important nodes.

[0048] The specific path planning is as follows:

[0049] For the realization of the robot inspection function: First, run the ros launch turn_on_wheel tec_robotmapping.launch command. Next, open rv ia in the virtual machine. After adding the map through the add command in the lower left corner, you can see the created map. Next, you should start the map_sever node to save the map and enter

[0050] " / home / wheel tec / wheel tec_robot / src / turn_on_wheel tec_robot / map" path. Execute the rosrun map_server map_saver-f mymap command. At this point, the map has been saved with the name mtmap. If a map file named mamap already exists before, the newly created map will overwrite the existing map. If you delete the -f mymap command in the command, the system will save the map with map as the name, and the map will be saved in the directory where the current terminal is located. The map not only includes a mymap.pgmd map data file, but also a mymap.yaml file. The mymap.yaml file is a configuration file for the map, and mymap.pgm can also be edited using software such as GIMP.

[0051] After the map is built, the next step is robot navigation. The key to navigation is to realize the positioning and path planning of the robot. ROS provides two function packages, mov_base and amc l, as solutions to the robot's behavior and path planning. mov_base can realize the optimal path planning in robot navigation, and amc l can realize the robot positioning in the two-dimensional map. When using it, you only need to set the robot's target posture in the map, and the robot can reach the specified target point according to the map and the optimal path.

[0052] like Figure 1 As shown, the control component also includes a laser radar 11 and a detection camera 10, and the laser radar 11 and the detection camera 10 are fixed to the front side of the fixing frame at the top of the front end of the chassis 1;

[0053] Laser radar 11 is Silan laser radar, its working principle is to emit laser beams and receive reflected laser beams. According to the time difference and angle difference between the sending and receiving of laser beam signals, the distance and angle information between the radar and the target are calculated, which can help the inspection robot realize autonomous navigation, obstacle avoidance and positioning functions;

[0054] The detection camera 10 is a high-precision camera, so it can accurately capture the picture;

[0055] It should be understood that the information collected by the laser radar 11 and the detection camera 10 will be fed back to the onboard computer, so that the onboard computer can analyze and convert the collected information, thereby planning the optimal path according to the on-site conditions.

[0056] like Figure 1 and 2 As shown, the detection assembly includes a pan / tilt 18, a first camera 2, a second camera 3 and a detector 12;

[0057] The pan / tilt head 18 is fixed to the top of the fixing frame on the top of the chassis 1, the top of the pan / tilt head 18 is fixedly connected with the first camera 2, the middle of the front end of the fixing frame is fixed with the second camera 3, the two sides of the front end of the fixing frame are fixed with detectors 12, and the signal output ends of the first camera 2, the second camera 3 and the detector 12 are connected to the signal input end of the onboard computer;

[0058] The first camera 2 and the second camera 3 can be used to capture images of the detection area, and the pan / tilt head 18 can be used to capture images from multiple angles, ensuring a wide and accurate capture area.

[0059] The detector 12 includes a temperature sensor and a dust sensor, which monitors the ambient temperature and air quality in real time and displays them on the terminal. The staff can observe the corresponding parameters through the terminal device.

[0060] like Figure 1 As shown, a recharging seat 8 is fixedly installed at the rear end of the chassis 1, and the recharging seat 8 is electrically connected to the battery installed inside the chassis 1;

[0061] For the realization of the automatic recharging function: in terms of software operation, you first need to build a map for automatic recharging. After completing the map building and saving, close the relevant nodes, and then turn on the navigation nodes and automatic recharging functions by executing specific commands. Then modify the 2D Nav Goal topic in rvi z and mark the location and direction of the charging pile. After completing these operations, the automatic recharging function of the inspection robot can be realized, so that the inspection robot can autonomously find the charging pile and perform charging operations.

[0062] The implementation principle of the data fusion intelligent inspection robot based on multiple sensors in the present application is as follows: first, the robot's route is set in advance through a program, and the rear wheel 7 is driven to rotate by the power motor 17, so that the driving device can be moved as a whole, and in the process of moving, the steering member 15 is driven to move by the steering motor 14, so as to drive the front wheel 9 to turn. During the driving process, the information collected by the laser radar 11 and the detection camera 10 will be fed back to the onboard computer, and the onboard computer is used to control the steering motor 14 to drive the steering member 15 to turn accurately. During the inspection process, the first camera 2 and the second camera 3 can be used to collect images of the detection part, and the pan-tilt head 18 can be used to collect images from multiple angles to ensure a wide collection area and accurate collection. The temperature sensor and the dust sensor monitor the ambient temperature and air quality in real time and display them on the terminal. The staff can observe the corresponding parameters through the terminal device. When the inspection is over and charging is required, a map for automatic recharging is established. After completing the map building and saving, the relevant nodes are closed, and then the navigation node and the automatic recharging function are enabled by executing specific commands, and then 2D Nav is performed in rv iz. By modifying the Goal topic and marking the location and direction of the charging pile, the automatic recharging function of the inspection robot can be realized, allowing the inspection robot to autonomously find the charging pile and perform charging operations.

[0063] In addition, the components included in the multi-sensor data fusion intelligent inspection robot of the present invention are all universal standard parts or components known to technical personnel in this field. The structure and principle can be known to technical personnel in this field through technical manuals or through conventional experimental methods. In the idle part of this device, all the above-mentioned electrical components, which refer to power elements, electrical components, and adapted monitoring computers and power supplies are connected through wires. The specific connection means should refer to the following working principle. The electrical connection is completed in the working order of each electrical component. The detailed connection means are well-known technologies in this field. The following mainly introduces the working principles and processes, and no explanation of electrical control is given.

Claims

1. A multi-sensor data fusion intelligent inspection robot, characterized in that: include: Drive components, control components and detection components; The driving assembly comprises a chassis (1), power motors (17) are fixed on both sides of the rear end of the bottom of the chassis (1), the outer end of the output shaft of the power motor (17) is fixedly connected to the rear wheel (7), a steering motor (14) is fixed on one side of the bottom of the chassis (1), the output end of the steering motor (14) is connected to a steering member (15), the output end of the steering member (15) is hinged to a carrier (16), the carrier (16) is rotatably mounted on the bottom of the chassis (1), and the outer end of the carrier (16) is rotatably connected to the front wheel (9); The detection component comprises a pan / tilt platform (18), a first camera (2), a second camera (3) and a detector (12); The pan / tilt head (18) is fixed to the top of a fixing frame on the top of the chassis (1); a first camera (2) is fixedly connected to the top of the pan / tilt head (18); a second camera (3) is fixed at the middle of the front end of the fixing frame; and detectors (12) are fixed on both sides of the front end of the fixing frame; The control assembly comprises a control box (4), an onboard computer and an encoder are fixed in the inner cavity of the control box (4), and a display (5) is fixed on the surface of the control box (4).

2. The multi-sensor data fusion intelligent inspection robot according to claim 1, characterized in that: The control component also includes a laser radar (11) and a detection camera (10), and the laser radar (11) and the detection camera (10) are fixed to the front side of a fixing frame at the top of the front end of the chassis (1).

3. The multi-sensor data fusion intelligent inspection robot according to claim 1, characterized in that: The onboard computer includes a 4G communication module, a PWM signal driving module, an STM32 core module, and a Bluetooth module.

4. The multi-sensor data fusion intelligent inspection robot according to claim 1, characterized in that: The detector (12) comprises a temperature sensor and a dust sensor.

5. The multi-sensor data fusion intelligent inspection robot according to claim 1, characterized in that: A recharging seat (8) is fixedly mounted on the rear end of the chassis (1).

6. The multi-sensor data fusion intelligent inspection robot according to claim 1, characterized in that: Emergency stop switches (6) are fixed on both sides of the top of the control box (4).

7. The multi-sensor data fusion intelligent inspection robot according to claim 1, characterized in that: A front stopper (13) is fixed to the front end of the chassis (1).

Images