Picking robot orchard operation area division method and device, equipment and medium

Abstract

The application relates to a picking robot orchard operation area division method, device, equipment and medium, which comprises the following steps: determining the D-H standard parameters corresponding to each joint in a mechanical arm, obtaining the homogeneous transformation matrix of each joint in the mechanical arm according to the D-H standard parameters, determining the position and posture of the end effector of the mechanical arm, and determining the picking area of the mechanical arm according to the position of the end effector by using a probability density function; determining the reachable area corresponding to each grape cluster based on the grape cluster coordinates corresponding to each grape cluster and the picking area of the mechanical arm, and dividing the operation area of the picking robot in the target grape orchard according to the overall distribution information of each grape cluster and the reachable area corresponding to each grape cluster, so as to complete the picking robot orchard operation area division of the picking robot. The application can pay attention to the gathering area with grape distribution for picking, and greatly improves the precision of automatic grape picking.

Description

Technical Field

[0001] The present application relates to the field of automated picking, and in particular to a method for dividing an orchard operation area of ​​a picking robot, a corresponding device, an electronic device, and a computer-readable storage medium. Background Art

[0002] Fruit harvesting is a crucial part of grape cultivation management. Currently, fruit harvesting remains a labor-intensive and inefficient task. With the development of robotics, autonomously navigated harvesting robots have been widely used in the fruit picking field, significantly improving operational efficiency. Path planning is a crucial component of harvesting robot technologies. For orchard path planning tasks, dividing the work area is a crucial step.

[0003] Existing methods for dividing the work area for fruit-picking robots typically focus on global, large-scale divisions. This approach works well for orchards with evenly distributed fruit. However, under the same cultivation conditions, grape berries are generally distributed relatively evenly within the tree canopy. Especially when high-density planting is used, berries may cluster in certain areas, particularly in areas with sufficient sunlight, such as the outer sides of the trunk and main branches. This causes the berries in these locations to mature faster and yield relatively higher. Given the uneven distribution of grape berries in orchards, larger orchards require more attention to clustered areas where berries are distributed. While existing methods for dividing the work area for harvesting robots can divide orchards, they suffer from a large number of divisions, low efficiency, and low precision. This makes it impossible to focus on clustered areas where berries are distributed and accurately harvest the berries.

[0004] To sum up, the method of dividing the working area of ​​the picking robot in the existing technology has the problems of a large number of divisions, low division efficiency and low division accuracy, and is unable to focus on the concentrated areas where grape fruits are distributed and to accurately pick the grape fruits. In order to solve this problem, the applicant has made corresponding explorations. Summary of the Invention

[0005] The purpose of this application is to solve the above problems and provide a method for dividing the orchard operation area of ​​a picking robot, a corresponding device, an electronic device and a computer-readable storage medium.

[0006] In order to meet the various objectives of this application, this application adopts the following technical solutions:

[0007] A method for dividing an orchard operation area for a picking robot, which is proposed to meet one of the purposes of this application, includes:

[0008] Acquiring laser radar data and inertial measurement unit data from an information acquisition module of a picking robot, constructing a two-dimensional grid map of the grape orchard based on the laser radar data and the inertial measurement unit data, and constructing a grape orchard spatial model based on a spatial pose relationship between the information acquisition module and the picking module of the picking robot and a coordinate relationship between a grid map coordinate system of the two-dimensional grid map of the grape orchard and a grape orchard coordinate system;

[0009] determining grape bunch point cloud data from different viewing angles of each grape bunch collected by a structured light camera in a robotic arm of the picking robot and its corresponding point cloud collection position, and registering the grape bunch point cloud data from different viewing angles using a preset iterative closest point algorithm to determine complete grape bunch information at the same position;

[0010] Based on the point cloud collection positions corresponding to the grape bunches, the complete grape bunch information at different positions is integrated in the grape orchard spatial model to determine the grape bunch coordinates and overall distribution information corresponding to each grape bunch in the two-dimensional grid map of the grape orchard;

[0011] Determine the DH standard parameters corresponding to each joint in the robotic arm, obtain the homogeneous transformation matrix of each joint in the robotic arm based on the DH standard parameters to determine the position and posture of the end effector of the robotic arm, and use a probability density function to determine the picking area of ​​the robotic arm based on multiple end effector positions;

[0012] Based on the grape fruit bunch coordinates corresponding to each grape fruit bunch and the picking area of ​​the robotic arm, the reachable area corresponding to each grape fruit bunch is determined; according to the overall distribution information of each grape fruit bunch and the reachable area corresponding to each grape fruit bunch, the operating area of ​​the picking robot in the target grape orchard is divided to complete the division of the picking robot's orchard operating area.

[0013] Optionally, the step of constructing a two-dimensional grid map of the grape orchard based on the lidar data and the inertial measurement unit data includes:

[0014] Determining laser radar data and inertial measurement unit data in the information acquisition module of the picking robot;

[0015] constructing a three-dimensional grape orchard map of the target grape orchard based on the lidar data and the inertial measurement unit data using a preset simultaneous positioning and mapping algorithm;

[0016] The three-dimensional map of the grape orchard is projected onto a two-dimensional plane to construct a two-dimensional grid map of the grape orchard.

[0017] Optionally, before the step of determining grape fruit bunch point cloud data of each grape fruit bunch at different viewing angles and the corresponding point cloud collection position thereof collected by the structured light camera in the robotic arm of the picking robot, and registering the grape fruit bunch point cloud data at different viewing angles using a preset iterative closest point algorithm to determine the complete grape fruit bunch information at the same position, the step includes:

[0018] The structured light camera in the robotic arm of the picking robot is used to collect viewing angle information at different positions in the target grape orchard, and each posture parameter of the robotic arm is recorded, wherein the posture parameters include position coordinates and rotation angles.

[0019] Optionally, determining DH standard parameters corresponding to each joint in the robotic arm, obtaining a homogeneous transformation matrix of each joint in the robotic arm based on the DH standard parameters to determine the position and posture of the end effector of the robotic arm, and using a probability density function to determine the picking area of ​​the robotic arm based on multiple end effector positions includes:

[0020] Obtaining the joint angle, joint offset, connecting rod length, and connecting rod torsion angle corresponding to each joint in the robotic arm of the picking robot, wherein the DH standard parameters include the joint angle, joint offset, connecting rod length, and connecting rod torsion angle;

[0021] Determine a homogeneous transformation matrix corresponding to each joint according to the joint angle, joint offset, connecting rod length, and connecting rod torsion angle corresponding to each joint, and multiply the homogeneous transformation matrices corresponding to each joint to determine the position and posture of the end effector of the robotic arm;

[0022] Sampling the end effector position multiple times and recording the multiple end effector positions, and calculating and determining the probability density of each end effector position based on the multiple end effector positions using a preset probability density function;

[0023] Detect whether the probability density of the end effector position exceeds a preset probability density threshold; if so, use the position exceeding the preset probability density threshold as the picking area of ​​the robotic arm.

[0024] Optionally, the step of determining the reachable area corresponding to each grape bunch based on the grape bunch coordinates corresponding to each grape bunch and the picking area of ​​the robotic arm includes:

[0025] A spherical area is obtained with the coordinates of each grape bunch in the target grape orchard as the center and the picking area of ​​the robotic arm as the radius, and the spherical area is used as the reachable area corresponding to each grape bunch, wherein the spherical area is the spatial position where the picking robot can pick the grape bunch;

[0026] The spherical area of ​​each grape bunch in the target grape orchard is projected onto a two-dimensional plane to determine a circular area corresponding to each grape bunch, and the circular area is used as the reachable plane of each grape bunch.

[0027] Optionally, the step of dividing the operation area of ​​the picking robot in the target grape orchard according to the overall distribution information of the grape bunches and the reachable areas corresponding to the grape bunches includes:

[0028] Taking the first grape bunch close to the origin of the two-dimensional grid map of the grape orchard as the starting point and the diameter of the picking area of ​​the robotic arm as the radius, a circular coverage area is determined, and the grape bunches within the circular coverage area are numbered as grape bunch P0, grape bunch P1, grape bunch P2, grape bunch P3, and grape bunch P4 according to the distance between each grape bunch and the origin of the map from near to far;

[0029] Determine the reachable areas corresponding to the grape bunch P1, grape bunch P2, grape bunch P3, and grape bunch P4 within the circular coverage area;

[0030] Determine whether the reachable area corresponding to the grape bunch P1 and the reachable area corresponding to the grape bunch P2 intersect; if the reachable areas corresponding to the grape bunch P1 and the grape bunch P2 do not intersect, use the reachable plane of the grape bunch P1 as the operation area D1;

[0031] If the reachable area corresponding to the grape bunch P1 intersects with the reachable area corresponding to the grape bunch P2, the intersection is recorded as intersection T1. Further, it is determined whether the intersection T1 intersects with the reachable area corresponding to the grape bunch P3. If so, the intersection is recorded as intersection T2. ​​If not, the intersection T1 is used as the operation area D1.

[0032] It is determined in sequence whether the reachable areas corresponding to the grape fruit clusters with later numbers intersect with the reachable areas corresponding to the grape fruit clusters with earlier numbers, until the grape fruit clusters P1, P2, P3, and P4 within the circular coverage area are determined;

[0033] The above steps are repeated until the reachable areas of all grape bunches in the target grape orchard are determined, so as to determine the operating area of ​​the picking robot in the target grape orchard.

[0034] Optionally, the point cloud collection position representation refers to the specific spatial coordinates and related status information of each grape bunch when collected in the grape orchard; the probability density function includes a Gaussian distribution model, and the simultaneous positioning and mapping algorithm includes a FASTL 10 algorithm, a LIOSAM algorithm or an R3 live algorithm.

[0035] A device for dividing an orchard operation area for a picking robot is provided to meet another purpose of the present application, comprising:

[0036] a spatial model construction module configured to obtain laser radar data and inertial measurement unit data from an information acquisition module of a picking robot, construct a two-dimensional grid map of the grape orchard based on the laser radar data and the inertial measurement unit data, and construct a grape orchard spatial model based on a spatial posture relationship between the information acquisition module and the picking module of the picking robot and a coordinate relationship between a grid map coordinate system of the two-dimensional grid map of the grape orchard and a grape orchard coordinate system;

[0037] a fruit information determination module configured to determine grape fruit cluster point cloud data of each grape fruit cluster at different viewing angles and corresponding point cloud acquisition positions collected by a structured light camera in a robotic arm of the picking robot, and to register the grape fruit cluster point cloud data at different viewing angles using a preset iterative closest point algorithm to determine complete grape fruit cluster information at the same position;

[0038] a fruit distribution information determination module configured to integrate complete grape fruit bunch information at different locations in the grape orchard spatial model based on point cloud collection locations corresponding to each grape fruit bunch, so as to determine grape fruit bunch coordinates and overall distribution information corresponding to each grape fruit bunch in the grape orchard two-dimensional grid map;

[0039] a picking area determination module configured to determine DH standard parameters corresponding to each joint in the robotic arm, obtain a homogeneous transformation matrix of each joint in the robotic arm based on the DH standard parameters to determine the position and posture of the end effector of the robotic arm, and use a probability density function to determine the picking area of ​​the robotic arm based on multiple end effector positions;

[0040] The operation area division module is configured to determine the reachable area corresponding to each grape fruit bunch based on the grape fruit bunch coordinates corresponding to each grape fruit bunch and the picking area of ​​the robotic arm, and divide the operation area of ​​the picking robot in the target grape orchard according to the overall distribution information of each grape fruit bunch and the reachable area corresponding to each grape fruit bunch, so as to complete the picking robot orchard operation area division of the picking robot.

[0041] An electronic device provided to meet another purpose of the present application includes a central processing unit and a memory, wherein the central processing unit is used to call and run a computer program stored in the memory to execute the steps of the orchard operation area division method of the picking robot described in the present application.

[0042] A computer-readable storage medium is provided to meet another purpose of the present application, which stores a computer program implemented according to the method for dividing the orchard operation area of ​​the picking robot in the form of computer-readable instructions. When the computer program is called and run by the computer, it executes the steps included in the corresponding method.

[0043] Compared with the prior art, the present application addresses the problems of the prior art method for dividing the working area of ​​the picking robot, such as a large number of divisions, low division efficiency, and low division accuracy, which make it impossible to focus on the concentrated areas where grapes are distributed and to accurately pick the grapes. The present application has, but is not limited to, the following beneficial effects:

[0044] This application obtains fruit information through a structured light camera, and integrates the fruits through the established spatial model to obtain the distribution information and distribution coordinates of the fruits in the orchard. Finally, the orchard area is divided to obtain the operating area of ​​the picking robot. This application proposes a new idea for the division of operating areas of picking robots equipped with robotic arms in orchards with uneven distribution of grape fruits. The orchard operating area division method of the picking robot of this application can obtain a much smaller number of operating areas than the operating areas obtained by traditional solutions, and can focus on the concentrated areas where grape fruits are distributed for picking, greatly improving the accuracy and efficiency of automated grape picking; significantly improving the overall operating efficiency of the picking robot, precise positioning and detection, optimized path planning and efficient operation capabilities, which can significantly improve the picking speed and quality of grapes, thereby increasing the yield and economic benefits of the vineyard. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0046] Figure 1 Schematic diagram of the process of dividing the orchard operation area of ​​the picking robot in the embodiment of the present application;

[0047] Figure 2 This is a flowchart of a method for dividing an orchard operation area for a picking robot in an embodiment of the present application;

[0048] Figure 3 This is a schematic diagram of the accessible area of ​​a grape bunch in an embodiment of the present application;

[0049] Figure 4 This is a schematic diagram of numbering grape bunches within a circular coverage area in an embodiment of the present application;

[0050] Figure 5 This is a schematic diagram of grape bunches P0, P1, P2, P3, and P4 recorded within a circular coverage area in an embodiment of the present application;

[0051] Figure 6 Schematic diagram of the accessible area of ​​the fruit within the circular coverage area in the embodiment of the present application;

[0052] Figure 7 This is a schematic diagram of determining the operating area D1 in an embodiment of the present application;

[0053] Figure 8 This is a principle block diagram of the orchard operation area division device of the picking robot in the embodiment of the present application;

[0054] Figure 9 Schematic diagram of the structure of the computer device in the embodiment of the present application. DETAILED DESCRIPTION

[0055] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and are not to be construed as limiting the present application.

[0056] It will be understood by those skilled in the art that, unless expressly stated otherwise, the singular forms "a", "an", "said" and "the" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, "connected" or "coupled" as used herein may include wireless connections or wireless couplings. The term "and / or" used herein includes all or any units and all combinations of one or more associated listed items.

[0057] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0058] Those skilled in the art will appreciate that the terms "client," "terminal," and "terminal device" as used herein include both devices that are wireless signal receivers, i.e., devices that only have wireless signal receivers without transmission capabilities, and devices that have receiving and transmitting hardware capable of two-way communication over a two-way communication link. Such devices may include: cellular or other communication devices such as personal computers and tablet computers, which have single-line displays, multi-line displays, or cellular or other communication devices without multi-line displays; PCS (Personal Communications Services), which may combine voice, data processing, fax, and / or data communication capabilities; PDA (Personal Digital Assistant), which may include a radio frequency receiver, a pager, Internet / Intranet access, a web browser, a notepad, a calendar, and / or a GPS (Global Positioning System) receiver; and conventional laptop and / or palmtop computers or other devices, which have and / or include a radio frequency receiver. As used herein, the terms "client," "terminal," or "terminal device" may be portable, transportable, or installed in a vehicle (air, sea, and / or land), or may be adapted and / or configured to operate locally, and / or in a distributed manner, at any other location on Earth and / or in space. As used herein, the terms "client," "terminal," or "terminal device" may also refer to a communication terminal, an Internet access terminal, or a music / video playback terminal, such as a PDA, a MID (Mobile Internet Device), and / or a mobile phone with music / video playback capabilities, or may refer to a smart TV, a set-top box, or other device.

[0059] The hardware referred to by names such as "server", "client", and "service node" in this application is essentially an electronic device with capabilities equivalent to those of a personal computer. It is a hardware device that has the necessary components revealed by the von Neumann principle, such as a central processing unit (including an arithmetic unit and a controller), a memory, an input device, and an output device. Computer programs are stored in its memory, and the central processing unit loads the program stored in the external memory into the internal memory for execution, executes the instructions in the program, and interacts with the input and output devices to complete specific functions.

[0060] It should be noted that the concept of "server" referred to in this application can also be extended to server clusters. Based on the network deployment principles understood by those skilled in the art, the servers described should be logically divided. In physical space, these servers can be independent of each other but callable through interfaces, or integrated into a single physical computer or a computer cluster. Those skilled in the art should understand this flexibility and should not use it to constrain the implementation of the network deployment method of this application.

[0061] Unless expressly specified, one or more technical features of the present application can be deployed on a server for implementation and accessed by a client through a remote call to obtain an online service interface provided by the server, or can be directly deployed and run on a client for implementation.

[0062] Unless expressly specified otherwise, the neural network models referenced or may be referenced in this application may be deployed on a remote server and remotely called on the client, or may be deployed and directly called on a client with sufficient device capabilities. In some embodiments, when it runs on the client, its corresponding intelligence may be obtained through transfer learning to reduce the requirements for the client's hardware operating resources and avoid excessive occupation of the client's hardware operating resources.

[0063] Unless explicitly specified, the various data involved in this application can be stored remotely on a server or on a local terminal device, as long as they are suitable for being called by the technical solution of this application.

[0064] Those skilled in the art should be aware that although the various methods of this application are described based on the same concept and thus exhibit commonality, unless otherwise specified, these methods can be independently executed. Similarly, the various embodiments disclosed in this application are all based on the same inventive concept. Therefore, concepts with the same expression, as well as concepts that are appropriately transformed for convenience despite different expression, should be understood as equivalent.

[0065] Unless expressly stated to be mutually exclusive, the various embodiments disclosed in this application may be cross-combined with the relevant technical features of the various embodiments to flexibly construct new embodiments, as long as such combination does not deviate from the creative spirit of this application and can meet the needs of the prior art or resolve certain deficiencies in the prior art. Those skilled in the art should be aware of such flexibility.

[0066] See also Figures 1 to 3 In one embodiment, the method for dividing the orchard operation area of ​​the picking robot of the present application includes:

[0067] Step S10: Acquire laser radar data and inertial measurement unit data from the information acquisition module of the picking robot, construct a two-dimensional grid map of the grape orchard based on the laser radar data and the inertial measurement unit data, and construct a grape orchard spatial model based on the spatial pose relationship between the information acquisition module and the picking module of the picking robot and the coordinate relationship between the grid map coordinate system of the two-dimensional grid map of the grape orchard and the grape orchard coordinate system;

[0068] The terminal device can obtain the laser radar data and the inertial measurement unit data in the information acquisition module of the picking robot, construct a two-dimensional grid map of the grape orchard based on the laser radar data and the inertial measurement unit data, and construct a grape orchard spatial model based on the spatial posture relationship between the information acquisition module and the picking module of the picking robot and the coordinate relationship between the grid map coordinate system of the two-dimensional grid map of the grape orchard and the grape orchard coordinate system;

[0069] In some embodiments, the information acquisition module includes a lidar sensor, an IMU (inertial measurement unit) sensor, and a structured light camera, among other functions, for sensing the grape orchard environment and identifying grape bunch locations and obstacles. The picking module, responsible for executing the picking action, includes a robotic arm and other components. The coordinates of the information acquisition module can be converted to those of the picking module using a pose transformation matrix, ensuring that the grape bunch location information collected by the information acquisition module is correctly transmitted to the picking module for execution.

[0070] In some embodiments, a grape orchard picking robot is enabled to perceive the grape orchard environment and identify the location of grape bunches through an information acquisition module, accurately converting this information into operational instructions for the picking module, thereby ensuring an accurate and efficient picking process. A two-dimensional grid map of the grape orchard is constructed based on the lidar data and inertial measurement unit data. A grape orchard spatial model is constructed based on the spatial pose relationship between the information acquisition module and the picking module of the picking robot, as well as the coordinate relationship between the grid map coordinate system of the two-dimensional grid map and the grape orchard coordinate system. Once the spatial pose relationship between the information acquisition module and the picking module, as well as the transformation relationship between the grid map coordinate system and the grape orchard coordinate system, is determined, a complete grape orchard spatial model can be established. This grape orchard spatial model can be implemented using geometric modeling techniques and a simultaneous localization and mapping algorithm. The simultaneous localization and mapping algorithm enables the picking robot to construct a real-time map of the environment and update its own position during movement. During the picking process, the robot can use this spatial model to adjust its position and the motion trajectory of its robotic arm in real time to adapt to the complex environment of the grape orchard and the diverse distribution of grape bunches. At the same time, the spatial model can also be used for path planning and obstacle avoidance, making the robot's movement in the grape orchard safer and more efficient.

[0071] In summary, the establishment of the above-mentioned grape orchard spatial model is based on the spatial posture relationship between the information acquisition module and the picking module, as well as the coordinate relationship between the grid map coordinate system of the grape orchard two-dimensional grid map and the grape orchard coordinate system, ensuring that the picking robot can work efficiently in the grape orchard.

[0072] In some embodiments, the step of constructing a two-dimensional grid map of a grape orchard based on the lidar data and the inertial measurement unit data includes:

[0073] Step S101: determining the laser radar data and inertial measurement unit data in the information acquisition module of the picking robot;

[0074] Step S102: constructing a three-dimensional grape orchard map of the target grape orchard based on the lidar data and the inertial measurement unit data using a preset simultaneous positioning and mapping algorithm;

[0075] Specifically, the simultaneous positioning and mapping algorithm includes the FASTLIO algorithm, the LIOSAM algorithm or the R3 live algorithm.

[0076] Step S103: Projecting the three-dimensional map of the grape orchard onto a two-dimensional plane to construct a two-dimensional grid map of the grape orchard.

[0077] Step S20: determining grape bunch point cloud data at different viewing angles of each grape bunch collected by the structured light camera in the robotic arm of the picking robot and the corresponding point cloud collection position; and registering the grape bunch point cloud data at different viewing angles using a preset iterative closest point algorithm to determine complete grape bunch information at the same position;

[0078] After constructing the grape orchard spatial model, the grape fruit bunch point cloud data of each grape fruit bunch at different perspectives collected by the structured light camera in the robotic arm of the picking robot and its corresponding point cloud collection position are determined, and the grape fruit bunch point cloud data at different perspectives are aligned using a preset iterative closest point algorithm to determine the complete grape fruit bunch information at the same position, wherein the point cloud collection position representation refers to the specific spatial coordinates and related status information of each grape fruit bunch at the time of collection in the grape orchard, and the complete grape fruit bunch information at the same position refers to processing all point cloud data of each grape fruit bunch at different perspectives, and finally obtaining a detailed and complete grape fruit bunch point cloud model at that position.

[0079] In some embodiments, before determining grape bunch point cloud data of each grape bunch at different viewing angles and its corresponding point cloud collection position collected by a structured light camera in a robotic arm of the picking robot, and registering the grape bunch point cloud data at different viewing angles using a preset iterative closest point algorithm to determine complete grape bunch information at the same position, the method includes:

[0080] The structured light camera in the robotic arm of the picking robot is used to collect viewing angle information at different positions in the target grape orchard, and each posture parameter of the robotic arm is recorded, wherein the posture parameters include position coordinates and rotation angles.

[0081] In some embodiments, the structured light camera is a device that uses structured light technology for 3D imaging. This camera typically projects a specific pattern of light (e.g., stripes, dots, or other shapes) onto a surface and captures the deformation of this light pattern, thereby obtaining 3D shape and depth information of individual grape bunches in a grape orchard.

[0082] In some embodiments, a structured light camera mounted on the robotic arm of a harvesting robot collects grape cluster point cloud data corresponding to each grape cluster in the orchard and records the point cloud acquisition location of each grape cluster, laying the foundation for subsequent data processing. A preset iterative closest point (ICP) algorithm is used to align the grape cluster point cloud data from different perspectives to determine the complete grape cluster information at the same location. The ICP algorithm is then used to align multi-viewpoint point clouds at the same location to obtain complete information about the same grape cluster. This process helps identify and integrate information from different perspectives, resulting in more accurate grape cluster features.

[0083] Step S30: Based on the point cloud collection positions corresponding to the grape bunches, the complete grape bunch information at different positions is integrated in the grape orchard spatial model to determine the grape bunch coordinates and overall distribution information corresponding to each grape bunch in the two-dimensional grid map of the grape orchard;

[0084] After determining the complete grape bunch information at the same location, integrating the complete grape bunch information at different locations in the grape orchard spatial model based on the point cloud collection location corresponding to each grape bunch, to determine the corresponding grape bunch coordinates and overall distribution information of each grape bunch on the two-dimensional grid map of the grape orchard;

[0085] Specifically, the spatial model is used to integrate grape bunch information from different locations, combining the recorded point cloud collection locations. The goal of this process is to determine the distribution of individual grape bunches throughout the orchard. By integrating grape bunch information from different locations and forming an overall grape bunch distribution map, the distribution of grape bunches of different types or varieties within the orchard and the distribution of different individual grape bunches in different areas of the orchard can be determined.

[0086] As well as the specific coordinate position of each grape bunch on the map, this grape bunch distribution map information is very important for the division of the picking robot's working area.

[0087] As can be seen from the above steps, the robotic arm's onboard structured light camera, grape bunch point cloud data collection, data registration, and spatial integration ultimately achieve accurate identification and positioning of grape bunches within the orchard. This provides the necessary information foundation for the harvesting robot's work area division, enabling it to perform this division more efficiently and accurately. This method not only improves the robotic arm's operating efficiency but also enhances the feasibility of performing work area division for the harvesting robot in complex environments.

[0088] Step S40: determining the DH standard parameters corresponding to each joint in the robotic arm, obtaining the homogeneous transformation matrix of each joint in the robotic arm based on the DH standard parameters to determine the position and posture of the end effector of the robotic arm, and using a probability density function to determine the picking area of ​​the robotic arm based on the multiple end effector positions;

[0089] After determining the grape fruit bunch coordinates and overall distribution information corresponding to each grape fruit bunch on the two-dimensional grid map of the grape orchard, determining the DH standard parameters corresponding to each joint in the robotic arm, obtaining the homogeneous transformation matrix of each joint in the robotic arm based on the DH standard parameters to determine the end effector position and posture of the robotic arm, and using a probability density function to determine the picking area of ​​the robotic arm based on the multiple end effector positions, wherein the probability density function includes a Gaussian distribution model or a Gaussian mixture model, etc.;

[0090] In some embodiments, determining DH standard parameters corresponding to each joint in the robotic arm, obtaining a homogeneous transformation matrix of each joint in the robotic arm based on the DH standard parameters to determine the position and posture of the end effector of the robotic arm, and using a probability density function to determine the picking area of ​​the robotic arm based on multiple end effector positions includes:

[0091] Step S401: Acquire the joint angle, joint offset, connecting rod length, and connecting rod torsion angle corresponding to each joint in the robotic arm of the picking robot, wherein the DH (Denavit-Hartenberg) standard parameters include the joint angle, joint offset, connecting rod length, and connecting rod torsion angle;

[0092] Step S402: determining a homogeneous transformation matrix corresponding to each joint based on the joint angle, joint offset, connecting rod length, and connecting rod torsion angle corresponding to each joint, and multiplying the homogeneous transformation matrices corresponding to each joint to determine the position and posture of the end effector of the robotic arm;

[0093] Step S403: sampling the end effector position multiple times and recording the multiple end effector positions, and calculating and determining the probability density of each end effector position based on the multiple end effector positions using a preset probability density function;

[0094] Step S404: Detect whether the probability density of the end effector position exceeds a preset probability density threshold. If so, use the position exceeding the preset probability density threshold as the picking area of ​​the robotic arm.

[0095] The probability density function, which includes a Gaussian distribution model or a Gaussian mixture model, obtains the joint angles, joint offsets, link lengths, and link torsion angles corresponding to each joint in the robotic arm of the harvesting robot. Based on the joint angles, joint offsets, link lengths, and link torsion angles, a homogeneous transformation matrix corresponding to each joint is determined. The homogeneous transformation matrices corresponding to each joint are multiplied to determine the position and posture of the robotic arm's end effector. The end effector position is sampled multiple times and recorded. A predetermined probability density function is used to calculate the probability density of each end effector position based on the multiple end effector positions. The probability density of the end effector position is then tested to see if it exceeds a predetermined probability density threshold. If so, the position exceeding the predetermined probability density threshold is designated as the harvesting area of ​​the robotic arm. Using the predetermined probability density function and calculating the probability density of the end effector position effectively determines the harvesting area that exceeds the predetermined probability density threshold. This method helps optimize the harvesting process, improve work efficiency, and reduce unnecessary operations. Ultimately, the selection of the harvesting area makes the system more intelligent and efficient under specific circumstances.

[0096] Step S50: determining the reachable area corresponding to each grape bunch based on the grape bunch coordinates corresponding to each grape bunch and the picking area of ​​the robotic arm; dividing the operating area of ​​the picking robot in the target grape orchard according to the overall distribution information of each grape bunch and the reachable area corresponding to each grape bunch, so as to complete the division of the picking robot orchard operating area of ​​the picking robot.

[0097] After determining the picking area of ​​the robotic arm according to the positions of the multiple end effectors using a probability density function, determining the reachable area corresponding to each grape bunch based on the grape bunch coordinates corresponding to each grape bunch and the picking area of ​​the robotic arm, and dividing the operating area of ​​the picking robot in the target grape orchard according to the overall distribution information of each grape bunch and the reachable area corresponding to each grape bunch, so as to complete the division of the picking robot's orchard operating area.

[0098] In some embodiments, Figure 3 Schematic diagram of the accessible area of ​​the grape bunch in this embodiment, wherein: Figure 3 A1, A2 and A3 are accessible areas, and g1, g2 and g3 are grape bunches.

[0099] In some embodiments, the step of determining the reachable area corresponding to each grape bunch based on the grape bunch coordinates corresponding to each grape bunch and the picking area of ​​the robotic arm includes:

[0100] Step S501: A spherical area is obtained with the coordinates of each grape bunch in the target grape orchard as the center and the picking area of ​​the robotic arm as the radius, and the spherical area is used as the reachable area corresponding to each grape bunch. The spherical area is the spatial position where the picking robot can pick the grape bunch;

[0101] Step S502: Project the spherical area of ​​each grape bunch in the target grape orchard onto a two-dimensional plane to determine a circular area corresponding to each grape bunch, and use the circular area as the reachable plane of each grape bunch.

[0102] Furthermore, the step of dividing the operation area of ​​the picking robot in the target grape orchard according to the overall distribution information of the grape bunches and the reachable areas corresponding to the grape bunches includes:

[0103] Step S5001: Taking the first grape bunch close to the origin of the two-dimensional grid map of the grape orchard as the starting point and the diameter of the picking area of ​​the robotic arm as the radius, a circular coverage area is determined, and the grape bunches within the circular coverage area are numbered as grape bunch P0, grape bunch P1, grape bunch P2, grape bunch P3, and grape bunch P4 according to the distance between each grape bunch and the origin of the map from near to far.

[0104] Taking the first grape bunch close to the origin of the two-dimensional grid map of the grape orchard as the starting point and the diameter of the picking area of ​​the robotic arm as the radius, a circular coverage area is determined. The grape bunches within the circular coverage area are numbered as grape bunch P0, grape bunch P1, grape bunch P2, grape bunch P3, and grape bunch P4 according to the distance between each grape bunch and the origin of the mapping, from near to far.

[0105] Step S5002: determining the reachable areas corresponding to the grape bunch P1, grape bunch P2, grape bunch P3, and grape bunch P4 within the circular coverage area;

[0106] Step S5003: determining whether the reachable area corresponding to the grape bunch P1 and the reachable area corresponding to the grape bunch P2 intersect; if the reachable areas corresponding to the grape bunch P1 and the grape bunch P2 do not intersect, using the reachable plane of the grape bunch P1 as the operation area D1;

[0107] Step S5004: If the reachable area corresponding to the grape bunch P1 intersects with the reachable area corresponding to the grape bunch P2, the intersection is recorded as intersection T1. A determination is then made as to whether the intersection T1 intersects with the reachable area corresponding to the grape bunch P3. If so, the intersection is recorded as intersection T2. ​​If not, the intersection T1 is used as the operation area D1.

[0108] Step S5005: sequentially determining whether the reachable areas corresponding to the grape bunches with later numbers intersect with the reachable areas corresponding to the grape bunches with earlier numbers, until the determination of the grape bunches P1, P2, P3, and P4 within the circular coverage area is completed;

[0109] Step S5006: Repeat the above steps until the reachable areas of all grape bunches in the target grape orchard are determined, so as to determine the operating area of ​​the picking robot in the target grape orchard.

[0110] Specifically, the step of dividing the operation area of ​​the picking robot in the target grape orchard according to the overall distribution information of the grape bunches and the reachable areas corresponding to the grape bunches includes:

[0111] Step S1100: Taking the first grape bunch close to the grape orchard mapping origin as the starting point and the diameter of the picking area of ​​the above-mentioned robot arm as the radius, determine a circular coverage area. Figure 4 and Figure 5 The distance between each grape bunch and the mapping origin is used as a judgment basis, and the grape bunches in the circular coverage area are numbered as grape bunch P0, grape bunch P1, grape bunch P2, grape bunch P3, and grape bunch P4 according to the distance between each grape bunch and the mapping origin from near to far;

[0112] Step S1200, please refer to Figure 6 , determine the reachable area of ​​each grape bunch within the circular coverage area;

[0113] Step S1300 , determining whether the reachable areas of grape bunch P1 and grape bunch P2 intersect; if so, recording the intersection as intersection T1; if not, using the reachable area of ​​grape bunch P1 as operation area D1.

[0114] Step S1400: If the reachable area corresponding to the grape bunch P1 intersects with the reachable area corresponding to the grape bunch P2, the intersection is recorded as intersection T1. A determination is then made as to whether the intersection T1 intersects with the reachable area corresponding to the grape bunch P3. If so, the intersection is recorded as intersection T2. ​​If not, the intersection T1 is used as the operation area D1.

[0115] Step S1500, please refer to Figure 7 Repeat the above steps to determine whether the reachable areas corresponding to the grape fruit clusters with later numbers intersect with the reachable areas corresponding to the grape fruit clusters with earlier numbers, until the grape fruit clusters P1, P2, P3, and P4 within the circular coverage area are determined;

[0116] Step S1600: Repeat the above steps until the reachable areas of all grape bunches in the target grape orchard are determined, so as to determine the operating area of ​​the picking robot in the target grape orchard.

[0117] In some embodiments, Figure 4 This is a schematic diagram of numbering grape bunches within the circular coverage area in this embodiment; Figure 5 Schematic diagram of recording grape bunches P0, P1, P2, P3, and P4 within the circular coverage area in this embodiment; Figure 6 Schematic diagram of the accessible area of ​​the fruit within the circular coverage area in this embodiment; Figure 7 Schematic diagram of determining the operation area D1 in this embodiment; wherein P0, P1, P2, P3, and P4 are grape bunches in a grape orchard, and D1 is the operation area.

[0118] Compared with the prior art, the present application addresses the problems of the prior art method for dividing the working area of ​​the picking robot, such as a large number of divisions, low division efficiency, and low division accuracy, which make it impossible to focus on the concentrated areas where grapes are distributed and to accurately pick the grapes. The present application has, but is not limited to, the following beneficial effects:

[0119] This application obtains fruit information through a structured light camera, and integrates the fruits through the established spatial model to obtain the distribution information and distribution coordinates of the fruits in the orchard. Finally, the orchard area is divided to obtain the operating area of ​​the picking robot. This application proposes a new idea for the division of operating areas of picking robots equipped with robotic arms in orchards with uneven distribution of grape fruits. The orchard operating area division method of the picking robot of this application can obtain a much smaller number of operating areas than the operating areas obtained by traditional solutions, and can focus on the concentrated areas where grape fruits are distributed for picking, greatly improving the accuracy and efficiency of automated grape picking; significantly improving the overall operating efficiency of the picking robot, precise positioning and detection, optimized path planning and efficient operation capabilities, which can significantly improve the picking speed and quality of grapes, thereby increasing the yield and economic benefits of the vineyard.

[0120] See also Figure 8A picking robot orchard operation area division device is provided to meet one of the purposes of this application, including a space model construction module 1100, a fruit information determination module 1200, a fruit distribution information determination module 1300, a picking area determination module 1400 and an operation area division module 1500. Among them, the spatial model construction module 1100 is configured to obtain the laser radar data and inertial measurement unit data in the information acquisition module of the picking robot, construct a two-dimensional grid map of the grape orchard based on the laser radar data and the inertial measurement unit data, and construct a grape orchard spatial model based on the spatial posture relationship between the information acquisition module and the picking module of the picking robot and the coordinate relationship between the grid map coordinate system of the two-dimensional grid map of the grape orchard and the grape orchard coordinate system; the fruit information determination module 1200 is configured to determine the grape fruit bunch point cloud data of each grape fruit bunch under different perspectives and its corresponding point cloud collection position collected by the structured light camera in the robotic arm of the picking robot, and use a preset iterative closest point algorithm to align the grape fruit bunch point cloud data under different perspectives to determine the complete grape fruit bunch information at the same position; the fruit distribution information determination module 1300 is configured to, based on the point cloud collection position corresponding to each grape fruit bunch, The complete grape bunch information of the position is integrated to determine the grape bunch coordinates and overall distribution information corresponding to each grape bunch under the two-dimensional grid map of the grape orchard; a picking area determination module 1400 is configured to determine the DH standard parameters corresponding to each joint in the robotic arm, obtain the homogeneous transformation matrix of each joint in the robotic arm according to the DH standard parameters, determine the position and posture of the end effector of the robotic arm, and use a probability density function to determine the picking area of ​​the robotic arm according to multiple end effector positions; an operation area division module 1500 is configured to determine the reachable area corresponding to each grape bunch based on the grape bunch coordinates corresponding to each grape bunch and the picking area of ​​the robotic arm, and divide the operation area of ​​the picking robot in the target grape orchard according to the overall distribution information of each grape bunch and the reachable area corresponding to each grape bunch, so as to complete the orchard operation area division of the picking robot.

[0121] Based on any embodiment of this application, please refer to Figure 9 Another embodiment of the present application further provides an electronic device, which can be implemented by a computer device, such as Figure 9As shown, a schematic diagram of the internal structure of a computer device. The computer device includes a processor, a computer-readable storage medium, a memory, and a network interface connected via a system bus. Among them, the computer-readable storage medium of the computer device stores an operating system, a database, and computer-readable instructions, and the database may store a control information sequence, and when the computer-readable instructions are executed by the processor, the processor may implement a method for dividing the orchard operating area of ​​a picking robot. The processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device. The memory of the computer device may store computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor may execute the method for dividing the orchard operating area of ​​a picking robot of the present application. The network interface of the computer device is used to connect and communicate with the terminal. Those skilled in the art will understand that Figure 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0122] In this embodiment, the processor is used to execute Figure 8 The memory stores the program code and various data required to execute the specific functions of each module and its submodule in the orchard operation area division device of the harvesting robot. The memory stores the program code and data required to execute the functions of all submodules in the orchard operation area division device of the harvesting robot. The server can call the server's program code and data to execute the functions of all submodules.

[0123] The present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the method for dividing the orchard operation area of ​​the picking robot described in any embodiment of the present application.

[0124] The present application also provides a computer program product, including a computer program / instruction, which, when executed by one or more processors, implements the steps of the method for dividing the orchard operation area of ​​the picking robot described in any embodiment of the present application.

[0125] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments of the present application can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The aforementioned storage medium can be a computer-readable storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0126] The above description is only part of the implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

[0127] To sum up, by adopting the orchard operation area division method of the harvesting robot of this application, the number of operation areas obtained is far less than the operation areas obtained by the traditional scheme, and it can focus on the concentrated areas where grape fruits are distributed for picking, greatly improving the accuracy and efficiency of automated grape picking; significantly improving the overall operation efficiency of the harvesting robot, precise positioning and detection, optimized path planning and efficient operation capabilities, which can significantly improve the picking speed and quality of grapes, thereby increasing the yield and economic benefits of the vineyard.

Claims

1. A method for dividing the operation area of ​​an orchard by a picking robot, characterized in that: include: Acquiring laser radar data and inertial measurement unit data from an information acquisition module of a picking robot, constructing a two-dimensional grid map of the grape orchard based on the laser radar data and the inertial measurement unit data, and constructing a grape orchard spatial model based on a spatial pose relationship between the information acquisition module and the picking module of the picking robot and a coordinate relationship between a grid map coordinate system of the two-dimensional grid map of the grape orchard and a grape orchard coordinate system; determining grape bunch point cloud data from different viewing angles of each grape bunch collected by a structured light camera in a robotic arm of the picking robot and its corresponding point cloud collection position, and registering the grape bunch point cloud data from different viewing angles using a preset iterative closest point algorithm to determine complete grape bunch information at the same position; Based on the point cloud collection positions corresponding to the grape bunches, the complete grape bunch information at different positions is integrated in the grape orchard spatial model to determine the grape bunch coordinates and overall distribution information corresponding to each grape bunch in the two-dimensional grid map of the grape orchard; Determine the DH standard parameters corresponding to each joint in the robotic arm, obtain the homogeneous transformation matrix of each joint in the robotic arm based on the DH standard parameters to determine the position and posture of the end effector of the robotic arm, and use a probability density function to determine the picking area of ​​the robotic arm based on multiple end effector positions; Based on the grape fruit bunch coordinates corresponding to each grape fruit bunch and the picking area of ​​the robotic arm, a reachable area corresponding to each grape fruit bunch is determined, and according to the overall distribution information of each grape fruit bunch and the reachable area corresponding to each grape fruit bunch, an operating area of ​​the picking robot in a target grape orchard is divided, which includes: taking the first grape fruit bunch close to the mapping origin of the grape orchard two-dimensional grid map as the starting point, and taking the diameter of the picking area of ​​the robotic arm as the radius, determining a circular coverage area, and recording the grape fruit bunches in the circular coverage area according to the distance between each grape fruit bunch and the mapping origin from near to far as numbered as grape fruit bunch P0, grape fruit bunch P1, grape fruit bunch P2, grape fruit bunch P3, and grape fruit bunch P4; Determine the reachable areas corresponding to the grape bunch P1, grape bunch P2, grape bunch P3, and grape bunch P4 within the circular coverage area; Determine whether the reachable area corresponding to the grape bunch P1 and the reachable area corresponding to the grape bunch P2 intersect; if the reachable areas corresponding to the grape bunch P1 and the grape bunch P2 do not intersect, use the reachable plane of the grape bunch P1 as the operation area D1; If the reachable area corresponding to the grape bunch P1 intersects with the reachable area corresponding to the grape bunch P2, the intersection is recorded as intersection T1. Further, it is determined whether the intersection T1 intersects with the reachable area corresponding to the grape bunch P3. If so, the intersection is recorded as intersection T2. ​​If not, the intersection T1 is used as the operation area D1. It is determined in sequence whether the reachable areas corresponding to the grape fruit clusters with later numbers intersect with the reachable areas corresponding to the grape fruit clusters with earlier numbers, until the grape fruit clusters P1, P2, P3, and P4 within the circular coverage area are determined; Repeat the above steps until the reachable areas of all grape bunches in the target grape orchard are determined, so as to determine the operating area of ​​the picking robot in the target grape orchard, thereby completing the division of the picking robot orchard operating area of ​​the picking robot.

2. The method for dividing the orchard operation area of ​​the picking robot according to claim 1, characterized in that: The steps of constructing a two-dimensional grid map of a grape orchard based on the lidar data and the inertial measurement unit data include: Determining laser radar data and inertial measurement unit data in the information acquisition module of the picking robot; constructing a three-dimensional grape orchard map of the target grape orchard based on the lidar data and the inertial measurement unit data using a preset simultaneous positioning and mapping algorithm; The three-dimensional map of the grape orchard is projected onto a two-dimensional plane to construct a two-dimensional grid map of the grape orchard.

3. The method for dividing an orchard operation area for a picking robot according to claim 1, characterized in that: Before the step of determining grape fruit bunch point cloud data of each grape fruit bunch at different viewing angles and the corresponding point cloud collection position thereof collected by the structured light camera in the robotic arm of the picking robot, and registering the grape fruit bunch point cloud data at different viewing angles using a preset iterative closest point algorithm to determine the complete grape fruit bunch information at the same position, the method includes: The structured light camera in the robotic arm of the picking robot is used to collect viewing angle information at different positions in the target grape orchard, and each posture parameter of the robotic arm is recorded, wherein the posture parameters include position coordinates and rotation angles.

4. The method for dividing an orchard operation area for a picking robot according to claim 1, characterized in that: The steps of determining DH standard parameters corresponding to each joint in the robotic arm, obtaining a homogeneous transformation matrix of each joint in the robotic arm according to the DH standard parameters to determine the position and posture of the end effector of the robotic arm, and using a probability density function to determine the picking area of ​​the robotic arm according to the multiple end effector positions include: Obtaining the joint angle, joint offset, connecting rod length, and connecting rod torsion angle corresponding to each joint in the robotic arm of the picking robot, wherein the DH standard parameters include the joint angle, joint offset, connecting rod length, and connecting rod torsion angle; Determine a homogeneous transformation matrix corresponding to each joint according to the joint angle, joint offset, connecting rod length, and connecting rod torsion angle corresponding to each joint, and multiply the homogeneous transformation matrices corresponding to each joint to determine the position and posture of the end effector of the robotic arm; Sampling the end effector position multiple times and recording the multiple end effector positions, and calculating and determining the probability density of each end effector position based on the multiple end effector positions using a preset probability density function; Detect whether the probability density of the end effector position exceeds a preset probability density threshold; if so, use the position exceeding the preset probability density threshold as the picking area of ​​the robotic arm.

5. The method for dividing the orchard operation area of ​​the picking robot according to claim 1, characterized in that: The step of determining the reachable area corresponding to each grape bunch based on the grape bunch coordinates corresponding to each grape bunch and the picking area of ​​the robotic arm includes: A spherical area is obtained with the coordinates of each grape bunch in the target grape orchard as the center and the picking area of ​​the robotic arm as the radius, and the spherical area is used as the reachable area corresponding to each grape bunch, wherein the spherical area is the spatial position where the picking robot can pick the grape bunch; The spherical area of ​​each grape bunch in the target grape orchard is projected onto a two-dimensional plane to determine a circular area corresponding to each grape bunch, and the circular area is used as the reachable plane of each grape bunch.

6. The method for dividing orchard operation areas of a picking robot according to claim 2, characterized in that: The point cloud collection position representation refers to the specific spatial coordinates and related status information of each grape bunch when collected in the grape orchard; the probability density function includes a Gaussian distribution model or a Gaussian mixture model, and the simultaneous positioning and mapping algorithm includes a FASTLIO algorithm, a LIOSAM algorithm, or an R3live algorithm.

7. A device for dividing an orchard operation area for a picking robot, applied to the method for dividing an orchard operation area for a picking robot according to claim 1, characterized in that: include: a spatial model construction module configured to obtain laser radar data and inertial measurement unit data from an information acquisition module of a picking robot, construct a two-dimensional grid map of the grape orchard based on the laser radar data and the inertial measurement unit data, and construct a grape orchard spatial model based on a spatial posture relationship between the information acquisition module and the picking module of the picking robot and a coordinate relationship between a grid map coordinate system of the two-dimensional grid map of the grape orchard and a grape orchard coordinate system; a fruit information determination module configured to determine grape fruit cluster point cloud data of each grape fruit cluster at different viewing angles and corresponding point cloud acquisition positions collected by a structured light camera in a robotic arm of the picking robot, and to register the grape fruit cluster point cloud data at different viewing angles using a preset iterative closest point algorithm to determine complete grape fruit cluster information at the same position; a fruit distribution information determination module configured to integrate complete grape fruit bunch information at different locations in the grape orchard spatial model based on point cloud collection locations corresponding to each grape fruit bunch, so as to determine grape fruit bunch coordinates and overall distribution information corresponding to each grape fruit bunch in the grape orchard two-dimensional grid map; a picking area determination module configured to determine DH standard parameters corresponding to each joint in the robotic arm, obtain a homogeneous transformation matrix of each joint in the robotic arm based on the DH standard parameters to determine the position and posture of the end effector of the robotic arm, and use a probability density function to determine the picking area of ​​the robotic arm based on multiple end effector positions; an operating area division module configured to determine a reachable area corresponding to each grape fruit bunch based on the grape fruit bunch coordinates corresponding to each grape fruit bunch and the picking area of ​​the robotic arm, and divide the operating area of ​​the picking robot in the target grape orchard according to the overall distribution information of each grape fruit bunch and the reachable area corresponding to each grape fruit bunch, comprising: taking the first grape fruit bunch close to the mapping origin of the grape orchard two-dimensional grid map as the starting point and taking the diameter of the picking area of ​​the robotic arm as the radius, determining a circular coverage area, and recording the grape fruit bunches within the circular coverage area according to the distance between each grape fruit bunch and the mapping origin from near to far as numbered as grape fruit bunch P0, grape fruit bunch P1, grape fruit bunch P2, grape fruit bunch P3, and grape fruit bunch P4; Determine the reachable areas corresponding to the grape bunch P1, grape bunch P2, grape bunch P3, and grape bunch P4 within the circular coverage area; Determine whether the reachable area corresponding to the grape bunch P1 and the reachable area corresponding to the grape bunch P2 intersect; if the reachable areas corresponding to the grape bunch P1 and the grape bunch P2 do not intersect, use the reachable plane of the grape bunch P1 as the operation area D1; If the reachable area corresponding to the grape bunch P1 intersects with the reachable area corresponding to the grape bunch P2, the intersection is recorded as intersection T1. Further, it is determined whether the intersection T1 intersects with the reachable area corresponding to the grape bunch P3. If so, the intersection is recorded as intersection T2. ​​If not, the intersection T1 is used as the operation area D1. It is determined in sequence whether the reachable areas corresponding to the grape fruit clusters with later numbers intersect with the reachable areas corresponding to the grape fruit clusters with earlier numbers, until the grape fruit clusters P1, P2, P3, and P4 within the circular coverage area are determined; Repeat the above steps until the reachable areas of all grape bunches in the target grape orchard are determined, so as to determine the operating area of ​​the picking robot in the target grape orchard, thereby completing the division of the picking robot orchard operating area of ​​the picking robot.

8. An electronic device comprising a central processing unit and a memory, characterized in that: The central processing unit is configured to call and run a computer program stored in the memory to execute the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that It stores a computer program implemented according to the method described in any one of claims 1 to 6 in the form of computer-readable instructions, and when the computer program is called and executed by a computer, the steps included in the corresponding method are executed.

Images