Intelligent carrying robot vision recognition system based on big data

Abstract

The present application relates to the technical fields of intelligent carrying robot, in particular to an intelligent carrying robot vision identification system based on big data, which comprises a vision hardware system and a vision software system, the vision hardware system comprises a camera, a robot body, a robot controller and an external industrial computer; the camera in the vision hardware system is combined by a mounting bracket, a mounting shaft, a connecting beam, a camera body and a dustproof module, an air chamber is formed in the side wall of the shell of the dustproof module, a diversion pipe is arranged at the edge of the air hole in the side wall of the air chamber, and a high-pressure aeration head is installed at the port of the diversion pipe, so that the lens direction of the camera body is constantly blown by the high-pressure aeration head, a wind wall is formed by the action of a circle of high-pressure aeration heads, dust is effectively prevented from entering the inside of the dustproof module and adhering to the lens of the camera body, and the identification accuracy of the camera body is effectively ensured.

Description

Technical Field

[0001] This invention relates to the technical field of intelligent handling robots, specifically to a visual recognition system for intelligent handling robots based on big data. Background Technology

[0002] Currently, the manufacturing industry has a demand for intelligent manufacturing, and both domestic and international manufacturers are beginning to upgrade their production lines to automation. Intelligent manufacturing, represented by robots, is meeting the transformation needs of the industry. Handling robots are no longer limited to traditional handling robots such as robotic arms and handling platforms. Endowing handling robots with various advanced sensing capabilities, such as touch, force, vision, and hearing, can make robots more intelligent. In particular, adding visual capabilities to robots greatly enhances their ability to perceive their environment and their level of intelligence.

[0003] Material handling refers to the use of equipment to hold workpieces and move them from one processing position to another. Material handling robots can be equipped with different end effectors to handle workpieces of various shapes and states, greatly reducing the burden of heavy manual labor. Currently, there are over 100,000 material handling robots in use worldwide, widely applied in machine tool loading and unloading, automated production lines for stamping machines, automated assembly lines, palletizing, and container handling. Some developed countries have established maximum limits for manual handling; tasks exceeding these limits must be performed by material handling robots. Material handling robots represent a high-tech advancement in the field of modern automatic control, involving disciplines such as mechanics, mechanical engineering, electrical, hydraulic, and pneumatic technologies, automatic control technology, sensor technology, microcontroller technology, and computer technology. They have become an important component of modern mechanical manufacturing systems. Their advantages include the ability to complete various pre-defined tasks through programming, combining the strengths of both humans and machines in their structure and performance, particularly demonstrating artificial intelligence and adaptability. Traditionally, robots are precisely taught to operate at various points and then execute tasks step-by-step in sequence. In this process, the workpiece's pose relative to the robot must be fixed. If the workpiece's pose changes, there will be a deviation between the actual pose and the preset pose, which may lead to the robot's operation failure. This requires the robot to have the ability to adapt to the environment. To this end, this invention proposes an intelligent handling robot visual recognition system based on big data to solve the above problems. Summary of the Invention

[0004] The purpose of this invention is to provide a visual recognition system for intelligent handling robots based on big data, so as to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a visual recognition system for intelligent handling robots based on big data, wherein the visual recognition system for intelligent handling robots based on big data includes a visual hardware system and a visual software system;

[0006] The vision hardware system includes a camera, a robot body, a robot controller, and an external industrial control computer. The robot controller is installed on the robot body, and both the robot controller and the camera are connected to the external industrial control computer via Ethernet.

[0007] The camera includes:

[0008] Mounting bracket, which is fixed to a bracket on the edge of the robot's running track;

[0009] Mounting shaft, which is connected to mounting bracket;

[0010] A connecting beam, wherein the connecting beam is fixedly connected to the end of the mounting shaft;

[0011] The camera body is fixed to the connecting beam;

[0012] The dustproof module has a spherical shell structure and an open front end. The lens of the camera body faces the opening on the dustproof module. A circular hole is provided on the rear end of the dustproof module. An installation tube is integrally formed on the dustproof module at the edge of the circular hole. The installation tube is rotatably mounted on the installation shaft through a primary sealing shaft and a secondary sealing bearing.

[0013] Preferably, the mounting shaft and the connecting beam are integrally formed, and the mounting shaft and the connecting beam are provided with cable routing grooves, in which cables are laid, and the camera body is electrically connected to the power supply through the cables.

[0014] Preferably, an air chamber is provided on the mounting shaft, and an air passage is provided on the lower side wall of the air chamber. The air passage is located between the primary sealing shaft and the secondary sealing bearing. An air chamber is provided in the side wall of the dustproof module housing. An air hole is provided on the inner side wall of the air chamber at the opening of the dustproof module. A directional pipe is fixedly connected to the dustproof module at the port of the air hole. A high-pressure aerator is connected to the port of the directional pipe. An air pipe connection port is provided on the mounting shaft at the port of the air chamber. The air pipe connection port is connected to an air pump through an air pipe.

[0015] Preferably, the steering pipe is a rigid pipe, the air holes are arranged in a circle around the opening of the dustproof module, and the high-pressure aeration head is arranged facing the center of the opening on the dustproof module.

[0016] Preferably, a reinforcing rod is integrally formed in the inner and outer walls of the air chamber, and multiple sets of the reinforcing rod are evenly arranged in the air chamber.

[0017] Preferably, a ring gear is fixedly installed on the outer wall of the mounting tube, a drive motor is fixedly installed on the mounting bracket, a transmission gear is fixedly installed on the output shaft of the drive motor, the transmission gear meshes with the ring gear, and the drive motor is a geared motor.

[0018] Preferably, the air inlet port of the air pump is equipped with a dust filter.

[0019] Preferably, the mounting bracket is composed of a primary bracket body, a secondary bracket body, and a tertiary bracket body. The primary bracket body is fixedly connected to the bracket at the edge of the robot's running track. The upper end of the primary bracket body and the lower end of the secondary bracket body are both integrally formed with primary connecting lugs. The drive motor is clamped and positioned between the primary bracket body and the secondary bracket body. The upper end of the secondary bracket body and the lower end of the tertiary bracket body are both integrally formed with secondary connecting lugs. The mounting shaft is clamped and positioned between the secondary bracket body and the tertiary bracket body.

[0020] Preferably, the vision software system runs on an external industrial control computer, and the vision software system includes:

[0021] The module includes a management module, an image processing module, a function package module, a result analysis and conversion module, and a communication module.

[0022] Preferably, the management module includes a user management module, an engineering file management module, and a log management module; the image processing module includes an image preprocessing module and an image feature extraction module; the function package module includes an image acquisition module, a camera calibration module, a hand-eye calibration module, a template matching module, an object classification and recognition module, and a plane measurement module; the result analysis and conversion module includes a coordinate conversion module and a feature analysis module; and the communication module includes an external industrial control computer communication module and a robot controller communication module.

[0023] Compared with the prior art, the beneficial effects of the present invention are:

[0024] 1. The robot learns environmental information through visual sensors, and then the computer processes the visual information to extract information that is useful to the robot, thereby guiding the robot's behavior and enabling the robot to better adapt to changes in the environment, thus improving the intelligence level of robot operations.

[0025] 2. Furthermore, the camera in the vision hardware system is configured to consist of a mounting bracket, a mounting shaft, a connecting beam, a camera body, and a dustproof module. An air chamber is formed in the side wall of the dustproof module's housing, and a deflector tube is installed at the edge of the air hole on the side wall of the air chamber. A high-pressure aeration head is installed at the port of the deflector tube. The high-pressure aeration head continuously blows air towards the lens of the camera body, forming an air wall through the action of a ring of high-pressure aeration heads. This effectively prevents dust from entering the dustproof module and adhering to the lens of the camera body, thus ensuring the recognition accuracy of the camera body. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of the structure of the present invention;

[0027] Figure 2 for Figure 1 Enlarged schematic diagram of the structure at point A in the middle;

[0028] Figure 3 This is a rear view of the present invention;

[0029] Figure 4 for Figure 3 Enlarged schematic diagram of the structure at point B;

[0030] Figure 5 This is a half-sectional view of the present invention;

[0031] Figure 6 for Figure 5 Enlarged schematic diagram of the structure at point C;

[0032] Figure 7 for Figure 5 Enlarged schematic diagram of the structure at point D;

[0033] Figure 8 for Figure 7 Enlarged schematic diagram of the structure at point E in the middle;

[0034] Figure 9 This is a schematic diagram of the mounting shaft structure of the present invention;

[0035] Figure 10 for Figure 9 Enlarged schematic diagram of the structure at point F;

[0036] Figure 11 This is a diagram of the vision software system of the present invention;

[0037] Figure 12 This is a flowchart of the handling and assembly operations of the present invention.

[0038] In the diagram: 1. Mounting bracket; 2. Mounting shaft; 3. Connecting beam; 4. Camera body; 5. Dustproof module; 6. Mounting pipe; 7. Primary sealing shaft; 8. Secondary sealing bearing; 9. Air chamber; 10. Air duct; 11. Air cavity; 12. Steering pipe; 13. High-pressure aeration head; 14. Cable tray; 15. Cable body; 16. Ring gear; 21. Drive motor; 22. Transmission gear; 23. Primary support body; 24. Secondary support body; 25. Tertiary support body; 26. Primary connecting ear plate; 27. Secondary connecting ear plate; 28. Air pipe connection port; 29. ​​Reinforcing rod; 30. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] Please see Figure 1-12 The present invention provides the following four preferred embodiments.

[0041] Example 1

[0042] The intelligent handling robot vision recognition system based on big data includes a vision hardware system and a vision software system. The vision hardware system includes a camera, a robot body, a robot controller, and an external industrial control computer. The robot controller is installed on the robot body. Both the robot controller and the camera are connected to the external industrial control computer via Ethernet. The camera includes a mounting bracket 1, a mounting shaft 2, a connecting beam 3, a camera body 4, and a dustproof module 5. The mounting bracket 1 is fixed on a bracket at the edge of the robot's running track. The mounting shaft 2 is connected to the mounting bracket 1. The connecting beam 3 is fixedly connected to the end of the mounting shaft 2. The camera body 4 is fixed on the connecting beam 3. The dustproof module 5 has a spherical shell structure, and the front end of the dustproof module 5 is open. The lens of the camera body 4 faces the opening on the dustproof module 5, and the rear end of the dustproof module 5 has a round hole. An installation tube 6 is integrally formed on the dustproof module 5 at the edge of the round hole. The installation tube 6 is rotatably mounted on the mounting shaft 2 through a primary sealing shaft 7 and a secondary sealing bearing 8.

[0043] The mounting shaft 2 and the connecting beam 3 are integrally formed, and the mounting shaft 2 and the connecting beam 3 are provided with a cable tray 15. The cable tray 15 is provided with a cable body 16, and the camera body 4 is electrically connected to the power supply through the cable body.

[0044] An air chamber 9 is provided on the mounting shaft 2, and an air passage 10 is provided on the lower side wall of the air chamber 9. The air passage 10 is located between the primary sealing shaft 7 and the secondary sealing bearing 8. An air chamber 11 is provided in the side wall of the housing of the dustproof module 5. An air hole 12 is provided on the inner side wall of the air chamber 11 at the opening of the dustproof module 5. A diverting pipe 13 is fixedly connected to the dustproof module 5 at the port of the air hole 12. A high-pressure aeration head 14 is connected to the port of the diverting pipe 13. An air pipe connection port 29 is provided on the mounting shaft 2 at the port of the air chamber 9. The air pipe connection port 29 is connected to the air pump through an air pipe.

[0045] The directional tube 13 is a rigid tube, and the air holes 12 are arranged in a circle around the opening of the dustproof module 5. The high-pressure aeration head 14 is set towards the center of the opening on the dustproof module 5. The camera in the vision hardware system is configured to be composed of a mounting bracket 1, a mounting shaft 2, a connecting beam 3, a camera body 4, and a dustproof module 5. An air chamber 11 is opened in the side wall of the dustproof module 5 housing, and the directional tube 13 is set at the edge of the air holes 12 on the side wall of the air chamber 11. The high-pressure aeration head 14 is installed at the port of the directional tube 13. The high-pressure aeration head 14 blows air continuously towards the lens of the camera body 4 through the high-pressure aeration head 14. The action of the high-pressure aeration head 14 forms a wind wall, which effectively prevents dust from entering the interior of the dustproof module 5 and adhering to the lens of the camera body 4, thereby effectively ensuring the recognition accuracy of the camera body 4.

[0046] A reinforcing rod 30 is integrally formed in the inner and outer walls of the air chamber 11. Multiple sets of reinforcing rods 30 are evenly arranged in the air chamber 11 to improve the overall strength of the dustproof module 5.

[0047] A ring gear 21 is fixedly installed on the outer wall of the mounting tube 6. A drive motor 22 is fixedly installed on the mounting bracket 1. A transmission gear 23 is fixedly installed on the output shaft of the drive motor 22. The transmission gear 23 meshes with the ring gear 21. The drive motor 22 is a geared motor.

[0048] Example 2

[0049] Based on Embodiment 1, a dust filter is provided at the air inlet port of the air pump to prevent the air blown out of the high-pressure aeration head 14 from containing dust.

[0050] Example 3

[0051] Based on Embodiment 2, the mounting bracket 1 is composed of a primary bracket body 24, a secondary bracket body 25, and a tertiary bracket body 26. The primary bracket body 24 is fixedly connected to the bracket at the edge of the robot's running track. The upper end of the primary bracket body 24 and the lower end of the secondary bracket body 25 are both integrally formed with primary connecting ear plates 27. The drive motor 22 is clamped and positioned between the primary bracket body 24 and the secondary bracket body 25. The upper end of the secondary bracket body 25 and the lower end of the tertiary bracket body 26 are both integrally formed with secondary connecting ear plates 28. The mounting shaft 2 is clamped and positioned between the secondary bracket body 25 and the tertiary bracket body 26, improving the overall ease of assembly and disassembly of the structure.

[0052] The vision software system runs on an external industrial control computer and includes: a management module, an image processing module, a function package module, a result analysis and conversion module, and a communication module. The management module includes a user management module, a project file management module, and a log management module. The image processing module includes an image preprocessing module and an image feature extraction module. The function package module includes an image acquisition module, a camera calibration module, a hand-eye calibration module, a template matching module, an object classification and recognition module, and a plane measurement module. The result analysis and conversion module includes a coordinate transformation module and a feature analysis module. The communication module includes an external industrial control computer communication module and a robot controller communication module. The robot obtains environmental information through vision sensors, and then the computer processes the visual information to extract information useful to the robot, thereby guiding the robot's behavior and enabling the robot to better adapt to changes in the environment, thus improving the intelligence level of robot operations.

[0053] Handling operation process:

[0054] Workpiece recognition and handling: First, control the robot to move to the pre-taught photo point. The controller sends a trigger signal to control the camera to collect images. After image processing, the workpiece is recognized and located. The workpiece's pose information is sent to the robot controller to control the robotic arm gripper to pick up the workpiece.

[0055] Positioning and workpiece placement: First, the robot moves to the camera point, the controller sends a trigger signal to control the camera to collect images, and after image processing, the workpiece is positioned so that the workpiece and the placement position are aligned.

[0056] Requirements for visual function;

[0057] Image acquisition: Activates the camera to display and acquire images in real time;

[0058] Image preprocessing: Performing operations such as filtering, enhancement, binarization, and morphological processing on the acquired images;

[0059] Image feature extraction: extracting features such as the edges and contours of objects;

[0060] Visual calibration: camera calibration and hand-eye calibration;

[0061] Object recognition and classification: identification of target parts and classification of multiple parts;

[0062] Planar measurement: measuring the length of a part;

[0063] Communication: Communication between the robot controller and the vision system. The controller sends a trigger signal to the vision system to acquire images, and the vision system sends the coordinate results to the controller.

[0064] Although the illustrative specific embodiments of this application have been described above to enable those skilled in the art to understand this application, this application is not limited to the scope of the specific embodiments. For those skilled in the art, all applications utilizing the concept of this application are protected as long as various variations are within the spirit and scope of this application as defined and determined by the appended claims.

Claims

1. A visual recognition system for intelligent handling robots based on big data, characterized in that: The intelligent handling robot visual recognition system based on big data includes a visual hardware system and a visual software system. The vision hardware system includes a camera, a robot body, a robot controller, and an external industrial control computer. The robot controller is installed on the robot body, and both the robot controller and the camera are connected to the external industrial control computer via Ethernet. The camera includes: Mounting bracket (1), which is fixed on a bracket at the edge of the robot's running track; Mounting shaft (2), which is connected to mounting bracket (1); A connecting beam (3) is fixedly connected to the end of the mounting shaft (2); Camera body (4), which is fixed on connecting beam (3); The dustproof module (5) is a spherical shell structure, and the front end of the dustproof module (5) is open. The lens of the camera body (4) faces the opening on the dustproof module (5), and the rear end of the dustproof module (5) is provided with a round hole. An installation tube (6) is integrally formed on the dustproof module (5) at the edge of the round hole. The installation tube (6) is rotatably mounted on the installation shaft (2) through a primary sealing shaft (7) and a secondary sealing bearing (8). An air chamber (9) is provided on the mounting shaft (2), and an air passage (10) is provided on the lower side wall of the air chamber (9). The air passage (10) is located between the primary sealing shaft (7) and the secondary sealing bearing (8). An air chamber (11) is provided in the side wall of the housing of the dustproof module (5). An air hole (12) is provided on the inner side wall of the air chamber (11) at the opening of the dustproof module (5). A directional pipe (13) is fixedly connected to the port of the air hole (12) on the dustproof module (5). A high-pressure aeration head (14) is connected to the port of the directional pipe (13). An air pipe connection port (29) is provided on the mounting shaft (2) at the port of the air chamber (9). The air pipe connection port (29) is connected to the air pump through an air pipe. The turning pipe (13) is a rigid pipe, the air hole (12) is arranged in a circle around the opening of the dustproof module (5), and the high-pressure aeration head (14) is arranged facing the center of the opening of the dustproof module (5). A reinforcing rod (30) is integrally formed in the inner and outer walls of the air chamber (11), and multiple sets of the reinforcing rod (30) are evenly arranged in the air chamber (11).

2. The intelligent handling robot visual recognition system based on big data as described in claim 1, characterized in that: The mounting shaft (2) and the connecting beam (3) are integrally formed, and the mounting shaft (2) and the connecting beam (3) are provided with cable trays (15). Cables (16) are arranged in the cable trays (15), and the camera body (4) is electrically connected to the power supply through the cables.

3. The intelligent handling robot visual recognition system based on big data according to claim 2, characterized in that: A ring gear (21) is fixedly installed on the outer wall of the mounting tube (6), a drive motor (22) is fixedly installed on the mounting bracket (1), a transmission gear (23) is fixedly installed on the output shaft of the drive motor (22), the transmission gear (23) meshes with the ring gear (21), and the drive motor (22) is a reduction motor.

4. The intelligent handling robot visual recognition system based on big data as described in claim 3, characterized in that: The air pump is equipped with a dust filter at its air inlet port.

5. The intelligent handling robot visual recognition system based on big data according to claim 4, characterized in that: The mounting bracket (1) is composed of a primary bracket body (24), a secondary bracket body (25) and a tertiary bracket body (26). The primary bracket body (24) is fixedly connected to the bracket at the edge of the robot running track. The upper end of the primary bracket body (24) and the lower end of the secondary bracket body (25) are integrally formed with a primary connecting ear plate (27). The drive motor (22) is clamped and positioned between the primary bracket body (24) and the secondary bracket body (25). The upper end of the secondary bracket body (25) and the lower end of the tertiary bracket body (26) are integrally formed with a secondary connecting ear plate (28). The mounting shaft (2) is clamped and positioned between the secondary bracket body (25) and the tertiary bracket body (26).

6. The intelligent handling robot visual recognition system based on big data according to claim 5, characterized in that: The vision software system runs on an external industrial control computer, and the vision software system includes: The module includes a management module, an image processing module, a function package module, a result analysis and conversion module, and a communication module.

7. The intelligent handling robot visual recognition system based on big data as described in claim 6, characterized in that: The management module includes a user management module, a project file management module, and a log management module. The image processing module includes an image preprocessing module and an image feature extraction module. The function package module includes an image acquisition module, a camera calibration module, a hand-eye calibration module, a template matching module, an object classification and recognition module, and a plane measurement module. The result analysis and conversion module includes a coordinate conversion module and a feature analysis module. The communication module includes an external industrial control computer communication module and a robot controller communication module.

Images