Intelligent driving system of intelligent industrial mechanical arm

Abstract

The invention relates to the technical field of mechanical arm driving, and discloses an intelligent driving system of an intelligent industrial mechanical arm, which comprises a mechanical arm, a data acquisition module and an intelligent driving module. According to the intelligent driving system of the intelligent industrial mechanical arm, a three-dimensional coordinate system is established through the data acquisition module to acquire a data set, accurate positioning and path optimization are facilitated, and the intelligent driving module classifies target objects according to section shapes, generates corresponding recognition areas, quickly adapts to a dynamic sorting scene and improves the sorting efficiency. The driving distance between the driving end and the target object is analyzed and generated, a moving path is coherently optimized, the intelligent driving module analyzes the pressure change degree of the driving end of the mechanical arm, the corresponding fluctuation rate is generated, the target object is prevented from sliding off, the multi-dimensional cooperative control precision is high, the intelligent driving module is provided with a fixed threshold value, and the intelligent driving module is convenient to operate. The grabbing grades of different types of target objects are evaluated, the optimal section contact point is selected, the grabbing state of the driving end of the mechanical arm is monitored, corresponding driving suggestions are generated, driving is efficient, and the production efficiency is high.

Description

Technical Field

[0001] The present invention relates to the technical field of robot arm driving, and in particular to an intelligent driving system of an intelligent industrial robot arm. Background Art

[0002] The intelligent industrial robot arm is a machine device that can imitate the movement of the human arm. Through high-precision sensors, advanced control systems and powerful actuators, it can achieve tasks such as grasping, carrying, manipulating and placing various workpieces. Its structure usually includes parts such as a base, an arm, a joint and an end effector. The base provides a stable support for the robot arm to ensure its stability during work. The arm can be flexibly extended and rotated like a human arm. The joint is the key part that connects the various parts. Through precise control, the robot arm can achieve multi-dimensional movement, and the end effector is designed into various shapes and functions according to different work tasks, such as grippers, suction cups, welding heads, etc., to meet the operation requirements in different scenarios. In terms of sorting function, the intelligent industrial robot arm has extremely high sorting accuracy. Equipped with advanced visual recognition systems and high-precision position sensors, the robot arm can accurately identify workpieces of different shapes, sizes and materials, and classify and sort them according to preset rules. Whether it is a tiny electronic component or a large mechanical component, it can be accurately grasped and placed in a designated position, greatly improving the accuracy and efficiency of sorting. The sorting function of intelligent industrial robotic arms is widely used in many industries. In the logistics industry, it can be used to sort and distribute express parcels to improve logistics efficiency. In the manufacturing industry, it can classify and assemble parts to ensure product quality. In the food industry, it can sort and package food to ensure food safety.

[0003] At present, the intelligent drive system of traditional industrial robotic arms has poor environmental adaptability and is difficult to adapt to dynamic sorting scenarios in real time. There are deviations in the motion trajectory, and the sorting efficiency and accuracy are low. In addition, when the robotic arm grasps the target object, it is difficult to promptly detect problems such as missed grasping and slipping. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the shortcomings of the prior art, the present invention provides an intelligent driving system for an intelligent industrial robot arm, which has the advantages of high precision of multi-dimensional collaborative control and high efficient driving production efficiency. It solves the problem that the intelligent driving system of the traditional industrial robot arm has poor environmental adaptability and difficulty in timely detection of missed grasps and slippage.

[0006] (II) Technical solution

[0007] To achieve the above-mentioned object, the present invention provides the following technical solutions: an intelligent driving system for an intelligent industrial robot arm, comprising a robot arm, a data acquisition module and an intelligent driving module;

[0008] The mechanical arm comprises a fixed end, a large arm, a joint movable end, a small arm and a driving end, wherein the fixed end is used to fix and install the mechanical arm, the joint movable end is used to drive the large arm and the small arm, and the driving end is provided with a gripper for grabbing a target object;

[0009] The data acquisition module establishes a three-dimensional coordinate system Z with the fixed end as the origin. The data acquisition module is composed of a scanning data unit, a driving data unit and a sensing data unit. The scanning data unit is connected to an infrared camera through a network to collect a target data set, and the target data set includes scanning data of the target object. The driving data unit collects a driving data set according to the three-dimensional coordinate system Z, and the driving data set includes coordinate data of all nodes. The sensing data unit is connected to a sensing device through a network to collect a sensing data set, and the sensing data set includes pressure data of the driving end of the robotic arm.

[0010] The intelligent driving module consists of a target recognition unit, a distance evaluation unit, a pressure monitoring unit and a driving management unit. The target recognition unit classifies the target according to the cross-sectional shape based on the target data set and generates a corresponding recognition area Smj. The distance evaluation unit analyzes and generates a driving distance Qdj between the driving end and the target according to the driving data unit. The pressure monitoring unit analyzes the pressure change degree of the driving end of the robot arm according to the sensor data set and generates a corresponding fluctuation rate Bdl. The driving management unit is provided with a fluctuation threshold BDY in a fixed range, and then combines the recognition area Smj, the driving distance Qdj and the fluctuation rate Bdl to evaluate the grasping level of different types of targets, select the optimal cross-sectional contact point, monitor the grasping state of the driving end of the robot arm, and generate corresponding driving suggestions.

[0011] Preferably, the target data set is expressed as {M1, M2, M3, ..., Mn}, where M1 to Mn represent the scanning data of the first to nth target objects, and the scanning data include cross-sectional shapes and cross-sectional dimensions.

[0012] Preferably, the expression of the driving data set is {J1, J2, J3, ..., Je}, where J1 to Je represent the coordinate data of the first to e-th nodes, and the nodes include the moving points of the driving end and the cross-sectional contact points of the target object.

[0013] Preferably, the expression of the sensor data set is {Y1, Y2, Y3, ..., Yv}, where Y1 to Yv represent pressure values ​​from the first time point to the vth time point.

[0014] Preferably, the calculation process of the identification area Smj is as follows:

[0015] According to the target data set, the targets are classified according to their cross-sectional shapes. Targets with circular cross-sectional shapes are classified as Class A targets, and targets with square cross-sectional shapes are classified as Class B targets.

[0016]

[0017] In the formula, r a represents the cross-sectional radius of the a-th target. The cross-sectional shape of the a-th target is circular. A represents the number of targets with circular cross-sectional shapes. represents the total area of ​​all targets with circular cross-sections, l b represents the cross-sectional length of the bth target, k b represents the cross-sectional width of the b-th target. The cross-sectional shape of the b-th target is a square. B represents the number of targets with a square cross-sectional shape. Represents the total area of ​​all targets with square cross-sections, s c represents the cross-sectional length of the cth target object, h c represents the height of the cth target object in the cross section perpendicular to sc. The cross section of the cth target object is a triangle. C represents the number of targets with a triangular cross section. Represents the total area of ​​all objects with a triangular cross-section.

[0018] Preferably, the driving distance Qdj calculation process is as follows:

[0019] According to the driving data set, the coordinates of the f-th moving point are marked as Jf(x f ,y f ,z f ), and the coordinates of the contact point of the g-th section are marked as Jg(x g ,y g ,z g );

[0020]

[0021] In the formula, According to the Pythagorean theorem, the straight-line distance from the fth moving point to the gth cross-sectional contact point is calculated, which is the driving distance Qdj between the driving end and the target object. f-g .

[0022] Preferably, the calculation process of the volatility Bdl is as follows:

[0023]

[0024] In the formula, μ represents the average pressure at the driving end of the robot arm. It indicates that the fluctuation rate of the pressure change at the driving end of the robot arm is calculated according to the standard deviation formula.

[0025] Preferably, in the identification area Smj, when the number A of targets with circular cross-sectional shapes is greater than the number B of targets with square cross-sectional shapes and the number C of targets with triangular cross-sectional shapes, the grasping level of targets with triangular cross-sectional shapes is higher than the grasping level of targets with square cross-sectional shapes, and the grasping level of targets with square cross-sectional shapes is higher than the grasping level of targets with circular cross-sectional shapes. In the identification area Smj, when the number of different types of targets is the same, the grasping levels will be arranged according to the total area of ​​the targets. If the total area of ​​targets of a single type is smaller than the total area of ​​targets of other types, the grasping level of targets of the corresponding type is the highest.

[0026] Preferably, the drive management unit arranges the cross-sectional contact points from short to long according to the drive distance Qdj, and controls the robot arm to preferentially select the cross-sectional contact point with the shortest drive distance Qdj to grasp the target object.

[0027] Preferably, when the fluctuation rate Bdl is higher than the fluctuation threshold BDY, it indicates that the pressure change at the driving end of the robot arm is abnormal, and it is recommended to check the abnormal grasping situation in time.

[0028] Compared with the prior art, the present invention provides an intelligent driving system for an intelligent industrial robot arm, which has the following beneficial effects:

[0029] 1. The present invention establishes a three-dimensional coordinate system Z with the fixed end as the origin through a data acquisition module, which is convenient for precise positioning and path optimization. The data acquisition module is composed of a scanning data unit, a driving data unit and a sensing data unit. The scanning data unit collects a target data set through a network connection to an infrared camera, the driving data unit collects a driving data set according to the three-dimensional coordinate system Z, and the sensing data unit collects a sensing data set through a network connection to a sensing device. The intelligent driving module classifies the target objects according to the cross-sectional shape according to the target data set, and generates a corresponding identification area Smj. Through real-time data updates, it can quickly adapt to dynamic sorting scenarios. The intelligent driving module analyzes and generates a driving distance Qdj between the driving end and the target object according to the driving data unit, and optimizes the moving path in a coherent manner to avoid frequent start-stop or overload operation of the robotic arm, thereby extending the service life of the equipment. The intelligent driving module analyzes the pressure change degree of the driving end of the robotic arm according to the sensing data set, and generates a corresponding fluctuation rate Bdl to avoid the target object from slipping. The multi-dimensional collaborative control has high accuracy.

[0030] 2. The present invention sets a fixed range of fluctuation threshold BDY through the intelligent driving module, and then combines the identification area Smj, the driving distance Qdj and the fluctuation rate Bdl to evaluate the grasping level of different types of targets, select the optimal cross-sectional contact point, and monitor the grasping state of the driving end of the robot arm. In the identification area Smj, when the number of targets with circular cross-sectional shapes A> the number of targets with square cross-sectional shapes B> the number of targets with triangular cross-sectional shapes C, the grasping level of the target with triangular cross-sectional shape is higher than the grasping level of the target with square cross-sectional shape, and the grasping level of the target with square cross-sectional shape is higher than the grasping level of the target with circular cross-sectional shape. In the identification area Smj, when the number of different types of targets is the same, the grasping level will be arranged according to the total area of ​​the target. If the total area of ​​a single type of target is smaller than the total area of ​​other types of targets, the corresponding type of target has the highest grasping level. This judgment logic ensures that the system can quickly select the optimal grasping target in complex scenarios and significantly improve the sorting efficiency. The drive management unit arranges the cross-sectional contact points from short to long according to the drive distance Qdj, and controls the robot arm to prioritize the cross-sectional contact points with the shortest drive distance Qdj to grasp the target, shorten the robot arm's moving path, and reduce energy consumption and time costs. When the fluctuation rate Bdl is higher than the fluctuation threshold BDY, it indicates that the pressure change at the driving end of the robot arm is abnormal. It is recommended to check the grasping abnormality in time, monitor the pressure in real time and issue warnings in time to avoid equipment damage or sorting errors, improve safety, and drive production efficiency efficiently. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a flow chart of the system of the present invention. DETAILED DESCRIPTION

[0032] 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.

[0033] The intelligent drive system of traditional industrial robot arms has poor environmental adaptability and is difficult to adapt to dynamic sorting scenarios in real time. There are deviations in the motion trajectory, and the sorting efficiency and accuracy are low. In addition, when the robot arm grasps the target object, it is difficult to detect problems such as missed grasping and slipping in time. Therefore, an intelligent drive system for an intelligent industrial robot arm is provided. Please refer to Figure 1 , an intelligent driving system of an intelligent industrial robot arm, comprising a robot arm, a data acquisition module and an intelligent driving module;

[0034] The robot arm includes a fixed end, a large arm, a joint movable end, a small arm and a driving end. The fixed end is used to fix and install the robot arm, the joint movable end is used to drive the large arm and the small arm, and the driving end is provided with a gripper for grabbing the target object;

[0035] The data acquisition module establishes a three-dimensional coordinate system Z with the fixed end as the origin, which is convenient for accurate positioning and path optimization. The data acquisition module consists of a scanning data unit, a driving data unit and a sensor data unit. The scanning data unit connects to the infrared camera through the network to collect the target data set. The target data set includes the scanning data of the target object. The expression of the target data set is {M1, M2, M3, ..., Mn}, where M1 to Mn represent the scanning data of the first to the nth target object. The scanning data includes the cross-sectional shape and cross-sectional size, which is convenient for automatic classification of objects of different shapes;

[0036] The driving data unit collects the driving data set according to the three-dimensional coordinate system Z. The driving data set includes the coordinate data of all nodes. The expression of the driving data set is {J1, J2, J3, ..., Je}, where J1 to Je represent the coordinate data of the first to the e-th nodes. The nodes include the moving points of the driving end and the cross-sectional contact points of the target object, ensuring the accuracy of spatial positioning;

[0037] The sensor data unit collects a sensor data set by connecting to the sensor device through a network. The sensor data set includes pressure data of the driving end of the robot arm. The expression of the sensor data set is {Y1, Y2, Y3, ..., Yv}, where Y1 to Yv represent pressure values ​​from the first time point to the vth time point;

[0038] The intelligent driving module consists of a target recognition unit, a distance evaluation unit, a pressure monitoring unit, and a driving management unit. The target recognition unit classifies the target objects according to the cross-sectional shape based on the target data set and generates the corresponding recognition area Smj. The calculation process is as follows:

[0039] According to the target data set, the targets are classified according to their cross-sectional shapes. Targets with circular cross-sectional shapes are classified as Class A targets, and targets with square cross-sectional shapes are classified as Class B targets.

[0040]

[0041] In the formula, r a represents the cross-sectional radius of the a-th target. The cross-sectional shape of the a-th target is circular. A represents the number of targets with circular cross-sectional shapes. represents the total area of ​​all targets with circular cross-sections, l b represents the cross-sectional length of the bth target, k b represents the cross-sectional width of the b-th target. The cross-sectional shape of the b-th target is a square. B represents the number of targets with a square cross-sectional shape. Represents the total area of ​​all targets with square cross-sections, s c represents the cross-sectional length of the cth target object, h c Indicates the cth target cross section perpendicular to s c The height of the cth target is a triangle in cross section. C represents the number of targets with a triangle in cross section. Indicates the total area of ​​all objects with triangular cross-sections. It can quickly adapt to dynamic sorting scenarios through real-time data updates.

[0042] The distance evaluation unit analyzes and generates the driving distance Qdj between the driving end and the target object according to the driving data unit. The calculation process is as follows:

[0043] According to the driving data set, the coordinates of the f-th moving point are marked as Jf(x f ,y f ,z f ), and the coordinates of the contact point of the g-th section are marked as Jg(x g ,y g ,z g );

[0044]

[0045] In the formula, According to the Pythagorean theorem, the straight-line distance from the fth moving point to the gth cross-sectional contact point is calculated, which is the driving distance Qdj between the driving end and the target object. f-g , optimize the moving path in a coherent manner, avoid frequent start and stop or overload operation of the robot arm, and extend the service life of the equipment;

[0046] The pressure monitoring unit analyzes the pressure change degree of the robot arm drive end according to the sensor data set and generates the corresponding fluctuation rate Bdl. The calculation process is as follows:

[0047]

[0048] In the formula, μ represents the average pressure at the driving end of the robot arm. It means that according to the standard deviation formula, the fluctuation rate of the pressure change at the driving end of the robot arm is calculated and applied to the moving stage of the grasping process to prevent the target from slipping, and the multi-dimensional collaborative control has high accuracy;

[0049] The drive management unit is set with a fixed range of fluctuation threshold BDY, and then combined with the recognition area Smj, driving distance Qdj and fluctuation rate Bdl, evaluates the grasping level of different types of targets, selects the optimal cross-sectional contact point, monitors the grasping state of the driving end of the robot arm, and generates corresponding driving suggestions;

[0050] In the recognition area Smj, when the number of objects with circular cross-section shapes A> the number of objects with square cross-section shapes B> the number of objects with triangular cross-section shapes C, the grasping level of objects with triangular cross-sections is higher than that of objects with square cross-sections, and the grasping level of objects with square cross-sections is higher than that of objects with circular cross-sections. In the recognition area Smj, when the number of objects of different types is the same, the grasping level will be arranged according to the total area of ​​the objects. If the total area of ​​objects of a single type is smaller than the total area of ​​objects of other types, the grasping level of the corresponding type of objects is the highest. This judgment logic It ensures that the system can quickly select the optimal grasping target in complex scenarios and significantly improve the sorting efficiency. The drive management unit arranges the cross-sectional contact points from short to long according to the drive distance Qdj, and controls the robot arm to prioritize the cross-sectional contact points with the shortest drive distance Qdj to grasp the target object, shortening the robot arm's movement path, reducing energy consumption and time costs. When the fluctuation rate Bdl is higher than the fluctuation threshold BDY, it indicates that the pressure change at the driving end of the robot arm is abnormal. It is recommended to check the grasping abnormality in time, monitor the pressure in real time and issue early warning in time to avoid equipment damage or sorting errors, improve safety, and drive production efficiency efficiently.

[0051] Embodiment 1:

[0052] In this experiment, a robotic arm with a driving end coordinate of (1,2,3) is selected as the experimental object. After scanning, the coordinates of the contact point of the target cross section are (4,6,8). The calculation process of the driving distance Qdj between the driving end of the robotic arm and the target is as follows:

[0053]

[0054] In the formula, according to the Pythagorean theorem, the straight-line distance from the moving point of the driving end to the contact point of the cross section of the target object is calculated to be approximately 7.07. The driving distance Qdj between the driving end of the robot and the target object is f-g About 7.07.

[0055] Embodiment 2:

[0056] In this experiment, a robotic arm used to sort tubular objects was selected as the experimental object. After testing, the pressure values ​​at the driving end of the robotic arm were 10Pa, 12Pa, 15Pa, 11Pa and 13Pa respectively within 5 minutes. The calculation process of the fluctuation rate Bdl of the pressure change at the driving end of the robotic arm is as follows:

[0057]

[0058] In the formula, μ=12.2Pa represents the average pressure at the driving end of the robot arm. According to the standard deviation formula, the fluctuation rate of the pressure change at the driving end of the robot arm is calculated to be 2.96, and the fluctuation threshold BDY is set to 3.5~9.8. After judgment, 2.96 is lower than the fluctuation threshold BDY. The pressure change at the driving end of the robot arm is normal, and there is no need to check for abnormal grasping.

[0059] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent driving system for an intelligent industrial robot arm, characterized in that: Including robotic arm, data acquisition module and intelligent drive module; The mechanical arm comprises a fixed end, a large arm, a joint movable end, a small arm and a driving end, wherein the fixed end is used to fix and install the mechanical arm, the joint movable end is used to drive the large arm and the small arm, and the driving end is provided with a gripper for grabbing a target object; The data acquisition module establishes a three-dimensional coordinate system Z with the fixed end as the origin. The data acquisition module is composed of a scanning data unit, a driving data unit and a sensing data unit. The scanning data unit is connected to an infrared camera through a network to collect a target data set, and the target data set includes scanning data of the target object. The driving data unit collects a driving data set according to the three-dimensional coordinate system Z, and the driving data set includes coordinate data of all nodes. The sensing data unit is connected to a sensing device through a network to collect a sensing data set, and the sensing data set includes pressure data of the driving end of the robotic arm. The intelligent driving module consists of a target recognition unit, a distance evaluation unit, a pressure monitoring unit and a driving management unit. The target recognition unit classifies the target according to the cross-sectional shape based on the target data set and generates a corresponding recognition area Smj. The distance evaluation unit analyzes and generates a driving distance Qdj between the driving end and the target according to the driving data unit. The pressure monitoring unit analyzes the pressure change degree of the driving end of the robot arm according to the sensor data set and generates a corresponding fluctuation rate Bdl. The driving management unit is provided with a fluctuation threshold BDY in a fixed range, and then combines the recognition area Smj, the driving distance Qdj and the fluctuation rate Bdl to evaluate the grasping level of different types of targets, select the optimal cross-sectional contact point, monitor the grasping state of the driving end of the robot arm, and generate corresponding driving suggestions.

2. The intelligent driving system of an intelligent industrial robot arm according to claim 1, characterized in that: The target data set is expressed as {M1, M2, M3, ..., Mn}, where M1 to Mn represent the scanning data of the first to nth target objects, and the scanning data includes a cross-sectional shape and a cross-sectional size.

3. The intelligent driving system of an intelligent industrial robot arm according to claim 2, characterized in that: The expression of the driving data set is {J1, J2, J3, ..., Je}, where J1 to Je represent the coordinate data of the first to e-th nodes, and the nodes include the moving points of the driving end and the cross-sectional contact points of the target object.

4. The intelligent driving system of an intelligent industrial robot arm according to claim 3, characterized in that: The expression of the sensing data set is {Y1, Y2, Y3, ..., Yv}, where Y1 to Yv represent the pressure values ​​from the first time point to the vth time point.

5. The intelligent driving system of an intelligent industrial robot arm according to claim 4, characterized in that: The calculation process of the identification area Smj is as follows: According to the target data set, the targets are classified according to their cross-sectional shapes. Targets with circular cross-sectional shapes are classified as Class A targets, and targets with square cross-sectional shapes are classified as Class B targets. In the formula, r a represents the cross-sectional radius of the a-th target. The cross-sectional shape of the a-th target is circular. A represents the number of targets with circular cross-sectional shapes. represents the total area of ​​all targets with circular cross-sections, l b represents the cross-sectional length of the bth target object, k b represents the cross-sectional width of the b-th target. The cross-sectional shape of the b-th target is a square. B represents the number of targets with a square cross-sectional shape. Represents the total area of ​​all targets with square cross-sections, s c represents the cross-sectional length of the cth target object, h c Indicates the cth target cross section perpendicular to s c The height of the cth target is a triangle in cross section. C represents the number of targets with a triangle in cross section. Represents the total area of ​​all objects with a triangular cross-section.

6. The intelligent driving system of an intelligent industrial robot arm according to claim 5, characterized in that: The driving distance Qdj calculation process is as follows: According to the driving data set, the coordinates of the f-th moving point are marked as Jf(x f ,y f ,z f ), and the coordinates of the contact point of the g-th section are marked as Jg(x g ,y g ,z g ); In the formula, According to the Pythagorean theorem, the straight-line distance from the fth moving point to the gth cross-sectional contact point is calculated, which is the driving distance Qdj between the driving end and the target object. f-g .

7. The intelligent driving system of an intelligent industrial robot arm according to claim 6, characterized in that: The calculation process of the volatility Bdl is as follows: In the formula, μ represents the average pressure at the driving end of the robot arm. It indicates that the fluctuation rate of the pressure change at the driving end of the robot arm is calculated according to the standard deviation formula.

8. The intelligent driving system of an intelligent industrial robot arm according to claim 7, characterized in that: In the identification area Smj, when the number A of targets with circular cross-sectional shapes is greater than the number B of targets with square cross-sectional shapes and the number C of targets with triangular cross-sectional shapes, the grasping level of targets with triangular cross-sectional shapes is higher than the grasping level of targets with square cross-sectional shapes, and the grasping level of targets with square cross-sectional shapes is higher than the grasping level of targets with circular cross-sectional shapes. In the identification area Smj, when the number of targets of different types is the same, the grasping levels will be arranged according to the total area of ​​the targets. If the total area of ​​targets of a single type is smaller than the total area of ​​targets of other types, the grasping level of targets of the corresponding type is the highest.

9. The intelligent driving system of an intelligent industrial robot arm according to claim 8, characterized in that: The drive management unit arranges the cross-sectional contact points from short to long according to the drive distance Qdj, and controls the robot arm to preferentially select the cross-sectional contact point with the shortest drive distance Qdj to grasp the target object.

10. The intelligent driving system of an intelligent industrial robot arm according to claim 9, characterized in that: When the fluctuation rate Bdl is higher than the fluctuation threshold BDY, it indicates that the pressure change at the driving end of the robot arm is abnormal, and it is recommended to check the abnormal grasping situation in time.

Images