Intelligent plate grabbing robot operation action monitoring control system

Abstract

The invention discloses an intelligent plate grabbing robot operation action monitoring control system, and relates to the technical field of robot action monitoring control. Comprising the following steps: data acquisition: installing a sensor at an execution end of the intelligent plate grabbing robot, collecting shape data of a plate in real time, and collecting positions of surrounding obstacles at the same time to obtain plate shape data and obstacle shape data; by constructing a dynamic grabbing scheme and a template library, the system can effectively cope with plates of different shapes and materials and achieve a targeted grabbing strategy, so that the grabbing efficiency is improved, meanwhile, the problems in the grabbing process can be rapidly recognized, the grabbing strategy is automatically adjusted, the requirement for human intervention is lowered, the autonomy of the system is improved, and the system is suitable for popularization and application. And meanwhile, various data in the grabbing process can be collected and analyzed in real time, instant feedback and adjustment of grabbing actions are ensured, and the operation flexibility and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of robot motion monitoring and control, and in particular to an intelligent gripping robot running motion monitoring and control system. Background Art

[0002] For example, a performance robot model control system with patent publication number CN117492407A includes a host master control system and machine model devices located in different scenes, each scene contains multiple machine model devices, and the host master control system is used to control the movements of the machine model devices in all scenes; the host master control system includes a communication module, an equipment operation module, an equipment monitoring module, an equipment maintenance module, an equipment scheduling module, an alarm management module, and a user management module; the machine model device includes a servo motor, a PLC, a joint motor, and an industrial computer, and the PLC is used to control the movement and operation of the servo motor, and the industrial computer is used to control the movement and operation of the joint motor. The host master control system is used to achieve unified control of the machine model devices in all scenes.

[0003] In the process of monitoring the robot's running movements, the above-mentioned and similar technical solutions have different shapes and specifications of the plates. When it is necessary to grasp a variety of special-shaped plates, such as curved metal plates, irregular-sized gypsum boards and composite boards with holes, traditional plate-grabbing robots rely on preset paths and fixed fixtures. It is difficult to adapt to the changes in the shape of the plates in real time, such as curved edges, surface unevenness and sudden obstacles, such as tools or personnel that suddenly appear, resulting in grasping failures, plate wear, and even safety accidents caused by delayed obstacle avoidance. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent gripping robot operation motion monitoring and control system to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a monitoring and control system for the operation of an intelligent board-grabbing robot, comprising the following steps: data acquisition, a sensor is installed at the execution end of the intelligent board-grabbing robot to collect the shape data of the board in real time, and the positions of the surrounding obstacles are collected at the same time, so as to obtain the shape data of the board and the shape data of the obstacle; Dynamic grabbing optimization: Build dynamic grabbing solutions and template libraries. The template library contains the shape features and grabbing solutions of various common plates. The matching method is used to match the plate shape data with the template library to generate dynamic grabbing data. Real-time monitoring: Based on dynamic grasping data, the grasping point, grasping force and grasping posture parameters of the intelligent gripper robot during the grasping action are monitored in real time to obtain real-time monitoring data; Feedback adjustment: Based on real-time monitoring data, the grasping action is optimized and adjusted, and the grasping point, grasping force and grasping posture parameters of the intelligent gripper robot during the grasping action are adjusted to obtain the adjustment results; The feedback adjustment comprises the following steps: Step 1: Data comparison and analysis: Based on real-time monitoring data, collect the grasping point, grasping force and grasping posture of various parameters in the grasping process and compare them with the preset dynamic grasping data to obtain the comparison results, analyze whether there are deviations or abnormalities in the grasping point, grasping force and grasping posture parameters, identify the parameters that need to be adjusted, and obtain the analysis results; Step 2: Deviation evaluation: Based on the comparison and analysis results, the degree of deviation and its impact on the grasping effect are evaluated, and it is determined whether the grasping point deviates from the target position, whether the grasping force is too large or too small, and whether the grasping posture is stable to obtain the evaluation result. Step 3: Generate adjustment strategy based on the evaluation results; Step 4: Adjustment execution: Based on the adjustment strategy, the robot's grasping point, grasping force and grasping posture are adjusted in real time to obtain adjusted grasping data; Step 5: Feedback verification: Based on the adjusted grabbing data, real-time monitoring is performed to verify whether the adjusted grabbing action meets expectations and obtain feedback adjustment results.

[0006] Furthermore, the adjustment strategy generation comprises the following steps: S1, gripping point adjustment, based on the evaluation results, plate shape data and obstacle position, recalculate the gripping point to obtain the gripping point adjustment result; S2, grasping force adjustment, based on the grasping point adjustment result, dynamically adjust the grasping force according to the material, weight and shape of the plate to obtain the grasping force adjustment result; S3, grasping posture adjustment, based on the real-time monitoring data, adjust the posture of the robot arm to obtain the grasping posture adjustment result.

[0007] The dynamic crawling scheme includes the following steps: Q1. Grasping point planning: based on the plate shape data, extract the key features of the plate, calculate the optimal grasping point, and obtain the grasping point data; Q2. Grasping force control: Based on the grasping point data, the grasping force is calculated through the material, weight distribution and grasping point data of the plate to obtain the grasping force data; Q3. Grasping posture control: based on the plate shape data, grasping point data and grasping force data, the robot's grasping posture is planned, and the robot's posture is adjusted in real time to obtain the grasping posture data; Q4, path optimization, based on the plate shape data, calculate the optimal path from the current position of the robot to the grasping point to obtain the dynamic grasping path.

[0008] Furthermore, the data acquisition method includes: N1: Image acquisition: acquiring the plate shape sensor image and the position and shape information of the obstacle based on the sensor data, and obtaining the initial plate shape data and initial obstacle data; N2: Data analysis: Based on the initial plate shape data and initial obstacle data, the target image is analyzed to identify the specific shape and size of the plate and the precise position and shape of the obstacle to obtain the analysis results; N3: Data fusion: the initial plate shape data, initial obstacle data and analysis results are fused to obtain a comprehensive data set containing complete plate shape and obstacle information; N4: Data matching, based on the comprehensive data set, by matching with the target initial plate shape data and initial obstacle data, to obtain the plate shape data and obstacle data.

[0009] Furthermore, the grasping point planning comprises the following steps: Z1. Plate feature extraction: Based on the plate shape data, the edge contour, hole position and surface concave-convex of the plate are extracted to generate a three-dimensional model of the plate, thereby obtaining the plate feature data; Z2, grasping point calculation, based on the plate feature data, use the algorithm to calculate the best grasping point of the plate, the grasping point is located at the position where the edge contour of the plate is stable, the holes are far away and the surface is less uneven, and the original grasping point data is obtained; Z3, grasping point optimization, based on the original grasping point data and robot motion parameters, combined with the actual shape and size of the plate and the operating limitations of the grasping robot, the initial grasping point data is optimized to obtain the initial grasping point data; Z4, grasping point verification, based on the initial grasping point data, the feasibility and stability of the final grasping point are verified by simulation to obtain the grasping point data.

[0010] Furthermore, the grasping force control comprises the following steps: X1. Force calculation: based on the material, weight distribution and gripping point data of the board, calculate the required gripping force and obtain the initial gripping force data; X2. Force optimization: Based on the initial grasping force data, combined with the robot's grasping ability, the force characteristics of the plate and environmental factors, the grasping force is optimized and adjusted to obtain the optimized grasping force data; X3. Force verification: Based on the optimized grasping force data, the rationality and effectiveness of the grasping force are verified through simulation to obtain the grasping force data.

[0011] Furthermore, the grasping posture control comprises the following steps: Y1. Posture planning: Based on the plate shape data, grasping point data and grasping force data, the robot's posture during the grasping process is planned to obtain the initial grasping posture data; Y2. Posture adjustment: Based on the initial grasping posture data and combined with the robot's kinematic and dynamic characteristics, the robot's posture is adjusted in real time to obtain the optimized grasping posture data; Y3. Posture verification: Based on the optimized grasping posture data, the rationality and effectiveness of the grasping posture are verified through simulation to obtain the grasping posture data.

[0012] Furthermore, the path planning comprises the following steps: L1, path planning, based on the plate shape data and the current position of the robot, calculate the optimal path from the current position of the robot to the grasping point and obtain the initial path data; L2, path optimization, based on the initial path data, combined with the obstacle information in the environment, the robot's motion restrictions and the real-time requirements of the grasping task, the path is optimized and adjusted to obtain the optimized path data; L3, path verification, based on the optimized path data, the rationality and effectiveness of the path are verified through simulation to obtain the dynamic crawling path.

[0013] Furthermore, the matching method comprises the following steps: B1. Feature matching: matching the plate shape data with the template library, calculating the similarity between the plate feature and the grabbing scheme in the template library, selecting the template with the highest similarity as the matching result, and obtaining the matching result; B2. Dynamic grasping scheme generation: based on the matching results, the corresponding grasping scheme is extracted from the template library. Combined with the specific shape data and environmental information of the current plate, the grasping scheme is dynamically adjusted to obtain the initial dynamic grasping scheme; B3, optimization and verification, based on the initial dynamic crawling plan, the generated dynamic crawling plan is optimized and verified to obtain a dynamic crawling plan; B4. Real-time update: Based on the dynamic grasping plan, monitor the execution of the grasping action and feed back the monitoring data to the system. If the monitoring data does not match the expectation, it will issue abnormal situations such as grasping point offset and insufficient force, dynamically adjust the grasping plan, and re-match and optimize.

[0014] Furthermore, the method for acquiring real-time monitoring data comprises the following steps: A1. Dynamic signal acquisition: various parameters of the robot during grasping action, including grasping point, grasping force and grasping posture, are collected in real time through distributed sensors to obtain original monitoring data; A2, noise filtering, based on the original monitoring data, denoise the original signal, extract the effective frequency band signal related to the grasping point, grasping force and grasping posture, and obtain the initial monitoring data; A3. Feature extraction: Based on the initial monitoring data, key features are extracted from the initial monitoring data, including the position information of the grasping point, the change trend of the grasping force, and the angle change of the grasping posture, to form a feature data set; A4. Anomaly detection: Based on the feature data set, the feature data set is analyzed to identify abnormal situations in which the grasping force in the grasping action is too large or too small, and the grasping posture deviates from the expected, and obtain the abnormal data set; A4. Real-time feedback: Based on the abnormal data set, the robot's grasping action parameters, grasping force and corrected grasping posture are adjusted, and finally real-time monitoring data is obtained.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The intelligent plate-grabbing robot's motion monitoring and control system builds dynamic grasping solutions and template libraries. The system can effectively cope with plates of different shapes and materials and implement targeted grasping strategies, thereby improving grasping efficiency. At the same time, it can quickly identify problems in the grasping process and automatically adjust the grasping strategy, reducing the need for human intervention and improving the autonomy of the system.

[0016] At the same time, it can collect and analyze various data in the grasping process in real time, ensure instant feedback and adjustment of the grasping action, and improve the flexibility and accuracy of the operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the overall process principle of the present invention; Figure 2 It is a schematic diagram of the structure of the feedback adjustment principle of the present invention; Figure 3 It is a schematic diagram of the real-time monitoring process of the present invention; Figure 4 It is a schematic diagram of grabbing point acquisition of the present invention; Figure 5 It is a schematic diagram of obtaining the plate shape data of the present invention; Figure 6 It is a schematic diagram of the overall working principle of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] In the process of sheet metal processing, a robot motion monitoring and control system is required. The robot motion monitoring and control system provided by the present invention is specifically used for robot motion monitoring and control operations in the process of sheet metal processing. In the process of using this system for monitoring and control operations, it is necessary to conduct a comprehensive inspection and test of the system before using this system to ensure the normal operation of each functional module to avoid failures or errors in the operation process. When acquiring sheet metal shape data, the accuracy and stability of the sensor should be ensured to accurately collect information such as the contour and size of the sheet metal, so as to provide reliable data support for subsequent grasping operations. During the grasping process, the system should be able to monitor the robot's motion and data in real time. Once an abnormal situation or error is found, it should be adjusted and optimized immediately to ensure the smooth progress of the grasping operation.

[0020] like Figure 1-Figure 6As shown, the present invention provides a technical solution: a control system for monitoring and controlling the operation of an intelligent gripping robot, comprising the following steps: data acquisition, a sensor is installed at the execution end of the intelligent gripping robot to collect the shape data of the plate in real time, and at the same time collects the positions of the surrounding obstacles to obtain the shape data of the plate and the shape data of the obstacle; dynamic grasping optimization: constructing a dynamic grasping scheme and a template library, the template library contains the shape features and grasping schemes of a variety of common plates, and a matching method is used to match the plate shape data and the template library, so as to generate dynamic grasping data; real-time monitoring: based on the dynamic grasping data, real-time monitoring of the grasping point, grasping force and grasping posture parameters of the intelligent gripping robot in the process of grasping action to obtain real-time monitoring data; feedback adjustment: based on the real-time monitoring data, optimizing and adjusting the grasping action, adjusting the grasping point, grasping force and grasping posture parameters of the intelligent gripping robot in the process of grasping action to obtain an adjustment result; the feedback adjustment comprises the following steps Steps: Step 1, data comparison and analysis, based on real-time monitoring data, collect the grasping point, grasping force and grasping posture of various parameters in the grasping process and compare them with the preset dynamic grasping data to obtain the comparison results, analyze whether there are deviations or abnormalities in the grasping point, grasping force and grasping posture parameters, identify the parameters that need to be adjusted, and obtain the analysis results; Step 2, deviation evaluation, based on the comparison results and analysis results, evaluate the degree of deviation and its impact on the grasping effect, and judge whether the grasping point deviates from the target position, whether the grasping force is too large or too small, and whether the grasping posture is stable, and obtain the evaluation results; Step 3, adjustment strategy generation, based on the evaluation results, generate an adjustment strategy; Step 4, adjustment execution, based on the adjustment strategy, adjust the robot's grasping point, grasping force and grasping posture in real time to obtain adjusted grasping data; Step 5, feedback verification, based on the adjusted grasping data, conduct real-time monitoring to verify whether the adjusted grasping action meets expectations, and obtain feedback adjustment results.

[0021] It should be noted that the shape data of the plate includes the shape, size and surface state of the plate, and the surface morphology includes: curved edges, bumps and holes.

[0022] like Figure 2 As shown, the adjustment strategy generation includes the following steps: S1, grasping point adjustment, based on the evaluation results, plate shape data and obstacle position, recalculate the grasping point to obtain the grasping point adjustment result; S2, grasping force adjustment, based on the grasping point adjustment result, dynamically adjust the grasping force according to the material, weight and shape of the plate to obtain the grasping force adjustment result; S3, grasping posture adjustment, based on real-time monitoring data, adjust the posture of the robot arm to obtain the grasping posture adjustment result.

[0023] It should be noted that the optimal grasping point position is determined through the evaluation results, plate shape data and obstacle position. After the grasping point is determined, the grasping force is dynamically adjusted according to the material, weight and shape characteristics of the plate. Finally, the posture of the robot arm is adjusted according to the real-time monitoring data.

[0024] Building a dynamic grasping solution includes the following steps: Q1, grasping point planning, based on the plate shape data, extract the key features of the plate, and calculate the optimal grasping point to obtain the grasping point data; Q2, grasping force control, based on the grasping point data, calculate the grasping force through the material, weight distribution and grasping point data of the plate, and obtain the grasping force data; Q3, grasping posture control, based on the plate shape data, grasping point data and grasping force data, plan the robot's grasping posture, and adjust the robot's posture in real time to obtain the grasping posture data; Q4, path optimization, based on the plate shape data, calculate the optimal path of the robot from the current position to the grasping point, and obtain the dynamic grasping path. The grasping point planning includes the following steps: Z1, plate feature extraction , based on the plate shape data, the edge contour, hole position and surface convexity of the plate are extracted to generate a three-dimensional model of the plate, thereby obtaining the plate feature data; Z2, grasping point calculation, based on the plate feature data, the algorithm is used to calculate the best grasping point of the plate, the grasping point is located at a position where the edge contour of the plate is stable, the holes are far away and the surface convexity is less, and the original grasping point data is obtained; Z3, grasping point optimization, based on the original grasping point data and the robot's motion parameters, combined with the actual shape and size of the plate and the operating limitations of the grasping robot, the initial grasping point data is optimized to obtain the initial grasping point data; Z4, grasping point verification, based on the initial grasping point data, the feasibility and stability of the final grasping point are verified by simulation to obtain the grasping point data, and the grasping point data is obtained. The grasping force control includes the following steps: X1, force calculation, based on the material, weight distribution and grasping point data of the plate, calculate the required grasping force to obtain the initial grasping force data; X2, force optimization, based on the initial grasping force data, combined with the robot's grasping ability, the force characteristics of the plate and environmental factors, optimize and adjust the grasping force to obtain the optimized grasping force data; X3, force verification, based on the optimized grasping force data, verify the rationality and effectiveness of the grasping force through simulation to obtain the grasping force data. The grasping posture control includes the following steps: Y1, posture planning, based on the plate shape data, grasping point data and grasping force data, plan the posture of the robot during the grasping process to obtain the initial grasping posture data. Y2, posture adjustment, based on the initial grasping posture data, combined with the robot's kinematic and dynamic characteristics, adjust the robot's posture in real time to obtain the optimized grasping posture data; Y3, posture verification, based on the optimized grasping posture data, verify the rationality and effectiveness of the grasping posture through simulation to obtain the grasping posture data. The path planning includes the following steps: L1, path planning, based on the plate shape data and the current position of the robot, calculate the optimal path of the robot from the current position to the grasping point to obtain the initial path data; L2, path optimization, based on the initial path data, combined with the obstacle information in the environment, the robot's motion restrictions and the real-time requirements of the grasping task, optimize and adjust the path to obtain the optimized path data;L3, path verification, based on the optimized path data, the rationality and effectiveness of the path are verified through simulation to obtain the dynamic crawling path. ;

[0025] It should be noted that the key features of the plate are extracted in the grasping point planning mainly through the edge detection algorithm to calculate the grasping point, the grasping force is mainly calculated by the neural network algorithm, and the path optimization is mainly calculated by the genetic algorithm to calculate the robot's motion path.

[0026] The data acquisition method includes: N1: image acquisition, based on the sensor data, the sensor image of the plate shape and the position and shape information of the obstacle are acquired to obtain the initial plate shape data and the initial obstacle data; N2: data analysis, based on the initial plate shape data and the initial obstacle data, the target image is analyzed to identify the specific shape and size of the plate and the precise position and shape of the obstacle to obtain the analysis result; N3: data fusion, the initial plate shape data, the initial obstacle data and the analysis result are fused to obtain a comprehensive data set containing complete plate shape and obstacle information; N4: data matching, based on the comprehensive data set, the plate shape data and the initial obstacle data are matched to obtain the plate shape data and the obstacle data.

[0027] It should be noted that the sensor image of the plate shape and the position and shape information of the obstacle are obtained through visual sensors or distance measurement sensors, and the target image is deeply analyzed. The specific shape and size of the plate and the precise position and shape of the obstacle are identified through the image recognition algorithm. The initial plate shape data, initial obstacle data and analysis results are fused and processed, and the accuracy and consistency of the data are further verified by matching with the target initial plate shape data and obstacle data.

[0028] The matching method includes the following steps: B1, feature matching, matching based on the plate shape data with the template library, calculating the similarity between the plate feature and the grasping scheme in the template library, selecting the template with the highest similarity as the matching result, and obtaining the matching result; B2, dynamic grasping scheme generation, based on the matching result, extracting the corresponding grasping scheme from the template library, combining the specific shape data and environmental information of the current plate, dynamically adjusting the grasping scheme to obtain the initial dynamic grasping scheme; B3, optimization and verification, based on the initial dynamic grasping scheme, optimizing and verifying the generated dynamic grasping scheme to obtain the dynamic grasping scheme; B4, real-time update, based on the dynamic grasping scheme, monitoring the execution of the grasping action, and feeding back the monitoring data to the system. If the monitoring data does not meet the expectations, it will issue abnormal situations of grasping point offset and insufficient force, dynamically adjust the grasping scheme, and re-match and optimize.

[0029] It should be noted that the plate shape data is first matched with the template library, and the similarity between the plate features and the grasping solutions in the template library is calculated, and the template with the highest similarity is selected as the matching result, thereby obtaining a preliminary matching solution. After obtaining the matching result, the corresponding grasping solution is extracted from the template library, and the generated initial dynamic grasping solution is optimized and verified. Finally, the execution of the grasping action is continuously monitored, and the monitoring data is fed back to the system in real time.

[0030] The method for acquiring real-time monitoring data includes the following steps: A1, dynamic signal acquisition, through distributed sensors, real-time acquisition of various parameters in the process of grasping action performed by the robot, including grasping point, grasping force and grasping posture, to obtain original monitoring data; A2, noise filtering, based on the original monitoring data, denoising the original signal, extracting the effective frequency band signal related to the grasping point, grasping force and grasping posture, to obtain initial monitoring data; A3, feature extraction, based on the initial monitoring data, extracting key features from the initial monitoring data, including the position information of the grasping point, the change trend of the grasping force and the angle change of the grasping posture, to form a feature data set; A4, anomaly detection, based on the feature data set, analyzing the feature data set, identifying abnormal situations in which the grasping force in the grasping action is too large or too small, and the grasping posture deviates from the expected, to obtain an abnormal data set; A4, real-time feedback, based on the abnormal data set, adjusting the robot's grasping action parameters, grasping force and correcting the grasping posture, and finally obtaining real-time monitoring data.

[0031] It should be noted that various parameters of the robot when performing grasping actions are collected in real time through distributed sensors, and feature extraction is performed while the original monitoring data is subjected to noise filtering. The feature data set is then deeply analyzed to identify abnormal situations in the grasping action. These abnormal situations may include grasping force that is too large or too small, grasping posture that deviates from expectations, etc. The system adjusts the robot's grasping action parameters, grasping force, and corrects the grasping posture through the abnormal data set.

[0032] Embodiment 1: In a sheet processing workshop, an intelligent sheet grabbing robot needs to grab sheets from stacked sheets and move them to processing equipment for cutting or drilling. The sheet is a rectangular sheet with a length of 100 cm and a width of 60 cm. The outer surface of the sheet is provided with multiple groups of through holes and is uneven, and the four corners are right angles. The robot is equipped with a high-precision sensor at the execution end to collect shape data of the stacked sheets such as edge contour, hole position, surface convexity, etc. in real time, and match the collected sheet shape data with common sheet shape features in the template library. When the match is successful, a dynamic grabbing scheme suitable for the current sheet is generated. Finally, the grabbing action of the robot is monitored in real time and compared with the preset dynamic grabbing data. If there is a deviation between the monitoring data and the preset data, such as the grabbing point deviates from the target position or the grabbing force is insufficient, the grabbing point is recalculated, the grabbing force is adjusted, and the posture of the robotic arm is optimized. After the robot successfully grabs the sheet, it moves it to the processing equipment according to the optimized path.

[0033] Embodiment 2: In a sheet processing workshop, the intelligent sheet grabbing robot needs to grab sheets from the stacked sheets and transport them to the processing equipment for cutting or drilling. The sheet surface is arc-shaped, and the length is 1120cm, the width is 40cm, and the thickness is 20cm. The outer surface of the sheet is smooth, and the four corners are 60-degree corners. The robot is equipped with a high-precision sensor at the execution end to collect the shape data of the stacked sheets in real time, such as edge contour, hole position, surface convexity, etc., and compares the collected sheet shape data with the common ones in the template library. The shape features of the plate are matched. When the match is unsuccessful, the grasping point, grasping force and grasping posture are recalculated according to the plate shape data to form a new grasping plan, and the new plan is imported into the template library. Finally, the robot's grasping action is monitored in real time and compared with the preset dynamic grasping data. If there is a deviation between the monitoring data and the preset data, such as the grasping point deviates from the target position or the grasping force is insufficient, the grasping point is recalculated, the grasping force is adjusted, and the posture of the robotic arm is optimized. After the robot successfully grasps the plate, it is moved to the processing equipment according to the optimized path.

[0034] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is limited by the attached embodiments and their equivalents.

Claims

1. An intelligent gripping robot operation monitoring and control system, characterized in that: The following steps are involved: Data acquisition: A sensor is installed on the execution end of the intelligent plate grabbing robot to collect the shape data of the plate in real time, and at the same time collect the positions of surrounding obstacles to obtain the shape data of the plate and the shape data of the obstacles; Dynamic grabbing optimization: Build dynamic grabbing schemes and template libraries, and use matching methods to match sheet shape data with template libraries to generate dynamic grabbing data; Real-time monitoring: Based on dynamic grasping data, the grasping point, grasping force and grasping posture parameters of the intelligent gripper robot during the grasping action are monitored in real time to obtain real-time monitoring data; Feedback adjustment: Based on real-time monitoring data, the grasping action is optimized and adjusted, and the grasping point, grasping force and grasping posture parameters of the intelligent gripper robot during the grasping action are adjusted to obtain the adjustment results; The feedback adjustment comprises the following steps: Step 1: Data comparison and analysis: Based on real-time monitoring data, various parameters in the grasping process are collected and compared with the preset dynamic grasping data to obtain the comparison results, analyze whether there are deviations or abnormalities in the grasping posture parameters, identify the parameters that need to be adjusted, and obtain the analysis results; Step 2: Deviation evaluation: Based on the comparison and analysis results, the degree of deviation and its impact on the grasping effect are evaluated, and it is determined whether the grasping point deviates from the target position, whether the grasping force is too large or too small, and whether the grasping posture is stable to obtain the evaluation result. Step 3: Generate adjustment strategy based on the evaluation results; Step 4: Adjustment execution: Based on the adjustment strategy, the robot's grasping point, grasping force and grasping posture are adjusted in real time to obtain adjusted grasping data; Step 5: Feedback verification: Based on the adjusted grabbing data, real-time monitoring is performed to verify whether the adjusted grabbing action meets expectations and obtain feedback adjustment results.

2. The intelligent gripping robot operation monitoring and control system according to claim 1 is characterized in that: The adjustment strategy generation comprises the following steps: S1, gripping point adjustment, based on the evaluation results, plate shape data and obstacle position, recalculate the gripping point to obtain the gripping point adjustment result; S2, grasping force adjustment, based on the grasping point adjustment result, dynamically adjust the grasping force according to the material, weight and shape of the plate to obtain the grasping force adjustment result; S3, grasping posture adjustment, based on the real-time monitoring data, adjust the posture of the robot arm to obtain the grasping posture adjustment result.

3. The intelligent gripping robot operation monitoring and control system according to claim 1 is characterized in that: The dynamic crawling scheme includes the following steps: Q1. Grasping point planning: based on the plate shape data, extract the key features of the plate, calculate the optimal grasping point, and obtain the grasping point data; Q2. Grasping force control: Based on the grasping point data, the grasping force is calculated through the material, weight distribution and grasping point data of the plate to obtain the grasping force data; Q3. Grasping posture control: based on the plate shape data, grasping point data and grasping force data, the robot's grasping posture is planned, and the robot's posture is adjusted in real time to obtain the grasping posture data; Q4, path optimization, based on the plate shape data, calculate the optimal path from the current position of the robot to the grasping point to obtain the dynamic grasping path.

4. The intelligent gripping robot operation monitoring and control system according to claim 1 is characterized in that: The method for obtaining the data includes: N1: Image acquisition: acquiring the plate shape sensor image and the position and shape information of the obstacle based on the sensor data, and obtaining the initial plate shape data and initial obstacle data; N2: Data analysis: Based on the initial plate shape data and initial obstacle data, the target image is analyzed to identify the specific shape and size of the plate and the precise position and shape of the obstacle to obtain the analysis results; N3: Data fusion: the initial plate shape data, initial obstacle data and analysis results are fused to obtain a comprehensive data set containing complete plate shape and obstacle information; N4: Data matching, based on the comprehensive data set, by matching with the target initial plate shape data and initial obstacle data, to obtain the plate shape data and obstacle data.

5. The intelligent gripping robot operation monitoring and control system according to claim 3 is characterized in that: The grasping point planning comprises the following steps: Z1. Plate feature extraction: Based on the plate shape data, the edge contour, hole position and surface concave-convex of the plate are extracted to generate a three-dimensional model of the plate, thereby obtaining the plate feature data; Z2, grasping point calculation, based on the plate feature data, use the algorithm to calculate the best grasping point of the plate, the grasping point is located at the position where the edge contour of the plate is stable, the holes are far away and the surface is less uneven, and the original grasping point data is obtained; Z3, grasping point optimization, based on the original grasping point data and robot motion parameters, combined with the actual shape and size of the plate and the operating limitations of the grasping robot, the initial grasping point data is optimized to obtain the initial grasping point data; Z4, grasping point verification, based on the initial grasping point data, the feasibility and stability of the final grasping point are verified by simulation to obtain the grasping point data.

6. The intelligent gripping robot operation monitoring and control system according to claim 3 is characterized in that: The grasping force control comprises the following steps: X1. Force calculation: based on the material, weight distribution and gripping point data of the board, calculate the required gripping force and obtain the initial gripping force data; X2. Force optimization: Based on the initial grasping force data, combined with the robot's grasping ability, the force characteristics of the plate and environmental factors, the grasping force is optimized and adjusted to obtain the optimized grasping force data; X3. Force verification: Based on the optimized grasping force data, the rationality and effectiveness of the grasping force are verified through simulation to obtain the grasping force data.

7. The intelligent gripping robot operation monitoring and control system according to claim 3 is characterized by: The grasping posture control comprises the following steps: Y1. Posture planning: Based on the plate shape data, grasping point data and grasping force data, the robot's posture during the grasping process is planned to obtain the initial grasping posture data; Y2. Posture adjustment: Based on the initial grasping posture data and combined with the robot's kinematic and dynamic characteristics, the robot's posture is adjusted in real time to obtain the optimized grasping posture data; Y3. Posture verification: Based on the optimized grasping posture data, the rationality and effectiveness of the grasping posture are verified through simulation to obtain the grasping posture data.

8. The intelligent gripping robot operation monitoring and control system according to claim 3 is characterized in that: The path planning comprises the following steps: L1, path planning, based on the plate shape data and the current position of the robot, calculate the optimal path from the current position of the robot to the grasping point and obtain the initial path data; L2, path optimization, based on the initial path data, combined with the obstacle information in the environment, the robot's motion restrictions and the real-time requirements of the grasping task, the path is optimized and adjusted to obtain the optimized path data; L3, path verification, based on the optimized path data, the rationality and effectiveness of the path are verified through simulation to obtain the dynamic crawling path.

9. The intelligent gripping robot operation monitoring and control system according to claim 1, characterized in that: The matching method comprises the following steps: B1. Feature matching: matching the plate shape data with the template library, calculating the similarity between the plate feature and the grabbing scheme in the template library, selecting the template with the highest similarity as the matching result, and obtaining the matching result; B2. Dynamic grasping scheme generation: based on the matching results, the corresponding grasping scheme is extracted from the template library. Combined with the specific shape data and environmental information of the current plate, the grasping scheme is dynamically adjusted to obtain the initial dynamic grasping scheme; B3, optimization and verification, based on the initial dynamic crawling plan, the generated dynamic crawling plan is optimized and verified to obtain a dynamic crawling plan; B4. Real-time update: Based on the dynamic grasping plan, monitor the execution of the grasping action and feed back the monitoring data to the system. If the monitoring data does not match the expectation, it will issue abnormal situations such as grasping point offset and insufficient force, dynamically adjust the grasping plan, and re-match and optimize.

10. The intelligent gripping robot operation monitoring and control system according to claim 1, characterized in that: The method for acquiring real-time monitoring data comprises the following steps: A1. Dynamic signal acquisition: various parameters of the robot during grasping action, including grasping point, grasping force and grasping posture, are collected in real time through distributed sensors to obtain original monitoring data; A2, noise filtering, based on the original monitoring data, denoise the original signal, extract the effective frequency band signal related to the grasping point, grasping force and grasping posture, and obtain the initial monitoring data; A3. Feature extraction: Based on the initial monitoring data, key features are extracted from the initial monitoring data, including the position information of the grasping point, the change trend of the grasping force, and the angle change of the grasping posture, to form a feature data set; A4. Anomaly detection: Based on the feature data set, the feature data set is analyzed to identify abnormal situations in which the grasping force in the grasping action is too large or too small, and the grasping posture deviates from the expected, and obtain the abnormal data set; A4. Real-time feedback: Based on the abnormal data set, the robot's grasping action parameters, grasping force and corrected grasping posture are adjusted, and finally real-time monitoring data is obtained.

Images