Weeding machine

Abstract

The utility model provides a weeding machine, and belongs to the field of agricultural machinery. The problem that alignment is inaccurate in the traditional weeding alignment process is solved. A weeding machine comprises a weeding machine body, the front side of the weeding machine body is connected with a moving vehicle, and the moving vehicle is used for driving the weeding machine body to walk; the multi-mode vision assembly is arranged on the front side of the weeding machine body and used for collecting picture information and depth information of seedlings and weeds; the weeding translation mechanism is connected with the weeding machine body, and a weeding assembly is arranged on the near-ground side; the fixed end of the translation driving assembly is connected with the weeding machine main body, and the movable end is connected with the weeding translation mechanism for driving the weeding translation mechanism to act; and the controller is used for responding to a signal of the multi-mode vision assembly to control the translation driving assembly to drive the weeding translation mechanism and the weeding assembly to act. The weeding machine is mainly used for weeding.

Description

Technical Field

[0001] The utility model belongs to the field of agricultural machinery, in particular to a weeder. Background Art

[0002] In agriculture, weed control is crucial, directly impacting crop growth and yield. Traditional weed control methods, such as manual weeding, chemical weed control, and mechanical weed control, all have limitations. Manual weed control is inefficient and labor-intensive; while chemical weed control is highly effective, it can pollute the environment, and long-term use can lead to weed resistance; and mechanical weed control can be imprecise and damage crops.

[0003] To address these issues, the research and development of intelligent weeding robots has become a key area of ​​agricultural science and technology development. Key technologies for intelligent weeding robots include intelligent sensing, a robotic platform, and a mechanical weeding device. Intelligent sensing primarily distinguishes crops from weeds through crop row and weed recognition technologies. The design of the robotic platform must consider weeding efficiency across different crops and operating environments. Common robot platforms include wheeled, tracked, legged, and hybrid models. The design of the mechanical weeding device, as the robot's end effector, directly impacts weeding effectiveness.

[0004] With technological advancements, the future development trends of intelligent weeding robots will focus on four key areas: intelligent perception, precision weeding, efficient operations, and smart management. Intelligent perception technology will provide more comprehensive information about farmland environments through multi-sensor information fusion. Precision weeding will combine robotics and automatic control technologies to achieve high-precision weeding. Efficient operations will improve the quality and efficiency of weeding through artificial intelligence. Smart management will leverage technologies such as the Internet of Things, big data, and cloud computing to enable remote monitoring and intelligent decision-making of robotic operations.

[0005] In addition, some advanced agricultural robotics companies, such as FarmWise, are developing AI-powered weeding robots that use image recognition technology to identify and remove weeds in fields, thereby reducing the use of chemical herbicides.

[0006] In image recognition technology, when image information is used for comparison, there may be cases of misidentification. This is because when there are many weeds and sunlight is shining, the shadows of the seedlings will have a certain impact on the identification of the seedling strip, thereby causing certain difficulties in the weeding alignment process. Utility Model Content

[0007] In view of this, the present invention aims to provide a weeder to solve the problem of inaccurate positioning in the traditional weeding positioning process.

[0008] To achieve the above-mentioned purpose, the present invention adopts the following technical solutions to provide a weed remover, including:

[0009] The front side of the weeder body is connected to a moving vehicle, and the moving vehicle is used to drive the weeder body to move;

[0010] A multimodal vision component is located on the front of the weeder body and is used to collect image and depth information of seedlings and weeds.

[0011] A weeding translation mechanism is connected to the main body of the weeder, and a weeding assembly is provided on the ground side;

[0012] A translation drive assembly, the fixed end of which is connected to the weeder body, and the movable end of which is connected to the weeding translation mechanism for driving the weeding translation mechanism;

[0013] The controller is used to respond to the signal of the multimodal vision component to control the translation drive component to drive the weeding translation mechanism and the weeding component to move.

[0014] Furthermore, the multimodal vision components are provided in two and are distributed on both sides of the lawn mower body.

[0015] Furthermore, the multimodal vision component includes an RGB camera and a depth-of-field camera.

[0016] Furthermore, the multimodal vision component is connected to the lawn mower body via a camera bracket, wherein the camera bracket is a telescopic bracket.

[0017] Furthermore, the translation drive assembly is a hydraulic push rod.

[0018] Furthermore, two hydraulic push rods are provided and are symmetrically distributed on both sides of the weeding translation mechanism.

[0019] Furthermore, the weeding translation mechanism is provided with a displacement sensor for collecting its position, and the displacement sensor is connected to the controller.

[0020] Furthermore, the main body of the lawn mower is provided with a ground wheel, the ground wheel is provided with a Hall sensor, and the Hall sensor is connected to the controller.

[0021] Furthermore, a floor proximity switch is provided on the weeding component. The floor proximity switch has no signal when the weeding component is out of the weeding state and has a signal when the weeding component is in the weeding state. The floor proximity switch is connected to the controller.

[0022] Furthermore, the mobile vehicle is a tractor.

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

[0024] 1. The utility model adopts the following technical solutions: a weeder body, used to drive the weeder to move; a multimodal vision component, arranged on the front side of the weeder body, used to collect image information and depth information of seedlings and weeds; a weeding translation mechanism, connected to the weeder body, and a weeding component is arranged on the ground side; a translation drive component, the fixed end of which is connected to the weeder body, and the movable end is connected to the weeding translation mechanism for driving the weeding translation mechanism to move; a controller, used to respond to the signal of the multimodal vision component to control the translation drive component to drive the weeding translation mechanism and the weeding component to move. It can collect image information and depth information through the multimodal vision component and compare it with the database in the controller. After the comprehensive detection of the outline, texture, color and other multi-information of the seedlings, it can accurately identify the location of the seedlings in the current scene, and then drive the weeding translation mechanism to move through the translation drive component, thereby ultimately changing the position of the weeding component, so that the weeding component can be adjusted accordingly according to the position of the seedling belt, thereby improving the accuracy of weeding and preventing the occurrence of accidental damage to the seedlings. In scenes with a lot of weeds, since the weeds are in rows of data, the template matching method of the existing technology cannot find regular row data or there are multiple regular row data, resulting in deviations in the seedling belt matching and recognition or the inability to align the rows, thereby causing the controlled tool position to be not in the middle of the two rows of seedling belts, resulting in damage to the seedlings. The above solution can well solve the technical problem of inaccurate positioning;

[0025] 2. By incorporating a depth-of-field camera, this weeder avoids the traditional method of weeding, which creates lateral shadows when the seedlings are exposed to sunlight, causing the seedlings and shadows to match as a whole, resulting in a widened seedling belt and a deviation in the weeding position. The depth-of-field camera can identify seedling height information in addition to the outline, texture, and color of the seedlings. Because the shadows are projected onto the ground, there is no height difference information from the ground. This can more accurately solve the recognition defects of the original technology and improve the accuracy of seedling recognition in complex scenes.

[0026] 3. In high-light conditions, the existing technology using a single RGB camera cannot capture the status of the seedlings. To address this, a depth camera is used to directly identify the outline and position of the seedlings and perform corresponding processing, improving the applicability of the weeder.

[0027] 4. This lawn mower is equipped with a floor proximity switch, which can control whether the multimodal vision component performs recognition based on the presence or absence of a signal, thereby preventing the multimodal vision component from always being in working state and improving the operating economy of the lawn mower. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings, which constitute part of the present invention, are intended to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are intended to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0029] Figure 1 This is a front view of a weeder according to the utility model;

[0030] Figure 2 This is a top view of a weeder according to the utility model;

[0031] Figure 3 This is a side view of a weeder according to the utility model;

[0032] Figure 4 This is an axonometric drawing of a weeder according to the present utility model;

[0033] Figure 5 This is a structural diagram of the weeding translation mechanism of the present invention;

[0034] Figure 6 This is a structural diagram of the hydraulic push rod described in the utility model;

[0035] Figure 7 This is a diagram showing the relative positions of the ground wheel and the Hall sensor of the present invention;

[0036] Figure 8 This is a schematic diagram of the structure of the multimodal vision component described in the present invention;

[0037] Figure 9 This is a schematic diagram of the structure of the controller described in the present utility model;

[0038] Figure 10 This is a schematic diagram of the structure of the HMI touch screen described in the present utility model;

[0039] Figure 11-13 This is a schematic diagram of the control principle of the weed control method used in the present invention.

[0040] Multimodal vision component 1; controller 2; weeding translation mechanism 3; weeding component 4; ground wheel 5; displacement sensor 6; Hall sensor 7; floor proximity switch 8; HMI touch screen 9; camera bracket 10; hydraulic push rod 11; weeder body 12. DETAILED DESCRIPTION

[0041] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely explain the technical solutions in the embodiments of the present invention. It should be noted that the embodiments and features in the embodiments of the present invention can be combined with each other in the absence of conflict, and the embodiments described are only part of the embodiments of the present invention, not all of the embodiments.

[0042] It should be noted that the descriptions of directions such as "left," "right," "left side," "right side," "upper," "lower," "top," and "bottom" in this utility model are defined based on the orientations or positions shown in the accompanying drawings. These are intended solely to facilitate the description of this utility model and to simplify the description. They do not indicate or imply that the structure described must be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this utility model. In the description of this utility model, "plurality" means more than two, unless otherwise specifically defined.

[0043] In the description of this utility model, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; they may refer to direct connections, indirect connections through an intermediate medium, or internal communication between two components. Those skilled in the art will understand the specific meanings of these terms in this utility model based on the specific circumstances.

[0044] Referring to the accompanying drawings, this embodiment is described, which provides a weeder, comprising:

[0045] The weeder body 12 is connected to a moving vehicle at its front side. The moving vehicle is used to drive the weeder body 12 to move, thereby helping the weeding process to be completed smoothly.

[0046] The multimodal visual component 1 is arranged on the front side of the lawn mower body 12 and is used to collect image information and depth information of seedlings and weeds; wherein, the image information and depth information include a variety of information such as the outline, texture, color, etc. of the seedlings, and the depth information can help improve accuracy. The length, width and height of the lawn mower body 12 are 7088mm, 2475mm and 1828mm, and the main beam of the lawn mower is made of Q345 low alloy steel, which has excellent mechanical properties, low temperature properties and processing properties. The weeding blade is made of 65Mn material, which has high toughness and wear resistance in the quenched state. The controller 2 is also electrically connected to the fifth generation mobile communication technology, and can upload the current real-time working status and position of the lawn mower to the cloud server for display and storage, making it convenient for managers to view the lawn mower status and historical records.

[0047] The weeding translation mechanism 3 is connected to the weeder body 12, and a weeding assembly 4 is provided on the ground side. The weeding assembly 4 used in this application is specifically a twelve-way weeding unit, which can also be increased or decreased according to actual needs. The twelve-way weeding unit uses a plunger cylinder and four-link profiling technology to achieve consistent pressure on the ground of multiple units, thereby ensuring consistent weeding depth. On the basis of not damaging the twelve seedling strips, the weeds between the rows in the ridge are processed separately. The position of the weeding assembly 4 can be adjusted by the weeding translation mechanism 3, and the position of the weeding assembly 4 can be adjusted as a whole. Because the relative distance between the seedling strips is fixed, the relative distance between each group of weeding cutters in the weeding assembly 4 is fixed, so after the overall adjustment, each seedling strip can be accurately processed accordingly. The weeding translation mechanism 3 is specifically connected to the weeder body 12 by a three-point suspension method through a positioning and suppressing wheel mechanism. Other connection methods can also be used for connection according to actual needs. The specific structure of the weeding translation mechanism 3 is a fixed C-beam and a movable base structure. The movable base structure can slide relative to the weeder body 12 within the C-beam via three sets of pulleys. There is no creeping or shaking during movement, ensuring the stability of the mechanism's translation. When the translation drive assembly is driven by two hydraulic push rods 11, they are distributed on both sides of the movable base. The specific connection form is selected according to actual conditions. The offset result is calculated by the multimodal vision and machine learning algorithm controller device, that is, the controller 2. The multimodal vision and machine learning algorithm controller controls the left hydraulic push rod or the right hydraulic push rod to push the twelve-way weeding unit, so that the weeding blade can be dynamically adjusted to the center position of the two seedling strips.

[0048] The translation drive assembly has a fixed end connected to the weeder body 12 and a movable end connected to the weeding translation mechanism 3 for driving the weeding translation mechanism 3. The translation drive assembly is specifically configured as a hydraulic push rod 11 for driving, and the number can be set according to actual conditions. To ensure good movement stability, the number of translation drive assemblies can be set to two, one on each side of the movable end. When driving the weeding translation mechanism 3, the two translation drive assemblies can be driven in a coordinated manner to achieve the purpose of smooth and accurate driving. When two hydraulic cylinders are used, the type of hydraulic cylinder can be a one-way hydraulic cylinder. As for the specific fixed position of the hydraulic cylinder, the cylinder body can be fixed to the weeder body 12 to complete the installation. The movable end of the hydraulic cylinder, i.e., the hydraulic rod, is connected to the end face of the corresponding side of the weeding translation mechanism 3 by bolts. The connection form can be adjusted accordingly according to actual conditions. For example, the use of a ball screw structure for driving is also within the spirit of the utility model of this application. For other drives, the specific connection method can be adaptively designed according to the actual structure.

[0049] Controller 2 responds to signals from multimodal vision component 1 to control the translation drive component, driving weeding translation mechanism 3 and weeding component 4. Controller 2 performs multimodal clustering analysis and localization on images captured by the camera. It then extracts seedlings and performs a Hough transform based on the vehicle's direction of travel to calculate the angle and curvature of the crop row. Controller 2 serves as a multimodal vision and machine learning algorithm controller. It runs the multimodal vision and machine learning algorithm system on the Python-based ROS robot operating system, using the Ubuntu system on an ARM hardware platform. It connects to a camera via a network or USB port to capture images and execute the recognition program.

[0050] In this embodiment, two multimodal vision components 1 are provided, one on each side of the lawn mower body 12. Using two multimodal vision components 1 allows for simultaneous acquisition of data from both sides of the lawn mower body 12, improving acquisition accuracy and preventing damage to one multimodal vision component 1, which could prevent loss of normal visual recognition. Using two multimodal vision components 1 simultaneously improves visual recognition accuracy.

[0051] In this embodiment, the multimodal vision component 1 includes an RGB camera and a depth-of-field camera. The RGB camera and the depth-of-field camera are a group and are installed on the corresponding camera bracket 10 at the same time. For the RGB camera and the depth-of-field camera, it is necessary to meet the requirements of adjustable viewing angle, and adjust the visual field of the camera to the front of the lawn mower, and at least capture two seedling strips, each with 8-10 seedlings as the ideal field of view. The RGB camera and the depth camera are DFRobot brand SEN0583 model TOF cameras. SEN0583 is divided into two parts, one is an ordinary RGB camera, and the other is a TOF module including a TOF array transmitter and a TOF infrared light receiving camera. By measuring the "flight time" of the light signal between the transmitter and the receiver to calculate the distance between the two, a TOF ranging depth camera can be realized.

[0052] In practical applications, RGB cameras capture field imagery, and the intelligent weeder system, using multimodal vision and machine learning to identify crop rows, identifies seedlings and forms seedling strips. In high-light conditions, seedling height information collected by the depth camera is integrated with the RGB camera to determine seedling boundaries and eliminate interference from shadows or low-light conditions.

[0053] In this embodiment, the multimodal vision component 1 is connected to the lawn mower body 12 via a camera bracket 10, wherein the camera bracket 10 is a telescopic bracket. The support height can be adjusted according to actual requirements. The RGB camera and depth camera 1 are mounted on the camera bracket 10 via U-shaped clips. The height of the U-shaped clips can be adjusted according to the row spacing and seedling spacing of the actual weeding environment to ensure that the RGB camera and depth camera 1 can meet the field of view of at least two rows of seedlings and 8-10 seedlings. The camera bracket 10 uses a 40 square tube with a height of 800mm and is mounted on the crossbeam of the lawn mower body 12 via U-shaped clips.

[0054] In this embodiment, the weeding translation mechanism 3 is provided with a displacement sensor 6 for collecting its position, and the displacement sensor 6 is connected to the controller 2. The displacement sensor 6 can detect the current position of the weeding translation mechanism 3 and feed it back to the controller 2, and can form a closed-loop control with the controller 2. The specific installation method of the displacement sensor 6 is that one end is installed on the frame of the weeding machine body 12, and the other end is installed on the weeding translation mechanism 3. When the weeding translation mechanism 3 translates left and right, it can drive the displacement sensor 6 to stretch or contract. According to the different extension and contraction strokes, the stroke simulation signal is fed back to the multimodal vision and machine learning algorithm controller, that is, the controller 2 for processing. After collecting the signal, the multimodal vision and machine learning algorithm system converts the analog quantity in real time to calculate the current extension and contraction position of the displacement sensor, thereby determining the current left and right offset position of the weeding mechanism, and assisting visual recognition to calculate the actual offset.

[0055] As for the power supply, the tractor power supply system provides a 12V power supply to meet the power requirements of the RGB camera and depth camera, multimodal vision and machine learning algorithm controller device, namely the controller 2, displacement sensor 6, Hall sensor 7, floor proximity switch 8, and HMI touch screen 9.

[0056] In this embodiment, the mower body 12 is provided with a ground wheel 5, which is equipped with a Hall effect sensor 7, which is connected to the controller 2. The ground wheel 5 is specifically installed on the ground side of the mower body 12 and can be fixed by bolts. During the movement of the mower body 12, the wheel body of the ground wheel 5 contacts the ground and rotates relative to the ground. During this rotation, the Hall effect sensor 7 counts the rotations of the ground wheel 5. If the wheel diameter is known, the current vehicle speed can be calculated based on the count and the wheel diameter. Based on the images captured by the current RGB camera and the depth camera, the longitudinal distance of the left and right deviation position of the seedling strip from the mowing assembly 4 can be identified to determine when the mowing assembly 4 performs the left and right offset action. The rotation counting method is to install the Hall effect sensor on the ground wheel with a metal grille structure. When the mower is mowing, the ground wheel rotates. When the metal grille sheet blocks the Hall effect sensor, a digital IO signal is generated and transmitted to the controller 2. Controller 2 collects IO signals and calculates the number of IO signals per unit time in real time through a multimodal vision and machine learning algorithm system. The current vehicle speed is calculated based on the number, time, and preset ground wheel diameter.

[0057] In this embodiment, the weeding component 4 is provided with a floor proximity switch 8. The floor proximity switch 8 has no signal when the weeding component 4 is out of the weeding state and has a signal when the weeding component 4 is in the weeding state. The floor proximity switch 8 is connected to the controller 2. The above-mentioned weeding machine body 12 is also provided with an HMI touch screen 9 for displaying control and operating status. The connection method with the controller can be conventional. The HMI touch screen 9 is connected to the multimodal vision and machine learning algorithm controller device via HDMI, and the device operation interface is created using pyqt. The display of the device operating status, abnormal status and input of related parameters can be completed through the interface. The multimodal vision and machine learning algorithm controller, that is, the controller 2, collects the floor proximity switch signal and determines the current working status through the multimodal vision and machine learning algorithm system, thereby stopping or starting recognition.

[0058] According to another aspect of the present invention, a weeding alignment method is provided, using the above-mentioned weeder, comprising the following steps:

[0059] S1, multimodal vision component 1 starts working, specifically the RGB camera and depth camera start working, and transmit the video stream to controller 2;

[0060] S2: Controller 2 captures the current video stream frame and uses a multimodal vision algorithm to identify the seedlings and weeds in the frame image captured by the RGB camera and compares them with the model library. In high-light-ratio environments, the depth camera obtains depth frame data to identify seedlings and weeds, enhancing the accuracy and robustness of crop detection.

[0061] S3, the controller 2 calibrates the positions of all seedlings in the frame image through the machine, converts them into seedling belt information through Hough transform according to the direction of the weeder's movement, and calculates the angle and curvature of the seedling belt row;

[0062] S4, the controller 2 calculates the center position of the seedling strip through machine learning, and converts the camera matrix into a quaternion matrix through the rotation matrix to obtain the actual deviation distance between the weeding component 4 and the seedling strip;

[0063] S5, the controller 2 calculates the driving speed through the Hall sensor and then performs a spatial model conversion between the modal vision component 1 and the weeding component 4, specifically the spatial model conversion between the camera and the weeding knife. The controller 2, i.e., the multimodal vision and machine learning crop row recognition intelligent weeding machine system, calculates the movement time of the weeding component 4, i.e., the knife;

[0064] S6: When the weeding time point is reached, controller 2 controls weeding translation mechanism 3 to move weeding assembly 4 to the target position, ensuring weeding conditions. Specifically, when the weeding time point is reached, the position detected by displacement sensor 6 on weeding translation mechanism 3 and the calculated offset position are combined to determine the actual position reached. The multimodal vision and machine learning crop row recognition intelligent weeder system intelligently determines the current control action of the left or right hydraulic push rod, ensuring the weeding blades reach the corresponding position.

[0065] In this embodiment, the model library in step S2 is obtained by labeling and training the seedling strips and weeds in the pictures collected by the multimodal vision component 1 in real time when the weeder is moving at a low speed. After the optimal model library is trained, it is deployed in the intelligent weeder system for multimodal vision and machine learning crop row recognition.

[0066] Refer to the attached Figure 13 The RGB camera and depth camera use visual sensors to capture real-time image information of the field in the current field of view and transmit it over the network to the Neousys NRU-230V multimodal vision and machine learning algorithm controller, also known as Controller 2. Controller 2 uses the internal multimodal vision and machine learning crop row recognition algorithm of the intelligent weeder system to identify emerging seedlings, detect the emergence band using Hough transform, and then send the offset data to the controller of the STM32F405RGT6 main control chip via RS485.

[0067] The controller of the STM32F405RGT6 main control chip collects multiple information such as the position information of the displacement sensor through the ADC interface, the speed information of the encoder is detected through input capture, and the status of the landing switch is detected through the IO input port. It integrates the offset data sent by the visual processor to calculate the position where the current translation mechanism should be offset, and controls the opening or closing of the solenoid valve of the weeding translation mechanism 3 through the switch quantity to achieve left or right translation of the weeding translation mechanism 3.

[0068] When in use, the weeder body 12 is mounted on the rear suspension of the tractor through a suspension mechanism and is towed by the tractor. The left and right deviations of the seedling belt are identified through the RGB camera and the depth camera on the camera bracket 10, and the hydraulic push rod 11 is powered by the tractor oil circuit system. The hydraulic push rod 11 controls the twelve-way weeding assembly 4 to move left and right, so that the weeding knife is kept dynamically in the middle of the two seedling belts.

[0069] In the above description, the controllers, sensors, control programs, and model libraries that may be involved all adopt existing technologies and are not described in detail here.

[0070] The embodiments of the present invention disclosed above are intended only to illustrate the present invention. These embodiments do not exhaust all details, nor do they limit the present invention to the specific embodiments described. Numerous modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention.

Claims

1. A weeder, characterized in that: include: The front side of the weeder body (12) is connected to a moving vehicle, and the moving vehicle is used to drive the weeder body (12) to move; A multimodal vision component (1) is provided on the front side of the weeder body (12) and is used to collect image information and depth information of seedlings and weeds; A weeding translation mechanism (3) is connected to the weeder body (12), and a weeding assembly (4) is provided on the ground side; A translation drive assembly, wherein the fixed end is connected to the weeder body (12), and the movable end is connected to the weeding translation mechanism (3) for driving the weeding translation mechanism (3) to move; The controller (2) is used for responding to the signal of the multimodal vision component (1) to control the translation drive component to drive the weeding translation mechanism (3) and the weeding component (4) to move.

2. A weeder according to claim 1, characterized in that: The multimodal vision components (1) are provided in two numbers and are distributed on both sides of the lawn mower body (12).

3. A weeder according to claim 1 or 2, characterized in that: The multimodal vision component (1) comprises an RGB camera and a depth-of-field camera.

4. A weed remover according to claim 3, characterized in that: The multimodal vision component (1) is connected to a lawn mower body (12) via a camera bracket (10), wherein the camera bracket (10) is a telescopic bracket.

5. A weeder according to claim 1, 2 or 4, characterized in that: The translation drive assembly is a hydraulic push rod (11).

6. A weeder according to claim 5, characterized in that: Two hydraulic push rods (11) are provided and are symmetrically distributed on both sides of the weeding translation mechanism (3).

7. The weeder according to claim 1, characterized in that: The weeding translation mechanism (3) is provided with a displacement sensor (6) for collecting its position, and the displacement sensor (6) is connected to the controller (2).

8. A weeder according to claim 1 or 7, characterized in that: The weeder body (12) is provided with a ground wheel (5), the ground wheel (5) is provided with a Hall sensor (7), and the Hall sensor (7) is connected to the controller (2).

9. A weeder according to claim 8, characterized in that: The weeding component (4) is provided with a floor proximity switch (8), which has no signal when the weeding component (4) is out of the weeding state and has a signal when the weeding component (4) is in the weeding state, and is connected to the controller (2).

10. The weeder according to claim 1, characterized in that: The mobile vehicle is a tractor.

Images