Weeding robot based on machine vision

Abstract

The utility model discloses a weeding robot based on machine vision, which comprises a walking cabin, four corners of the walking cabin are connected with walking wheels, a driving motor for driving the walking wheels is arranged in the walking cabin, the driving motor is connected with a PLC (programmable logic controller), a top plate is arranged at the upper end of the walking cabin, and a detection module, a detection module, a weeding module and a control module are arranged on the top plate. The control module is connected with the detection module, the detection module, the weeding module and the PLC. Automatic cruise of the robot is achieved through cooperation of the detection module and the walking mechanism, the control module achieves accurate detection of weed targets through the detection module, a pesticide nozzle is accurately moved to the position above weeds through the mechanical arm, and quantitative herbicide stored in a herbicide container is sprayed to the weeds. After the herbicide is sprayed, the control module stores the target, repeated weeding is prevented, pertinence is high, equipment flexibility is high, pesticide waste can be effectively reduced, and the influence on normal crops is reduced.

Description

Technical Field

[0001] This utility model relates to the field of agricultural robot technology, and in particular to a weeding robot based on machine vision. Background Technology

[0002] With the development of agricultural automation, machinery and computer technology have been widely used in agricultural production and management. Automatic weeding systems for clearing weeds in farmland are becoming more and more sophisticated. However, most existing weeding machines spray herbicides by using drones or fixed equipment to spray herbicides over a large area of ​​weedy areas. This not only easily affects the growth of normal crops but also wastes a lot of herbicides. The equipment lacks flexibility and the methods lack specificity. Utility Model Content

[0003] The purpose of this invention is to provide a machine vision-based weeding robot to solve the problems of existing drones or fixed equipment that easily affect the growth of normal crops, waste herbicides, and lack flexibility.

[0004] The objective of this utility model is achieved through the following technical solution:

[0005] A machine vision-based weeding robot includes a walking chamber with wheels connected to its four corners. The walking chamber is equipped with a drive motor that drives the wheels, and the drive motor is connected to a PLC controller. The upper part of the walking chamber is equipped with a top plate, and the top plate is equipped with a detection module, a probe module, a weeding module, and a control module. The control module is connected to the detection module, the probe module, the weeding module, and the PLC controller.

[0006] Furthermore, a placement component is detachably connected to the middle of the walking cabin, and a storage battery is installed inside the placement component. The storage battery is connected to the control module, detection module, probe module, weeding module, PLC controller and drive motor.

[0007] Furthermore, the detection module includes a robotic arm, which is installed at the front of the top plate. The front end of the robotic arm is equipped with a binocular camera for detecting weeds. The control module is connected to the robotic arm and the binocular camera, and the battery is connected to the robotic arm and the binocular camera.

[0008] Furthermore, the weeding module includes a herbicide container installed in the middle of the top plate. A herbicide pump is provided on the front side wall of the herbicide container. The herbicide pump is connected to a herbicide nozzle via a hose. The herbicide nozzle is installed at the front end of the robotic arm. The installation height of the herbicide nozzle is lower than the installation height of the binocular camera. The control module is connected to the herbicide pump and the herbicide nozzle. The battery is connected to the herbicide pump and the herbicide nozzle.

[0009] Furthermore, a control compartment is provided at the rear of the top plate, the control module is provided inside the control compartment, the PLC controller is located inside the control compartment, and the detection module is provided at the upper end of the control compartment.

[0010] Furthermore, the detection module includes a rotating servo motor installed on the top of the control cabin, and a lidar for detecting information about the robot's surrounding environment is provided on the top of the rotating servo motor. The control module is connected to the rotating servo motor and the lidar, and the battery is connected to the rotating servo motor and the lidar.

[0011] Furthermore, the side wall of the walking compartment is provided with a door adapted to the placement component, and the side wall of the placement component facing the door is provided with a pick-up and put-down buckle.

[0012] Furthermore, the herbicide container has a lid at the top and a viewing window on the side wall.

[0013] This invention has the following advantages: the robot can automatically cruise by cooperating with the detection module and the walking mechanism; the control module can accurately detect weed targets by using the detection module; and the robotic arm can precisely move the pesticide nozzle above the weeds to spray a fixed amount of herbicide stored in the herbicide container onto the weeds. After spraying the herbicide, the control module saves the target to prevent repeated weeding. It is highly targeted, the equipment is highly flexible, and it can effectively reduce pesticide waste and reduce the impact on normal crops. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of the structure of this utility model.

[0015] Figure 2 This is a perspective view of the walking cabin.

[0016] In the diagram, 1-walking compartment, 2-walking wheels, 3-drive motor, 4-top plate, 5-control module, 6-placement component, 601-release buckle, 7-battery, 8-door, 9-robotic arm, 10-binocular camera, 11-herbicide container, 1101-box cover, 12-pesticide pump, 13-hose, 14-pesticide nozzle, 15-control compartment, 16-rotation servo motor, 17-lidar. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of this utility model clearer, the technical solutions of the embodiments of this utility model will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this utility model, not all embodiments. The components of the embodiments of this utility model described and shown in the accompanying drawings can typically be arranged and designed in various different configurations.

[0018] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0019] It should be noted that, where there is no conflict, the embodiments and features in the embodiments of this utility model can be combined with each other.

[0020] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0021] In the description of this utility model, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of this utility model is in use, or the orientation or positional relationship commonly understood by those skilled in the art. They are only used for the convenience of describing this utility model and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this utility model. In addition, the terms "first," "second," etc., are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0022] In the description of this utility model, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this utility model based on the specific circumstances.

[0023] refer to Figure 1As shown in Figure 2, one embodiment of this utility model is as follows:

[0024] A machine vision-based weeding robot includes a walking chamber 1, with walking wheels 2 connected to the four corners of the walking chamber 1. The walking chamber 1 is equipped with a drive motor 3 that drives the walking wheels 2. The drive motor 3 is connected to a PLC controller. The upper end of the walking chamber 1 is equipped with a top plate 4. The top plate 4 is equipped with a detection module, a probe module, a weeding module, and a control module 5. The control module is connected to the detection module, the probe module, the weeding module, and the PLC controller.

[0025] Furthermore, to ensure the operation of the weeding robot, a placement component 6 is detachably connected to the middle of the walking chamber 1. A storage battery 7 is installed inside the placement component 6. The storage battery 7 is connected to the control module 5, detection module, probe module, weeding module, PLC controller and drive motor 3.

[0026] The storage component 6 and the battery 7 are placed in the middle of the travel compartment to balance the weight distribution of the equipment and enhance the stability of the travel compartment during movement. The battery 7 can be a high-capacity, easy-to-maintain, and inexpensive lead-acid battery. Meanwhile, the side wall of the travel compartment 1 is provided with a door 8 adapted to the storage component 6, and the side wall of the storage component 6 facing the door 8 is provided with a retrieval buckle 601 to facilitate the removal of the storage component for charging or replacement of the battery.

[0027] Furthermore, the detection module includes a robotic arm 9, which is installed at the front of the top plate 4. The front end of the robotic arm 9 is equipped with a binocular camera 10 for detecting weeds. The control module 5 is connected to the robotic arm 9 and the binocular camera 10, and the battery 7 is connected to the robotic arm 9 and the binocular camera 10.

[0028] The robotic arm 9 drives the binocular camera 10 to rotate and move, and monitors the real-time image status during the robot's movement. At the same time, the image is uploaded to the control module 5, which analyzes the uploaded image to detect whether weeds are present.

[0029] For weed detection, the control module is based on YOLOv11 and uses the PyTorch deep learning framework to implement weed detection. In specific implementation, image data is first collected through the binocular camera 10; then the control module 5 performs data augmentation, feature extraction, feature fusion, generates detection boxes, and outputs detection results based on YOLOv11 on the collected data; the confidence of the detection results is analyzed, and if it exceeds the set threshold, it is judged as a weed.

[0030] The weeding module includes a herbicide container 11, which is installed in the middle of the top plate 4. A herbicide pump 12 is provided on the front side wall of the herbicide container 11. The herbicide pump 12 is connected to a herbicide nozzle 14 through a hose 13. The herbicide nozzle 14 is installed at the front end of the robotic arm 9. The installation height of the herbicide nozzle 14 is lower than the installation height of the binocular camera 10. The control module 5 is connected to the herbicide pump 12 and the herbicide nozzle 14. The battery 7 is connected to the herbicide pump 12 and the herbicide nozzle 14.

[0031] To facilitate the addition of herbicide, the herbicide container 11 is equipped with a lid 1101 at the top. Additionally, the side wall of the herbicide container has a viewing window to allow on-site personnel to easily monitor the amount of herbicide used.

[0032] The robotic arm 9 moves the pesticide nozzle 14 above the weeds according to the weed target location information provided by the control module 5. Then, the pesticide pump 2 pumps the herbicide from the herbicide container 11 and pumps it to the pesticide nozzle 14 through the hose 13. The pesticide nozzle 14 sprays the herbicide under the control of the control module 5. After spraying the herbicide, the control module 5 saves the target to prevent repeated weeding.

[0033] Furthermore, a control cabin 15 is located at the rear of the top plate 4, and the control module 5 is housed within the control cabin 15. The PLC controller is located within the control cabin 15, and the detection module is located at the upper end of the control cabin 15. The detection module includes a rotating servo motor 16 mounted on the top of the control cabin 15, and a lidar 17 for detecting information about the robot's surrounding environment is mounted on the top of the rotating servo motor 16. The control module 5 is connected to the rotating servo motor 16 and the lidar 17, and the battery 7 is connected to the rotating servo motor 16 and the lidar 17.

[0034] The rotary servo motor 16 drives the lidar 17 to rotate at high speed and emit lidar signals. Through data processing by the control module 5, a 3D model of the environment in which the weeding robot is located is established. The weeding robot automatically cruises according to the predetermined route and the environmental model. The cruise is controlled by the PLC controller to drive the drive motor 3 to drive the corresponding walking wheels 2 to rotate.

[0035] After startup, the weeding robot's rotary servo motor 16 drives the lidar 17 to rotate at high speed and emit lidar signals. Data processing by the control module 6 creates a 3D model of the robot's environment. The robot automatically navigates according to a predetermined route and the environmental model. It can also be controlled via a mobile phone or PC using a control system developed in Python. The robotic arm 9 drives the binocular camera 11 and the pesticide nozzle 14 to rotate and shift, monitoring real-time image conditions during the robot's movement. Simultaneously, the images are uploaded to the control module 5, which analyzes them to detect weed targets. If weed targets are found, the robotic arm 9, based on the weed target location information provided by the control module 5, moves the pesticide nozzle 14 above the weeds. Then, the pesticide pump 12 dispenses herbicide from the herbicide container 11 through the hose 16 to the pesticide nozzle 14. The nozzle 11 sprays the herbicide under the control of the control module 5. After spraying, the mainboard 6 saves the target information to prevent repeated weeding. This system is highly targeted, flexible, and effectively reduces pesticide waste.

[0036] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A machine vision-based weeding robot, characterized in that: The device includes a walking compartment with four wheels connected to its four corners. The walking compartment contains a drive motor that drives the wheels and is connected to a PLC controller. The walking compartment has a top plate at its upper end, and the top plate contains a detection module, a probe module, a weeding module, and a control module. The control module is connected to the detection module, the probe module, the weeding module, and the PLC controller.

2. The weeding robot based on machine vision according to claim 1, characterized in that: The walking cabin is detachably connected to a placement component in the middle, and the placement component contains a storage battery. The storage battery is connected to the control module, detection module, probe module, weeding module, PLC controller and drive motor.

3. The weeding robot based on machine vision according to claim 2, characterized in that: The detection module includes a robotic arm, which is installed at the front of the top plate. The front end of the robotic arm is equipped with a binocular camera for detecting weeds. The control module is connected to the robotic arm and the binocular camera, and the battery is connected to the robotic arm and the binocular camera.

4. The weeding robot based on machine vision according to claim 3, characterized in that: The weeding module includes a herbicide container installed in the middle of the top plate. A herbicide pump is provided on the front side wall of the herbicide container. The herbicide pump is connected to a herbicide nozzle via a hose. The herbicide nozzle is installed at the front end of the robotic arm. The installation height of the herbicide nozzle is lower than the installation height of the binocular camera. The control module is connected to the herbicide pump and the herbicide nozzle. The battery is connected to the herbicide pump and the herbicide nozzle.

5. A machine vision-based weeding robot according to claim 2, characterized in that: The rear of the top plate is provided with a control compartment, the control module is provided in the control compartment, the PLC controller is located in the control compartment, and the detection module is provided at the upper end of the control compartment.

6. The weeding robot based on machine vision according to claim 5, characterized in that: The detection module includes a rotating servo motor installed on the top of the control cabin. The top of the rotating servo motor is equipped with a lidar for detecting information about the robot's surrounding environment. The control module is connected to the rotating servo motor and the lidar. The battery is connected to the rotating servo motor and the lidar.

7. A machine vision-based weeding robot according to claim 2, characterized in that: The side wall of the walking compartment is provided with a door adapted to the placement component, and the side wall of the placement component facing the door is provided with a pick-up and put-down buckle.

8. A machine vision-based weeding robot according to claim 4, characterized in that: The herbicide container has a lid at the top and a viewing window on the side wall.

Images