Dynamic unhooking control method and system of unhooking robot based on feedback mechanism

Abstract

The present invention discloses a dynamic hook-unhooking control method and system for a hook-unhooking robot based on a feedback mechanism, which relates to the technical field of robot control. The method includes: acquiring the hook-unhooking robot, moving it to a preset hook-unhooking position, and simultaneously starting the visual sensor to collect hook-unhooking image information and environmental perception image information; performing edge detection and feature extraction on the hook-unhooking image information to determine the spatial coordinate information of the hook; performing feature abstraction on the environmental perception image information to obtain the target hook-unhooking path; acquiring the dynamic characteristic parameters and motion constraint information of the hook-unhooking robot, performing hook-unhooking analysis to obtain hook-unhooking control parameters, and performing dynamic hook-unhooking control. The present invention solves the technical problems of low hook-unhooking efficiency and insufficient control accuracy of the hook-unhooking robot in the prior art, and there are certain safety risks, and achieves the technical effects of improving the hook-unhooking efficiency and control accuracy of the hook-unhooking robot and ensuring the operation safety.

Description

Technical Field

[0001] The present invention relates to the technical field of robot control, and particularly to a dynamic hook-unhooking control method and system for a hook-unhooking robot based on a feedback mechanism. Background Art

[0002] In the thermoelectric field, coal is widely used as the main fuel in thermal power plants. A large number of hook devices and complex operating environments are involved in the coal transportation process. Traditional manual hook-up and hook-unhooking operations have problems such as low efficiency, inaccurate control, and high safety risks. To ensure the stable supply of coal and transportation safety, power plants need to rely on hook-unhooking robots to achieve automated operations, thereby improving the overall operating efficiency. During the coal transportation process, the layout and state of the hook devices are complex and changeable. The hook-unhooking robot needs to perform high-precision hook-unhooking tasks under various uncertain conditions. Traditional hook-unhooking robots often rely on fixed path planning and static control methods, and it is difficult to cope with the real-time changing hook postures, position deviations, and obstacles in the transportation environment. This not only affects the hook-unhooking efficiency but also may cause collisions between the robot and the equipment, increasing potential safety hazards.

[0003] The prior art has technical problems such as low hook-unhooking efficiency and insufficient control accuracy of the hook-unhooking robot, and there are certain safety risks. Summary of the Invention

[0004] The present application provides a dynamic hook-unhooking control method and system for a hook-unhooking robot based on a feedback mechanism, which is used to solve the technical problems of low hook-unhooking efficiency and insufficient control accuracy of the hook-unhooking robot in the prior art, and there are certain safety risks.

[0005] In view of the above problems, the present application provides a dynamic hook-unhooking control method and system for a hook-unhooking robot based on a feedback mechanism.

[0006] In the first aspect of the present application, a dynamic hook-unhooking control method for a hook-unhooking robot based on a feedback mechanism is provided, and the method includes:

[0007] Obtain a hook-unhooking robot. The hook-unhooking robot integrates a vision sensor and an image processing unit. Move the hook-unhooking robot to a preset hook-unhooking position, and at the same time start the vision sensor to collect hook-unhooking image information and environmental perception image information; based on the image processing unit, perform edge detection and feature extraction on the hook-unhooking image information to obtain hook position information and hook attitude information, and perform coordinate transformation on the hook position information according to the preset hook-unhooking position to determine the hook spatial coordinate information; perform feature abstraction on the environmental perception image information to generate a hook-unhooking environment area map, and perform path planning on the hook spatial coordinate information based on the hook-unhooking environment area map to obtain a target hook-unhooking path; obtain the dynamic characteristic parameters and motion constraint information of the hook-unhooking robot, and based on the dynamic characteristic parameters and motion constraint information, perform hook-unhooking analysis on the hook attitude information to obtain hook-unhooking control parameters; perform dynamic hook-unhooking control on the hook-unhooking robot based on the target hook-unhooking path and the hook-unhooking control parameters, and introduce a feedback mechanism to perform real-time deviation analysis and compensation hook-unhooking control on the hook-unhooking control process.

[0008] In the second aspect of the present application, a dynamic hook-unhooking control system for a hook-unhooking robot based on a feedback mechanism is provided. The system includes:

[0009] An image information acquisition module, which is used to obtain a hook-unhooking robot. The hook-unhooking robot integrates a vision sensor and an image processing unit. Move the hook-unhooking robot to a preset hook-unhooking position, and at the same time start the vision sensor to collect hook-unhooking image information and environmental perception image information; a hook spatial coordinate information determination module, which based on the image processing unit, performs edge detection and feature extraction on the hook-unhooking image information to obtain hook position information and hook attitude information, and performs coordinate transformation on the hook position information according to the preset hook-unhooking position to determine the hook spatial coordinate information; a target hook-unhooking path acquisition module, which is used to perform feature abstraction on the environmental perception image information to generate a hook-unhooking environment area map, and perform path planning on the hook spatial coordinate information based on the hook-unhooking environment area map to obtain a target hook-unhooking path; a hook-unhooking control parameter acquisition module, which is used to obtain the dynamic characteristic parameters and motion constraint information of the hook-unhooking robot, and based on the dynamic characteristic parameters and motion constraint information, perform hook-unhooking analysis on the hook attitude information to obtain hook-unhooking control parameters; a dynamic hook-unhooking control module, which based on the target hook-unhooking path and the hook-unhooking control parameters, performs dynamic hook-unhooking control on the hook-unhooking robot, and introduces a feedback mechanism to perform real-time deviation analysis and compensation hook-unhooking control on the hook-unhooking control process.

[0010] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0011] Obtain a hook-unhooking robot, move the hook-unhooking robot to a preset hook-unhooking position, and at the same time start the vision sensor to collect hook-unhooking image information and environmental perception image information; based on the image processing unit, perform edge detection and feature extraction on the hook-unhooking image information to obtain hook position information and hook attitude information, and determine hook spatial coordinate information according to the preset hook-unhooking position; perform feature abstraction on the environmental perception image information to generate a hook-unhooking environment area map, perform path planning, and obtain a target hook-unhooking path; obtain the dynamic characteristic parameters and motion constraint information of the hook-unhooking robot, perform hook-unhooking analysis on the hook attitude information to obtain hook-unhooking control parameters; perform dynamic hook-unhooking control on the hook-unhooking robot, and introduce a feedback mechanism to perform real-time deviation analysis and compensated hook-unhooking control on the hook-unhooking control process. The technical effect of improving the hook-unhooking efficiency and control accuracy of the hook-unhooking robot and ensuring operation safety is achieved. Description of the Drawings

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0013] Figure 1 It is a schematic flowchart of the dynamic hook-unhooking control method of the hook-unhooking robot based on the feedback mechanism provided by the embodiment of the present application;

[0014] Figure 2 It is a schematic structural diagram of the dynamic hook-unhooking control system of the hook-unhooking robot based on the feedback mechanism provided by the embodiment of the present application.

[0015] Description of the reference numerals: 10 image information acquisition module, 20 hook spatial coordinate information determination module, 30 target hook-unhooking path acquisition module, 40 hook-unhooking control parameter acquisition module, 50 dynamic hook-unhooking control module. Detailed Embodiments

[0016] The present application provides a dynamic hook-unhooking control method and system for a hook-unhooking robot based on a feedback mechanism, which is used to solve the technical problems of low hook-unhooking efficiency and insufficient control accuracy of the hook-unhooking robot in the prior art, and there are certain safety risks.

[0017] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts belong to the scope of protection of the present application.

[0018] Embodiment 1, as Figure 1 shown, the present application provides a dynamic hook unhooking control method for a hook unhooking robot based on a feedback mechanism, and the method includes:

[0019] Step S100: Obtain a hook unhooking robot, which integrates a vision sensor and an image processing unit. Move the hook unhooking robot to a preset hook unhooking position, and at the same time start the vision sensor to collect hook image information and environmental perception image information.

[0020] Specifically, first obtain a robot for hook unhooking operations. This hook unhooking robot integrates a vision sensor and an image processing unit. The vision sensor can capture images of the surrounding environment, and the image processing unit is responsible for deeply analyzing and processing the images collected by the vision sensor to extract key information. Then, move this hook unhooking robot to a preset hook unhooking position, which is an initial hook unhooking point preset according to the actual operation situation before starting the hook unhooking operation. It has several important characteristics: on the one hand, this position is known, and its specific spatial coordinates and relative position relationships provide a clear reference for subsequent operations. On the other hand, it is relatively fixed and will not change easily within a certain operation cycle, providing a stable basis for the hook unhooking operation. Moreover, this position can ensure that the robot stably captures the entire picture of the hook, whether it is the shape, size, position or posture of the hook, which can be clearly captured, and this is crucial for subsequent hook unhooking operations, enabling the robot to better plan and execute hook unhooking actions. After the robot accurately reaches the preset hook unhooking position, start the vision sensor at the same time. At this time, the vision sensor starts to work efficiently, collecting hook image information and environmental perception image information respectively. The hook image information mainly focuses on the hook itself, providing key data for determining the specific position and posture of the hook subsequently, while the environmental perception image information covers the entire operation environment around the robot, including existing obstacles, other equipment, and spatial layout, etc., providing an important basis for the robot to comprehensively understand the operation environment and formulate a reasonable hook unhooking strategy.

[0021] Step S200: Based on the image processing unit, perform edge detection and feature extraction on the hook image information to obtain hook position information and hook posture information, and perform coordinate transformation on the hook position information according to the preset hook unhooking position to determine the hook spatial coordinate information.

[0022] Specifically, in this process, the image processing unit plays a crucial role. It first performs edge detection on the unhooking image information. By identifying the edges of objects in the image, it emphasizes the contour edges of the hook. Then, it extracts features, extracting unique features of the hook from the image, including shape, color, texture, etc. Through in-depth analysis of these features, the position information of the hook in the image can be determined, that is, the specific coordinates of the hook on the two-dimensional image plane. At the same time, based on features such as the shape and direction of the hook, the attitude information of the hook can be further determined, such as the angle and tilt state of the hook. Subsequently, based on the preset unhooking position, coordinate transformation is performed. Taking the preset unhooking position as the origin of the spatial coordinates, a three-dimensional spatial coordinate system is constructed. In this coordinate system, the hook position information obtained from the unhooking image information is transformed, and the hook position coordinates on the two-dimensional image plane are transformed into coordinates in the three-dimensional space. In this way, the specific position of the hook in the actual space can be accurately known, providing crucial position basis for accurately determining the spatial coordinate information of the hook in the subsequent unhooking operation and realizing accurate unhooking operation.

[0023] Step S300: Abstract the features of the environmental perception image information to generate an unhooking environment area map, and perform path planning on the hook spatial coordinate information based on the unhooking environment area map to obtain the target unhooking path.

[0024] Specifically, first process the environmental perception image information, abstract the features of the environmental perception image information, and extract key feature information from the complex image, including the shape, size, position, color, etc. of the objects in the environment, as well as information such as the spatial layout. Using these abstracted features, an unhooking environment area map is generated. This map is an abstract representation of the robot's surrounding environment, clearly showing various objects and spatial relationships in the environment where the robot is located. After obtaining the unhooking environment area map, based on this map, path planning is performed on the hook spatial coordinate information. Considering various factors in the environment, such as the position of obstacles and passable areas, combined with the spatial coordinates of the hook, the optimal path from the current position of the robot to the hook position is calculated through path planning algorithms. In the planning process, factors such as the length, safety, and efficiency of the path should be comprehensively considered to ensure that the robot can reach the hook position in the fastest and safest way, and finally obtain the target unhooking path, which will guide the robot to accurately move to the hook position for unhooking operation in actual operation.

[0025] Step S400: Obtain the dynamic characteristic parameters and motion constraint information of the unhooking robot, and perform unhooking analysis on the hook attitude information based on the dynamic characteristic parameters and motion constraint information to obtain unhooking control parameters.

[0026] Specifically, first, obtain the dynamic characteristic parameters and motion constraint information of the unhooking robot. The dynamic characteristic parameters include the robot's power output ability, acceleration, speed, etc. These parameters determine the power performance and motion ability of the robot during the unhooking operation. The motion constraint information includes limiting conditions such as the joint movement range, maximum load, and motion accuracy of the robot, ensuring that the robot operates within a safe and feasible range. Based on these dynamic characteristic parameters and motion constraint information, perform unhooking analysis on the hook attitude information. The hook attitude information reflects the state of the hook in space, such as its position, angle, and direction. By analyzing the attitude of the hook and the power and motion ability of the robot, determine the specific control parameters required for the robot during the unhooking operation. These control parameters include joint angle adjustment, motion speed setting, grasping force control, etc. of the robot. Judge whether the robot has sufficient power to complete a specific unhooking action according to the dynamic characteristic parameters, and at the same time consider the motion constraint information to ensure that the operation is within a safe range. Combine the hook attitude information to accurately calculate the specific parameter values of each action required for the robot to successfully pick up the hook. The obtained unhooking control parameters will guide the specific actions of the robot during the actual execution of the unhooking task, ensuring that the robot can accurately and efficiently complete the unhooking operation while ensuring the safety and stability of the operation.

[0027] Step S500: Perform dynamic unhooking control on the unhooking robot based on the target unhooking path and the unhooking control parameters, and introduce a feedback mechanism to perform real-time deviation analysis and compensating unhooking control on the unhooking control process.

[0028] Specifically, first, dynamic unhooking control is performed on the unhooking robot according to the previously obtained target unhooking path and unhooking control parameters. The target unhooking path is used to provide action guidance for the robot, enabling the robot to accurately move towards the position of the hook. At the same time, the specific actions of the robot are adjusted according to the unhooking control parameters, including the movement angles, speeds, and grasping forces of the joints, etc., to ensure that the robot can perform the unhooking operation in the best way. During this process, a feedback mechanism is introduced. By real-time monitoring of the unhooking control process, various feedback parameters are obtained, such as the actual position, attitude, and movement speed of the robot. These actual parameters are compared with the preset target state, and the deviation between the two is calculated. For example, the distance deviation between the actual position and the target position, the angle deviation between the actual attitude and the target attitude, etc. Then, the deviation is analyzed to determine the direction and magnitude of the deviation, and further analyze the cause of the deviation. According to the results of the deviation analysis, a fine-tuning strategy for the control parameters is formulated. If the actual position deviates greatly from the target position, the movement speed and direction of the robot need to be adjusted; if the deviation between the actual attitude and the target attitude is large, the angle of the joint needs to be adjusted. Finally, based on the fine-tuning strategy for the control parameters, deviation fine-tuning compensation is performed on the unhooking control parameters, and the actions of the robot are adjusted in real time, enabling the robot to continuously correct the deviation and approach the target state. This can ensure the accuracy and stability of the unhooking process, and even in the face of various uncertain factors and interferences, it can ensure that the robot efficiently completes the unhooking task.

[0029] In a possible implementation manner, step S200 further includes:

[0030] Step S210: Convert the unhooking image information into an unhooking grayscale image, and perform filtering denoising and image enhancement on the unhooking grayscale image to obtain an unhooking standard grayscale image.

[0031] Step S220: Perform edge detection on the unhooking standard grayscale image through a Canny edge detector to obtain unhooking edge detection information.

[0032] Step S230: Preset an edge low threshold and an edge high threshold, and based on the edge low threshold and the edge high threshold, perform edge contour screening on the unhooking edge detection information to obtain unhooking contour information.

[0033] Step S240: Perform anchor box positioning on the unhooking contour information to obtain unhooking anchor box information, and calculate the center point based on the unhooking anchor box information to obtain the hook position information.

[0034] Step S250: Extract hook attitude features based on the unhooking contour information and the hook position information to obtain the hook attitude information.

[0035] Specifically, first convert the unhooking image information into an unhooking grayscale image. This step converts the color image into a grayscale image, reducing the color information of the image and making subsequent processing more focused on the brightness changes of the image. Then, perform filtering and denoising on the unhooking grayscale image using the median filtering algorithm to remove noise interference in the image and improve the image quality. Next, perform image enhancement operations using histogram equalization to enhance the contrast and clarity of the image, thereby obtaining the unhooking standard grayscale image, providing a better basis for subsequent edge detection.

[0036] Use the Canny edge detector to perform edge detection on the unhooking standard grayscale image. The Canny edge detector can effectively detect the edge information in the image. By calculating the gradient magnitude and direction of the image, it determines the edge intensity and direction of the pixel points in the image, thereby obtaining the unhooking edge detection information. These edge detection information contains important features such as the contours and boundaries of the objects in the image.

[0037] First, preset the edge low threshold and the edge high threshold. The setting of these two thresholds is to effectively screen the unhooking edge detection information. The edge low threshold is used to determine the possible starting points of the edges, while the edge high threshold is used to determine the more obvious and definite edges. For the unhooking edge detection information, which contains multiple different contours, in order to accurately find the contour representing the hook, it is necessary to screen according to the characteristics such as the size and shape of the contour. If the size and shape of a contour do not match the expected characteristics of the hook, then it is not the hook contour we are looking for. At the same time, set the gray levels less than the edge low threshold in the unhooking edge detection information to 0, which means that those parts with lower gray levels and not being edges are regarded as non-edge regions, removing some weak edge interferences. And set the gray levels greater than the edge high threshold to 1, indicating that these parts are relatively obvious edge regions. Through such processing, the edge information can be more clearly highlighted, facilitating the accurate identification and extraction of the hook contour. Finally, after screening and processing, the unhooking contour information is obtained, providing key basic data for determining the position and posture of the hook.

[0038] Perform anchor box localization on the unhooking contour information. Anchor box localization is a target detection technique. By placing rectangular boxes (anchor boxes) of different sizes and ratios in the image, the area containing the target object (the hook) is determined. According to the characteristics of the unhooking contour information, such as shape and size, the position of the anchor box most likely to contain the hook will be searched in the image, thereby obtaining the unhooking anchor box information. Then, based on the unhooking anchor box information, calculate the center point. The center point coordinates can be calculated by calculating the geometric center of the anchor box. For example, for a rectangular anchor box, calculate the midpoint coordinates of its length and width. This center point coordinate represents the position information of the hook in the image. In this way, the specific position of the hook in the image can be more accurately determined, providing key position data for subsequent unhooking operations.

[0039] The hook attitude feature extraction is carried out by using the unhooking contour information and the hook position information, so as to obtain the hook attitude information. Combining the unhooking contour information, the shape features of the hook are analyzed. For example, by analyzing the curvature of the contour, the bending degree of the hook is judged; observing the symmetry of the contour to determine whether the hook is tilted or not. At the same time, according to the direction of the contour, the general orientation of the hook can be initially judged. Then, using the hook position information, the relative position relationship of the hook in space is further determined. For example, by comparing with the positions of surrounding environmental objects, the height, horizontal angle, etc. of the hook are judged. Combining these information, the attitude features of the hook can be extracted, including the angle of the hook (such as pitch angle, yaw angle, roll angle, etc.), direction and tilt state, etc., and finally the hook attitude information is obtained. These attitude information are crucial for the unhooking robot to accurately perform the unhooking operation, which can help the robot better plan the action path and adjust the grasping angle to ensure the efficient and accurate completion of the unhooking task.

[0040] In a possible implementation manner, step S300 further includes:

[0041] Step S310: Perform multi-dimensional feature extraction and feature dimensionality reduction processing on the environmental perception image information to obtain a multi-dimensional feature set of the unhooking environment.

[0042] Step S320: Perform distributed entity recognition based on the multi-dimensional feature set of the unhooking environment to obtain a set of unhooking environment entities, and perform attribute marking on the set of unhooking environment entities to obtain a set of unhooking environment entity attribute information.

[0043] Step S330: Abstract the set of unhooking environment entities into a set of map nodes, and perform edge attribute abstraction on the set of map nodes based on the set of unhooking environment entity attribute information to obtain a set of map connection edges.

[0044] Step S340: Perform map topological connection on the set of map nodes based on the set of map connection edges to generate the unhooking environment area map.

[0045] Specifically, for environmental perception image information, multi-dimensional feature extraction is first carried out. In terms of texture feature extraction, the gray-level co-occurrence matrix (GLCM) algorithm is adopted. This algorithm calculates the gray-level co-occurrence relationship of pixel pairs in the image at different directions and distances, and obtains a matrix reflecting the texture roughness, directionality and other characteristics. From this matrix, texture features such as energy, contrast, and correlation can be extracted. For color feature extraction, the color histogram method is used. The color space of the image is divided into multiple intervals, and the number of pixels in each interval is counted to describe the color distribution of the image. In edge feature extraction, the Canny edge detection algorithm is used. It can effectively detect the edge contours of objects in the image, providing the shape and boundary information of the objects. Through these methods, features in multiple dimensions such as texture, color, and edge are extracted from the environmental perception image to form a rich initial feature set. Then, feature dimensionality reduction processing is carried out, and the principal component analysis (PCA) algorithm is adopted. The PCA algorithm finds the main components in the data, projects the high-dimensional feature vectors into a low-dimensional space, while retaining the main feature information, removing redundant features. By calculating the covariance matrix of the features, the main component directions of the features are determined, and then the original feature vectors are projected onto these main component directions to obtain a low-dimensional feature representation. This not only reduces the redundancy of the features, reduces the computational amount and complexity of subsequent processing, but also improves the effectiveness of the features, making the extracted features more accurately reflect the essential features of the environment, and finally obtaining the multi-dimensional feature set of the hook-unhooking environment.

[0046] Based on the multi-dimensional feature set of the hook-unhooking environment, distribution entity recognition is carried out. Using the object detection algorithm in deep learning, various entities in the environment are recognized. By analyzing the multi-dimensional features, the positions and categories of different objects in the image are determined, so as to obtain the hook-unhooking environment entity set. Then, attribute marking is carried out on this entity set, and specific attribute information such as size, shape, and passability is assigned to each recognized entity. In this way, the hook-unhooking environment entity attribute information set is obtained, providing more detailed information for subsequent map construction.

[0047] Abstract the collection of decoupling environment entities into a collection of map nodes. This means transforming various entities in the actual environment, such as roads, obstacles, road signs, etc., into abstract map nodes. Each entity corresponds to a node, and a collection of nodes corresponding to the actual environment is established. Based on the collection of entity attribute information of the decoupling environment, abstract the edge attributes of the collection of map nodes. Use the previously obtained entity attribute information, such as the distance and passability between entities, to determine the connection relationship between map nodes and the attributes of the edges. If the distance between two entities is relatively close and they are passable, then a connection edge can be established between the corresponding map nodes. At the same time, assign specific attributes to these connection edges. For example, the length of the edge can be determined according to the actual distance between entities, and the difficulty of passing through the edge can be set according to the attributes of the entities (such as the size and crossability of obstacles). Through such processing, obtain the collection of map connection edges. This collection describes the connection relationship and attributes between map nodes and provides a basis for subsequent map topological connection.

[0048] Use the collection of map connection edges to perform map topological connection on the collection of map nodes, thereby generating the decoupling environment area map. Based on each node in the collection of map nodes, these nodes represent different entities in the decoupling environment. Then, according to the information in the collection of map connection edges, determine which nodes are connected. If there is a connection edge between two nodes, it means there is a certain association between the corresponding entities in the actual environment, which is a passable path or a specific spatial relationship. For the node pairs with connection edges, perform connection operations according to the attributes of the connection edges. For example, if the connection edge indicates that there is a passable road between two entities, then connect the corresponding nodes on the map with the corresponding lines to represent the existence of this path. The attributes of the connection edges, such as length and difficulty of passing through, can be reflected in different ways on the map. For example, the thickness of the line can represent the difficulty of passing through, and a longer line may correspond to a longer actual distance. By performing such connection operations on all nodes, gradually construct a complete map structure. This map clearly shows the relationships between various entities in the decoupling environment and information such as passable paths, and finally generates the decoupling environment area map. This map provides an important reference basis for subsequent path planning and the actions of the decoupling robot.

[0049] In a possible implementation manner, step S300 further includes:

[0050] Step S350: Mark the path obstacles in the decoupling environment area map according to the collection of entity attribute information of the decoupling environment, and obtain the available decoupling environment area map.

[0051] Step S360: Define the hook - unhooking control objective, construct a path cost function according to the hook - unhooking control objective, and at the same time perform robot execution analysis based on the hook - hanging space coordinate information to determine the robot execution space coordinate information.

[0052] Step S370: Obtain a list of path planning algorithms, and use the path cost function to perform iterative planning optimization on the robot execution space coordinate information respectively based on the path planning algorithm list and the available hook - unhooking environment area map to obtain multiple hook - unhooking path information.

[0053] Step S380: Conduct feasibility evaluation and cost - ratio comparison and optimization on the multiple hook - unhooking path information to determine the target hook - unhooking path.

[0054] Specifically, according to the set of hook - unhooking environment entity attribute information, mark the path obstacles in the hook - unhooking environment area map. Since the set of hook - unhooking environment entity attribute information has been obtained in the previous steps, which includes the attributes of each entity, such as passability, etc. Through these attribute information, those obstacles that will hinder the progress of the hook - unhooking robot in the map can be accurately identified, and these obstacles are marked on the hook - unhooking environment area map, so that subsequent path planning can avoid these non - passable areas. After marking, the available hook - unhooking environment area map is obtained, providing a clear map environment free from obstacle interference for subsequent path planning.

[0055] First, define the hook-unhooking control objective, which is determined according to specific application scenarios and requirements. For example, it can be reaching the hook position along the shortest path to save time, or minimizing energy consumption to improve the working efficiency of the robot, etc. Construct a path cost function based on the determined hook-unhooking control objective. If the objective is the shortest path, the path cost function considers the length of the path and takes the sum of the distances between each node on the path as the cost. If the objective is to minimize energy consumption, then the path cost function is constructed by combining factors such as the movement resistance of the robot on different terrains and the energy consumption required for performing different actions. At the same time, perform robot execution analysis based on the hook spatial coordinate information. This step needs to consider factors such as the structural dimensions and torque of the robot. According to the structural dimensions of the robot, analyze the movable range of the robot at different positions and postures to ensure that the robot can reach certain areas without being restricted by its own size when performing the hook-unhooking task. Through torque analysis, determine the torque required for the robot to perform actions at different positions and judge whether the robot has sufficient power to complete the hook-unhooking operation. Determine the hook-unhooking execution coordinates for the hook spatial coordinate information. Considering the structural dimensions of the robot and the results of torque analysis comprehensively, select the coordinate positions suitable for the robot to perform the hook-unhooking operation from the hook spatial coordinates to ensure that the robot can stably perform the hook-unhooking task at these determined coordinates without being unable to complete the operation due to insufficient space or power. In this way, the robot execution spatial coordinate information is obtained, providing a clear target position and a feasible operation space for subsequent path planning and hook-unhooking operations.

[0056] First, obtain the list of path planning algorithms. This list contains various different path planning algorithms, such as the A* algorithm, Dijkstra algorithm, RRT (Rapidly-Exploring Random Tree) algorithm, etc. Then, using the path cost function constructed previously, combined with the list of path planning algorithms and the map of the available hook-unhooking environment area, perform iterative planning optimization on the spatial coordinate information of the robot. For each planning algorithm in the list, the operation is aimed at finding the shortest and safest optimal hook-unhooking path. Taking the A* algorithm as an example, it calculates the cost of each node according to the path cost function, selects the node with the minimum cost for expansion. In the map of the available hook-unhooking environment area, the algorithm starts from the current position of the robot and gradually searches for the target node (the coordinates corresponding to the hook position), while considering factors such as the length and safety of the path. Through continuous iterative calculations, the optimal path from the current position to the target position is found. The Dijkstra algorithm starts from the starting node and gradually expands to other nodes, calculating the shortest distance from each node to the starting node. During this process, it also ensures that the path found is safe and shortest according to the obstacle information and path cost function in the map of the available hook-unhooking environment area. The RRT algorithm quickly explores the space by means of random sampling and expanding the tree. In the map of the available hook-unhooking environment area, some points are randomly generated, and then these points are connected to the existing tree structure, gradually expanding the scope of the tree until the target position is found. Similarly, during this process, it ensures that the generated path is shortest and safe according to the path cost function and the obstacle information in the map. By optimizing separately with different path planning algorithms, multiple hook-unhooking path information can be obtained finally. These path information are all the optimal paths found by their respective algorithms considering factors such as path length and safety, providing multiple possibilities for subsequent path selection.

[0057] Evaluate the feasibility of multiple unhooking path information. This process is mainly to screen out the paths that the robot can actually pass through. For each unhooking path, check whether it meets the motion constraint conditions of the robot. For example, considering the maximum turning angle of the robot, if there is a turning operation in a certain path that requires the robot to turn more than its maximum turning angle, then this path is determined to be infeasible. Similarly, check the slope of the path to ensure that the slope on the path does not exceed the maximum climbing slope limit of the robot. The size limit of the robot can also be considered to ensure that there is enough space on the path for the robot to pass through without collision. After the feasibility evaluation, a set of paths that the robot can pass through is obtained. Then, perform a cost comparison and optimization on these passable paths. The basis for the cost comparison is the previously constructed path cost function. If the path cost function mainly considers the path length, then select the path with the shortest length. If other factors such as time and energy consumption are also considered, the total cost of each path can be calculated by integrating these factors, and then select the path with the minimum total cost. For example, for two passable paths A and B, if path A is shorter in length but contains some complex terrains that require more time; path B is slightly longer in length but has a flatter terrain and lower energy consumption when the robot passes through. After comprehensively considering factors such as length, time, and energy consumption according to the path cost function, calculate the total costs of path A and path B, and finally select the path with the minimum total cost as the target unhooking path. Through such a feasibility evaluation and cost comparison and optimization process, it can be ensured that the determined target unhooking path not only meets the motion constraints of the robot but also is optimal in terms of cost, thus providing the best action route for the robot to complete the unhooking task efficiently and accurately.

[0058] In a possible implementation manner, step S360 further includes:

[0059] Step S361: Obtain the structural characteristic parameters of the unhooking robot, and perform robot execution space analysis on the hook space coordinate information based on the structural characteristic parameters to obtain the robot's executable space.

[0060] Step S362: Conduct torque test fitting and dynamic modeling on the unhooking robot, construct a robot dynamic model, and define an execution objective function according to the robot dynamic model.

[0061] Step S363: Use the execution objective function to perform global coordinate optimization in the robot's executable space to determine the robot execution space coordinate information.

[0062] Specifically, obtain the structural characteristic parameters of the hook-unhooking robot. These parameters are crucial for determining the executable space of the robot and include the angular ranges of the robot's various joints, which determine the different postures that the robot's limbs can achieve. For example, certain joints have certain rotational angle limitations, which will affect the overall movement range of the robot. At the same time, it also includes the relevant parameters of the end position, such as the end effector, specifically the structural dimensions and lengths of the robotic gripper, etc. The size of the robotic gripper determines the size range of the objects it can grasp, and the length affects the distance it can reach. Based on these structural characteristic parameters, conduct a robotic execution space analysis on the hook space coordinate information. Considering the spatial coordinate position of the hook and combining the structural characteristics of the robot, determine whether the robot can reach the hook position within its own structural limitations. If a certain combination of the robot's joint angles can enable the end effector to reach the spatial coordinates where the hook is located, then this position is within the executable space of the robot. By analyzing different combinations of joint angles and considering factors such as the size and length of the end effector, the spatial range that the robot can reach can be gradually determined, meeting the movable space for the robot's joints to perform the hook-unhooking operation.

[0063] Conduct torque test fitting on the hook-unhooking robot. By conducting actual torque tests on the robot under different working conditions, collect a large amount of data on the torque required by the robot at different joint angles. Then, use the least squares method to process these data to establish a relationship model between torque and joint angle. Next, conduct dynamic modeling, comprehensively considering factors such as the physical structure, mass distribution, and joint movement of the robot, and construct a robot dynamic model. This model can accurately describe the movement state and torque requirements of the robot at different joint angles. For example, according to parameters such as the link lengths, masses, and moments of inertia of the joints of the robot, the acceleration and required torque of the robot in different postures can be calculated. Based on the constructed robot dynamic model, define the execution objective function, which is set as the sum of the joint torques, and optimize to determine the situation of minimizing the torque. When planning the movement path of the robot, by adjusting the combination of the robot's joint angles, ensure that when reaching the hook space coordinate information, the sum of the joint torques required by the robot is minimized, so as to ensure that the robot is the most labor-saving when performing the hook-unhooking task.

[0064] Define the range of the robot's executable space, which is determined based on the structural characteristic parameters of the robot and the analysis of the hook space coordinate information. Then, define the execution objective function. For example, with the goal of minimizing the total joint torque, ensure that the robot uses the least force when unhooking at the hook space coordinate information. Use the simulated annealing algorithm to randomly generate an initial coordinate point within the robot's executable space as the current solution, calculate the objective function value corresponding to the current solution, that is, the total joint torque of the robot when reaching the hook space coordinate in the current state. Then, randomly generate a new coordinate point near the current solution as the candidate solution and calculate the objective function value of the candidate solution as well. If the objective function value of the candidate solution is better than that of the current solution, then accept the candidate solution as the new current solution. If the objective function value of the candidate solution is not as good as that of the current solution, then accept the candidate solution with a certain probability, and this probability gradually decreases as the algorithm progresses, just like the cooling process in physics. During the iterative process of the algorithm, continuously repeat the above steps, that is, generate new candidate solutions near the current solution, and perform evaluation and acceptance decisions. By continuously exploring and accepting a certain degree of "worse solutions", the simulated annealing algorithm can avoid falling into local optimal solutions and thus perform global optimization within the robot's executable space. Finally, when the algorithm meets the stop condition, the current solution is the determined robot execution space coordinate information, and this coordinate enables the robot to reach the hook space coordinate in a better way for unhooking operations.

[0065] In a possible implementation manner, step S400 further includes:

[0066] Step S410: Perform attitude simulation on the unhooking robot according to the target unhooking path to obtain the spatial position information of the end effector of the unhooking robot.

[0067] Step S420: Based on the dynamic characteristic parameters and motion constraint information, perform movable space analysis on the spatial position information of the end effector to construct a robot motion control space.

[0068] Step S430: Based on the robot motion control space, perform unhooking execution analysis on the hook attitude information to obtain the unhooking control parameters.

[0069] Specifically, first, clarify the determined target unhooking path, which is obtained through the calculation and optimization process and aims to provide the best action route for the unhooking robot to complete the unhooking task. Then, conduct pose simulation. Using computer simulation technology or the kinematic model of the robot, simulate the process of the robot moving along the target unhooking path. During the simulation, according to the structural characteristics of the robot, the joint movement mode, and each position point on the target unhooking path, gradually calculate the pose of the robot at different positions. Pay special attention to the end effector of the robot because it is the key part directly interacting with the hook to complete the unhooking operation. By simulating the movement of the robot along the target unhooking path, continuously track and calculate the spatial position of the end effector. Considering factors such as the joint angle change and link length of the robot, use kinematic equations and geometric calculation methods to determine the specific coordinates of the end effector in three-dimensional space.

[0070] First, analyze the dynamic characteristic parameters and motion constraint information of the unhooking robot. The dynamic characteristic parameters include the motor power, torque output ability, acceleration performance, etc. of the robot, which determine the power magnitude and motion ability that the robot can generate in different states. The motion constraint information covers the joint motion range limit, maximum speed limit, acceleration limit, and physical limitations in structure of the robot, etc. Use these parameters and information to conduct a movable space analysis on the spatial position information of the end effector. For each spatial position of the end effector, combine the dynamic characteristic parameters to judge whether the robot has enough power to drive itself to reach that position. For example, if a certain position requires the robot to output a large torque to overcome the resistance, but the dynamic characteristics of the robot cannot meet the requirement, then this position is not within the movable space range. At the same time, considering the motion constraint information, check whether this position exceeds the joint motion range or speed and acceleration limits of the robot. If it exceeds these limits, it will also be excluded from the movable space. By conducting such analysis on each spatial position of the end effector, gradually determine the spatial range that the robot can safely and effectively reach and operate, thereby constructing the robot motion control space. This space provides a feasible motion area for the subsequent unhooking operation, ensuring that the robot will not malfunction or be unable to complete the task due to exceeding its own capabilities or violating the motion constraints when performing the task.

[0071] Based on the already constructed robot motion control space, which is determined by comprehensively considering the dynamic characteristic parameters and motion constraint information of the robot and limits the range within which the robot can move safely and effectively when performing the hook unhooking task. Then, the hook attitude information is introduced. The hook attitude information includes the position, direction, and specific state of the hook in space, and the hook attitude information is analyzed for hook unhooking execution using the robot motion control space. In this process, it is necessary to analyze how the robot adjusts its own attitude and actions within the motion control space to achieve accurate grasping of the hook. Determine the robot control parameters when grasping the hook, and these parameters include the rotation angle and direction of the robot hook unhooking control. By analyzing the position and direction of the hook and combining the current position of the robot end effector and the limitations of the motion control space, calculate the rotation angle and direction adjustments that the robot needs to make so that the end effector can accurately align with the hook and perform the grasping operation.

[0072] In a possible implementation manner, step S500 further includes:

[0073] Step S510: Monitor the hook unhooking control of the hook unhooking robot based on the target hook unhooking path and the hook unhooking control parameters to obtain hook unhooking control feedback parameters.

[0074] Step S520: Calculate the deviation between the hook unhooking control feedback parameters and the preset hook unhooking state to determine the hook unhooking state deviation parameters.

[0075] Step S530: Analyze the optimization direction of the hook unhooking state deviation parameters to obtain a fine-tuning strategy for the control parameters, and perform deviation fine-tuning compensation on the hook unhooking control parameters based on the fine-tuning strategy for the control parameters.

[0076] Specifically, the unhooking robot is comprehensively monitored for unhooking control based on the target unhooking path and unhooking control parameters. The target unhooking path provides the best route planning for the robot to reach the hook position, while the unhooking control parameters specifically specify various key parameters of the robot when performing the unhooking action, such as the rotation angle and direction. During the monitoring process, a series of sensors installed on the unhooking robot are used to obtain various feedback parameters in real time. The position sensor can accurately determine the position coordinates of the robot in space to understand whether it is moving at the correct position according to the target unhooking path. The speed sensor can measure the moving speed of the robot to ensure that its speed is within a safe and efficient range. The acceleration sensor monitors the acceleration changes during the movement of the robot, which is very important for judging whether the movement state of the robot is stable and whether the control strategy needs to be adjusted. The attitude sensor can feedback the body attitude of the robot, including information such as the tilt angle and rotation angle, to ensure that the robot maintains the correct attitude when performing the unhooking task and avoid affecting the accuracy of unhooking due to improper attitude. In addition, the force condition is also one of the important feedback parameters. By installing force sensors on the end effector or key parts of the robot, the forces received by the robot during the interaction with the environment and the unhooking operation can be detected, which helps to judge whether the robot collides with obstacles, whether it successfully grabs the hook, and whether the grasping force is appropriate. By monitoring these parameters, comprehensive unhooking control feedback parameters can be obtained, providing accurate data basis for subsequent deviation calculation and control parameter adjustment.

[0077] Two key elements, namely the unhooking control feedback parameters and the preset unhooking state, are clarified. The unhooking control feedback parameters are the actual state information obtained by monitoring the unhooking robot, including position, speed, acceleration, attitude, force condition, etc. The preset unhooking state is the state that the robot should reach set according to the requirements of the ideal unhooking task. When calculating the deviation, each feedback parameter dimension is compared with the corresponding parameter in the preset state respectively. For example, for the position parameter, the distance difference between the actual position and the preset position is calculated; for the speed parameter, the magnitude difference between the actual speed and the preset speed is compared; for the attitude parameter, the angle deviation between the actual attitude and the preset attitude is analyzed, etc. By calculating each parameter dimension one by one, the unhooking state deviation parameters can be determined, which comprehensively reflect the gap between the current actual state of the robot and the ideal preset state. If the deviation is large, it means that there is a large deviation between the actual operating state of the robot and the expected target, and a large adjustment is required; if the deviation is small, only fine-tuning is needed to make the robot reach the preset unhooking state. Determining the unhooking state deviation parameters provides a specific quantitative basis for subsequent optimization direction analysis and control parameter fine-tuning, enabling targeted adjustment of the robot's control parameters to reduce the deviation and make the robot perform the unhooking task more accurately.

[0078] Analyze the optimization direction of the unhooking state deviation parameters. Since the deviation parameters reflect the gap between the actual state of the robot and the preset unhooking state, by analyzing these deviations, the direction of adjustment can be determined to reduce the deviation. For different types of deviation parameters, the analysis methods are different. For example, if the position deviation shows that the actual position of the robot deviates from the preset position, then it is necessary to determine in which direction the robot should move to reduce the position deviation. If the speed deviation indicates that the robot's speed is too fast or too slow, it is necessary to determine whether to increase or decrease the speed to meet the preset speed requirement. For the attitude deviation, analyze which joint angles need to be adjusted to make the robot's attitude closer to the preset attitude. Through such analysis, a fine-tuning strategy for control parameters is obtained, which specifically points out the direction and amplitude of the adjustment of the unhooking control parameters. For example, if the position deviation is large, the strategy is to adjust the movement speed and direction of the robot to make it move towards the preset position faster; if the attitude deviation is small, the strategy is to fine-tune the angles of some joints to gradually correct the robot's attitude. Based on the fine-tuning strategy for control parameters, perform deviation fine-tuning compensation on the unhooking control parameters, and make fine adjustments to the unhooking control parameters according to the adjustment direction and amplitude determined in the strategy. For example, if the strategy requires increasing the rotation angle of a certain joint of the robot, the corresponding joint angle value in the unhooking control parameters is increased. By continuously performing deviation fine-tuning compensation, the unhooking state deviation can be gradually reduced, making the actual state of the robot closer and closer to the preset unhooking state, thereby improving the accuracy and stability of the unhooking operation.

[0079] Embodiment 2, based on the same inventive concept as the dynamic unhooking control method of the unhooking robot based on the feedback mechanism in the foregoing embodiment, as Figure 2 shown, the present application provides a dynamic unhooking control system for an unhooking robot based on a feedback mechanism. The embodiments in the present application are based on the same inventive concept as the method embodiments. Among them, the system includes:

[0080] An image information acquisition module 10, which is used to acquire an unhooking robot. The unhooking robot is integrated with a vision sensor and an image processing unit. Move the unhooking robot to a preset unhooking position, and at the same time start the vision sensor to collect unhooking image information and environmental perception image information.

[0081] A hook spatial coordinate information determination module 20, which performs edge detection and feature extraction on the unhooking image information based on the image processing unit to obtain hook position information and hook attitude information, and performs coordinate transformation on the hook position information according to the preset unhooking position to determine hook spatial coordinate information.

[0082] The target unhooking path acquisition module 30 is used to abstract the features of the environmental perception image information to generate an unhooking environment area map, and plan a path for the hook spatial coordinate information based on the unhooking environment area map to obtain a target unhooking path.

[0083] The unhooking control parameter acquisition module 40 is used to acquire the dynamic characteristic parameters and motion constraint information of the unhooking robot, and perform unhooking analysis on the hook attitude information based on the dynamic characteristic parameters and motion constraint information to obtain unhooking control parameters.

[0084] The dynamic unhooking control module 50 performs dynamic unhooking control on the unhooking robot based on the target unhooking path and the unhooking control parameters, and introduces a feedback mechanism to perform real-time deviation analysis and compensating unhooking control on the unhooking control process.

[0085] Furthermore, the hook spatial coordinate information determination module 20 further includes:

[0086] The unhooking standard grayscale image acquisition unit is used to convert the unhooking image information into an unhooking grayscale image, and perform filtering denoising and image enhancement on the unhooking grayscale image to obtain an unhooking standard grayscale image.

[0087] The unhooking edge detection information acquisition unit is used to perform edge detection on the unhooking standard grayscale image through a Canny edge detector to obtain unhooking edge detection information.

[0088] The unhooking contour information acquisition unit is used to preset an edge low threshold and an edge high threshold, and perform edge contour screening on the unhooking edge detection information based on the edge low threshold and the edge high threshold to obtain unhooking contour information.

[0089] The hook position information acquisition unit is used to perform anchor box positioning on the unhooking contour information to obtain unhooking anchor box information, and calculate a center point based on the unhooking anchor box information to obtain the hook position information.

[0090] The hook attitude information acquisition unit performs hook attitude feature extraction based on the unhooking contour information and the hook position information to obtain the hook attitude information.

[0091] Furthermore, the target unhooking path acquisition module 30 further includes:

[0092] Uncoupling environment multi-dimensional feature set acquisition unit, which is used to perform multi-dimensional feature extraction and feature dimensionality reduction processing on the environmental perception image information to obtain the uncoupling environment multi-dimensional feature set.

[0093] Uncoupling environment entity attribute information set acquisition unit, which is based on the uncoupling environment multi-dimensional feature set to perform distributed entity recognition to obtain the uncoupling environment entity set, and perform attribute marking on the uncoupling environment entity set to obtain the uncoupling environment entity attribute information set.

[0094] Map connection edge set acquisition unit, which is used to abstract the uncoupling environment entity set into a map node set, and perform edge attribute abstraction on the map node set based on the uncoupling environment entity attribute information set to obtain the map connection edge set.

[0095] Uncoupling environment area map generation unit, which is based on the map connection edge set to perform map topological connection on the map node set to generate the uncoupling environment area map.

[0096] Furthermore, the target uncoupling path acquisition module 30 further includes:

[0097] Available uncoupling environment area map acquisition unit, which is used to mark the path obstacles in the uncoupling environment area map according to the uncoupling environment entity attribute information set to obtain the available uncoupling environment area map.

[0098] Execution space coordinate information determination unit, which is used to define the uncoupling control target, construct a path cost function according to the uncoupling control target, and at the same time perform robot execution analysis according to the hook space coordinate information to determine the robot execution space coordinate information.

[0099] Multiple uncoupling path information acquisition units, which are used to obtain a list of path planning algorithms, and use the path cost function based on the path planning algorithm list and the available uncoupling environment area map to respectively perform iterative planning optimization on the robot execution space coordinate information to obtain multiple uncoupling path information.

[0100] Target uncoupling path determination unit, which is used to perform feasibility evaluation and cost ratio comparison and optimization on the multiple uncoupling path information to determine the target uncoupling path.

[0101] Furthermore, the execution space coordinate information determination unit further includes:

[0102] A robot executable space acquisition unit, which is used to acquire the structural characteristic parameters of the unhooking robot, perform robot executable space analysis on the hook space coordinate information based on the structural characteristic parameters, and obtain the robot executable space.

[0103] An execution objective function definition unit, which is used to perform torque test fitting and dynamic modeling on the unhooking robot, construct a robot dynamic model, and define an execution objective function according to the robot dynamic model.

[0104] A coordinate global optimization unit, which is used to perform coordinate global optimization in the robot executable space by using the execution objective function to determine the robot execution space coordinate information.

[0105] Furthermore, the unhooking control parameter acquisition module 40 further includes:

[0106] A space position information acquisition unit, which is used to perform attitude simulation on the unhooking robot according to the target unhooking path and acquire the space position information of the end effector of the unhooking robot.

[0107] A motion control space construction unit, which performs movable space analysis on the space position information of the end effector based on the dynamic characteristic parameters and motion constraint information to construct a robot motion control space.

[0108] An unhooking execution analysis unit, which performs unhooking execution analysis on the hook attitude information based on the robot motion control space to obtain the unhooking control parameters.

[0109] Furthermore, the dynamic unhooking control module 50 further includes:

[0110] An unhooking control feedback parameter acquisition unit, which monitors the unhooking control of the unhooking robot based on the target unhooking path and the unhooking control parameters to obtain unhooking control feedback parameters.

[0111] An unhooking state deviation parameter determination unit, which is used to calculate the deviation between the unhooking control feedback parameters and the preset unhooking state to determine the unhooking state deviation parameters.

[0112] A deviation fine-tuning compensation unit, which is used to analyze the optimization direction of the unhooking state deviation parameters to obtain a control parameter fine-tuning strategy, and perform deviation fine-tuning compensation on the unhooking control parameters based on the control parameter fine-tuning strategy.

[0113] It should be noted that the above order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. In addition, the above specific embodiments of this specification have been described. Further, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0114] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0115] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A dynamic hook removal control method for a hook removal robot based on a feedback mechanism, characterized in that: The method comprises: Acquire a hook-removing robot, wherein the hook-removing robot integrates a visual sensor and an image processing unit, move the hook-removing robot to a preset hook-removing position, and simultaneously activate the visual sensor to collect and obtain hook-removing image information and environment perception image information; Based on the image processing unit, edge detection and feature extraction are performed on the hook removal image information to obtain hook position information and hook posture information, and coordinate conversion is performed on the hook position information according to the preset hook removal position to determine the hook space coordinate information; Performing feature abstraction on the environmental perception image information to generate a hook removal environment area map, and performing path planning on the hook space coordinate information based on the hook removal environment area map to obtain a target hook removal path; Acquiring the power characteristic parameters and motion constraint information of the hook-removing robot, and performing hook-removing analysis on the hook posture information based on the power characteristic parameters and motion constraint information to obtain hook-removing control parameters; Dynamically controlling the unhooking robot based on the target unhooking path and the unhooking control parameters, and introducing a feedback mechanism to perform real-time analysis of deviations and compensatory unhooking control during the unhooking control process; The feedback mechanism is introduced to perform real-time analysis of deviations and compensation for hook removal control during the hook removal control process, including: Based on the target hook removal path and the hook removal control parameters, the hook removal robot is monitored for hook removal control to obtain a hook removal control feedback parameter; Performing deviation calculation on the hook removal control feedback parameter and the preset hook removal state to determine the hook removal state deviation parameter; The decoupling state deviation parameter is analyzed in an optimization direction to obtain a control parameter fine-tuning strategy, and the decoupling control parameter is fine-tuned and compensated for the deviation based on the control parameter fine-tuning strategy.

2. The dynamic hook-removing control method of the hook-removing robot based on the feedback mechanism as claimed in claim 1 is characterized in that: The obtaining of the hook position information includes: Converting the hook removal image information into a hook removal grayscale image, and performing filtering, denoising and image enhancement on the hook removal grayscale image to obtain a hook removal standard grayscale image; Performing edge detection on the hook removal standard grayscale image by using a Canny edge detector to obtain hook removal edge detection information; Preset an edge low threshold and an edge high threshold, and perform edge contour screening on the hook removal edge detection information based on the edge low threshold and the edge high threshold to obtain hook removal contour information; Anchor frame positioning is performed on the hook removal contour information to obtain hook removal anchor frame information, and center point calculation is performed based on the hook removal anchor frame information to obtain the hook position information; The hook posture feature is extracted based on the hook removal contour information and the hook position information to obtain the hook posture information.

3. The dynamic hook-removing control method of the hook-removing robot based on the feedback mechanism as claimed in claim 1, characterized in that: The generating of the decoupling environment area map comprises: Performing multi-dimensional feature extraction and feature dimension reduction processing on the environmental perception image information to obtain a multi-dimensional feature set of the hook removal environment; Perform distributed entity recognition based on the multi-dimensional feature set of the unhooking environment to obtain an unhooking environment entity set, and perform attribute marking on the unhooking environment entity set to obtain an unhooking environment entity attribute information set; Abstracting the unhooking environment entity set into a map node set, performing edge attribute abstraction on the map node set based on the unhooking environment entity attribute information set, and obtaining a map connection edge set; The map node set is topologically connected based on the map connection edge set to generate the dehooking environment area map.

4. The dynamic hook-removing control method of the hook-removing robot based on the feedback mechanism as claimed in claim 3 is characterized in that: The step of obtaining the target hook removal path comprises: Marking the path obstacles in the dehooking environment area map according to the dehooking environment entity attribute information set to obtain an available dehooking environment area map; Defining a hook removal control target, constructing a path cost function according to the hook removal control target, and performing robot execution analysis according to the hook space coordinate information to determine the robot execution space coordinate information; Obtain a path planning algorithm list, and use the path cost function to perform iterative planning and optimization on the robot execution space coordinate information based on the path planning algorithm list and the available hook removal environment area map to obtain multiple hook removal path information; Perform feasibility assessment and cost comparison on the multiple unhooking path information to determine the target unhooking path.

5. The dynamic hook-removing control method of the hook-removing robot based on the feedback mechanism as claimed in claim 4 is characterized in that: The determining of the robot execution space coordinate information includes: Acquire the structural characteristic parameters of the hook-removing robot, perform robot execution space analysis on the hook space coordinate information based on the structural characteristic parameters, and obtain the robot executable space; Performing torque test fitting and dynamic modeling on the unhooking robot, building a robot dynamic model, and defining an execution objective function according to the robot dynamic model; The execution objective function is used to perform global coordinate optimization in the robot executable space to determine the robot execution space coordinate information.

6. The dynamic hook-removing control method of the hook-removing robot based on the feedback mechanism as claimed in claim 1, characterized in that: The obtaining of the unhooking control parameters includes: Performing posture simulation on the hook-removing robot according to the target hook-removing path to obtain spatial position information of the end effector of the hook-removing robot; Based on the dynamic characteristic parameters and motion constraint information, a movable space analysis is performed on the spatial position information of the end effector to construct a robot motion control space; The hooking posture information is analyzed based on the robot motion control space to obtain the hooking control parameters.

7. The dynamic hook removal control system of the hook removal robot based on feedback mechanism is characterized by: The system comprises: An image information acquisition module, wherein the image information acquisition module is used to acquire a hook-removing robot, wherein the hook-removing robot integrates a visual sensor and an image processing unit, moves the hook-removing robot to a preset hook-removing position, and simultaneously activates the visual sensor to acquire hook-removing image information and environment perception image information; A hook space coordinate information determination module, wherein the hook space coordinate information determination module performs edge detection and feature extraction on the hook removal image information based on the image processing unit to obtain hook position information and hook posture information, and performs coordinate conversion on the hook position information according to the preset hook removal position to determine the hook space coordinate information; A target hook removal path acquisition module, the target hook removal path acquisition module is used to perform feature abstraction on the environmental perception image information, generate a hook removal environment area map, perform path planning on the hook space coordinate information based on the hook removal environment area map, and obtain a target hook removal path; A hook removal control parameter acquisition module, the hook removal control parameter acquisition module is used to obtain the power characteristic parameters and motion constraint information of the hook removal robot, and based on the power characteristic parameters and motion constraint information, perform hook removal analysis on the hook posture information to obtain the hook removal control parameters; A dynamic hook removal control module, wherein the dynamic hook removal control module performs dynamic hook removal control on the hook removal robot based on the target hook removal path and the hook removal control parameters, and introduces a feedback mechanism to perform real-time deviation analysis and compensatory hook removal control on the hook removal control process; The dynamic unhooking control module includes: an unhooking control feedback parameter acquisition unit, an unhooking state deviation parameter determination unit and a deviation fine-tuning compensation unit; The hook unhooking control feedback parameter acquisition unit performs hook unhooking control monitoring on the hook unhooking robot based on the target hook unhooking path and the hook unhooking control parameter to obtain the hook unhooking control feedback parameter; The hook-off state deviation parameter determination unit is used to calculate the deviation between the hook-off control feedback parameter and the preset hook-off state to determine the hook-off state deviation parameter; The deviation fine-tuning compensation unit is used to perform optimization direction analysis on the dehooking state deviation parameter, obtain a control parameter fine-tuning strategy, and perform deviation fine-tuning compensation on the dehooking control parameter based on the control parameter fine-tuning strategy.

Images