Robotic arm motion control method based on Internet of Things and knowledge graph

Abstract

The present invention discloses a robot arm motion control method based on the Internet of Things and a knowledge graph, and belongs to the field of motion control technology. The method performs multi-dimensional data processing and analysis on the parameters to be clamped obtained for the object to be clamped, obtains the clamping test parameters corresponding to the object to be clamped, and synchronously updates and stores the parameters to be clamped corresponding to the clamping test requirements in a clamping database and a clamping knowledge graph. The method performs calculation and data analysis on various clamping test data that do not meet the clamping test requirements, determines the clamping test error type corresponding to a special clamping scheme, and dynamically corrects the clamping test of the special clamping scheme according to the clamping test invalid state obtained through analysis, until the clamping test state corresponding to the corrected special clamping scheme is a clamping test valid state. The method is used to solve the technical problems in the existing scheme that the clamping of strange objects in the robot arm motion control cannot be dynamically supervised and corrected, and the clamping parameters cannot be autonomously and dynamically supplemented and improved.

Description

Technical Field

[0001] The present invention relates to the field of motion control technology, and in particular to a robotic arm motion control method based on the Internet of Things and a knowledge graph. Background Art

[0002] The motion control of a robotic arm mainly involves precise control of parameters such as position, velocity, acceleration, and torque of each joint of the robotic arm to achieve predetermined movements and tasks. A robotic arm is usually composed of multiple links (or arm segments) connected by rotatable or linearly movable joints, and each joint can have one or more degrees of freedom. The goal of motion control is to enable the robotic arm to perform complex operations such as grasping, placing, assembling, welding, etc. according to a set trajectory.

[0003] When implemented, the existing robotic arm motion control scheme cannot monitor and analyze the clamping status of different unfamiliar objects, and cannot adaptively and dynamically adjust the abnormal clamping status according to the analysis results, and add the clamping parameters corresponding to the normal clamping state and the parameters to be clamped of the unfamiliar objects to the clamping database. There are defects in that the clamping of unfamiliar objects controlled by the robotic arm motion cannot be dynamically supervised and corrected, and the clamping parameters cannot be autonomously and dynamically supplemented and improved. Summary of the invention

[0004] The purpose of the present invention is to provide a robotic arm motion control method based on the Internet of Things and knowledge graphs, which is used to solve the technical problems in the existing solutions that the gripping of unfamiliar objects in the robotic arm motion control cannot be dynamically supervised and corrected and the gripping parameters cannot be autonomously and dynamically supplemented and improved.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] The robot arm motion control method based on the Internet of Things and knowledge graph includes:

[0007] Based on the Internet of Things technology, the model code corresponding to the object to be clamped is obtained, and the model code is processed and analyzed to dynamically implement a conventional clamping solution or a special clamping solution for the clamped object;

[0008] When implementing a special clamping scheme, the clamping parameters corresponding to the object to be clamped are obtained and data processing and analysis are performed to obtain the clamping test parameters corresponding to the object to be clamped;

[0009] Using the clamping test parameters, a clamping test is performed on the object to be clamped, and the test data is analyzed to determine the clamping test state corresponding to the special clamping scheme. According to the clamping test valid state obtained by the analysis, the clamping test parameters and the clamping parameters corresponding to the object to be clamped are synchronously updated and stored in the clamping database and the clamping knowledge graph;

[0010] The clamping test of the special clamping scheme is dynamically corrected according to the invalid clamping test state obtained through analysis, until the clamping test state corresponding to the corrected special clamping scheme is the valid clamping test state, and the clamping test parameters corresponding to the clamping test requirements that finally meet the requirements and the clamping parameters corresponding to the object to be clamped are synchronously updated and stored in the clamping database and the clamping knowledge graph.

[0011] Preferably, the model code is traversed and matched with the clamping database. If there is a sample model code identical to the model code in the clamping database, the sample clamping parameters associated with the same sample model code are obtained to implement a conventional clamping solution for the object to be clamped.

[0012] If the sample model code identical to the model code does not exist in the clamping database, a special clamping solution is implemented for the object to be clamped.

[0013] Preferably, a stereoscopic image corresponding to the object to be clamped is obtained, and image processing and data analysis are performed on the stereoscopic image to obtain the corresponding shape of the object;

[0014] And, obtaining the weight of the object corresponding to the object to be clamped;

[0015] The shapes and weights of the objects to be clamped are sorted and combined to obtain the parameters to be clamped;

[0016] When performing data processing and analysis on the parameters to be clamped, the shapes of the objects in the parameters to be clamped are traversed and matched with the standard object shapes associated with all the object shape attributes in the clamping knowledge graph.

[0017] Preferably, if there is a standard object shape that is the same as the object shape, then several clamping position points associated with the standard object shape are all marked as test clamping position points;

[0018] If there is no standard object shape that is the same as the object shape, all of the preset clamping position points are marked as test clamping position points;

[0019] And, the weight of the object in the to-be-clamped parameter is traversed and matched with the weights of all the objects in the clamping knowledge graph, and all the object clamping forces corresponding to the same object weight obtained by matching are sorted and combined to obtain a matching object clamping force processing sequence;

[0020] Get the minimum value element in the matching item gripping force processing sequence and mark it as the test gripping force;

[0021] Several test clamping position points and test clamping forces are sorted and combined to obtain clamping test parameters.

[0022] Preferably, the robot arm is controlled to clamp the object to be clamped according to several test clamping position points and test clamping force in the clamping test parameters, and the robot arm is controlled to lift the object to the evaluation height Hp and pause, and at the same time, the target monitoring height Hj corresponding to the object clamped by the robot arm is obtained, and the formula Calculate and obtain the gripping test value JC corresponding to the object gripped by the robotic arm; where Hb is the height of the object gripped by the robotic arm;

[0023] Perform data analysis on the clamping test values ​​to determine the clamping test state corresponding to the special clamping scheme;

[0024] If the clamping test value is 1, a clamping test status valid label is generated and the clamping test valid status is prompted.

[0025] Preferably, if the clamping test value is less than 1, a clamping test state invalid label is generated and the clamping test invalid state is prompted, and at the same time, the special clamping scheme is dynamically corrected according to the clamping test state invalid label;

[0026] By formula Calculate and obtain the gripping test error value CW corresponding to the object gripped by the robot arm; where α is the gripping test error standard value;

[0027] Data analysis is performed on the clamping test error values ​​to determine the clamping test error type corresponding to the special clamping scheme.

[0028] Preferably, if the clamping test error value is less than 1, the special clamping scheme is associated with the clamping test slight error type;

[0029] If the clamping test error value is greater than or equal to 1, the special clamping scheme is associated with the clamping test severe error type;

[0030] The clamping test slight error type or the clamping test severe error type constitutes the clamping test error processing data;

[0031] According to the clamping test slight error type or the clamping test severe error type in the clamping test error processing data, the corresponding first clamping test correction scheme or the second clamping test correction scheme is implemented respectively.

[0032] Preferably, when implementing the first clamping test correction scheme or the second clamping test correction scheme, the corresponding clamping correction difference is obtained according to the clamping test mild error type or the clamping test severe error type in the clamping test error processing data, and the test clamping force and the clamping correction difference are summed to obtain the clamping correction implementation value.

[0033] Preferably, the clamping correction implementation value obtained by processing is matched with a number of test clamping position points to control the robot arm to perform secondary clamping on the object to be clamped, and data analysis is performed on the clamping test value obtained by processing after the secondary clamping;

[0034] If the result of the analysis is that the clamping test is in a valid state, the subsequent clamping test correction is stopped.

[0035] Preferably, if the result of the analysis is that the clamping test is in an invalid state, the above-mentioned clamping test correction scheme is repeated to continue the subsequent clamping test correction until the result of the analysis is a clamping test state valid label, and at the same time, the clamping test parameters corresponding to the clamping test state valid label and the to-be-clamped parameters corresponding to the to-be-clamped object are synchronously updated and stored in the clamping database and the clamping knowledge graph.

[0036] Compared with the existing solutions, the present invention achieves the following beneficial effects:

[0037] The present invention obtains clamping test parameters corresponding to the object to be clamped by performing multi-dimensional data processing and analysis on the clamping parameters obtained for the object to be clamped, and can provide reliable clamping position data support and clamping force data support for the implementation of subsequent clamping tests on the object to be clamped, thereby improving the autonomous analysis effect of the clamping test data of the robot arm clamping unfamiliar objects.

[0038] The present invention synchronously updates and stores the parameters to be clamped corresponding to the clamping test requirements in the clamping database and the clamping knowledge graph, thereby realizing the storage and utilization of the clamping test data when the robot arm clamps unfamiliar objects qualifiedly, thereby improving the autonomous analysis and management effect of the robot arm clamping test data.

[0039] The present invention obtains the clamping test error value by calculating the various clamping test data that do not meet the clamping test requirements, and performs data analysis on the clamping test error value to determine the clamping test error type corresponding to the special clamping scheme, thereby providing reliable implementation data support for the dynamic correction of the subsequent clamping test of the special clamping scheme.

[0040] The present invention dynamically corrects the clamping test of the special clamping scheme according to the invalid state of the clamping test obtained through analysis, until the clamping test state corresponding to the corrected special clamping scheme is the valid state of the clamping test, and the clamping test parameters corresponding to the clamping test requirements that finally meet the requirements and the to-be-clamped parameters corresponding to the object to be clamped are synchronously updated and stored in the clamping database and the clamping knowledge graph, thereby realizing adaptive dynamic adjustment and correction of the clamping test of the robot arm clamping unfamiliar objects, improving the dynamic supervision and correction effect of the robot arm motion control for clamping unfamiliar objects, and the autonomous dynamic supplementation and improvement effect of the clamping parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The present invention will be further described below in conjunction with the accompanying drawings.

[0042] Figure 1 This is a flowchart of the robot arm motion control method based on the Internet of Things and knowledge graph of the present invention.

[0043] Figure 2 It is a flowchart of data processing and analysis of clamping parameters in the present invention.

[0044] Figure 3 It is a flowchart of data analysis of clamping test values ​​in the present invention. DETAILED DESCRIPTION

[0045] 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.

[0046] like Figure 1 As shown, the present invention is a robot arm motion control method based on the Internet of Things and knowledge graph, comprising:

[0047] Based on the Internet of Things technology, the model code corresponding to the object to be clamped is obtained, and the model code is processed and analyzed to dynamically implement conventional clamping solutions or special clamping solutions for the clamped objects; including:

[0048] The model code is traversed and matched with the clamping database. If there is a sample model code identical to the model code in the clamping database, the sample clamping parameters associated with the same sample model code are obtained to implement a conventional clamping solution for the clamped object.

[0049] It should be noted that IoT technology can specifically be radio frequency technology, such as RFID (radio frequency identification), which is a contactless automatic identification technology that can identify specific targets and read and write related data through radio signals;

[0050] Model coding can be used to digitally represent all historically clamped items based on existing item coding rules. Model coding is used to analyze and determine whether the item to be clamped has been clamped before, so that a targeted clamping solution can be implemented.

[0051] In addition, the clamping database pre-stores a number of sample clamping objects and corresponding associated sample model codes, and the number of sample clamping objects is determined based on all clamping data corresponding to the objects successfully clamped by the robot arm in the past;

[0052] If the sample model code identical to the model code does not exist in the clamping database, a special clamping solution is implemented for the clamped object;

[0053] In an embodiment of the present invention, if the object has been clamped before, a conventional clamping scheme can be implemented using the same clamping parameters in the history; if the object has not been clamped before, a special clamping scheme can be implemented using all the clamping parameters in the history, thereby realizing autonomous clamping testing and training for unfamiliar clamped objects and improving the autonomous recognition and classification effect of the robot arm motion clamping control.

[0054] When implementing a special clamping scheme, obtain the clamping parameters corresponding to the object to be clamped and perform data processing and analysis to obtain the clamping test parameters corresponding to the object to be clamped; including:

[0055] Obtaining a stereoscopic image corresponding to the object to be clamped, and performing image processing and data analysis on the stereoscopic image to obtain the corresponding shape of the object;

[0056] Among them, performing image processing and data analysis on the stereoscopic image to obtain the corresponding object shape is an existing conventional image processing and recognition technology means, and the specific implementation steps are not repeated here;

[0057] And, obtaining the weight of the object to be clamped, and weighing and counting the object to be clamped by a weight sensor;

[0058] The shapes and weights of the objects to be clamped are sorted and combined to obtain the parameters to be clamped;

[0059] It should be noted that by obtaining the shape and weight of the object to be clamped, reliable multi-dimensional data support can be provided for the subsequent matching analysis of the clamping position and clamping force of the object to be clamped.

[0060] like Figure 2 As shown, when the data processing and analysis of the clamping parameters are performed, the shape of the object in the clamping parameters is traversed and matched with the standard object shapes associated with all the object shape attributes in the clamping knowledge graph;

[0061] If there is a standard object shape that is the same as the object shape, then several clamping position points associated with the standard object shape are marked as test clamping position points;

[0062] If there is no standard object shape that is the same as the object shape, all of the preset clamping position points are marked as test clamping position points;

[0063] Among them, the pre-stored clamping position points can be determined according to the total number of clamping times corresponding to all the clamping position points in history, for example, the midpoints of the left and right sides of the object are both test clamping position points;

[0064] And, the weight of the object in the to-be-clamped parameter is traversed and matched with the weights of all the objects in the clamping knowledge graph, and all the object clamping forces corresponding to the same object weight obtained by matching are sorted and combined to obtain a matching object clamping force processing sequence;

[0065] The gripping knowledge graph is obtained by processing all gripping data corresponding to the objects that the robot has successfully gripped in the past, and contains object weight data and object gripping force data corresponding to different gripped objects.

[0066] Get the minimum value element in the matching item gripping force processing sequence and mark it as the test gripping force;

[0067] Arrange and combine a number of test clamping position points and test clamping forces to obtain clamping test parameters;

[0068] In the embodiment of the present invention, by performing multi-dimensional data processing and analysis on the clamping parameters obtained for the object to be clamped, the clamping test parameters corresponding to the object to be clamped are obtained, which can provide reliable clamping position data support and clamping force data support for the implementation of subsequent clamping tests of the object to be clamped, thereby improving the autonomous analysis effect of the clamping test data of the robot arm clamping unfamiliar objects.

[0069] Using the clamping test parameters to perform a clamping test on the object to be clamped, and performing data analysis on the test data to determine the clamping test state corresponding to the special clamping scheme, and according to the clamping test valid state obtained by the analysis, the clamping test parameters and the clamping parameters corresponding to the object to be clamped are synchronously updated and stored in the clamping database and the clamping knowledge graph; including:

[0070] According to several test clamping position points and test clamping force in the clamping test parameters, the robot arm is controlled to clamp the object to be clamped, and the robot arm is controlled to lift the clamped object to the evaluation height Hp and pause. The evaluation height can be determined according to the median of all lifting heights corresponding to different objects clamped by the robot arm, and the target monitoring height Hj corresponding to the object clamped by the robot arm is obtained at the same time. The target monitoring height is specifically the vertical distance between the midpoint of the upper edge line of the front of the object clamped by the robot arm and the reference plane; the reference plane is the plane where the object to be clamped is placed when it is stationary, and is measured by the formula Calculate and obtain the gripping test value JC corresponding to the object gripped by the robot arm; where Hb is the height of the object gripped by the robot arm, and the units corresponding to the object's height, the evaluation height, and the target monitoring height are all the same, specifically centimeters;

[0071] In the embodiment of the present invention, the evaluation height is used to calculate various monitoring data after the robot arm grips and lifts the object, so as to digitally represent the gripping test state corresponding to the implemented special gripping scheme;

[0072] like Figure 3 As shown, the clamping test value is analyzed to determine the clamping test state corresponding to the special clamping scheme;

[0073] If the clamping test value is 1, a clamping test status valid label is generated and the clamping test valid status is prompted, and the clamping test parameters and the clamping parameters corresponding to the object to be clamped are synchronously updated and stored in the clamping database and the clamping knowledge graph;

[0074] It can be understood that the effective state of the gripping test indicates that the corresponding gripping test state when the robot arm grips the object meets the gripping test requirements, and no subsequent gripping test correction is required;

[0075] In the embodiment of the present invention, by synchronously updating and storing the parameters to be clamped corresponding to the clamping test requirements in the clamping database and the clamping knowledge graph, the storage and utilization of the clamping test data when the robot arm clamps unfamiliar objects qualifiedly is achieved, thereby improving the autonomous analysis and management effect of the robot arm clamping test data.

[0076] According to the obtained clamping test invalid state, the clamping test of the special clamping scheme is dynamically corrected until the clamping test state corresponding to the corrected special clamping scheme is the clamping test valid state, and the clamping test parameters corresponding to the clamping test requirements that finally meet the clamping test requirements and the clamping parameters corresponding to the object to be clamped are synchronously updated and stored in the clamping database and the clamping knowledge graph; including:

[0077] If the clamping test value is less than 1, a clamping test status invalid label is generated and the clamping test invalid status is prompted. At the same time, the special clamping scheme is dynamically corrected according to the clamping test status invalid label;

[0078] By formula Calculate and obtain the gripping test error value CW corresponding to the object gripped by the robot arm; where α is the gripping test error standard value, which can be determined based on the design requirement data of the object gripped by the robot arm;

[0079] In the embodiment of the present invention, the clamping test error value is used to calculate various clamping test data that do not meet the clamping test requirements, so as to digitally represent the clamping test error type corresponding to the special clamping scheme;

[0080] Perform data analysis on the clamping test error values ​​to determine the clamping test error type corresponding to the special clamping scheme;

[0081] If the clamping test error value is less than 1, the special clamping scheme is associated with the clamping test slight error type;

[0082] If the clamping test error value is greater than or equal to 1, the special clamping scheme is associated with the clamping test severe error type;

[0083] It can be understood that the slight error type of the clamping test indicates that the test error of the clamping of the robot arm is relatively light, and a clamping correction difference with a smaller value can be selected to perform the clamping test correction; the severe error type of the clamping test indicates that the test error of the clamping of the robot arm is relatively heavy, and a clamping correction difference with a larger value can be selected to perform the clamping test correction;

[0084] The clamping test slight error type or the clamping test severe error type constitutes the clamping test error processing data;

[0085] In an embodiment of the present invention, the clamping test error value is obtained by calculating the various clamping test data that do not meet the clamping test requirements, and the clamping test error value is analyzed to determine the clamping test error type corresponding to the special clamping scheme. This can provide reliable implementation data support for the dynamic correction of the subsequent clamping test of the special clamping scheme.

[0086] Implementing the corresponding first clamping test correction scheme or second clamping test correction scheme respectively according to the clamping test slight error type or the clamping test severe error type in the clamping test error processing data;

[0087] When implementing the first clamping test correction scheme or the second clamping test correction scheme, the corresponding clamping correction difference is obtained according to the clamping test slight error type or the clamping test severe error type in the clamping test error processing data, and the test clamping force and the clamping correction difference are summed to obtain the clamping correction implementation value;

[0088] The step of obtaining the corresponding clamping correction difference value for the clamping test slight error type or the clamping test severe error type includes:

[0089] Sequentially calculate and obtain adjacent differences between adjacent elements in the matching object clamping force processing sequence, and sort and combine all the adjacent differences obtained by calculation to obtain a first difference processing sequence;

[0090] Obtaining the median of all elements in the first difference processing sequence, and marking the median as the first clamping correction difference;

[0091] and obtaining the element median, element minimum, and element maximum corresponding to all elements in the matching object clamping force processing sequence;

[0092] Calculate the first difference between the median value of the element and the minimum value of the element, and calculate the second difference between the maximum value of the element and the median value of the element;

[0093] All the first differences and second differences are calculated and sorted and combined to obtain a second difference processing sequence;

[0094] Calculating an average of the first difference and the second difference in the second difference processing sequence and marking it as a second clamping correction difference;

[0095] Calculating and analyzing a correction difference between a first clamping correction difference and a second clamping correction difference;

[0096] If the correction difference is less than 0, the first clamping correction difference is set to the clamping correction difference corresponding to the slight error type of the clamping test, and the second clamping correction difference is set to the clamping correction difference corresponding to the severe error type of the clamping test;

[0097] If the correction difference is greater than 0, the first clamping correction difference is set to the clamping correction difference corresponding to the severe error type of the clamping test, and the second clamping correction difference is set to the clamping correction difference corresponding to the mild error type of the clamping test;

[0098] In an embodiment of the present invention, by performing multi-dimensional data processing and calculation classification on the matching object clamping force processing sequence obtained by preliminary processing, a first clamping correction difference and a second clamping correction difference calculated from different aspects are obtained, and the first clamping correction difference and the second clamping correction difference are calculated and analyzed to determine the clamping test slight error type or the clamping test severe error type, thereby improving the reliability and adaptability of the dynamic correction of the clamping test for special clamping schemes.

[0099] The obtained clamping correction implementation value is matched with a number of test clamping position points to control the robot arm to perform secondary clamping on the object to be clamped, and data analysis is performed on the clamping test value obtained after the secondary clamping;

[0100] If the result of the analysis is that the clamping test is in a valid state, the subsequent clamping test correction is stopped;

[0101] If the result of the analysis is that the clamping test is in an invalid state, the above-mentioned clamping test correction scheme is repeated to continue the subsequent clamping test correction until the result of the analysis is a clamping test state valid label. At the same time, the clamping test parameters corresponding to the clamping test state valid label and the clamping parameters corresponding to the object to be clamped are synchronously updated and stored in the clamping database and the clamping knowledge graph.

[0102] In an embodiment of the present invention, the clamping test of the special clamping scheme is dynamically corrected according to the invalid state of the clamping test obtained through analysis, until the clamping test state corresponding to the corrected special clamping scheme is the valid state of the clamping test, and the clamping test parameters corresponding to the clamping test requirements that finally meet the requirements and the to-be-clamped parameters corresponding to the object to be clamped are synchronously updated and stored in the clamping database and the clamping knowledge graph, thereby realizing adaptive dynamic adjustment and correction of the clamping test of the robot arm clamping unfamiliar objects, improving the dynamic supervision and correction effect of the clamping of unfamiliar objects by the robot arm motion control, and the autonomous dynamic supplementation and improvement effect of the clamping parameters.

[0103] In addition, the formulas involved in the above are all dimensionless and numerical calculations. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and simulating it with simulation software.

[0104] In the several embodiments provided by the present invention, it should be understood that the disclosed method can be implemented in other ways. For example, the above-described embodiments of the invention are only illustrative, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

[0105] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0106] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0107] It is obvious to a person skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the essential characteristics of the present invention.

[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A robotic arm motion control method based on the Internet of Things and knowledge graph, characterized in that: include: Based on the Internet of Things technology, the model code corresponding to the object to be clamped is obtained, and the model code is processed and analyzed to dynamically implement a conventional clamping solution or a special clamping solution for the clamped object; When implementing a special clamping scheme, the clamping parameters corresponding to the object to be clamped are obtained and data processing and analysis are performed to obtain the clamping test parameters corresponding to the object to be clamped; Among them, a stereoscopic image corresponding to the object to be clamped is obtained, and image processing and data analysis are performed on the stereoscopic image to obtain the corresponding shape of the object; And, obtaining the weight of the object corresponding to the object to be clamped; The shapes and weights of the objects to be clamped are sorted and combined to obtain the parameters to be clamped; When performing data processing and analysis on the clamping parameters, the object shapes in the clamping parameters are traversed and matched with the standard object shapes associated with all the object shape attributes in the clamping knowledge graph; If there is a standard object shape that is the same as the object shape, then several clamping position points associated with the standard object shape are marked as test clamping position points; If there is no standard object shape that is the same as the object shape, all of the preset clamping position points are marked as test clamping position points; And, the weight of the object in the to-be-clamped parameter is traversed and matched with the weights of all the objects in the clamping knowledge graph, and all the object clamping forces corresponding to the same object weight obtained by matching are sorted and combined to obtain a matching object clamping force processing sequence; Get the minimum value element in the matching item gripping force processing sequence and mark it as the test gripping force; Arrange and combine a number of test clamping position points and test clamping forces to obtain clamping test parameters; Using the clamping test parameters, a clamping test is performed on the object to be clamped, and the test data is analyzed to determine the clamping test state corresponding to the special clamping scheme. According to the clamping test valid state obtained by the analysis, the clamping test parameters and the clamping parameters corresponding to the object to be clamped are synchronously updated and stored in the clamping database and the clamping knowledge graph; The clamping test of the special clamping scheme is dynamically corrected according to the invalid clamping test state obtained through analysis, until the clamping test state corresponding to the corrected special clamping scheme is the valid clamping test state, and the clamping test parameters corresponding to the clamping test requirements that finally meet the requirements and the clamping parameters corresponding to the object to be clamped are synchronously updated and stored in the clamping database and the clamping knowledge graph.

2. According to claim 1, the method for controlling the motion of a robotic arm based on the Internet of Things and knowledge graph is characterized in that: The model code is traversed and matched with the clamping database. If there is a sample model code identical to the model code in the clamping database, the sample clamping parameters associated with the same sample model code are obtained to implement a conventional clamping solution for the clamped object. If the sample model code identical to the model code does not exist in the clamping database, a special clamping solution is implemented for the object to be clamped.

3. According to claim 1, the method for controlling the motion of a robotic arm based on the Internet of Things and knowledge graph is characterized in that: According to the test clamping position points and test clamping force in the clamping test parameters, the robot arm is controlled to clamp the object to be clamped, and the robot arm is controlled to lift the clamped object to the evaluation height Hp and pause, and the target monitoring height Hj corresponding to the object clamped by the robot arm is obtained, and the formula is used Calculate and obtain the gripping test value JC corresponding to the object gripped by the robotic arm; where Hb is the height of the object gripped by the robotic arm; Perform data analysis on the clamping test values ​​to determine the clamping test state corresponding to the special clamping scheme; If the clamping test value is 1, a clamping test status valid label is generated and the clamping test valid status is prompted.

4. The method for controlling the motion of a robotic arm based on the Internet of Things and knowledge graph according to claim 3 is characterized in that: If the clamping test value is less than 1, a clamping test status invalid label is generated and the clamping test invalid status is prompted. At the same time, the special clamping scheme is dynamically corrected according to the clamping test status invalid label; By formula Calculate and obtain the gripping test error value CW corresponding to the object gripped by the robot arm; where α is the gripping test error standard value; Data analysis is performed on the clamping test error values ​​to determine the clamping test error type corresponding to the special clamping scheme.

5. The method for controlling the motion of a robotic arm based on the Internet of Things and knowledge graph according to claim 4 is characterized in that: If the clamping test error value is less than 1, the special clamping scheme is associated with the clamping test slight error type; If the clamping test error value is greater than or equal to 1, the special clamping scheme is associated with the clamping test severe error type; The clamping test slight error type or the clamping test severe error type constitutes the clamping test error processing data; According to the clamping test slight error type or the clamping test severe error type in the clamping test error processing data, the corresponding first clamping test correction scheme or the second clamping test correction scheme is implemented respectively.

6. The method for controlling the motion of a robotic arm based on the Internet of Things and knowledge graph according to claim 5 is characterized in that: When implementing the first clamping test correction plan or the second clamping test correction plan, the corresponding clamping correction difference is obtained according to the clamping test mild error type or the clamping test severe error type in the clamping test error processing data, and the test clamping force and the clamping correction difference are summed to obtain the clamping correction implementation value.

7. The method for controlling the motion of a robotic arm based on the Internet of Things and knowledge graph according to claim 6 is characterized in that: The obtained clamping correction implementation value is matched with a number of test clamping position points to control the robot arm to perform secondary clamping on the object to be clamped, and data analysis is performed on the clamping test value obtained after the secondary clamping; If the result of the analysis is that the clamping test is in a valid state, the subsequent clamping test correction is stopped.

8. The method for controlling the motion of a robotic arm based on the Internet of Things and knowledge graph according to claim 7 is characterized in that: If the result of the analysis is that the clamping test is in an invalid state, the above-mentioned clamping test correction scheme is repeated to continue the subsequent clamping test correction until the result of the analysis is a clamping test state valid label. At the same time, the clamping test parameters corresponding to the clamping test state valid label and the clamping parameters corresponding to the object to be clamped are synchronously updated and stored in the clamping database and the clamping knowledge graph.

Images