Quality detection method, system, device and storage medium for objects grasped by a robotic arm

Abstract

The present invention relates to the field of robotic arm control technology, and more specifically, to a quality detection method, system, device and storage medium for robotic arm grasping objects. The scheme includes obtaining the degree of deformation through camera acquisition; judging the degree of deformation recovery according to the degree of deformation; presetting groups of deformation degrees, and performing robotic arm grasping and recovery control on each deformation degree group one by one; extracting the relative displacement of the grasped object during the grasping process according to the deformation degree groups; judging whether to start the gripping process according to the relative displacement of the grasped object; after starting the gripping process, judging the appropriate force as the final gripping force, and lifting the grasped object. The scheme quantifies the degree of deformation through a camera, and then forms an online analysis of the optimal gripping force through a rapid gripping force test.

Description

Technical Field

[0001] The present invention relates to the field of robotic arm control technology, and more specifically, to a quality detection method, system, device and storage medium for objects grasped by a robotic arm. Background Art

[0002] Robotics integrates the research results of multiple disciplines such as computers, cybernetics, mechanisms, information and sensor technology, artificial intelligence, and bionics. It is a high-tech field with active research and wide application in contemporary times. Robot design needs to be guided by market demand and meet the needs of different application environments through innovation. When adapting to environmental needs, it is often necessary to design common control methods for various environments.

[0003] Prior to the present invention, the gripping force of the existing robotic arms was fixed. When the force was too great, it could cause damage to the equipment, and when the force was too small, it could cause the object to slip and damage the grasped object. Summary of the invention

[0004] In view of the above problems, the present invention proposes a quality detection method, system, equipment and storage medium for a robotic arm to grasp objects, quantify the degree of deformation through a camera, and then form an online analysis of the optimal grasping force through a rapid gripping force test.

[0005] According to a first aspect of an embodiment of the present invention, a method for detecting the quality of an object grasped by a robotic arm is provided.

[0006] In one or more embodiments, preferably, the quality detection method of the object grasped by the robotic arm includes:

[0007] Obtain the degree of deformation through camera acquisition;

[0008] Determine the degree of deformation recovery according to the degree of deformation;

[0009] Pre-set groups of deformation degrees, and perform robotic arm grasping and recovery control on each deformation degree group one by one;

[0010] extracting the relative displacement of the grasped object during the grasping process according to the deformation degree group;

[0011] Determining whether to start a gripping process according to the relative displacement of the grasped object;

[0012] After the gripping process is started, the appropriate force is determined as the final gripping force, and the grasped object is lifted.

[0013] In one or more embodiments, preferably, obtaining the deformation degree through camera acquisition specifically includes:

[0014] The contact surface between the grasped object and the robotic arm is photographed through cameras at multiple angles;

[0015] The initial position of the contact surface and the deformation depth at each time after the robot grasps are determined, and the deformation depth in millimeters is used as the deformation degree.

[0016] In one or more embodiments, preferably, judging the degree of deformation recovery according to the degree of deformation specifically includes:

[0017] When the time after the robot arm leaves the grasped object satisfies the first calculation formula, the current time is recorded as the recovery state;

[0018] extracting the deformation degree corresponding to the recovery state as the deformation recovery degree;

[0019] The first calculation formula is:

[0020] T>5s

[0021] Where T is the time after the robot arm leaves the grasped object, in seconds, and s is the time unit in seconds.

[0022] In one or more embodiments, preferably, the pre-setting of the deformation degree groups and performing the robot arm grasping and recovery control on each deformation degree group one by one specifically include:

[0023] Presetting deformation degree groups, the deformation degree groups are stored according to a preset group order, wherein the group order includes a first, a second, ..., an Nth group;

[0024] Setting the deformation degrees corresponding to the first, second, ..., Nth groups to 1 mm, 2 mm, ..., N mm, wherein the deformation degrees are the deformation depths captured by the camera;

[0025] The robot arm grasps and recovers the objects one by one in the preset group order.

[0026] In one or more embodiments, preferably, extracting the relative displacement of the grasped object during the grasping process according to the deformation degree group specifically includes:

[0027] After each time the robot arm grasps the current grasped object, the robot arm lifts the grasped object upward according to the deformation degree group;

[0028] The second calculation formula is used to calculate the relative displacement between the grasped object and the robotic arm at the current moment;

[0029] The second calculation formula is:

[0030] Y=|X1-X0|

[0031] Among them, Y is the relative displacement between the grasped object and the robotic arm, X1 is the distance between the grasped object and the robotic arm at the current moment, and X0 is the distance between the grasped object and the robotic arm before lifting the grasped object.

[0032] In one or more embodiments, preferably, judging whether to start the gripping process according to the relative displacement of the grasped object specifically includes:

[0033] lifting the grasped objects one by one according to the order of the deformation degree groups, and judging whether the relative displacement of the grasped objects satisfies a third calculation formula;

[0034] If the third calculation formula is not satisfied, it is considered that the grip is not tight, and the gripping and lifting control is continued according to the group order of the deformation degree groups;

[0035] If the third calculation formula is satisfied, it is considered that the grip is tight, and the gripping process is started;

[0036] The third calculation formula is:

[0037] Y<5mm

[0038] Here, mm is the distance unit in millimeters.

[0039] In one or more embodiments, preferably, after starting the gripping process, determining the appropriate force as the final gripping force and lifting the grasped object specifically includes:

[0040] After starting the gripping process, the force margin is calculated using the fourth calculation formula;

[0041] Use the fifth calculation formula to calculate the current force on the robotic arm;

[0042] When the robotic arm holds the grasped object tightly until the force reaches the current robotic arm force, determine whether the current deformation recovery degree and the deformation recovery degree in the previous grasping process satisfy the sixth calculation formula; if not, continue to use the fifth calculation formula to update the current robotic arm force until the current deformation recovery degree and the deformation recovery degree in the previous grasping process satisfy the sixth calculation formula;

[0043] When the current deformation recovery degree and the deformation recovery degree in the previous grasping process satisfy the sixth calculation formula, the force of the robot arm at the current moment is used as the final gripping force, and the grasped object is lifted with the final gripping force;

[0044] The fourth calculation formula is:

[0045] LY=0.1×(LL1-LL0)

[0046] Among them, LY is the force margin, LL1 is the force on the robot arm during the gripping process, and LL0 is the force on the robot arm corresponding to the last lifting process in the gripping process;

[0047] The fifth calculation formula is:

[0048] Sa=LY+S l

[0049] Among them, Sa is the current force on the robot arm, and S l is the force on the robot arm during the last lifting process;

[0050] The sixth calculation formula is:

[0051] L0÷L1>0.95

[0052] Among them, L1 is the degree of deformation recovery in the previous grasping process, and L0 is the current degree of deformation recovery.

[0053] According to a second aspect of an embodiment of the present invention, a quality detection system for objects grasped by a robotic arm is provided.

[0054] In one or more embodiments, preferably, the quality detection system of the object grasped by the robotic arm includes:

[0055] A deformation degree monitoring module is used to obtain the deformation degree through camera acquisition;

[0056] A deformation recovery module is used to determine the degree of deformation recovery according to the degree of deformation;

[0057] The deformation lifting module is used to pre-set the deformation degree groups and perform the robot arm grasping and recovery control for each deformation degree group one by one;

[0058] A relative displacement judgment module, used to extract the relative displacement of the grasped object during the grasping process according to the deformation degree group;

[0059] A gripping judgment module, used to judge whether to start a gripping process according to the relative displacement of the grasped object;

[0060] The analysis module can be restored to determine the appropriate force as the final gripping force and lift the grasped object after the gripping process is started.

[0061] According to a third aspect of an embodiment of the present invention, there is provided a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method as described in any one of the first aspect of the embodiment of the present invention is implemented.

[0062] According to a fourth aspect of an embodiment of the present invention, there is provided an electronic device, comprising a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement any one of the methods described in the first aspect of the embodiment of the present invention.

[0063] The technical solution provided by the embodiments of the present invention may have the following beneficial effects:

[0064] In the solution of the present invention, stable and rapid force analysis and identification are achieved through rapid analysis of deformation degree.

[0065] In the scheme of the present invention, the optimal gripping force is selected according to the movement of the grasped object during the movement process and the recovery of the deformation after grasping to ensure the quality and safety of the grasping process of the robot arm without damaging the grasped object.

[0066] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0067] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0069] Figure 1 It is a flow chart of a method for detecting the quality of objects grasped by a robotic arm according to an embodiment of the present invention.

[0070] Figure 2 It is a flow chart of obtaining the degree of deformation through camera acquisition in a quality detection method for a robot arm grasping an object according to an embodiment of the present invention.

[0071] Figure 3 It is a flow chart of judging the degree of deformation recovery according to the degree of deformation in a quality detection method for grasping an object by a robot arm according to an embodiment of the present invention.

[0072] Figure 4 It is a flow chart of presetting groups of deformation degrees in a quality detection method for grasping objects by a robot arm according to an embodiment of the present invention, and performing grasping and recovery control of the robot arm one by one for each deformation degree group.

[0073] Figure 5 It is a flow chart of extracting the relative displacement of the grasped object during the grasping process according to the deformation degree group in a quality detection method of a robot arm grasping an object according to an embodiment of the present invention.

[0074] Figure 6 It is a flowchart of determining whether to start the gripping process according to the relative displacement of the grasped object in a quality detection method of a robot arm grasping an object according to an embodiment of the present invention.

[0075] Figure 7 It is a flow chart of a quality detection method for grasping an object by a robot arm according to an embodiment of the present invention, which determines the appropriate force as the final grasping force after starting the grasping process, and lifts the grasped object.

[0076] Figure 8 It is a structural diagram of a quality detection system for a robot arm grasping an object according to an embodiment of the present invention.

[0077] Fig. 9 It is a structural diagram of an electronic device in one embodiment of the present invention. DETAILED DESCRIPTION

[0078] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0079] 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0080] Robotics integrates the research results of multiple disciplines such as computers, cybernetics, mechanisms, information and sensor technology, artificial intelligence, and bionics. It is a high-tech field with active research and wide application in contemporary times. Robot design needs to be guided by market demand and meet the needs of different application environments through innovation. When adapting to environmental needs, it is often necessary to design common control methods for various environments.

[0081] Prior to the present invention, the gripping force of the existing robotic arms was fixed. When the force was too great, it could cause damage to the equipment, and when the force was too small, it could cause the object to slip and damage the grasped object.

[0082] In an embodiment of the present invention, a method, system, device and storage medium for quality detection of objects grasped by a robotic arm are provided. The solution quantifies the degree of deformation through a camera, and then forms an online analysis of the optimal grasping force through a rapid gripping force test.

[0083] According to a first aspect of an embodiment of the present invention, a method for detecting the quality of an object grasped by a robotic arm is provided.

[0084] Figure 1 It is a flow chart of a method for detecting the quality of objects grasped by a robotic arm according to an embodiment of the present invention.

[0085] In one or more embodiments, preferably, the quality detection method of the object grasped by the robotic arm includes:

[0086] S101, obtaining a deformation degree through camera acquisition;

[0087] S102, judging the degree of deformation recovery according to the degree of deformation;

[0088] S103, presetting groups of deformation degrees, and performing robotic arm grasping and recovery control on each group of deformation degrees one by one;

[0089] S104, extracting the relative displacement of the grasped object during the grasping process according to the deformation degree group;

[0090] S105, judging whether to start the gripping process according to the relative displacement of the grasped object;

[0091] S106: After starting the gripping process, determine the appropriate force as the final gripping force, and lift the grasped object.

[0092] In the embodiment of the present invention, by quantifying the deformation and conducting a specific analysis through the maximum deformation degree of the appearance, it is generally believed that the robotic arm is rigid and does not undergo any deformation. Finally, through a rapid gripping force test, an online analysis of the optimal grasping force is formed. It should be noted that the time for multiple grasping is relatively short, generally completed within 0.5 seconds. The core of the final confirmation of the gripping force is to quickly give a reasonable gripping force.

[0093] Figure 2 It is a flow chart of obtaining the degree of deformation through camera acquisition in a quality detection method for a robot arm grasping an object according to an embodiment of the present invention.

[0094] like Figure 2 As shown, in one or more embodiments, preferably, the deformation degree is obtained by collecting data through a camera, specifically including:

[0095] S201, photographing the contact surface between the grasped object and the robotic arm through cameras at multiple angles;

[0096] S202, determining the initial position of the contact surface and the deformation depth at each time after the robot arm grasps, and taking the deformation depth in millimeters as the deformation degree.

[0097] In an embodiment of the present invention, in order to realize the shooting of the contact surface between the grasped object and the robotic arm through cameras at multiple angles, and to determine the initial position of the contact surface and the deformation depth at each time after the robotic arm grasps, the deformation depth is taken in millimeters as the degree of deformation, and the following steps are followed: 1. System setting and calibration. Install the camera: Install multiple high-resolution cameras around the robotic arm to ensure that they can cover all necessary viewing angles of the contact surface between the grasped object and the robotic arm. Camera synchronization: Use hardware triggers or software synchronization mechanisms to ensure that all cameras can capture images at the same time. System calibration: Perform geometric calibration on each camera, including internal parameters (focal length, principal point, distortion coefficient, etc.) and external parameters (position and posture relative to the robotic arm). 2. Data acquisition. Continuous shooting: During the operation of the robotic arm, continuously capture images of the contact surface between the grasped object and the robotic arm. Timestamp: Add a timestamp to each frame of the image so that the image can be matched with a specific time point in subsequent analysis. 3. Image processing and feature extraction. Edge detection: Use edge detection algorithms (such as Canny edge detection) to extract the edge of the contact surface between the grasped object and the robotic arm. Feature matching: If there are multiple cameras, it is necessary to match the feature points in different camera views for 3D reconstruction. 4. 3D reconstruction and deformation analysis. 3D reconstruction: Based on the 2D images from multiple perspectives, stereo vision technology is used to reconstruct the 3D shape of the contact surface. Deformation monitoring: Compare the 3D models before and after grasping to monitor the deformation of the contact surface. Depth calculation: Calculate the depth change of the deformation area, that is, the deformation depth. 5. Quantify the degree of deformation. Unit conversion: Convert the deformation depth from pixel units to actual length units (mm). Deformation degree assessment: Based on the deformation depth, assess the degree of deformation of the object during the grasping process. 6. Result output and visualization. Data recording: Record the degree of deformation at each time point for further analysis. Visualization: Display the change of deformation degree over time through charts or other visualization methods.

[0098] Figure 3 It is a flow chart of judging the degree of deformation recovery according to the degree of deformation in a quality detection method for grasping an object by a robot arm according to an embodiment of the present invention.

[0099] like Figure 3As shown, in one or more embodiments, preferably, judging the degree of deformation recovery according to the degree of deformation specifically includes:

[0100] S301, when the time after the robot arm leaves the grasped object satisfies the first calculation formula, record the current time as the recovery state;

[0101] S302, extracting the deformation degree corresponding to the recovery state as the deformation recovery degree;

[0102] The first calculation formula is:

[0103] T>5s

[0104] Where T is the time after the robot arm leaves the grasped object, in seconds, and s is the time unit in seconds.

[0105] In an embodiment of the present invention, in order to realize that when the time after the robot arm leaves the grasped object satisfies the first calculation formula, the current moment is recorded as the recovery state, and the deformation degree corresponding to the recovery state is extracted as the deformation recovery degree, the following steps can be followed: 1. Time monitoring. Timing start: Start timing at the moment the robot arm leaves the grasped object. Time variable: Set a time variable T to record the time elapsed after the robot arm leaves the grasped object. 2. Continuous monitoring and judgment, continuous data collection: During the operation of the robot arm, continue to collect camera images and calculate the deformation degree. Time judgment: Update the time variable T in real time, and judge whether the first calculation formula T>5s is satisfied. 3. Record the recovery state. Satisfaction condition: Once T>5s, immediately record the deformation degree at the current moment. Recovery state: Mark the moment as the recovery state, that is, the state where the object begins to return to its original state. 4. Extract the deformation recovery degree. Deformation degree extraction: Extract the deformation degree from the image corresponding to the recovery state. Unit conversion: If necessary, convert the deformation degree into millimeter units.

[0106] Figure 4 It is a flow chart of presetting groups of deformation degrees in a quality detection method for grasping objects by a robot arm according to an embodiment of the present invention, and performing grasping and recovery control of the robot arm one by one for each deformation degree group.

[0107] like Figure 4 As shown, in one or more embodiments, preferably, the pre-setting of the deformation degree groups, and performing the robot arm grasping and recovery control on each deformation degree group one by one, specifically includes:

[0108] S401, presetting deformation degree groups, wherein the deformation degree groups are stored according to a preset group order, wherein the group order includes a first, a second, ..., an Nth group;

[0109] S402, setting the deformation degrees corresponding to the first, second, ..., Nth groups to 1 mm, 2 mm, ..., N mm, wherein the deformation degrees are the deformation depths captured by a camera;

[0110] S403, performing robot arm grasping and recovery control one by one according to the preset group order.

[0111] In an embodiment of the present invention, the current deformation degree group can be obtained according to the deformation degree acquired by the camera, the deformation degree group is pre-set, and the process of performing the robot arm grasping and recovery control according to the preset group order can be performed by the following steps: Formulate deformation degree groups: You need to pre-define the deformation degree groups, such as the first group, the second group, and the Nth group. Each group corresponds to a specific deformation degree, such as 1mm, 2mm, and Nmm. These groups will be stored in a certain order so that they can be called in sequence in subsequent operations. Establish the correspondence between the deformation degree and the group: Establish a lookup table or database in the control system to associate each group with its corresponding deformation degree. In this way, when the robot arm performs a task, the deformation degree that should be reached can be determined according to the information in the lookup table. Set up the camera system: Make sure that your camera system can accurately measure the deformation depth and convert it into millimeter units. This may require calibration of the camera to ensure the accuracy of the measurement results. Programming to achieve group sequence control: Write a program in the control system of the robot arm so that it can perform grasping and recovery operations one by one according to the preset group order. The program should be able to automatically adjust the robot's movements according to the set groups to achieve the corresponding deformation degree. Implement grasping and recovery operations: In actual operation, the robot will grasp the objects in the preset group order and recover after reaching the preset deformation degree of each group. During the whole process, the control system needs to monitor the deformation degree in real time and adjust the robot's movements according to the feedback. Record and analyze data: After each grasping and recovery operation, record the actual deformation degree and recovery status. This data can be used for further analysis and optimization of the robot's control strategy. Adjustment and optimization: According to the results of the actual operation, adjust the deformation degree settings in the lookup table to optimize the performance and accuracy of the robot.

[0112] Figure 5 It is a flow chart of extracting the relative displacement of the grasped object during the grasping process according to the deformation degree group in a quality detection method of a robot arm grasping an object according to an embodiment of the present invention.

[0113] like Figure 5 As shown, in one or more embodiments, preferably, extracting the relative displacement of the grasped object during the grasping process according to the deformation degree group specifically includes:

[0114] S501, after each time the robot arm grasps the current grasped object according to the deformation degree group, lift it upwards, the lifting is mainly used to determine whether relative displacement occurs, the lifting height is generally 5 mm, and it is completed within 0.1 s;

[0115] S502, calculating the relative displacement between the grasped object and the robotic arm at the current moment using a second calculation formula;

[0116] The second calculation formula is:

[0117] Y=|X1-X0|

[0118] Among them, Y is the relative displacement between the grasped object and the robotic arm, X1 is the distance between the grasped object and the robotic arm at the current moment, and X0 is the distance between the grasped object and the robotic arm before lifting the grasped object.

[0119] In an embodiment of the present invention, in order to lift the grasped object upward each time the robotic arm grasps the current grasped object according to the deformation degree group, record the relative displacement between the grasped object and the robotic arm at the current moment, and judge whether relative displacement occurs and whether the position slips, the following steps can be followed: 1. Initial position recording. Before the robotic arm starts to grasp the object, the initial distance between the grasped object and the robotic arm is recorded. 2. Grab and lift. The robotic arm grasps the object according to the preset deformation degree group and lifts it upward to the preset position. 3. Current position recording. After lifting, the distance between the grasped object and the robotic arm at the current moment is recorded. 4. Calculate relative displacement. Calculate the relative displacement using the second calculation formula. 5. Judge the relative displacement. If Y>0, it means that relative displacement occurs. If Y=0, it means that there is no relative displacement. 6. Judge the slip. If the relative displacement exceeds the preset threshold, it can be judged that the object has slipped during the lifting process. If it does not exceed the threshold, it can be considered that the object has not slipped during the lifting process.

[0120] Figure 6 It is a flowchart of determining whether to start the gripping process according to the relative displacement of the grasped object in a quality detection method of a robot arm grasping an object according to an embodiment of the present invention.

[0121] like Figure 6 As shown, in one or more embodiments, preferably, judging whether to start the gripping process according to the relative displacement of the grasped object specifically includes:

[0122] S601, lifting the grasped objects one by one according to the order of the deformation degree groups, and determining whether the relative displacement of the grasped objects satisfies a third calculation formula;

[0123] S602: If the third calculation formula is not satisfied, it is considered that the grip is not tight, and the gripping and lifting control is continued according to the group order of the deformation degree groups;

[0124] S603: If the third calculation formula is satisfied, it is considered that the grip is tight, and the gripping process is started;

[0125] The third calculation formula is:

[0126] Y<5mm

[0127] Here, mm is the distance unit in millimeters.

[0128] In an embodiment of the present invention, in order to realize lifting after grasping one by one according to the group order of the deformation degree groups, and to determine whether the relative displacement of the grasped object satisfies the third calculation formula, the following steps can be followed: 1. Initialization. Set the group order: pre-set the group order of the deformation degree, such as the first group, the second group, and so on to the Nth group. Set the deformation degree: set the corresponding deformation degree for each group, such as 1mm, 2mm, and so on to Nmm. 2. Grasping and lifting control. Start grasping: According to the preset group order, the robot arm starts to grasp the grasped object. Lift the object: After grasping, the robot arm lifts it upward and controls it according to the preset deformation degree. 3. Record the relative displacement. Measure the initial distance: record the initial distance between the grasped object and the robot arm before grasping. Measure the current distance: record the current distance between the grasped object and the robot arm after lifting. Calculate the relative displacement: use the second calculation formula to calculate the relative displacement. 4. Determine the relative displacement. Apply the third calculation formula: determine whether the calculated relative displacement Y is less than 5mm. Unsatisfied conditions: If Y ≥ 5mm, it is considered not grasped, and it is necessary to continue to grasp and lift in the order of deformation degree groups. Satisfied conditions: If Y < 5mm, it is considered to be grasped, and the grasping process can be started. 5. Grasping process. Execute grasping: Start the grasping process of the robot arm to ensure that the grasped object is firmly grasped by the robot arm. Subsequent operations: Perform subsequent operations, such as moving the grasped object to a specified position.

[0129] Figure 7 It is a flow chart of a quality detection method for grasping an object by a robot arm according to an embodiment of the present invention, which determines the appropriate force as the final grasping force after starting the grasping process, and lifts the grasped object.

[0130] like Figure 7 As shown, in one or more embodiments, preferably, after starting the gripping process, determining the appropriate force as the final gripping force and lifting the grasped object specifically includes:

[0131] S701, after starting the gripping process, calculating the force margin using a fourth calculation formula;

[0132] S702, calculating the current force of the robotic arm using the fifth calculation formula;

[0133] S703, when the mechanical arm holds the grasped object tightly until the force reaches the current mechanical arm force, determine whether the current deformation recovery degree and the deformation recovery degree in the previous grasping process satisfy the sixth calculation formula; if not, continue to use the fifth calculation formula to update the current mechanical arm force until the current deformation recovery degree and the deformation recovery degree in the previous grasping process satisfy the sixth calculation formula;

[0134] S704: When the current deformation recovery degree and the deformation recovery degree in the last grasping process satisfy the sixth calculation formula, the force of the robot arm at the current moment is used as the final gripping force, and the grasped object is lifted with the final gripping force. After this lifting, it will not be put down again, and the lifting height and position are the actual position and area where the lifted object needs to be reached;

[0135] The fourth calculation formula is:

[0136] LY=0.1×(LL1-LL0)

[0137] Among them, LY is the force margin, LL1 is the force on the robot arm during the gripping process, and LL0 is the force on the robot arm corresponding to the last lifting process in the gripping process;

[0138] The fifth calculation formula is:

[0139] Sa=LY+S l

[0140] Among them, Sa is the current force on the robot arm, and S l is the force on the robot arm during the last lifting process;

[0141] The sixth calculation formula is:

[0142] L0÷L1>0.95

[0143] Among them, L1 is the degree of deformation recovery in the previous grasping process, and L0 is the current degree of deformation recovery. It should be noted that when the degree of deformation recovery L1 in the previous grasping process is less than a preset value, it is also considered to satisfy the sixth calculation formula. This is because L1. When L1 is less than a preset value, it is considered that no obvious deformation will occur.

[0144] After starting the gripping process, it is necessary to calculate the force margin, the current force on the robotic arm, and determine whether the degree of deformation recovery meets specific conditions according to the given formula. First, use the fourth calculation formula to calculate the force margin. Then use the fifth calculation formula to calculate the current force on the robotic arm. Then, the robotic arm grips the object until the force reaches the current force on the robotic arm, and then determine whether the current degree of deformation recovery and the degree of deformation recovery during the last gripping process meet the sixth calculation formula. If the above conditions are not met, continue to update the current force on the robotic arm until the degree of deformation recovery meets the sixth calculation formula. Once the current degree of deformation recovery and the degree of deformation recovery during the last gripping process meet the sixth calculation formula, the force on the robotic arm at the current moment is used as the final gripping force, and the object to be gripped is lifted with this force. According to the second aspect of an embodiment of the present invention, a quality detection system for gripping objects by a robotic arm is provided.

[0145] Figure 8 It is a structural diagram of a quality detection system for a robot arm grasping an object according to an embodiment of the present invention.

[0146] In one or more embodiments, preferably, the quality detection system of the object grasped by the robotic arm includes:

[0147] The deformation degree monitoring module 801 is used to obtain the deformation degree through camera acquisition;

[0148] A deformation recovery module 802 is used to determine the degree of deformation recovery according to the degree of deformation;

[0149] The deformation lifting module 803 is used to pre-set groups of deformation degrees and perform robot arm grasping and recovery control on each deformation degree group one by one;

[0150] A relative displacement judgment module 804 is used to extract the relative displacement of the grasped object during the grasping process according to the deformation degree group;

[0151] A gripping judgment module 805 is used to judge whether to start a gripping process according to the relative displacement of the grasped object;

[0152] The analysis module 806 can be restored to determine the appropriate force as the final gripping force and lift the grasped object after the gripping process is started.

[0153] In the embodiment of the present invention, a system suitable for different structures is realized through a series of modular designs. The system can achieve closed-loop, reliable and efficient execution through collection, analysis and control.

[0154] According to a third aspect of an embodiment of the present invention, there is provided a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method as described in any one of the first aspect of the embodiment of the present invention is implemented.

[0155] According to a fourth aspect of an embodiment of the present invention, an electronic device is provided. Fig. 9 It is a structural diagram of an electronic device in one embodiment of the present invention. Fig. 9 The electronic device shown is a quality detection device for a universal manipulator grasping an object, which includes a universal computer hardware structure, which at least includes a processor 901 and a memory 902. The processor 901 and the memory 902 are connected via a bus 903. The memory 902 is suitable for storing instructions or programs executable by the processor 901. The processor 901 can be an independent microprocessor or a collection of one or more microprocessors. Thus, the processor 901 executes the instructions stored in the memory 902, thereby executing the method flow of the embodiment of the present invention as described above to realize the processing of data and the control of other devices. The bus 903 connects the above-mentioned multiple components together, and at the same time connects the above-mentioned components to the display controller 904 and the display device and the input / output (I / O) device 905. The input / output (I / O) device 905 can be a mouse, a keyboard, a modem, a network interface, a touch input device, a somatosensory input device, a printer, and other devices known in the art. Typically, the input / output device 905 is connected to the system via an input / output (I / O) controller 906.

[0156] The technical solution provided by the embodiments of the present invention may have the following beneficial effects:

[0157] In the solution of the present invention, stable and rapid force analysis and identification are achieved through rapid analysis of deformation degree.

[0158] In the scheme of the present invention, the optimal gripping force is selected according to the movement of the grasped object during the movement process and the recovery of the deformation after grasping to ensure the quality and safety of the grasping process of the robot arm without damaging the grasped object.

[0159] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0160] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0161] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0162] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0163] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for detecting the quality of objects grasped by a robot arm, characterized in that: The method includes: Obtain the degree of deformation through camera acquisition; Determine the degree of deformation recovery according to the degree of deformation; Pre-set groups of deformation degrees, and perform robotic arm grasping and recovery control on each deformation degree group one by one; extracting the relative displacement of the grasped object during the grasping process according to the deformation degree group; Determining whether to start a gripping process according to the relative displacement of the grasped object; After starting the gripping process, determining the appropriate force as the final gripping force, and lifting the grasped object; The deformation degree is obtained by collecting data through a camera, specifically including: The contact surface between the grasped object and the robotic arm is photographed through cameras at multiple angles; Determine the initial position of the contact surface and the deformation depth at each time after the robot grasps, and use the deformation depth in millimeters as the degree of deformation; Wherein, judging the degree of deformation recovery according to the degree of deformation specifically includes: When the time after the robot arm leaves the grasped object satisfies the first calculation formula, the current time is recorded as the recovery state; extracting the deformation degree corresponding to the recovery state as the deformation recovery degree; The first calculation formula is: T>5s Where T is the time after the robot arm leaves the grasped object, in seconds, and s is the time unit in seconds.

2. The quality detection method of the object grasped by the robot arm as claimed in claim 1, characterized in that: The pre-setting of deformation degree groups and performing robot arm grasping and recovery control on each deformation degree group one by one specifically include: Presetting deformation degree groups, the deformation degree groups are stored according to a preset group order, wherein the group order includes a first, a second, ..., an Nth group; Setting the deformation degrees corresponding to the first, second, ..., Nth groups to 1 mm, 2 mm, ..., N mm, wherein the deformation degrees are the deformation depths captured by the camera; The robot arm grasps and recovers the objects one by one according to the preset group order.

3. The quality detection method of the object grasped by the robot arm as claimed in claim 1, characterized in that: The extracting the relative displacement of the grasped object according to the deformation degree group during the grasping process specifically includes: After each time the robot arm grasps the current grasped object, the robot arm lifts the grasped object upward according to the deformation degree group; The second calculation formula is used to calculate the relative displacement between the grasped object and the robotic arm at the current moment; The second calculation formula is: Y=|X1-X0| Among them, Y is the relative displacement between the grasped object and the robotic arm, X1 is the distance between the grasped object and the robotic arm at the current moment, and X0 is the distance between the grasped object and the robotic arm before lifting the grasped object.

4. The quality detection method of the object grasped by the robot arm as claimed in claim 1, characterized in that: The determining whether to start the gripping process according to the relative displacement of the grasped object specifically includes: lifting the grasped objects one by one according to the order of the deformation degree groups, and judging whether the relative displacement of the grasped objects satisfies a third calculation formula; If the third calculation formula is not satisfied, it is considered that the grip is not tight, and the gripping and lifting control is continued according to the group order of the deformation degree groups; If the third calculation formula is satisfied, it is considered that the grip is tight, and the gripping process is started; The third calculation formula is: Y<5mm Here, mm is the distance unit in millimeters.

5. The quality detection method of the object grasped by the robot arm as claimed in claim 1, characterized in that: After the gripping process is started, determining the appropriate force as the final gripping force and lifting the grasped object specifically includes: After starting the gripping process, the force margin is calculated using the fourth calculation formula; Use the fifth calculation formula to calculate the current force on the robotic arm; When the robotic arm holds the grasped object tightly until the force reaches the current robotic arm force, determine whether the current deformation recovery degree and the deformation recovery degree in the previous grasping process satisfy the sixth calculation formula; if not, continue to use the fifth calculation formula to update the current robotic arm force until the current deformation recovery degree and the deformation recovery degree in the previous grasping process satisfy the sixth calculation formula; When the current deformation recovery degree and the deformation recovery degree in the previous grasping process satisfy the sixth calculation formula, the force of the robot arm at the current moment is used as the final gripping force, and the grasped object is lifted with the final gripping force; The fourth calculation formula is: LY=0.1×(LL1-LL0) Among them, LY is the force margin, LL1 is the force on the robot arm during the gripping process, and LL0 is the force on the robot arm corresponding to the last lifting process in the gripping process; The fifth calculation formula is: Sa=LY+Sl Among them, Sa is the current force on the robot arm, and Sl is the force on the robot arm during the last lifting process; The sixth calculation formula is: L0÷L1>0.95 Among them, L1 is the degree of deformation recovery in the previous grasping process, and L0 is the current degree of deformation recovery.

6. The quality inspection system of the object grasped by the robot arm is characterized by: The system is used to implement the method according to any one of claims 1 to 5, and the system comprises: A deformation degree monitoring module is used to obtain the deformation degree through camera acquisition; A deformation recovery module is used to determine the degree of deformation recovery according to the degree of deformation; The deformation lifting module is used to pre-set the deformation degree groups and perform the robot arm grasping and recovery control for each deformation degree group one by one; A relative displacement judgment module, used to extract the relative displacement of the grasped object during the grasping process according to the deformation degree group; A gripping judgment module, used to judge whether to start a gripping process according to the relative displacement of the grasped object; The analysis module can be restored to determine the appropriate force as the final gripping force and lift the grasped object after the gripping process is started.

7. A computer-readable storage medium storing computer program instructions, characterized in that: The computer program instructions implement the method according to any one of claims 1 to 5 when executed by a processor.

8. An electronic device, comprising a memory and a processor, characterized in that: The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1-5.

Images