Laser weeding robot and operation method therefor
The laser weeding robot, with its high-ground-clearance four-wheel four-turn structure and Beidou satellite navigation, combined with machine vision and laser galvanometer control, solves the problems of existing laser weeding robots being easily damaged and causing harm to crops, and achieves efficient and environmentally friendly weeding operations.
Patent Information
- Application Number
- PCT/CN2024/111634
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-04-17
- Filing Date
- 2024-08-13
- Publication Date
- 2025-10-23
AI Technical Summary
Existing laser weeding robots have problems such as easy damage to the laser, low control accuracy, low intelligence, and serious damage to crops, making it impossible to achieve efficient and environmentally friendly weeding operations.
The robot body adopts a high-ground-clearance four-wheel four-rotation structure, combined with Beidou satellite navigation and machine vision system, uses a 10600nm CO2 laser and laser galvanometer to control the laser light path, and is equipped with a flat-field focusing lens and a high-speed industrial camera to achieve precise weeding.
It realizes fully automatic weeding operations, avoids damage to crops, improves weeding efficiency and accuracy, reduces energy consumption and environmental pollution, and protects crops and the environment.
Smart Images

Figure CN2024111634_23102025_PF_FP_ABST
Abstract
Description
Laser weeding robot and working method thereof TECHNICAL FIELD
[0001] The present application relates to the technical field of mechanical automation, in particular to a laser weeding robot and a working method thereof. BACKGROUND
[0002] Existing weeding methods and disadvantages: Modern weeding methods mainly include spraying and mechanical weeding. Spraying refers to spraying chemical agents in the field to kill weeds through the action of the agents. This method can improve weeding efficiency, but also has an impact on the environment and ecology, because chemical agents can pollute the soil and water sources, and over time can also lead to weed resistance, greatly reducing weeding effectiveness. Another modern weeding method is mechanical weeding, which mainly uses rotating blades to remove weeds, which can quickly and efficiently clean the weeds in the field, but is prone to mechanical damage to crop seedlings.
[0003] Laser weeding, as a new environmentally friendly weeding method, is gradually gaining attention. Laser weeding uses a laser beam to directly irradiate weeds, burning the leaves of the weeds through high temperature, achieving the effect of weeding. This method does not require chemical agents and does not produce noise and air pollution, has less impact on the soil and water sources, and has high environmental friendliness and sustainability.
[0004] Existing laser weeding machines and disadvantages:
[0005] The laser weeding robot of patent (CN117652480A) mainly controls the position of the laser and the direction of the emitted laser with a mechanical structure, and the internal laser emitter is a glass laser tube. Frequent movement of the laser can easily damage the laser tube, and the speed and direction of the laser beam are not easy to accurately control, which seriously affects the normal use of the robot.
[0006] The laser weeding robot of patent (CN220384097U) uses a tracked chassis. Since laser weeding robots are currently mainly used for high-value crops such as organic vegetables, the tracked structure has a large contact area with the ground, which can cause more compaction on the crops and land, affecting crop yield and later land preparation. The patent only supports remote remote walking and touch screen operation walking, and has very low intelligence, and can only be considered a laser weeding machine.
[0007] The laser weeding robot of patent (CN101589705A) uses a mechanical moving focusing lens to control the laser light path. The significant shortcoming of this scheme is low control precision and slow control speed, which cannot improve weeding efficiency.
[0008] SUMMARY
[0009] In order to solve the above technical problems, the present application provides the following technical solutions: a laser weeding robot and a working method thereof.
[0010] The laser weeding robot comprises a robot body, a positioning device, a computing power unit, an image acquisition component, a laser emission and light path control component.
[0011] The robot body is of a four-wheel four-rotation structure and comprises four motors for controlling walking and four motors for controlling turning, each motor being provided with a separate motor driver, and the operation of each motor being independently controllable, the robot body being provided with a bearing platform, and a battery being installed on the bearing platform, and the motor driver being connected with the battery.
[0012] The positioning device comprises two GNSS antennas, a Beidou satellite navigation receiver, an IMU and a binocular camera, the two GNSS antennas being respectively installed at front and rear positions of the robot body, the IMU being installed on the bearing platform, and the binocular camera being installed at a front position in the walking direction of the robot, for dynamically adjusting a working path according to the arrangement of crops extracted from a crop row, and the two GNSS antennas being respectively connected with the Beidou satellite navigation receiver.
[0013] The computing power unit is a small computer for positioning calculation, walking control, image recognition, laser control and network communication, the computing power unit being connected with the battery, and the motor driver, the Beidou satellite navigation receiver, the IMU and the binocular camera being respectively connected with the computing power unit.
[0014] The image acquisition component comprises a high-speed industrial camera, which is installed below the bearing platform, and the high-speed industrial camera being connected with the computing power unit.
[0015] The laser emission and light path control component comprises a laser, a laser galvanometer mirror, a flat-field focusing lens, a laser driver board and a galvanometer mirror driver board, the flat-field focusing lens being installed at a light outlet position of the laser galvanometer mirror, the laser being connected with the laser driver board, the laser galvanometer mirror being connected with the galvanometer mirror driver board, and the laser driver board and the galvanometer mirror driver board being respectively connected with the battery and the computing power unit.
[0016] Preferably, the robot body is of a telescopic structure in the left-right, up-down and front-rear directions.
[0017] Preferably, the task issuing platform is further provided, and the computing power unit is connected with the task issuing platform through a wireless network.
[0018] Preferably, the battery is provided with a battery management system.
[0019] Preferably, the positioning device further comprises a laser radar installed above the bearing platform and connected with the computing power unit.
[0020] Preferably, the two GNSS antennas are respectively connected with the Beidou satellite navigation receiver through GNSS coaxial cables.
[0021] Preferably, the robot body is installed with light shielding cloth around.
[0022] Preferably, the image acquisition component further comprises two LED fill light lamps and an LED drive board, the two LED fill light lamps are respectively installed on the left and right sides of the high-speed industrial camera to assist in weed image acquisition, the two LED fill light lamps are connected with the LED drive board, and the LED drive board is connected with the battery.
[0023] Preferably, the laser is a CO2 laser with a wavelength of 10600nm.
[0024] A working method of a laser weeding robot, the laser weeding robot comprising any one of the laser weeding robots in the preceding 3-9, the method comprising the following steps:
[0025] S1. The telescopic structure of the robot body is manually adjusted according to the row spacing and height of the crops in the farmland, and the robot power is turned on after adjustment to meet the requirements of the working task and be in a ready state;
[0026] S2. The task issuing platform issues a working task to the robot, the computing power unit automatically plans a warehouse path, a working path and a warehouse entry path according to the farmland position in the task, and controls the motor driver according to the planned path, thereby controlling the robot to walk;
[0027] S3. The robot walks and works according to the planned working path, and simultaneously adjusts the working path dynamically according to the crop arrangement mode extracted from the crop row by the binocular camera during the working process;
[0028] S4. In the operation process, the computing unit automatically identifies weeds in crops according to image information provided by the high-speed industrial camera, and quickly calculates the three-dimensional relative coordinates of the weeds, while the computing unit sends control instructions to the laser galvanometer drive board to control the laser galvanometer to rotate to the direction corresponding to the weeds, after the rotation, the computing unit sends control instructions to the laser drive board to make the laser emit laser to irradiate the weeds, after the operation of the entire farmland, the robot returns to the hangar according to the storage path, and thus completes a complete weeding operation.
[0029] A computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method when executing the computer program.
[0030] A computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the method.
[0031] The application provides a laser weeding robot based on Beidou satellite navigation, wherein the robot body is a high-clearance four-wheel four-rotation walking platform, the laser light path is controlled by a laser galvanometer, and a CO2 laser with a wavelength of 10600nm is used as the laser.
[0032] Compared with the prior art, the application has the following beneficial effects:
[0033] 1. Based on Beidou satellite navigation, the robot can realize automatic planning and automatic execution of the whole path from the hangar to the field and the operation in the field, without additional manual operation.
[0034] 2. The robot is provided with a machine vision system in front, and can realize accurate row-by-row walking based on crop planting arrangement, so that even if the sowing accuracy is low, the crops will not be damaged.
[0035] 3. The robot body is a high-clearance four-wheel four-rotation structure, the high clearance can realize operation of crops with different heights, and the four-wheel four-rotation structure can realize parallel movement in the field, and in combination with the accurate row-by-row walking of the machine vision, the crops can be operated without damage.
[0036] 4. The four-wheel four-rotation structure of the robot body can realize stretching and contracting in front, back, left, right and up and down directions, so that users can satisfy operation of crops with different row distances and different crop heights.
[0037] 5. The laser adopts a CO2 laser with a wavelength of 10600nm, and the laser in this frequency band belongs to the far-infrared band in the spectrum and is most easily absorbed by organic tissues, so that the laser action energy efficiency is improved, and the operation energy consumption is further reduced.
[0038] 6. The light path control of the laser is completed by a laser galvanometer, and the laser remains fixed during the weeding process, avoiding damage caused by moving the laser, the laser galvanometer can quickly and accurately control the light path of the laser, reduce the additional cost caused by the damage of the laser, and meanwhile, the high-precision control of the galvanometer can reduce the injury to the main crops.
[0039] 7. An F-theta lens is arranged at the light outlet of the laser galvanometer, and after the laser passes through the lens, a uniform size of focused light spot is formed, the problem of off-axis deflection of the laser beam is solved, the laser energy is more focused, the operation effect is improved, and the energy consumption is reduced.
[0040] 8. A high-speed industrial camera is installed below the robot body bearing platform, and the angle between the camera lens axis and the robot body can be preset according to the height of the weeds, so that the weeds at different heights can be quickly identified.
[0041] 9. High-brightness LED fill light lamps are arranged on the left and right sides of the industrial camera, which are used to assist the industrial camera in collecting high-definition images of crops and weeds.
[0042] 10. An opaque shade cloth is arranged around the robot body, which is used to prevent the reflected laser beam from causing harm to the human body.
[0043] 11. The laser is used to irradiate the weeds with high intensity, high density and high energy in a short time, so that the weeds are heated and shrunk, and the weeds are killed, the whole weeding process is efficient, fast and pollution-free, the dead weeds left in the farmland can be used as fertilizer to provide value for crops, a large amount of manual labor is saved, the health of farmers is protected, the use of pesticides is reduced, and the environment is protected. BRIEF DESCRIPTION OF DRAWINGS
[0044] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, and are used together with embodiments of the present application to explain the present application, and do not constitute a limitation on the present application. In the drawings:
[0045] Fig. 1 is a schematic view of the robot body structure of the embodiment of the present application;
[0046] Fig. 2 is a schematic view of the front, rear, left, right, up and down adjustable structure of the robot body of the embodiment of the present application;
[0047] Fig. 3 is a system connection mode of the embodiment of the present application;
[0048] Fig. 4 is a visual line alignment schematic view of the embodiment of the present application;
[0049] Fig. 5 is a schematic view of the global automatic operation path planning of the embodiment of the present application.
[0050] Among them, 1 GNSS antenna; 2 LiDAR; 3 Binocular camera; 4 Left and right telescopic structure; 5 Up and down telescopic structure; 6 Front and back telescopic structure; 7 Walking motor; 8 Steering motor. DETAILED DESCRIPTION
[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.
[0052] This embodiment provides a laser weeding robot.
[0053] The laser weeding robot includes a robot body, a positioning device, a computing unit, an image acquisition component, a laser emission and light path control component (as shown in FIG1 ).
[0054] The robot body has a four-wheel four-rotor structure, including four motors for controlling walking (walking motors 7) and four motors for controlling steering (steering motors 8). Each motor is equipped with a separate motor driver, and the operation of each motor can be independently controlled.
[0055] The robot body has a carrying platform, on which a battery, a battery management system, and a motor driver are installed (as shown in FIG1 ).
[0056] The motor is connected to the motor driver, and the motor driver is connected to the battery.
[0057] The left and right, up and down, front and back of the robot body are designed to be retractable structures, specifically including: left and right retractable structure 4; up and down retractable structure 5; front and back retractable structure 6, which are used to meet the needs of operations with different crop row spacing and different crop heights (as shown in Figure 2).
[0058] The robot body is surrounded by shading cloth to prevent possible damage to the human body caused by the reflected laser beam.
[0059] The positioning device includes two GNSS antennas 1, a Beidou satellite navigation receiver, an IMU, a binocular camera 3, and an optional lidar 2. The two GNSS antennas are installed in front and behind the robot body, respectively. The IMU is installed anywhere on the robot's platform. The binocular camera is installed in front of the robot in the direction of travel. The lidar is installed above the platform (as shown in Figure 1).
[0060] The two GNSS antennas are respectively connected to the Beidou satellite navigation receiver via GNSS coaxial cables.
[0061] The computing unit is a small computer for positioning calculation, walking control, image recognition, laser control, and network communication. Its connection mode with other components is shown in FIG. 3. The computing unit is connected with the battery mounted on the carrying platform. The computing unit is connected with the task issuing platform through a wireless network.
[0062] The Beidou satellite navigation receiver, the IMU, the binocular camera, and the laser radar are respectively connected with the computing unit.
[0063] The image acquisition component includes a high-speed industrial camera, two LED fill light lamps, and an LED drive board.
[0064] The high-speed industrial camera is connected with the computing unit, the LED fill light lamp is connected with the LED drive board, and the LED drive board is connected with the battery mounted on the carrying platform.
[0065] The high-speed industrial camera is mounted below the carrying platform, and the camera lens axial angle with the robot body can be adjusted by adjusting the mounting structure to realize the recognition of weeds at different heights.
[0066] The two LED fill light lamps are respectively mounted on the left and right sides of the high-speed industrial camera to assist in weed image acquisition.
[0067] The laser emission and light path control component includes a laser, a laser galvanometer, a flat-field focusing lens, a laser drive board, and a galvanometer drive board.
[0068] The laser is a CO2 laser with a wavelength of 10600 nm.
[0069] The laser galvanometer and the laser can be combined and mounted.
[0070] The flat-field focusing lens is mounted at the light outlet position of the laser galvanometer.
[0071] The laser is connected with the laser drive board, the laser galvanometer is connected with the galvanometer drive board, the laser drive board and the galvanometer drive board are respectively connected with the battery mounted on the carrying platform. The laser drive board and the galvanometer drive board are respectively connected with the computing unit.
[0072] Operation process:
[0073] First, manually adjust the telescopic structure of the robot body according to the row spacing and height of the crops in the farmland, and turn on the robot power after adjusting to the requirements of the operation task to be in a ready state.
[0074] The weeding robot parked in the garage receives the task issued by the task issuing platform. The computing unit automatically plans the garage path, the operation path and the garage path according to the farmland position in the task (as shown in FIG. 5), and controls the motor driver according to the planned path, so as to control the robot to walk. If it is a non-open-air garage, the robot calculates its position in the garage according to the laser radar. After leaving the garage, the robot automatically walks according to the position provided by the Beidou navigation receiver. If it is an open-air garage, the position of the robot is always provided by the Beidou navigation receiver.
[0075] After reaching the farmland, the robot walks and works according to the planned operation path, and dynamically adjusts the operation path according to the crop arrangement mode extracted from the crop row by the binocular camera during the operation (as shown in FIG. 4), so as to avoid the situation of crushing crops.
[0076] During the operation, the computing unit automatically identifies weeds in the crops according to the image information provided by the high-speed industrial camera, and quickly calculates the three-dimensional relative coordinates of the weeds. At the same time, the computing unit sends control instructions to the galvanometer drive board to control the galvanometer to rotate to the direction corresponding to the weeds. After rotation, the computing unit sends control instructions to the laser driver board to make the laser emit laser to irradiate the weeds. After the operation of the entire farmland, the robot returns to the garage according to the garage path, thereby completing a complete weeding operation. After the task is issued, the whole operation is automatic, without remote control and manual intervention.
[0077] It should be noted that, in this text, relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the term "includes", "contains" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or equipment.
[0078] Finally, it should be noted that: the above only describes the preferred embodiments of the present application, and is not used to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.
Claims
1. A laser weeding robot, characterized by, The robot body, the positioning device, the computing unit, the image acquisition component, the laser emission and light path control component are included. The robot body is a four-wheel four-turn structure, including four motors for controlling walking and four motors for controlling turning, each motor is configured with a separate motor driver, the operation of each motor can be independently controlled, the robot body is provided with a bearing platform, a battery is installed on the bearing platform, the motor driver is connected with the battery. The positioning device includes two GNSS antennas, a Beidou satellite navigation receiver, an IMU, and a binocular camera, the two GNSS antennas are respectively installed at the front and rear positions of the robot body, the IMU is installed on the bearing platform, and the binocular camera is installed in front of the robot walking direction, which is used to dynamically adjust the operation path according to the arrangement of the crops extracted from the crop row, the two GNSS antennas are respectively connected with the Beidou satellite navigation receiver. The computing unit is a small computer for positioning calculation, walking control, image recognition, laser control and network communication, the computing unit is connected with the battery, and the motor driver, the Beidou satellite navigation receiver, the IMU and the binocular camera are respectively connected with the computing unit. The image acquisition component includes a high-speed industrial camera installed below the bearing platform, and the high-speed industrial camera is connected with the computing unit. The laser emission and light path control component includes a laser, a laser galvanometer, a flat-field focusing lens, a laser driver board and a galvanometer drive board, the flat-field focusing lens is installed at the light outlet position of the laser galvanometer, the laser is connected with the laser driver board, the laser galvanometer is connected with the galvanometer drive board, and the laser driver board and the galvanometer drive board are respectively connected with the battery and the computing unit.
2. The laser weeding robot according to claim 1, characterized in that, The left and right, up and down, front and back of the robot body are telescopic structures.
3. The laser weeding robot according to claim 2, wherein, The task issuing platform is further included, and the computing unit is connected with the task issuing platform through a wireless network.
4. The laser weeding robot according to claim 3, wherein, The battery is provided with a battery management system.
5. The laser weeding robot according to claim 3, wherein, The positioning device further includes a laser radar installed above the bearing platform and connected with the computing unit.
6. The laser weeding robot according to claim 3, wherein, The two GNSS antennas are respectively connected with the Beidou satellite navigation receiver through GNSS coaxial cables.
7. The laser weeding robot according to claim 3, wherein, The robot body is provided with a light shielding cloth around.
8. The laser weeding robot according to claim 3, wherein, The image acquisition component further includes two LED fill light lamps and an LED drive board, the two LED fill light lamps are respectively installed on the left and right sides of the high-speed industrial camera to assist in weed image acquisition, the two LED fill light lamps are connected with the LED drive board, and the LED drive board is connected with the battery.
9. The laser weeding robot according to claim 3, wherein, The laser is a CO2 laser with a wavelength of 10600nm.
10. A method of operating a laser weeding robot, characterized by, The laser weeding robot includes any one of the laser weeding robots in claims 3-9, and the method includes the following steps: S1. According to the row spacing of the crop in the farmland and the height of the crop, the telescopic structure of the robot body is manually adjusted to the requirements of the operation task, and the robot power is turned on to be in a ready state after adjustment; S2. The task issuing platform issues the operation task to the robot, the computing power unit automatically plans the warehouse path, the operation path and the warehouse entry path according to the farmland position in the task, and controls the motor driver according to the planned path, so as to control the robot to walk; S3. The robot walks and operates according to the planned operation path, and dynamically adjusts the operation path according to the crop arrangement mode extracted from the crop row by the binocular camera during operation; S4. During operation, the computing power unit automatically identifies weeds in the crop according to the image information provided by the high-speed industrial camera, and quickly calculates the three-dimensional relative coordinates of the weeds, at the same time, the computing power unit sends control instructions to the laser galvanometer drive board to control the laser galvanometer to rotate to the direction corresponding to the weeds, after rotation, the computing power unit sends control instructions to the laser driver board to make the laser emit laser to irradiate the weeds, after the operation of the whole farmland, the robot returns to the hangar according to the warehouse entry path, thus completing a complete weeding operation. 11.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-10 when the computer program is executed by the processor. The processor executes the computer program to realize the steps of the method of claim 10.
12. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method of claim 10.
Citation Information
Patent Citations
Laser weeding robot
CN101589705A
Laser weeding robot
CN117652480A
Laser weeding robot
CN220384097U
Intelligent laser weeding device and method based on machine vision
CN116250523A
Cordyceps sinensis laser removing method and laser cordyceps sinensis removing machine
CN117296644A