Mushroom mechanical arm reset control method and system based on path planning

Abstract

The invention discloses a reset control method and system of a mushroom mechanical arm based on path planning, relates to the technical field of path planning, and determines the clamping action of the mushroom mechanical arm according to the detection of a clamping path. And according to the clamping action and the corresponding clamping posture parameters, the clamping grade of the mushroom frame by the mushroom mechanical arm is determined, the clamping grade of the mushroom frame by the mushroom mechanical arm is guaranteed, and accurate clamping of the mushroom frame by the mushroom mechanical arm is achieved. Therefore, according to the position variable quantity of the first obstacle and the moving path of the mushroom mechanical arm, reverse reset of the mushroom mechanical arm is triggered; in the reverse reset process of the mushroom mechanical arm, the abnormal posture of the mushroom frame is determined based on the multiple posture parameters of the mushroom frame, and the mushroom mechanical arm is triggered to dynamically and stably control the mushroom frame according to the abnormal posture of the mushroom frame and the corresponding abnormal position, so that the reverse reset accuracy of the mushroom mechanical arm is guaranteed, and the mushroom frame is prevented from being damaged. And the dynamic stability of the mushroom mechanical arm to the mushroom frame is further improved.

Description

Technical Field

[0001] This invention relates to the technical field of path planning, and in particular to a reset control method and system for a mushroom robotic arm based on path planning. Background Technology

[0002] With the development of technology, mushroom robotic arms have emerged as a type of robotic arm and are applied in the automated cultivation of mushrooms. These robotic arms grip and reposition mushroom frames. At this time, path planning is performed based on the positions of the robotic arm and the mushroom frame. During the planning process, a first movement path and a second movement path are determined. Both the first and second movement paths require specific planning. Furthermore, the second movement path serves as a reset path and needs to be replanned after the robotic arm grips the mushroom frame. Failure to fully utilize the first movement path and neglecting the gripping level of the mushroom frame by the robotic arm affects the accuracy of the reverse reset of the robotic arm and cannot guarantee the dynamic stability of the robotic arm with respect to the mushroom frame. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of the prior art. This invention provides a reset control method and system for a mushroom robotic arm based on path planning.

[0004] This invention provides a reset control method for a mushroom-growing robotic arm based on path planning, comprising: determining the gripping path of the mushroom-growing robotic arm based on its current position and the target clamping position; determining the movement path and clamping path of the mushroom-growing robotic arm based on the division of the gripping path, identifying multiple first obstacles based on the traversal of the movement path, and the mushroom-growing robotic arm avoiding multiple first obstacles during movement; determining the gripping action of the mushroom-growing robotic arm based on the detection of the gripping path, and determining the gripping level of the mushroom frame by the mushroom-growing robotic arm based on the gripping action and the corresponding gripping posture parameters; if the mushroom-growing robotic arm completes the gripping of the mushroom frame, then collecting multiple first obstacles... The position change of an obstacle is used to trigger the reverse reset of the mushroom robotic arm based on the position change and the movement path of the mushroom robotic arm. The position change reflects the movement of the first obstacle during the operation of the mushroom robotic arm. During the reverse reset of the mushroom robotic arm, the abnormal posture of the mushroom frame is determined based on multiple posture parameters of the mushroom frame, and the dynamic and stable control of the mushroom frame by the mushroom robotic arm is triggered based on the abnormal posture and the corresponding abnormal position of the mushroom frame. During the execution, the status of the robotic arm and the mushroom frame is monitored in real time using sensors. If an abnormal situation or deviation from the expectation is detected, the system needs to adjust the control commands in a timely manner to ensure dynamic and stable control.

[0005] This invention provides a reset control system for a mushroom-growing robotic arm based on path planning. The reset control system is applied to the aforementioned reset control method for a mushroom-growing robotic arm based on path planning. The reset control system includes: The gripping path module is used to determine the gripping path of the mushroom robotic arm based on the current position of the mushroom robotic arm and the target gripping position. The obstacle module is used to determine the movement path and clamping path of the mushroom robot arm based on the division of the gripping path, and to determine multiple first obstacles based on the traversal of the movement path. The mushroom robot arm avoids multiple first obstacles during the movement. The gripping level module is used to determine the gripping action of the mushroom robot arm based on the detection of the gripping path, and to determine the gripping level of the mushroom robot arm on the mushroom frame based on the gripping action and the corresponding gripping posture parameters. The reverse reset module is used to collect the position changes of multiple first obstacles when the mushroom robot arm completes the gripping of the mushroom frame, and trigger the reverse reset of the mushroom robot arm based on the position changes and the movement path of the mushroom robot arm. The dynamic stabilization control module is used to determine the abnormal posture of the mushroom frame based on multiple posture parameters during the reverse reset process of the mushroom robot arm, and to trigger the dynamic stabilization control of the mushroom frame by the mushroom robot arm according to the abnormal posture and the corresponding abnormal position of the mushroom frame.

[0006] Compared with the prior art, the beneficial effects of the present invention are: In this embodiment of the invention, multiple first obstacles are determined based on the traversal of the movement path, and the mushroom robotic arm avoids these obstacles during its movement. The gripping action of the mushroom robotic arm is determined based on the detection of the gripping path, and the gripping level of the mushroom robotic arm on the mushroom frame is determined based on the gripping action and the corresponding gripping posture parameters. This approach incorporates the movement path and clamping path of the mushroom robotic arm, taking into account the overall consideration of the gripping action and the corresponding gripping posture parameters, thus ensuring the gripping level of the mushroom robotic arm on the mushroom frame and achieving precise gripping of the mushroom frame by the mushroom robotic arm.

[0007] Therefore, if the mushroom robotic arm completes the gripping of the mushroom frame, it collects the position changes of multiple first obstacles. Based on these position changes and the movement path of the mushroom robotic arm, it triggers the reverse reset of the mushroom robotic arm. During the reverse reset process, the abnormal posture of the mushroom frame is determined based on multiple posture parameters of the mushroom frame. Based on the abnormal posture and the corresponding abnormal position of the mushroom frame, the dynamic stability control of the mushroom robotic arm on the mushroom frame is triggered. This introduces the reverse reset of the mushroom robotic arm and makes full use of the position changes and the movement path of the mushroom robotic arm, ensuring the accuracy of the reverse reset of the mushroom robotic arm and further improving the dynamic stability of the mushroom robotic arm on the mushroom frame. Attached Figure Description

[0008] Figure 1 This is a flowchart illustrating the reset control method for a mushroom robotic arm based on path planning in an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of the reset control system of the mushroom robotic arm based on path planning in an embodiment of the present invention. Detailed Implementation

[0009] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0010] Please see Figure 1 and Figure 2 A reset control method for a mushroom cultivation robotic arm based on path planning includes: Step S100: Determine the gripping path of the mushroom robotic arm based on the current position of the mushroom robotic arm and the target clamping position; Step S200: Determine the movement path and clamping path of the mushroom robotic arm based on the division of the gripping path, and determine multiple first obstacles based on the traversal of the movement path. The mushroom robotic arm avoids multiple first obstacles during the movement. Step S300: Determine the gripping action of the mushroom robotic arm based on the detection of the gripping path, and determine the gripping level of the mushroom robotic arm on the mushroom frame based on the gripping action and the corresponding gripping posture parameters. Step S400: If the mushroom robotic arm completes the gripping of the mushroom frame, the position change of multiple first obstacles is collected, and the reverse reset of the mushroom robotic arm is triggered according to the position change and the movement path of the mushroom robotic arm. Step S500: During the reverse reset process of the mushroom robot arm, the abnormal posture of the mushroom frame is determined based on multiple posture parameters of the mushroom frame, and the dynamic and stable control of the mushroom robot arm on the mushroom frame is triggered according to the abnormal posture and the corresponding abnormal position of the mushroom frame. In step S100, the gripping path of the mushroom robotic arm is determined based on the current position of the mushroom robotic arm and the target clamping position. In the specific implementation of this invention, the specific steps are as follows: S110: Collect the number of the mushroom robotic arm, determine the action content of the mushroom robotic arm based on the number of the mushroom robotic arm and the mushroom database, and at the same time, monitor the mushroom robotic arm in real time and collect the current position of the mushroom robotic arm. S120: Mark the degrees of freedom of the mushroom robotic arm, determine the first path set based on the current position and degrees of freedom of the mushroom robotic arm; at the same time, determine the target clamping position of the mushroom robotic arm based on the recognition of the action content of the mushroom robotic arm, and determine the second path set based on the target clamping position and degrees of freedom of the mushroom robotic arm. S130: Determine the gripping path of the mushroom robotic arm based on the matching of the first path set and the second path set. The gripping path covers the continuous path between the current position of the mushroom robotic arm and the target clamping position.

[0011] In the embodiments of this application, each robotic arm is assigned a unique number during production or deployment. This number is usually a serial number or a string that can uniquely identify the robotic arm. In the system, this number is used to retrieve information related to the robotic arm, such as configuration, history, preset actions, etc. When the system needs to perform a task, it first identifies the currently available robotic arms, which is usually achieved by scanning the barcode on the robotic arm, reading the RFID tag, or requesting the robotic arm to report its number via the network.

[0012] Once the robotic arm's serial number is obtained, the system accesses a database that stores information related to the robotic arm, including its model, configuration, preset actions, and the association between these actions and specific tasks or mushroom species. The system retrieves this information based on the robotic arm's serial number and determines the specific actions that the robotic arm needs to perform.

[0013] After determining the action that the robotic arm needs to perform, the system needs to know the current position of the robotic arm in order to plan the path from the current position to the target position. This is usually achieved by sensors integrated on the robotic arm (such as GPS, inertial navigation system, or visual positioning system). These sensors can provide the position data of the robotic arm in real time, including its coordinates in three-dimensional space.

[0014] Furthermore, the system needs to determine the direction and range of free movement that the mushroom-growing robotic arm can freely move when performing a specific task, i.e., its degrees of freedom. The degrees of freedom of the robotic arm typically include rotation, translation, and other actions. The combination of these actions allows the robotic arm to reach any position within the workspace. The system will label these degrees of freedom according to the model and configuration of the robotic arm and the requirements of the current task. At this point, for a six-degree-of-freedom robotic arm, the system will label its translational degrees of freedom in the X, Y, and Z directions and its rotational degrees of freedom around these three axes. When performing a harvesting task, the system will selectively use these degrees of freedom according to the current posture of the robotic arm and the requirements of the task.

[0015] After determining the degrees of freedom of the robotic arm, the system needs to plan one or more paths based on the current position of the robotic arm and the task objective (such as the picking point). These paths are called the first set of paths, which represent the various ways the robotic arm can reach the task objective from its current position. The system uses a path planning algorithm, combined with the physical constraints of the robotic arm (such as joint angle constraints, range of motion constraints, etc.) and obstacle information in the environment, to generate these paths. At this point, suppose the robotic arm is currently located in one corner of the greenhouse, while the mushrooms to be picked are located at the other end of the greenhouse. The system will plan multiple paths based on the degrees of freedom of the robotic arm (such as six degrees of freedom) and obstacles in the greenhouse (such as other robotic arms, shelves, doors, etc.). These paths will take into account the need for the robotic arm to avoid collisions during movement and will try to optimize movement time and energy consumption.

[0016] The system needs to determine the target position of the robotic arm when performing the clamping action, i.e., the target clamping position. This target position is usually determined based on task requirements (such as picking a specific type of mushroom) and the physical characteristics of the robotic arm (such as the size and shape of the gripper). Once the target clamping position is determined, the system will plan a path from the current position (or a point in the first path set) to the target clamping position based on the robotic arm's degrees of freedom and obstacle information in the environment. These paths are called the second path set. At this point, in the task of picking shiitake mushrooms, the system will determine a precise target clamping position based on the size and position of the shiitake mushrooms. Then, the system will plan a path from the current position (or the optimal path point in the first path set) to the target clamping position based on the robotic arm's degrees of freedom and obstacle information in the greenhouse. This path will ensure that the robotic arm can perform the clamping action in the correct posture when it reaches the target position.

[0017] Specifically, suppose that in a greenhouse, a six-DOF robotic arm, numbered "ABC230," needs to harvest mature shiitake mushrooms located at the other end of the greenhouse. The system first marks the six degrees of freedom of the robotic arm (translation and rotation in the X, Y, and Z directions). Then, based on the current position of the robotic arm and the obstacle information in the greenhouse, the system plans multiple paths as a first set of paths. Next, the system determines the target clamping position based on the position and size of the shiitake mushrooms, and plans a path from the current position (or the optimal path point in the first set of paths) to the target clamping position based on the degrees of freedom of the robotic arm and the obstacle information as a second set of paths. Finally, the system selects the optimal path in the second set of paths to guide the robotic arm to complete the harvesting task.

[0018] Therefore, the gripping path of the mushroom robotic arm is determined based on the matching of the first path set and the second path set. This gripping path covers the continuous path between the current position of the mushroom robotic arm and the target clamping position, and takes into account the overall consideration of matching the first path set and the second path set, thus ensuring the accuracy of the gripping path of the mushroom robotic arm.

[0019] At this point, the system needs to match the first set of paths (the set of paths from the current position of the robotic arm to the midpoint) and the second set of paths (the set of paths from the midpoint to the target clamping position) to determine a complete clamping path from the current position to the target clamping position. The matching process considers multiple factors, such as path length, movement time, energy consumption, and obstacle density on the path. The system uses optimization algorithms (such as the shortest path algorithm) to find the optimal matching path. At this point, the system first traverses each path in the first set of paths, and for each path, it attempts to match it with the path in the second set of paths. During matching, the system calculates the connection points between paths (i.e., the end point of the first path and the start point of the second path) and checks whether these connection points are feasible in the actual environment (e.g., without obstacles). The system also evaluates the length, time cost, etc. of the complete path after matching to determine the optimal clamping path.

[0020] Once the optimal matching path is found, the system will determine it as the gripping path for the mushroom robotic arm. This path should be continuous, starting from the current position of the robotic arm, passing through one or more intermediate points, and finally reaching the target clamping position. Each point on the path should take into account the physical limitations of the robotic arm (such as joint angles, range of motion, etc.) and obstacles in the environment. At the same time, when determining the gripping path, the system will generate a detailed path description, including the coordinates of each point on the path, the posture of the robotic arm at each point (i.e., joint angles), and the movement instructions from one point to the next. This path description will then be sent to the robotic arm's control system to guide the robotic arm to move along the planned path and perform the clamping action.

[0021] Specifically, a path matching table is collected, as shown in Table 1:

[0022] In the example above, combination 4 scored the highest (95 points), so it was chosen as the gripping path.

[0023] In step S200, the movement path and clamping path of the mushroom robotic arm are determined according to the division of the gripping path, and multiple first obstacles are determined according to the traversal of the movement path. The mushroom robotic arm avoids multiple first obstacles during the movement. In the specific implementation of this invention, the specific steps are as follows: S210: Collect the gripping path, determine multiple moving nodes and multiple clamping nodes based on the recognition of the gripping path, and determine the movement path of the mushroom robotic arm according to the shape of the gripping end of the mushroom robotic arm and the multiple moving nodes. S220: Determine the movement space of the mushroom robotic arm based on its movement path, and capture real-time images of the movement space. Based on the detection of the real-time images, identify multiple first obstacles and mark the original positions of the multiple first obstacles. At this time, the mushroom robotic arm moves along the movement path and maintains a safe distance from adjacent first obstacles to avoid the original positions of the first obstacles. S230: Determine the clamping path of the mushroom robotic arm based on the shape of the gripping end and multiple clamping nodes, and mark the gripping action of the gripping end of the mushroom robotic arm at multiple clamping nodes in the clamping path.

[0024] In the embodiments of this application, the system needs to obtain the gripping path of the mushroom robotic arm from the current position to the target gripping position. This path is generated by the path planning algorithm and is also obtained by other means (such as manual teaching). The gripping path is usually a continuous curve or polyline, which describes the trajectory that the robotic arm needs to go through when performing the gripping task. At this time, it is assumed that the system has generated a gripping path from the starting point A to the target point B by the path planning algorithm. This path is an optimized smooth curve that takes into account the physical limitations of the robotic arm (such as joint angles and range of motion) and obstacles in the environment.

[0025] After obtaining the gripping path, the system needs to identify multiple moving nodes along this path. These nodes are key positions that the robotic arm needs to reach during its movement. They divide the gripping path into multiple segments, allowing the robotic arm to gradually approach the target position. The number and position of the moving nodes usually depend on the complexity of the gripping path and the control precision of the robotic arm. At the same time, the system will evenly distribute some moving nodes along the gripping path, such as A1, A2, A3, etc. Each node represents a key position of the robotic arm during its movement. The positions of these nodes will be determined based on the shape of the gripping path and the robotic arm's motion capability to ensure that the robotic arm can pass through these positions smoothly and accurately.

[0026] In addition to the moving nodes, the system also needs to determine one or more clamping nodes on the gripping path. These nodes are the specific locations where the robotic arm performs the clamping action, usually near the target object. The location and number of clamping nodes depend on the size, shape and position of the target object, as well as the shape and capability of the robotic arm's gripping end.

[0027] The system needs to combine the shape of the robotic arm's gripping end with the previously determined movement nodes to further refine the robotic arm's movement path. This includes determining the specific motion trajectory, speed, and acceleration parameters of the robotic arm between each movement node to ensure that the robotic arm can smoothly and quickly pass through these nodes and finally reach the clamping node. At the same time, the system will use inverse kinematics algorithms to calculate the specific joint angles and motion trajectory of the robotic arm between each node based on the shape of the robotic arm's gripping end (such as size, shape, material, etc.) and the position of the movement nodes. Then, based on these calculation results, the system will generate a detailed description of the movement path, including the coordinates of each point on the path, the posture of the robotic arm at each point (i.e., joint angles), and the movement command from one point to the next.

[0028] Furthermore, the movement space of the mushroom robotic arm is determined based on its movement path, and real-time images of this movement space are captured. Multiple first obstacles are identified based on the detection of these real-time images, and their original positions are marked. At this time, the mushroom robotic arm moves along the movement path and maintains a safe distance from adjacent first obstacles to avoid their original positions. This approach takes into account the overall movement path of the mushroom robotic arm and ensures the accuracy of its movement space.

[0029] At this point, the system first needs to define the movement space based on the movement path of the mushroom robotic arm. The movement space is usually a three-dimensional region that covers all the spatial positions occupied by the robotic arm during its movement. The determination of this space is crucial for subsequent obstacle detection and obstacle avoidance operations. At this time, the system will calculate and determine the movement space based on the movement path of the robotic arm, the size of the robotic arm (including length, width, height, etc.), and the posture changes of the robotic arm during its movement. This space is usually represented as one or more three-dimensional bounding boxes or bounding spheres to simplify calculation and processing.

[0030] Once the movement space is determined, the system needs to capture image information within this space in real time. This is usually accomplished by cameras installed around the robotic arm or within the movement space. The purpose of real-time image capture is to promptly detect and identify obstacles within the movement space. At this time, the system will be equipped with multiple high-definition cameras that cover the entire movement space to ensure there are no blind spots. The cameras will capture and transmit image information to the system's image processing module in real time. The image processing module will preprocess these images, such as denoising and enhancing contrast, to improve the accuracy of subsequent obstacle detection.

[0031] After acquiring real-time images, the system needs to use image processing and computer vision techniques to detect and identify obstacles in the images. These obstacles can be static (such as walls, pillars, etc.) or dynamic (such as other robotic arms, pedestrians, etc.). The system needs to be able to accurately distinguish these obstacles and determine their positions and shapes. At the same time, the system will use deep learning algorithms (such as convolutional neural networks CNN) to train an obstacle detection model. This model will receive real-time images as input and output information such as the position, size, and type of obstacles in the images. The system will then use this information to determine multiple primary obstacles within the moving space.

[0032] Once obstacles are detected, the system needs to mark their original positions. This positional information is crucial for subsequent obstacle avoidance operations, as it will guide the robotic arm on how to safely navigate around these obstacles. At the same time, the system assigns a unique identifier to each detected obstacle in three-dimensional space and records their original position information (such as coordinates, size, orientation, etc.). This information is stored in the system's obstacle database for reference and updates during subsequent movement and obstacle avoidance.

[0033] After determining the movement space and obstacle locations, the system guides the mushroom-growing robotic arm to move along a predetermined path. During the movement, the system needs to monitor the distance between the robotic arm and obstacles in real time, ensuring that the robotic arm always maintains a safe distance from adjacent obstacles. This safe distance is usually determined based on factors such as the size, speed, and acceleration of the robotic arm, as well as the type and location of the obstacles. At this time, the system uses sensors (such as lidar, ultrasonic sensors, etc.) to measure the distance between the robotic arm and obstacles in real time. When the system detects that the robotic arm is about to approach an obstacle, it calculates a safe distance threshold and instructs the robotic arm to decelerate or change its direction of movement to ensure that the robotic arm does not collide with the obstacle.

[0034] Therefore, the clamping path of the mushroom robotic arm is determined based on the shape of the gripping end and multiple clamping nodes, and the gripping action of the gripping end of the mushroom robotic arm is marked at multiple clamping nodes in the clamping path. This takes into account the overall shape of the gripping end of the mushroom robotic arm and multiple clamping nodes, ensuring the accuracy of the clamping path of the mushroom robotic arm.

[0035] At this point, the system needs to consider the shape of the gripping end of the mushroom robotic arm (such as size, shape, material, gripping force, etc.) and the positions of the previously determined clamping nodes to determine the clamping path of the robotic arm. The clamping path is the path that the robotic arm needs to take to move from its current position to the clamping node and perform the gripping action. The determination of this path needs to ensure that the robotic arm can reach the clamping node smoothly and accurately, and that the gripping end can clamp the target object with appropriate posture and force. At this time, the system will use inverse kinematics algorithm or path planning algorithm to calculate the clamping path based on the shape of the gripping end and the position of the clamping node. This path will take into account parameters such as the joint constraints, range of motion, speed, and acceleration of the robotic arm to ensure that the robotic arm can reach the clamping node in the optimal way. At the same time, the system will also adjust the posture and gripping force of the gripping end according to the size, shape, and position of the target object (such as the mushroom frame) to ensure the success rate and stability of the gripping.

[0036] After determining the clamping path, the system needs to mark multiple clamping nodes on the path. These nodes are key positions that the robotic arm needs to reach when performing the clamping action. The number and location of clamping nodes usually depend on the size, shape, and position of the target object, as well as the shape and capability of the robotic arm's gripping end. At each clamping node, the robotic arm needs to perform specific clamping actions, such as opening the gripping end, clamping the target object, and adjusting the clamping force. At this time, the system will determine one or more clamping nodes on the clamping path based on the position and shape of the target object. Each clamping node will have a specific coordinate and orientation (i.e., the angles of each joint of the robotic arm) to ensure that the robotic arm can accurately reach and clamp the target object. The system will also assign a unique identifier to each clamping node and mark the position of these nodes in the path planning for reference and updating in subsequent execution. The target object is a mushroom box.

[0037] After determining the clamping path and clamping nodes, the system needs to mark the clamping actions that the robotic arm's gripping end needs to perform at each clamping node. These actions include opening the gripping end to prepare for clamping, clamping the target object, adjusting the clamping force to ensure stable clamping, and releasing the gripping end to place the object. The system needs to ensure that these actions can be executed correctly in a predetermined order and under predetermined conditions to achieve a successful clamping operation. At this point, the system will define specific clamping actions for each clamping node based on the type of target object and the capabilities of the gripping end. For example, at the first clamping node, the robotic arm needs to open the gripping end to prepare for clamping the mushrooms; at the second clamping node, the robotic arm needs to clamp the mushroom frame and adjust the clamping force to ensure stability; at the last clamping node (or sometime thereafter), the robotic arm needs to release the gripping end to place the mushroom frame in the designated position.

[0038] In one embodiment of this application, a clamping node matching table is collected, as shown in Table 2:

[0039] Further weights are introduced: clamping node weights: node A1=2, node A2=3, node B1=1, node B2=4; clamping action weights: opening=1, clamping=2, adjusting angle=1.5, stable clamping=2.5; consider two clamping paths: path 1: shape A> node A1 (opening)> node A2 (clamping); path 2: shape B> node B1 (adjusting angle)> node B2 (stable clamping).

[0040] Path 1 score = (2×1) + (3×2) + (1×1) + (2×1) = 4 + 6 + 1 + 2 = 13; Path 2 score = (1×1) + (4×1) + (1.5×1) + (2.5×1) = 1 + 4 + 1.5 + 2.5 = 9; Therefore, Path 1 has the highest score and is selected as the optimal clamping path; During execution, the robotic arm will move and operate according to the clamping nodes and gripping actions on Path 1.

[0041] In step S300, the gripping action of the mushroom robotic arm is determined based on the detection of the gripping path, and the gripping level of the mushroom robotic arm on the mushroom frame is determined based on the gripping action and the corresponding gripping posture parameters. In the specific implementation of this invention, the specific steps are as follows: S310: When the mushroom robotic arm moves along the gripping path, the position of the gripping end of the mushroom robotic arm is collected, and the gripping state of the gripping end of the mushroom robotic arm is marked. The gripping action of the mushroom robotic arm is determined based on the position and gripping state of the gripping end of the mushroom robotic arm. S320: Real-time monitoring of the gripping action of the mushroom robotic arm, and marking the gripping posture parameters of the gripping end of the mushroom robotic arm at various positions. When the gripping end of the mushroom robotic arm grips the mushroom frame, it collects multiple contact nodes between the gripping end and the mushroom frame, and determines the gripping state of the gripping end on the mushroom frame based on the multiple contact nodes and the working parameters of the gripping end. S330: Determine the first-level parameters based on the gripping state and the corresponding gripping posture parameters; determine the second-level parameters based on the gripping state, the position of the gripping end, and the posture parameters of the mushroom frame; and determine the gripping level of the mushroom robot arm on the mushroom frame based on the first-level parameters, the second-level parameters, and the gripping level mapping relationship.

[0042] In the embodiments of this application, when the mushroom robotic arm moves along the preset gripping path, the system needs to collect the position information of the gripping end in real time. This is usually achieved by sensors installed on the robotic arm, such as encoders, gyroscopes, laser rangefinders, or vision sensors. These sensors can accurately measure the angles, linear displacements, or three-dimensional coordinates of each joint of the robotic arm relative to a reference point, thereby determining the real-time position of the gripping end. At this time, the encoder measures the rotation angle of the robotic arm joints and calculates the position of the gripping end through inverse kinematics algorithms; the gyroscope measures the angular velocity of the robotic arm and, combined with accelerometer data, calculates the real-time attitude and position changes of the robotic arm; the laser rangefinder emits a laser beam and measures the time or phase difference of the reflected light to determine the distance from the gripping end to the target object; the vision sensor identifies the positions of the gripping end and the target object through image processing technology to achieve precise positioning.

[0043] The gripping state refers to whether the gripping end is currently in an open, closed, or semi-closed state, as well as the magnitude of the gripping force. This information is crucial for determining the next gripping action. The system typically marks the gripping state by monitoring the motor current, position sensor, or force sensor of the gripping end actuator. When the gripping end performs an opening or closing action, the motor current will change. By analyzing the current change, the state of the gripping end is determined. The position sensor (such as a Hall sensor) installed on the gripping end actuator can directly detect the degree of opening or closing of the gripping end and measure the contact force between the gripping end and the target object to determine whether the gripping is stable.

[0044] After acquiring the position and gripping status of the gripping end, the system needs to combine this information with a preset gripping strategy or algorithm to determine the next gripping action. This includes continuing to move the robotic arm to approach the target, adjusting the angle or position of the gripping end to adapt to the target shape, opening or closing the gripping end to grip or release the target, etc. At this time, the optimal path is calculated based on the current position of the gripping end and the target position; the appropriate gripping method (such as parallel gripping, rotational gripping, etc.) is selected according to the shape, size, and material of the target object; the position and status of the gripping end are monitored in real time, and the movement of the robotic arm is adjusted through feedback control algorithms to ensure the accuracy and stability of the gripping action.

[0045] Furthermore, the gripping action of the mushroom robotic arm is monitored in real time, and the gripping posture parameters of the gripping end of the mushroom robotic arm at various positions are marked. When the gripping end of the mushroom robotic arm grips the mushroom frame, multiple contact nodes between the gripping end and the mushroom frame are collected. The gripping state of the gripping end on the mushroom frame is determined based on multiple contact nodes and the working parameters of the gripping end. This overall consideration of multiple contact nodes and the working parameters of the gripping end ensures the accuracy of the gripping state of the gripping end on the mushroom frame.

[0046] At this point, the system needs to monitor the gripping action of the mushroom-growing robotic arm in real time to ensure that the gripping process is executed according to the predetermined strategy. The monitoring content includes key parameters such as the speed, acceleration, position, and attitude of the gripping end. To achieve real-time monitoring, the system usually integrates high-precision sensors and advanced control algorithms. High-precision sensors, such as encoders, gyroscopes, and accelerometers, are installed on key parts of the robotic arm (such as the gripping end and joints) to acquire the motion status of the robotic arm in real time. Control algorithms (such as PID control and adaptive control) are used to adjust the motion of the robotic arm in real time to ensure the stability and accuracy of the gripping action. The data collected by the sensors are recorded and analyzed in real time to promptly detect and correct deviations or errors.

[0047] The gripping posture parameters refer to the posture of the gripping end relative to the target object (such as a mushroom basket) during the gripping process, including angle, direction, and position. The system needs to label these parameters in real time for subsequent analysis and evaluation of the gripping action. At this time, the posture of the gripping end is estimated in real time by using sensor data integrated on the robotic arm, combined with kinematic models or machine vision technology. The estimated posture parameters are labeled and stored together with the corresponding timestamps, position information, etc., for subsequent processing. Based on the real-time labeled posture parameters, the system automatically adjusts the robotic arm's motion strategy to ensure the accuracy and stability of the gripping action.

[0048] During the process of gripping the mushroom frame, multiple contact points are formed between the gripping end and the mushroom frame. These contact points are crucial for assessing the gripping status because they reflect the gripping force, stability, and risk of damage of the gripping end. Simultaneously, force sensors or tactile sensors integrated on the gripping end detect the contact between the gripping end and the mushroom frame in real time. Once contact is detected, the system immediately records key information such as the position and force of the contact point and generates a contact node dataset. The collected contact node data is analyzed to assess the gripping status and predict the gripping outcome.

[0049] By combining the collected contact node data and the working parameters of the gripping end (such as gripping force and gripping speed), the system comprehensively evaluates the gripping status of the mushroom frame, including the stability, firmness, and risk of damage. At the same time, by comparing the contact node data with preset gripping standards or thresholds, the system automatically evaluates the gripping status. Based on the evaluation results, the system adjusts the gripping strategy or parameters in real time to ensure the smooth progress of the gripping process. The evaluation results and related gripping parameters are recorded to generate a detailed gripping report for subsequent analysis and improvement.

[0050] Therefore, the first-level parameters are determined based on the gripping state and the corresponding gripping posture parameters, and the second-level parameters are determined based on the gripping state, the position of the gripping end, and the posture parameters of the mushroom frame. The gripping level of the mushroom robot arm on the mushroom frame is determined based on the mapping relationship between the first-level parameters, the second-level parameters, and the gripping level. This approach takes into account the overall consideration of the first-level parameters, the second-level parameters, and the gripping level mapping relationship, ensuring the accuracy of the gripping level of the mushroom robot arm on the mushroom frame. At the same time, the movement path and clamping path of the mushroom robot arm are introduced, taking into account the overall consideration of the gripping action and the corresponding gripping posture parameters, ensuring the gripping level of the mushroom robot arm on the mushroom frame, and realizing the precise gripping of the mushroom frame by the mushroom robot arm.

[0051] At this point, the system needs to determine the first-level parameters based on the gripping state and corresponding gripping posture parameters (such as the angle, direction, and positional stability of the gripping end) obtained in the previous steps. These parameters typically reflect the basic quality and stability of the gripping action. Key indicators, such as the gripping stability index and posture deviation, are then extracted from the gripping state and posture parameters. These key indicators are then divided into different levels according to preset level standards or thresholds, forming the first-level parameters. The first-level parameters are recorded and stored along with the corresponding gripping events for subsequent analysis and improvement.

[0052] The system needs to comprehensively consider the gripping state, the position of the gripping end, and the posture parameters of the mushroom frame (such as the tilt angle and stability of the mushroom frame) to determine the second-level parameters. These parameters usually reflect the influence and adaptability of the gripping action on the target object (mushroom frame). At this time, the gripping state, the position of the gripping end, and the posture parameters of the mushroom frame are fused to form a comprehensive evaluation index. According to the preset evaluation criteria or model, the comprehensive evaluation index is evaluated to form the second-level parameters. Based on the second-level parameters, the system provides real-time feedback on the effect of the gripping action and adjusts the gripping strategy or parameters to improve the gripping quality.

[0053] The system needs to determine the gripping level of the mushroom robotic arm on the mushroom frame based on the first-level parameters and the second-level parameters, combined with a preset gripping level mapping relationship. The gripping level usually reflects the overall quality and effect of the gripping action. At this time, a gripping level mapping relationship is established in advance, associating the first-level parameters and the second-level parameters with the gripping level. Based on the specific values ​​of the first-level parameters and the second-level parameters, the corresponding gripping level is found in the mapping relationship. The determined gripping level is output to the system or user for subsequent processing or decision-making.

[0054] In some embodiments of this application, a first-level parameter matching table is collected, as shown in Table 3:

[0055] A second-level parameter matching table was collected, as shown in Table 4:

[0056] The collection of the gripping level matching table is shown in Table 5:

[0057] Based on the first-level parameter A (excellent) and the second-level parameter A (excellent), the corresponding clamping level of AAA (superior) is found in the mapping table.

[0058] In step S400, if the mushroom robotic arm completes the gripping of the mushroom frame, the position change of multiple first obstacles is collected, and the reverse reset of the mushroom robotic arm is triggered according to the position change and the movement path of the mushroom robotic arm. In the specific implementation of this invention, the specific steps are as follows: S410: Collect the gripping level of the mushroom frame by the mushroom robotic arm, and determine the lifting node of the mushroom frame by the mushroom robotic arm based on the gripping level of the mushroom frame, the original position of the mushroom frame and the position change of the mushroom frame. The lifting node means that the mushroom robotic arm has completed the gripping of the mushroom frame. S420: Based on the obstacle detection triggered by the lifting node, the current position of multiple first obstacles is determined according to the obstacle detection of the surrounding cameras, and the position change of multiple first obstacles is determined according to the current position and the corresponding original position of the multiple first obstacles; S430: The position changes of multiple first obstacles are compared with preset position change thresholds. If the position change of the first obstacle is lower than the preset position change threshold, the reverse reset path of the mushroom robot arm is determined based on the movement path of the mushroom robot arm and the shape of the mushroom frame, and the reverse reset of the mushroom robot arm is triggered along the reverse reset path.

[0059] In the embodiments of this application, the system collects the gripping level of the mushroom frame by the mushroom robotic arm. The system needs to combine the gripping level, the original position of the mushroom frame (i.e., the position before gripping) and the position change (i.e., the amount of movement of the mushroom frame relative to the original position during gripping) to determine a key lifting node. The lifting node indicates that the mushroom robotic arm has successfully gripped the mushroom frame and is ready to perform lifting or moving operations.

[0060] The original and current positions of the mushroom frame are obtained using sensors or machine vision technology; the difference between the current position and the original position is calculated to obtain the position change; the stability of the gripping is evaluated based on the gripping level; if the gripping level is high, it indicates that the gripping is stable and the mushroom frame can be lifted safely; if the gripping level is low, it is necessary to re-grip or take other safety measures; by combining the gripping level, the original position and the position change, as well as other factors (such as the load capacity of the robotic arm, the safety of the movement path, etc.), a lifting node is determined.

[0061] Furthermore, based on the obstacle detection triggered by the boosting node, the current position of multiple first obstacles is determined according to the obstacle detection of the surrounding cameras. The position change of multiple first obstacles is determined according to the current position and the corresponding original position of the multiple first obstacles. This takes into account the overall consideration of the current position and the corresponding original position of the multiple first obstacles, ensuring the accuracy of the position change of the multiple first obstacles.

[0062] At this point, when the lifting node is reached, the system will trigger cameras installed around the mushroom-growing robotic arm or along its movement path to perform obstacle detection. These cameras typically have high sensitivity and a wide field of view, enabling them to capture images of the robotic arm's working area in real time. The purpose of triggering the cameras for obstacle detection is to ensure that potential obstacles can be identified and located in time before the robotic arm lifts or moves the mushroom frame, thereby avoiding collisions or safety accidents. When the system detects that the preset lifting node has been reached, it sends a signal to the camera control system. After receiving the signal, the camera control system activates the designated camera to perform obstacle detection. The camera begins to capture images of the working area and transmits them to the image processing system.

[0063] After the camera captures an image, the system needs to analyze the image using image processing algorithms or machine learning models to identify and locate obstacles in the image. These obstacles include other objects, equipment, people, or parts of the mushroom robotic arm itself (if in an unexpected location). The system determines the current position of each obstacle by comparing and analyzing information such as feature points, edges, and shapes in the image. At this point, the captured image is preprocessed, such as denoising and contrast enhancement, to improve the accuracy of obstacle recognition. Image processing algorithms or machine learning models are then applied to analyze the preprocessed image to identify and locate obstacles. Based on the recognition results, the current position coordinates of each obstacle are determined.

[0064] After determining the current position of each obstacle, the system needs to compare these positions with the obstacle's original position (i.e., the previously recorded or preset position) to calculate the position change. The position change reflects the movement of the first obstacle during the operation of the mushroom robotic arm and is crucial for assessing potential collision risks and developing obstacle avoidance strategies. At this point, the system retrieves the original position information of each first obstacle from the database or from other data sources; compares the current position with the original position, and calculates the position change of each obstacle in the X, Y, and Z directions; and stores the calculated position change in the system for use in subsequent steps.

[0065] Therefore, the position changes of multiple first obstacles are compared with preset position change thresholds. If the position change of the first obstacle is lower than the preset position change threshold, the reverse reset path of the mushroom robot arm is determined based on the movement path of the mushroom robot arm and the shape of the mushroom frame. The reverse reset of the mushroom robot arm is triggered along the reverse reset path, which takes into account the overall consideration of the movement path of the mushroom robot arm and the shape of the mushroom frame, and ensures the accuracy of the reverse reset path of the mushroom robot arm.

[0066] At this point, the system needs to compare the previously calculated position change of each obstacle with a preset position change threshold. The position change threshold is usually preset based on factors such as the safety requirements of the working environment, the operating accuracy of the robotic arm, and the potential impact of the obstacle. The purpose of the comparison is to determine whether the movement of the obstacle is sufficient to threaten the operation of the robotic arm, thereby deciding whether obstacle avoidance measures need to be taken. At this time, the preset position change threshold is obtained from the system configuration or database; the position change of each obstacle is compared with the corresponding threshold one by one; and the comparison result is recorded, that is, whether each obstacle exceeds the position change threshold.

[0067] If the positional change of an obstacle is less than a preset threshold, it means that the movement of the obstacle is insufficient to pose a significant threat to the operation of the robotic arm, or its impact is within an acceptable range. However, this does not mean that the obstacle should be completely ignored, especially in scenarios requiring high-precision operation or extremely high safety requirements. The system needs to further evaluate the movement path of the robotic arm and the shape of the mushroom frame to determine whether additional obstacle avoidance measures, such as reverse reset, are necessary. At this point, the current movement path of the robotic arm is analyzed to consider whether there is a risk of collision with the obstacle; the shape of the mushroom frame (such as size, weight, center of gravity position, etc.) and the impact of these factors on the operational stability of the robotic arm are considered; based on the path evaluation and shape considerations, a decision is made on whether to take reverse reset measures.

[0068] If a reverse reset is decided upon, the system needs to determine a suitable reverse reset path based on the current movement path of the robotic arm and the shape of the mushroom frame. This path should ensure that the robotic arm safely returns to a safe position, avoids collisions with obstacles, and minimizes the impact on operational efficiency and stability. At this point, a path planning algorithm is applied, considering factors such as the kinematic constraints of the robotic arm, obstacle avoidance requirements, and the shape of the mushroom frame, to generate a feasible reverse reset path. The generated path is then verified to ensure that it meets safety requirements and does not cause the robotic arm to collide with obstacles or other objects.

[0069] Once the reverse reset path is determined, the system needs to trigger the robotic arm to move along that path to achieve the reverse reset. During the movement, the system needs to continuously monitor the status of the robotic arm and changes in the surrounding environment to ensure the safety and stability of the operation. At this time, a command is sent to the robotic arm control system, instructing it to move along the reverse reset path. During the movement, the system continuously monitors the position, speed, acceleration, and other status parameters of the robotic arm, as well as changes in the surrounding environment. If any abnormal situation or potential risk is detected, safety measures are taken immediately, such as stopping the movement or emergency braking.

[0070] Specifically, suppose in an automated mushroom harvesting scenario, a mushroom robotic arm has successfully gripped a mushroom basket and is preparing to lift it to another location; however, during the lifting process, the system detects that the position of a nearby obstacle (such as another mushroom basket) has changed to a certain extent; the system calculates the amount of position change of the obstacle and compares it with a preset position change threshold; suppose the amount of position change of the obstacle is 5 centimeters in the X direction, while the preset threshold is 10 centimeters; therefore, the amount of position change of the obstacle is lower than the preset threshold.

[0071] Although the positional change of the obstacle is below the threshold, the system considers the movement path of the robotic arm and the shape of the mushroom frame (such as its large weight and high center of gravity) and believes there is a potential risk of collision or operational instability. Therefore, the system decides to take a reverse reset measure to ensure the safety and stability of the operation. The system applies a path planning algorithm, taking into account the kinematic constraints of the robotic arm, obstacle avoidance requirements, and the shape of the mushroom frame, to generate a feasible reverse reset path. This path ensures that the robotic arm can safely return to a safe position while avoiding collisions with obstacles.

[0072] The system sends instructions to the robotic arm control system, directing it to move along the reverse reset path. During the movement, the system continuously monitors the robotic arm's status and changes in the surrounding environment to ensure the safety and stability of the operation. Finally, the robotic arm successfully returns to a safe position along the reverse reset path, awaiting further instructions or operations. This example demonstrates that the various sub-steps in step S430 cooperate with each other to achieve the functions of comparing the change in obstacle position, making decisions, determining the reverse reset path, and triggering the reverse reset, providing important guarantees for the safe operation of the mushroom robotic arm.

[0073] In some embodiments of this application, an obstacle matching table is collected, as shown in Table 6:

[0074] In this example, the positional changes of obstacles 1 and 3 are below a preset threshold, while the positional change of obstacle 2 exceeds the threshold. For obstacles with positional changes below the threshold (such as obstacles 1 and 3), the system needs to determine the reverse reset path based on the movement path of the mushroom robot arm and the shape of the mushroom frame. This is achieved through a path planning algorithm, taking into account the kinematic constraints of the robot arm, obstacle avoidance requirements, and factors such as the weight and center of gravity of the mushroom frame. Once the reverse reset path is determined, the system sends a command to the robot arm, instructing it to perform a reverse reset along the path.

[0075] In step S500, during the reverse reset of the mushroom robotic arm, the abnormal posture of the mushroom frame is determined based on multiple posture parameters of the mushroom frame, and the dynamic and stable control of the mushroom robotic arm on the mushroom frame is triggered according to the abnormal posture and the corresponding abnormal position of the mushroom frame. In the specific implementation of this invention, the specific steps are as follows: S510: Real-time monitoring of the reverse reset of the mushroom robotic arm, collection of the posture parameters of the gripping end of the mushroom robotic arm and the posture parameters of the mushroom frame, and determination of the dynamic posture diagram of the mushroom frame based on the various posture parameters and corresponding positions of the mushroom frame; S520: Determine the abnormal posture of the mushroom frame based on the recognition of the dynamic posture diagram of the mushroom frame, mark the abnormal position corresponding to the abnormal posture, and determine the first balance parameter based on the abnormal posture of the mushroom frame and the posture parameters of the gripping end of the mushroom robotic arm. S530: Determine the second balance parameter based on the abnormal posture of the mushroom frame and the shape of the first obstacle on the periphery of the abnormal position. Determine the corresponding emergency balance measures based on the first balance parameter, the second balance parameter and the emergency balance mapping relationship. Realize the dynamic and stable control of the mushroom frame by the mushroom robotic arm based on the execution of the emergency balance measures.

[0076] In the embodiments of this application, the system needs to monitor the reverse reset process of the mushroom robotic arm in real time. This typically involves continuously tracking and recording the robotic arm's motion state, position information, and any abnormalities. The purpose of monitoring is to ensure that the robotic arm can smoothly reverse reset according to a predetermined path and speed, while promptly detecting and handling any faults or abnormalities. At this time, sensors are installed on key parts of the robotic arm (such as joints, gripping ends, etc.) to monitor the robotic arm's motion state and position information in real time. The sensors collect motion data of the robotic arm in real time, such as angle, speed, acceleration, etc., and process and analyze them to generate the robotic arm's motion trajectory and status information. The robotic arm's motion trajectory and status information are monitored in real time to promptly detect and report any abnormalities or faults.

[0077] The gripping end is the part of the robotic arm used to grasp and transport mushroom crates. Its posture parameters are crucial for ensuring the stable transport of the mushroom crates. In this step, the system needs to collect the posture parameters of the gripping end, including its position, angle, and speed, for subsequent analysis and processing. At this time, suitable sensors for measuring the posture of the gripping end are selected, such as angle sensors and position sensors. The posture parameters of the gripping end are collected in real time by the sensors to ensure the accuracy and real-time nature of the data. The collected data is stored in the system for subsequent analysis and processing.

[0078] The attitude parameters of the mushroom frame are crucial for assessing its stability and safety. In this step, the system needs to collect the mushroom frame's attitude parameters, including its tilt angle, sway amplitude, and positional offset. These parameters will be used to generate a dynamic attitude graph of the mushroom frame and help the system identify potential anomalies or risks. Sensors, such as accelerometers and tilt sensors, are installed on the mushroom frame to measure its attitude parameters in real time. The attitude parameters are collected in real time by the sensors, processed, and analyzed to extract useful information. It is essential to ensure that the collected mushroom frame attitude parameters are synchronized with the attitude parameters of the robotic arm's gripping end for subsequent correlation analysis.

[0079] The system needs to use the collected mushroom frame posture parameters and corresponding position information to generate a dynamic image of the mushroom frame's posture. This dynamic image will visually display the posture changes of the mushroom frame during the reverse reset process, including changes in its tilt angle and sway amplitude over time. By comparing and analyzing this dynamic image, the system can identify potential anomalies or risks and take corresponding measures to handle them. At this point, the collected mushroom frame posture parameters and corresponding position information are integrated to form a complete dataset. Using graphics processing technology or data visualization tools, a dynamic image of the mushroom frame's posture is generated based on the dataset. By comparing and analyzing the dynamic image, potential anomalies or risks, such as excessive tilting or violent swaying of the mushroom frame, are identified.

[0080] Furthermore, abnormal postures of the mushroom frame are determined based on the recognition of the dynamic posture diagram of the mushroom frame, and the abnormal positions corresponding to the abnormal postures are marked. The first balance parameter is determined based on the abnormal postures of the mushroom frame and the posture parameters of the gripping end of the mushroom robotic arm. This takes into account both the abnormal postures of the mushroom frame and the posture parameters of the gripping end of the mushroom robotic arm, ensuring the accuracy of the first balance parameter.

[0081] At this point, the system needs to perform an in-depth analysis of the previously generated mushroom frame posture animation to identify any abnormal postures. Abnormal postures manifest as excessive tilting, violent shaking, or positional deviations exceeding the normal range. The system needs to preset a set of judgment criteria or thresholds to determine whether the mushroom frame's posture is abnormal. Then, image processing or data analysis techniques are used to analyze the mushroom frame posture animation frame by frame. Based on the preset judgment criteria or thresholds, the system determines whether the mushroom frame's posture is abnormal in each frame. If an abnormal posture is identified, the system needs to record the time point of the abnormality, the type of abnormality, and the corresponding posture parameters.

[0082] Once an abnormal posture of the mushroom frame is detected, the system needs to determine the specific location where the abnormality occurred. This usually involves accurately locating the three-dimensional coordinates of the mushroom frame in space. Marking the abnormal location helps in subsequent analysis of the cause of the abnormality and taking corresponding corrective measures. At this time, the location information when the abnormality occurred, including the three-dimensional coordinates, is extracted from the dynamic posture diagram of the mushroom frame. The abnormal location is marked in the system for subsequent analysis and processing. This is achieved by overlaying marker points on the dynamic diagram and recording the location information in the data table.

[0083] The first balance parameter reflects the relative balance between the mushroom frame and the gripping end of the mushroom robotic arm. After determining the abnormal posture and position, the system needs to comprehensively consider the abnormal posture of the mushroom frame (such as tilt angle, sway amplitude, etc.) and the posture parameters of the gripping end (such as position, angle, speed, etc.) to calculate the first balance parameter. This parameter will be used to subsequently evaluate the stability of the robotic arm and formulate emergency balancing measures. At this point, the abnormal posture parameters of the mushroom frame and the posture parameters of the gripping end are integrated. Using a mechanical model or empirical formula, the first balance parameter is calculated based on the integrated data. This parameter is a scalar value and also a vector value containing multiple components. The calculated first balance parameter is stored in the system for subsequent analysis and processing.

[0084] Specifically, an anomaly occurred during the process of the mushroom robotic arm transporting the mushroom frame; the system conducted an in-depth analysis of the previously generated dynamic image of the mushroom frame's posture; in a certain frame, the system detected that the mushroom frame was significantly tilted, and the tilt angle exceeded the preset threshold; the system recorded the time point of the anomaly, the anomaly type as "excessive tilt", and extracted the corresponding posture parameters.

[0085] The system extracts the location information of the anomaly from the dynamic image, including the three-dimensional coordinates of the mushroom frame; the system overlays a marker point on the dynamic image to mark the location of the anomaly; at the same time, the system records the specific coordinate information of the location of the anomaly in the data table.

[0086] The system integrates abnormal posture parameters such as the tilt angle and sway amplitude of the mushroom frame, as well as posture parameters such as the position and angle of the gripping end. Using a preset mechanical model, the system calculates the first balance parameter based on the integrated data. This parameter reflects the relative balance state between the mushroom frame and the gripping end. The system stores the calculated first balance parameter and marks it as associated with previous abnormal records. This example shows that the various sub-steps in step S520 cooperate with each other to jointly realize the identification of abnormal posture of the mushroom frame, the marking of abnormal positions, and the determination of the first balance parameter. These steps provide important data support for subsequent analysis of the causes of abnormalities and the formulation of emergency balancing measures.

[0087] Therefore, based on the abnormal posture of the mushroom frame and the shape of the first obstacle around the abnormal position, the second balance parameter is determined. Based on the first balance parameter, the second balance parameter, and the emergency balance mapping relationship, the corresponding emergency balance measures are determined. Based on the execution of the emergency balance measures, the dynamic and stable control of the mushroom frame by the mushroom robotic arm is achieved. This method takes into account the overall consideration of the first balance parameter, the second balance parameter, and the emergency balance mapping relationship, ensuring the accuracy of the corresponding emergency balance measures. At the same time, the reverse reset of the mushroom robotic arm is introduced, and the position change and the movement path of the mushroom robotic arm are fully utilized to ensure the accuracy of the reverse reset of the mushroom robotic arm, further improving the dynamic stability of the mushroom frame by the mushroom robotic arm.

[0088] At this point, the system needs to comprehensively consider the abnormal posture of the mushroom frame and the shape of the first obstacle around the abnormal position. The shape of the obstacle includes its size, shape, position, and whether it is fixed. The system needs to evaluate the impact of these obstacles on the balance adjustment operation performed by the mushroom robot arm and determine the second balance parameter based on this information. The second balance parameter reflects the balance state between the robot arm and the mushroom frame under the influence of the obstacle, as well as the amount of adjustment required to achieve balance. At this point, detailed information about the obstacles around the abnormal position is obtained using sensors or pre-stored map information. The impact of the obstacle on the balance adjustment operation performed by the robot arm is analyzed, including space constraints and collision risks. Based on the shape of the obstacle and the abnormal posture of the mushroom frame, the second balance parameter is calculated. This second balance parameter includes the angle, displacement, or speed that the robot arm needs to adjust.

[0089] The system needs to combine the first balance parameter (reflecting the relative balance between the mushroom frame and the gripping end of the robotic arm) and the second balance parameter (considering the balance state after considering the influence of obstacles), as well as a preset emergency balance mapping relationship, to determine the corresponding emergency balance measures. The emergency balance mapping relationship is a preset set of rules or a model that determines the balance adjustment measures to be taken based on the values ​​of the balance parameters. At this time, the preset emergency balance mapping relationship is queried in the system. Based on the values ​​of the first and second balance parameters, the corresponding emergency balance measures are found in the mapping relationship. These measures include adjusting the angle, speed, and displacement of the robotic arm, or triggering a certain safety mechanism, etc.

[0090] The system needs to translate the determined emergency balancing measures into specific control commands and send them to the mushroom-growing robotic arm for execution. These control commands must ensure that the robotic arm can smoothly adjust the posture of the mushroom frame while avoiding collisions with surrounding obstacles. During execution, the system needs to monitor the status of the robotic arm and the mushroom frame in real time and adjust the control commands as needed to ensure dynamic and stable control. At this point, specific control commands are generated based on the determined emergency balancing measures and sent to the actuators of the mushroom-growing robotic arm. During execution, sensors are used to monitor the status of the robotic arm and the mushroom frame in real time. If any abnormalities or deviations from expectations are detected, the system needs to adjust the control commands promptly to ensure dynamic and stable control. After the robotic arm completes the balancing adjustment, the system needs to confirm whether the adjustment result meets expectations and update the status information for subsequent analysis.

[0091] Specifically, the mushroom robotic arm encountered an anomaly while handling the mushroom crate, and there were obstacles around the abnormal location. The system detected that the mushroom crate had an abnormal posture of excessive tilt and determined the abnormal location. At the same time, the system obtained detailed information about the obstacles around the abnormal location through sensors, including a fixed large piece of equipment and a movable shelf. The system evaluated the impact of these obstacles on the robotic arm's balance adjustment operation and calculated a second balance parameter, which included the angle and displacement that the robotic arm needed to adjust after taking the obstacles into account.

[0092] The system combines the previously calculated first and second balance parameters with the preset emergency balance mapping relationship. By querying the mapping relationship, the system determines the corresponding emergency balance measures, which include adjusting the angle of the robotic arm to reduce the tilt of the mushroom frame and slightly moving the robotic arm to avoid collisions with fixed large equipment. The system optimizes the determined emergency balance measures to ensure that the adjustment process is both smooth and efficient.

[0093] The system generates specific control commands based on the determined emergency balancing measures and sends these commands to the actuators of the mushroom robotic arm. During execution, the system uses sensors to monitor the status of the robotic arm and the mushroom frame in real time to ensure a smooth adjustment process. After the robotic arm completes the balancing adjustment, the system confirms that the adjustment result meets expectations and updates the status information for subsequent analysis. Ultimately, the mushroom robotic arm successfully achieves dynamic and stable control of the mushroom frame, avoiding collisions with surrounding obstacles and ensuring the smooth progress of the harvesting task.

[0094] In some embodiments of this application, an emergency balancing measures matching table is collected, as shown in Table 7:

[0095] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of the reset control system for the mushroom robotic arm based on path planning in an embodiment of the present invention; the reset control system for the mushroom robotic arm based on path planning includes: The gripping path module 610 is used to determine the gripping path of the mushroom robotic arm based on the current position of the mushroom robotic arm and the target gripping position. The obstacle module 620 is used to determine the movement path and clamping path of the mushroom robot arm according to the division of the gripping path, and to determine multiple first obstacles according to the traversal of the movement path. The mushroom robot arm avoids multiple first obstacles during the movement. The gripping level module 630 is used to determine the gripping action of the mushroom robot arm based on the detection of the gripping path, and to determine the gripping level of the mushroom robot arm on the mushroom frame based on the gripping action and the corresponding gripping posture parameters. The reverse reset module 640 is used to collect the position changes of multiple first obstacles when the mushroom robot arm completes the gripping of the mushroom frame, and trigger the reverse reset of the mushroom robot arm based on the position changes and the movement path of the mushroom robot arm. The dynamic stabilization control module 650 is used to determine the abnormal posture of the mushroom frame based on multiple posture parameters of the mushroom frame during the reverse reset process of the mushroom robotic arm, and to trigger the dynamic stabilization control of the mushroom frame by the mushroom robotic arm according to the abnormal posture and the corresponding abnormal position of the mushroom frame.

[0096] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A reset control method for a mushroom-growing robotic arm based on path planning, characterized in that, include: The gripping path of the mushroom robotic arm is determined based on the current position of the mushroom robotic arm and the target clamping position. The movement path and clamping path of the mushroom robotic arm are determined based on the division of the gripping path. Multiple first obstacles are determined based on the traversal of the movement path. The mushroom robotic arm avoids multiple first obstacles during the movement. The gripping action of the mushroom robotic arm is determined based on the detection of the gripping path, and the gripping level of the mushroom robotic arm on the mushroom frame is determined based on the gripping action and the corresponding gripping posture parameters. If the mushroom robotic arm completes the gripping of the mushroom frame, it collects the position changes of multiple first obstacles and triggers the reverse reset of the mushroom robotic arm based on the position changes and the movement path of the mushroom robotic arm. The change in position reflects the movement of the first obstacle during the operation of the mushroom robotic arm; During the reverse reset process of the mushroom robotic arm, the abnormal posture of the mushroom frame is determined based on multiple posture parameters of the mushroom frame, and the dynamic and stable control of the mushroom robotic arm on the mushroom frame is triggered according to the abnormal posture and the corresponding abnormal position of the mushroom frame. During the execution, the status of the robotic arm and the mushroom frame is monitored in real time using sensors. If an abnormal situation or deviation from the expectation is detected, the system needs to adjust the control command in a timely manner to ensure dynamic and stable control.

2. The reset control method for the mushroom robotic arm based on path planning according to claim 1, characterized in that, The step of determining the gripping path of the mushroom robotic arm based on its current position and the target gripping position includes: Collect the number of the mushroom robotic arm, determine the action content of the mushroom robotic arm based on the number of the mushroom robotic arm and the mushroom database, and at the same time, monitor the mushroom robotic arm in real time and collect the current position of the mushroom robotic arm. The degrees of freedom of the mushroom robotic arm are marked, and a first set of paths is determined based on the current position and degrees of freedom of the mushroom robotic arm. At the same time, the target clamping position of the mushroom robotic arm is determined based on the recognition of the action content of the mushroom robotic arm, and a second set of paths is determined based on the target clamping position and degrees of freedom of the mushroom robotic arm. The gripping path of the mushroom robotic arm is determined based on the matching of the first path set and the second path set. This gripping path covers a continuous path between the current position of the mushroom robotic arm and the target clamping position.

3. The reset control method for the mushroom robotic arm based on path planning according to claim 1, characterized in that, The process involves determining the movement path and clamping path of the mushroom-growing robotic arm based on the division of the gripping path, identifying multiple first obstacles based on the traversal of the movement path, and the mushroom-growing robotic arm avoiding these first obstacles during its movement, including: The gripping path is collected, and multiple moving nodes and multiple clamping nodes are determined based on the recognition of the gripping path. The movement path of the mushroom robotic arm is determined according to the shape of the gripping end of the mushroom robotic arm and the multiple moving nodes. The movement space of the mushroom robotic arm is determined based on its movement path, and real-time images of the movement space are captured. Multiple first obstacles are identified based on the detection of the real-time images, and the original positions of the multiple first obstacles are marked. At this time, the mushroom robotic arm moves along the movement path and maintains a safe distance from the adjacent first obstacles to avoid the original positions of the first obstacles. The clamping path of the mushroom robotic arm is determined based on the shape of its gripping end and multiple clamping nodes, and the gripping action of the gripping end of the mushroom robotic arm is marked at multiple clamping nodes in the clamping path.

4. The reset control method for the mushroom robotic arm based on path planning according to claim 1, characterized in that, The process of determining the gripping action of the mushroom-growing robot arm based on the detection of the gripping path, and determining the gripping level of the mushroom-growing robot arm on the mushroom frame based on the gripping action and the corresponding gripping posture parameters, includes: As the mushroom robotic arm moves along the gripping path, the position of the gripping end of the mushroom robotic arm is collected and the gripping state of the gripping end of the mushroom robotic arm is marked. The gripping action of the mushroom robotic arm is determined based on the position and gripping state of the gripping end of the mushroom robotic arm.

5. The reset control method for the mushroom robotic arm based on path planning according to claim 4, characterized in that, The step of determining the gripping action of the mushroom robotic arm based on the detection of the gripping path, and determining the gripping level of the mushroom robotic arm on the mushroom frame based on the gripping action and the corresponding gripping posture parameters, further includes: The gripping action of the mushroom robotic arm is monitored in real time, and the gripping posture parameters of the gripping end of the mushroom robotic arm at various positions are marked. When the gripping end of the mushroom robotic arm grips the mushroom frame, multiple contact nodes between the gripping end and the mushroom frame are collected. The gripping state of the gripping end on the mushroom frame is determined based on the multiple contact nodes and the working parameters of the gripping end. The first-level parameters are determined based on the gripping state and the corresponding gripping posture parameters. The second-level parameters are determined based on the gripping state, the position of the gripping end, and the posture parameters of the mushroom frame. The gripping level of the mushroom robot arm on the mushroom frame is determined based on the mapping relationship between the first-level parameters, the second-level parameters, and the gripping level.

6. The reset control method for the mushroom robotic arm based on path planning according to claim 1, characterized in that, If the mushroom-growing robotic arm completes the grasping of the mushroom frame, it collects the positional changes of multiple first obstacles, and triggers the reverse reset of the mushroom-growing robotic arm based on the positional changes and the movement path of the mushroom-growing robotic arm, including: The gripping level of the mushroom frame by the mushroom robotic arm is collected, and the lifting node of the mushroom frame by the mushroom robotic arm is determined based on the gripping level of the mushroom frame, the original position of the mushroom frame and the change in position of the mushroom frame. The lifting node means that the mushroom robotic arm has completed the gripping of the mushroom frame. The obstacle detection of the surrounding cameras is triggered by the lifting node. The current position of multiple first obstacles is determined based on the obstacle detection of the surrounding cameras. The position change of multiple first obstacles is determined based on the current position of multiple first obstacles and their corresponding original positions.

7. The reset control method for the mushroom robotic arm based on path planning according to claim 6, characterized in that, If the mushroom-growing robotic arm completes the grasping of the mushroom frame, it collects the positional changes of multiple first obstacles, and triggers the reverse reset of the mushroom-growing robotic arm based on the positional changes and the movement path of the mushroom-growing robotic arm. The method also includes: The position changes of multiple first obstacles are compared with preset position change thresholds. If the position change of the first obstacle is lower than the preset position change threshold, the reverse reset path of the mushroom robot arm is determined based on the movement path of the mushroom robot arm and the shape of the mushroom frame, and the reverse reset of the mushroom robot arm is triggered along the reverse reset path.

8. The reset control method for the mushroom robotic arm based on path planning according to claim 1, characterized in that, During the reverse reset process of the mushroom robotic arm, the abnormal posture of the mushroom frame is determined based on multiple posture parameters of the mushroom frame, and the dynamic stabilization control of the mushroom robotic arm on the mushroom frame is triggered according to the abnormal posture and corresponding abnormal position of the mushroom frame, including: The reverse reset of the mushroom robotic arm is monitored in real time. The posture parameters of the gripping end of the mushroom robotic arm and the posture parameters of the mushroom frame are collected. Based on the posture parameters of the mushroom frame and the corresponding position, the dynamic posture diagram of the mushroom frame is determined.

9. The reset control method for the mushroom robotic arm based on path planning according to claim 8, characterized in that, During the reverse reset process of the mushroom robotic arm, the abnormal posture of the mushroom frame is determined based on multiple posture parameters of the mushroom frame, and the dynamic stabilization control of the mushroom robotic arm on the mushroom frame is triggered according to the abnormal posture and corresponding abnormal position of the mushroom frame. This also includes: The abnormal posture of the mushroom frame is determined by recognizing the dynamic posture of the mushroom frame, and the abnormal position corresponding to the abnormal posture is marked. The first balance parameter is determined based on the abnormal posture of the mushroom frame and the posture parameters of the gripping end of the mushroom robot arm. The second balance parameter is determined based on the abnormal posture of the mushroom frame and the shape of the first obstacle on the periphery of the abnormal position. The corresponding emergency balance measures are determined based on the first balance parameter, the second balance parameter and the emergency balance mapping relationship. The dynamic and stable control of the mushroom frame by the mushroom robotic arm is achieved based on the execution of the emergency balance measures.

10. A reset control system for a mushroom-growing robotic arm based on path planning, characterized in that, The reset control system for the mushroom robotic arm based on path planning is applied to the reset control method for the mushroom robotic arm based on path planning as described in any one of claims 1-9, wherein the reset control system for the mushroom robotic arm based on path planning includes: The gripping path module is used to determine the gripping path of the mushroom robotic arm based on the current position of the mushroom robotic arm and the target gripping position. The obstacle module is used to determine the movement path and clamping path of the mushroom robot arm based on the division of the gripping path, and to determine multiple first obstacles based on the traversal of the movement path. The mushroom robot arm avoids multiple first obstacles during the movement. The gripping level module is used to determine the gripping action of the mushroom robot arm based on the detection of the gripping path, and to determine the gripping level of the mushroom robot arm on the mushroom frame based on the gripping action and the corresponding gripping posture parameters. The reverse reset module is used to collect the position changes of multiple first obstacles when the mushroom robot arm completes the gripping of the mushroom frame, and trigger the reverse reset of the mushroom robot arm based on the position changes and the movement path of the mushroom robot arm. The dynamic stabilization control module is used to determine the abnormal posture of the mushroom frame based on multiple posture parameters during the reverse reset process of the mushroom robot arm, and to trigger the dynamic stabilization control of the mushroom frame by the mushroom robot arm according to the abnormal posture and the corresponding abnormal position of the mushroom frame.

Images