Clamping control method and device, computer equipment and readable storage medium

Abstract

The invention relates to a clamping control method and device, computer equipment, a computer readable storage medium and a computer program product. The method is applied to a mechanical arm, the mechanical arm is provided with a clamping jaw, and the method comprises the steps that a contact image generated when the clamping jaw makes contact with a target object is obtained, and the clamping type of the target object is determined based on the contact image; under the condition that the clamping jaw is controlled to clamp the target object according to a first target angle corresponding to the clamping type, the first target angle is adjusted according to the parameter difference between the driving parameter of the clamping jaw and a reference driving parameter, and a second target angle is obtained; and according to the second target angle, the clamping jaw is controlled to clamp the target object. By the adoption of the method, self-adaptive clamping force adjustment of objects of different shapes and textures can be achieved under the condition that an additional force sensor is not added, and the clamping action of the mechanical arm is more intelligent.

Description

Technical Field

[0001] The present application relates to the field of robot arm control, and in particular to a gripping control method, device, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] With the continuous development of industrial technology, robotic arms have emerged in various fields. These robotic arms can perform predetermined tasks within a specific space to grasp, pick or carry specific structures.

[0003] In traditional technology, the robotic arm mainly clamps objects by controlling the corner points fixed by the motor, so the opening and closing angles of the robotic arm are relatively fixed; therefore, the robotic arm can only be used for a single type of object. A robotic arm used to pick tomatoes cannot be used to clamp wood blocks or sponges. Summary of the invention

[0004] Based on this, it is necessary to provide a clamping control method, device, computer equipment, computer-readable storage medium and computer program product that can adaptively adjust the clamping force and does not require a force sensor to address the above technical problems.

[0005] In a first aspect, the present application provides a gripping control method, which is applied to a robotic arm, wherein the robotic arm is provided with a gripper, and the method comprises:

[0006] Acquire a contact image when the clamping claw contacts the target object, and determine a clamping type of the target object based on the contact image;

[0007] When the gripper is controlled to grip the target object according to a first target angle corresponding to the gripping type, the first target angle is adjusted according to a parameter difference between a driving parameter of the gripper and a reference driving parameter to obtain a second target angle;

[0008] According to the second target angle, the gripper is controlled to grip the target object.

[0009] In one embodiment, controlling the gripper to grip the target object according to the first target angle corresponding to the gripping type includes:

[0010] Based on the contact image, determining that the gripping type of the target object belongs to an unknown type, and based on preset parameters corresponding to the unknown type, determining a first target angle; and controlling the gripper to grip the target object according to the first target angle;

[0011] The adjusting the first target angle according to the parameter difference between the driving parameter of the clamp and the reference driving parameter to obtain the second target angle comprises:

[0012] When the gripping type is an unknown type, capturing images of the gripper and the target object to obtain a deformation judgment image;

[0013] adjusting the first target angle according to the adjustment parameter corresponding to the deformation judgment image to obtain an adjusted first target angle;

[0014] According to the parameter difference between the driving parameter of the clamping jaw and the reference driving parameter, the adjusted first target angle is adjusted to obtain a second target angle.

[0015] In one embodiment, adjusting the first target angle according to the adjustment parameter corresponding to the deformation judgment image to obtain the adjusted first target angle includes:

[0016] When the deformation judgment image indicates that the target object is deformed, determining a first adjustment parameter corresponding to the deformation judgment image;

[0017] According to the first adjustment parameter, the first target angle is adjusted lower to obtain an adjusted first target angle.

[0018] In one embodiment, controlling the gripper to grip the target object according to the first target angle corresponding to the gripping type includes:

[0019] Based on the contact image, determining that the gripping type of the target object belongs to a known type;

[0020] Determining a first target angle based on a gripping property corresponding to a known type to which the target object belongs;

[0021] The gripper is controlled to grip the target object according to the first target angle.

[0022] In one embodiment, adjusting the first target angle to obtain the second target angle according to the parameter difference between the driving parameter of the gripper and the reference driving parameter includes:

[0023] When the current driving parameter of the gripper is greater than the reference driving parameter, the first target angle is reduced according to the parameter difference to obtain a second target angle;

[0024] When the current driving parameter of the gripper is less than the reference driving parameter, the first target angle is increased according to the parameter difference to obtain a second target angle.

[0025] In one embodiment, the driving parameters of the clamp include the driving parameters at each moment in a preset clamping time period, the previous driving parameters, and the current driving parameters; the parameter difference includes the current parameter difference, the cumulative value of the parameter difference, and the driving parameter change rate;

[0026] Before the parameter difference between the driving parameter of the clamp and the reference driving parameter, the method further comprises:

[0027] Determining the current parameter difference according to the difference between the current driving parameter and the reference driving parameter;

[0028] Perform difference processing on the driving parameters at each moment in the preset clamping time period and the reference driving parameters to obtain the parameter difference values ​​of the preset clamping time period; perform accumulation on the parameter difference values ​​of the preset clamping time period to obtain the parameter difference accumulation value;

[0029] The driving parameter change rate is determined based on the difference between the current driving parameter and the reference driving parameter, and the difference change rate between the difference between the previous driving parameter and the reference driving parameter.

[0030] In a second aspect, the present application further provides a gripping control device, which is applied to a robotic arm, wherein the robotic arm is provided with a gripper, and the device comprises:

[0031] a detection module, configured to obtain a contact image when the clamping claw contacts a target object, and determine a clamping type of the target object based on the contact image;

[0032] an adjustment module, configured to adjust the first target angle to obtain a second target angle according to a parameter difference between a driving parameter of the clamp and a reference driving parameter when controlling the clamp to clamp the target object according to a first target angle corresponding to the clamp type;

[0033] The gripping module is used to control the gripper to grip the target object according to the second target angle.

[0034] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the clamping control in any of the above embodiments are implemented.

[0035] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the clamping control in any of the above embodiments are implemented.

[0036] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of clamping control in any of the above embodiments are implemented.

[0037] The above-mentioned gripping control method, device, computer equipment, computer-readable storage medium and computer program product are applied to a robotic arm, wherein the robotic arm is provided with a gripper. On the one hand, the method provides multi-dimensional information through contact images, determines the gripping type more accurately, and adaptively adjusts toward the first target angle, thereby reducing the frequency of parameter adjustment in the gripping process; on the other hand, the information provided by the contact image may have recognition errors, and the appropriate gripping force of the gripper is defined by referring to the driving parameters, and the parameter difference between the driving parameters of the gripper and the reference driving parameters is adjusted to ensure that the gripping force is moderate. Thus, without adding additional force sensors, adaptive gripping force adjustment of objects of different shapes and textures is achieved, making the gripping action of the robotic arm more intelligent. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 is an application environment diagram of a clamping control method in an embodiment;

[0040] Figure 2 is a schematic diagram of the structure of a mechanical arm in one embodiment;

[0041] Figure 3 is a schematic diagram of the structure of a clamping jaw in an embodiment;

[0042] Figure 4 A schematic diagram of a flow chart of a clamping control method in one embodiment;

[0043] Figure 5 It is a flowchart of a gripping control method under an unknown type in one embodiment;

[0044] Figure 6 is a structural block diagram of a clamping control device in one embodiment;

[0045] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0047] The clamping control method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Wherein, the robot arm 100 is provided with a gripper 110 and a camera 120, and the camera is used to capture images toward the gripper 100 to obtain images of the gripper 110, these images include but are not limited to contact images when the gripper contacts the target object, and clamping images when the gripper clamps the target object. Wherein, this method can be controlled by a processor of the robot arm, or by an external device; the data to be processed by this method is located in a data storage system. The data storage system can be integrated in the built-in memory of the robot arm, or can be set on an external device, and the external device includes but is not limited to computer equipment, cloud or other network servers.

[0048] For example, Figure 2 As shown, the first link in the robot arm 100 is arranged on the base 101, and the base 101 is provided with a plurality of links 102 connected in sequence, and each link 102 is connected through a joint 103, and each link 102, and the last link in each link 102 is connected with the clamp 110; the base is provided with a plurality of suction cups, and each suction cup enables the robot arm 100 to be fixed to an object such as a table or a workbench. Since the fixing ability of the suction cup itself is relatively weak, a plurality of suction cups are provided to make the robot arm 100 more stable.

[0049] For example, Figure 3 As shown, the clamp 110 is an end effector of the robot arm 100. The clamp is provided with a clamp motor, a clamp arm 111 and a transmission gear 112; the force output by the clamp motor acts on the transmission gear 112, and then the transmission gear 112 drives the opening and closing angles of at least two clamp arms 111 to form a grasping action. The end of the clamp arm 111 is provided with an anti-slip structure, which can be a tooth-shaped structure, which is similar to the tooth-shaped protrusion of a gear, and is used to increase the friction between the clamp and the grasped object, thereby improving the stability and reliability of grasping.

[0050] In an exemplary embodiment, Figure 4 As shown, a gripping control method is provided, which is applied to a mechanical arm, and the mechanical arm is provided with a gripper, and the method includes the following steps 402 to 406. Among them:

[0051] Step 402 : Acquire a contact image when the gripper contacts the target object, and determine the gripping type of the target object based on the contact image.

[0052] The target object is the object to be clamped in the gripping control process. Since this method is mainly used to enrich the application field of the robot arm, the efficiency of the robot arm processor to determine the gripping type by itself when the gripper contacts the target object is low. The target object can be, but is not limited to, objects such as wood blocks and sponges. Since these objects have different shapes and hardness information, the gripping force needs to be adjusted adaptively.

[0053] The contact image is an image of the end of the gripper when it contacts the target object. The contact image contains information about the gripper, the target object, and the contact between the gripper and the target object. These three types of information can form at least three information dimensions to accurately determine the gripping type.

[0054] When the end of the clamp contacts the target object, there are multiple aspects of information reflected based on the contact image. On the one hand, the contact image is used to determine the opening and closing state of the clamp in the image and other information to control whether the clamp is adjusted; on the other hand, the contact image is used to reflect the visual information of the target object, so as to accurately analyze the clamping type suitable for the target object through object recognition and other methods; on the other hand, the contact image is used to reflect whether the force applied by the clamp to the target object is sufficient to clamp the target object, and can also be used to determine whether the force applied by the clamp to the target object causes the target object to deform or become abnormal, so as to adaptively adjust the grasping ability.

[0055] The gripping type is the type information set for the target object, and the gripping type is related to the first target angle of the motor. The gripping type can be divided into at least known types and unknown types. The known type can be further refined into multiple known sub-types to adaptively set the corresponding first target angle for different known sub-types. The unknown type can also be further refined into easily deformed types and non-deformed types according to hardness, so as to adjust parameters for easily deformed types and non-deformed types. Since the gripping type is acquired based on the contact image, the first target angle can be adaptively set from the perspective of image information to provide visual information of the image dimension; moreover, in order to ensure the compatibility of the robot arm, the actual attributes of the target object are difficult to determine, so the gripping type provided by the visual information can be more in line with the actual target object, thereby reducing the frequency of parameter adjustment in the gripping process.

[0056] In some embodiments, the target object contacted by the clamp can be classified and identified based on the YOLO model and the contact image to obtain the type information of the target object; the clamping type of the target object can be determined based on the type information of the target object. The features of the target object and the features of the contact between the clamp and the target object can also be classified and identified based on the feature template to obtain the clamping type of the target object.

[0057] Step 404, when the gripper is controlled to grip the target object according to the first target angle corresponding to the gripping type, the first target angle is adjusted according to the parameter difference between the driving parameters of the gripper and the reference driving parameters to obtain the second target angle.

[0058] The first target angle is the angle of the clamping jaw that corresponds to the clamping type. The first target angle is used to control the opening and closing angle indicated by the clamping jaw during the clamping process. When the clamping jaw does not reach the first target angle, the clamping jaw continues to exert force, so that it can clamp the target object. Since the clamping jaw clamps the target object through the opening and closing angle, the first target angle can be represented by driving parameters such as current and voltage. Since the first target angle is set based on the clamping type, and the clamping type is set based on the contact image, the information provided by the contact image may have recognition errors. Information such as the surface structure and quality of the object may cause errors, making the clamping force corresponding to the first target angle inappropriate, so the first target angle needs to be adjusted. Among them, the driving parameters are parameters generated by the driving process of the motor, cylinder or other power source.

[0059] The clamping force is expressed by the opening and closing angle of the clamping jaws, and the clamping jaw angle can be controlled by parameters such as current.

[0060] The driving parameters of the gripper are the driving parameters used by the gripper when the gripper is gripping the target object. As the gripper grips the target object, the target object will exert a force on the gripper, and this force can produce real-time parameter adjustments. At the initial moment of gripping, the driving parameters of the gripper include the driving parameters when the gripper contacts the motor; and after the initial moment of gripping, the driving parameters of the gripper are adjusted toward the second target angle of the previous moment, thereby forming an iterative update, forming an iterative update of the current driving parameters.

[0061] The reference driving parameters are driving parameter reference values ​​set for the gripping process of the gripper. The reference driving parameters are used to control the gripper to grip with an appropriate force. When the gripper grips the target object with moderate force, the driving parameters of the gripper should match the reference driving parameters. Correspondingly, if the object is clamped tightly, the driving parameters of the gripper characterize that the force of the gripper is too large. If the object is not clamped, the driving parameters of the gripper may be preset values, such as 0. Exemplarily, when the driving parameters are parameters of the gripper motor, if the gripper grips the target object tightly, the motor detects a relatively large current. If the gripper clamps the target object, the motor current is 0.

[0062] The parameter difference is the difference between the driving parameters of the clamp and the reference driving parameters. In the case where the parameter difference indicates that the driving parameters of the clamp do not match the reference driving parameters, step 404 needs to be continuously performed so that the second target angle is continuously updated. In the case where the parameter difference indicates that the driving parameters of the clamp match the reference driving parameters, the adjustment process of the first target angle can be stopped to clamp with appropriate force. The second target angle is the result of the adjustment of the first target angle.

[0063] Exemplarily, the driving parameters of the gripper include the driving parameters of the gripper at the current moment during the gripping process, and the driving parameters at the current moment within a certain time period; the driving parameters of the gripper and the reference driving parameters may both include the current of the gripper motor.

[0064] For example, if the first target angle is 60 degrees, and the clamp has already clamped the target object when the clamp reaches 58 degrees, the difference in parameters such as the current that can be generated at this time is too large, and the 60 degrees can be adjusted down. For another example, if the first target angle is 58 degrees, and the clamp needs to reach 59 degrees to clamp the target object, the difference in parameters such as the current that can be generated at this time is too small, and the 58 degrees can be adjusted up.

[0065] In some embodiments, the gripper is controlled to grip a target object toward a first target angle corresponding to the gripping type, including: mapping the gripping type according to a mapping table to obtain a first target angle; controlling the gripper motor to rotate toward the first target angle to drive the gripper arms of the gripper to merge through the gripper motor during the rotation process; and driving the target object through the force applied to the target object during the gripper arm merging process.

[0066] In some embodiments, the first target angle is adjusted according to the parameter difference between the driving parameters of the gripper and the reference driving parameters to obtain the second target angle, including: adjusting the driving parameters of the gripper according to a preset angle step until the parameter difference meets a preset condition, and taking the angle of the gripper during the rotation process when the parameter difference meets the preset condition as the second target angle.

[0067] In some embodiments, the first target angle is adjusted according to the parameter difference between the driving parameters of the gripper and the reference driving parameters to obtain the second target angle, including: determining the adjustment step according to the parameter difference between the driving parameters of the gripper and the reference driving parameters; and adjusting the first target angle according to the adjustment step to obtain the second target angle.

[0068] Step 406: Control the gripper to grip the target object according to the second target angle.

[0069] In some embodiments, controlling the gripper to grip the target object according to the second target angle includes: controlling the gripper motor to apply a force to the target object according to the second target angle to drive the target object.

[0070] Since the second target angle is close to the reference driving parameter, the force of the clamping jaws at this time is relatively more moderate. Therefore, when the type of the target object changes, the moderate force can also be guaranteed through steps 402-406.

[0071] Optionally, the first target angle and the second target angle are both based on the parameters of the PID controller. The PID controller is used to output PWM (pulse width modulation) and control the duty cycle of the PWM signal, which can change the average voltage received by the motor in each cycle. The higher the average voltage, the faster the motor speed, and as the speed decreases, the load current of the motor will also decrease, thereby reducing the current. In this way, the current fluctuation (i.e., current ripple) can be effectively suppressed, thereby improving the stability of the current.

[0072] In the above-mentioned gripping control method, a contact image when the gripper contacts the target object is obtained, and each contact image can provide multiple dimensional information such as the gripper, the target object, and the contact situation; therefore, the gripping type of the target object is determined based on the contact image, and a first target angle specifically used as the gripping target is constructed based on the gripping type, and a preliminary angle adjustment result is formed based on the first target angle, thereby reducing the frequency of parameter adjustment in the gripping process. Furthermore, with the gripping angle reaching the first target angle corresponding to the gripping type as the goal, the gripper is controlled to grip the target object. Since there are errors between the individual and gripping types of each target object, and the information provided by the contact image may be misidentified, the concept of reference drive parameters is set for the gripping process of the gripper itself, and the appropriate gripping force of the gripper is defined by the reference drive parameters, and the first target angle is adjusted according to the parameter difference between the gripper's drive parameters and the reference drive parameters to obtain a second target angle, so as to ensure that the gripping force is moderate through the second target angle; according to the second target angle, the gripper is controlled to grip the target object.

[0073] That is, on the one hand, the contact image provides multi-dimensional information, the gripping type is determined more accurately, and the first target angle is adjusted adaptively to reduce the frequency of parameter adjustment in the gripping process; on the other hand, the information provided by the contact image may be misidentified, and the appropriate gripping force of the gripper is defined by referring to the driving parameters, and the second target angle is obtained by the parameter difference between the driving parameters of the gripper and the reference driving parameters to ensure that the gripping force is moderate. In this way, without adding additional force sensors, intelligent gripping of objects can be achieved without increasing costs, and adaptive gripping of objects of different shapes and textures can be achieved, making the gripping action of the robot arm more intelligent.

[0074] In an exemplary embodiment, Figure 5 As shown, according to the first target angle corresponding to the gripping type, the gripper is controlled to grip the target object, including step 502; correspondingly, according to the parameter difference between the driving parameters of the gripper and the reference driving parameters, the first target angle is adjusted to obtain the second target angle, including steps 504-508, wherein:

[0075] Step 502: Based on the contact image, determine that the gripping type of the target object belongs to an unknown type, and determine a first target angle based on preset parameters corresponding to the unknown type; and control the gripper to grip the target object according to the first target angle.

[0076] The unknown type is used to indicate that the clamping type of the contact image does not belong to a known type. In the case of the unknown type, the first target angle of the target object cannot be obtained from the data storage system. In this case, the first target angle is directly obtained based on the preset parameters corresponding to the unknown type.

[0077] In some embodiments, based on the contact image, determining that the gripping type of the target object belongs to an unknown type includes: when the target object does not match the features of any candidate type, determining that the gripping type of the target object belongs to an unknown type. For example, similarity calculation can be performed based on the features of the target object and the features of any candidate type to obtain each similarity between the target object and each candidate type; if each similarity is less than a preset value, or the difference between each similarity is less than a preset value, then determining that the gripping type of the target object belongs to an unknown type.

[0078] In some embodiments, determining the first target angle based on a preset parameter corresponding to the unknown type includes: assigning the first target angle to the preset parameter corresponding to the unknown type.

[0079] In some embodiments, determining the first target angle based on preset parameters corresponding to the unknown type includes: randomly selecting the first target angle based on a set of preset parameters corresponding to the unknown type.

[0080] Step 504: When the gripping type is an unknown type, images of the gripper and the target object are captured to obtain a deformation judgment image.

[0081] The deformation judgment image is an image acquired after the contact image is collected. In the case where the gripping type is unknown, the deformation judgment image is used to provide information with deformation judgment of the clamp and the target object from the image dimension. These three types of information can form at least three information dimensions to accurately determine the gripping type. When the end of the clamp causes the target object to deform, it can be used to determine whether the force applied by the clamp to the target object causes the target object to deform or become abnormal, so as to adaptively adjust the gripping ability.

[0082] Step 506: adjust the first target angle according to the adjustment parameter corresponding to the deformation judgment image to obtain an adjusted first target angle.

[0083] The adjustment parameter is data corresponding to the recognition result of the deformation judgment image. The adjustment parameter is an adjustment dimension different from the parameter difference, and since the adjustment parameter belongs to the image dimension, it can be adjusted in advance to ensure the adjustment speed.

[0084] In some embodiments, when the deformation judgment image indicates that the target object is not deformed, the adjustment parameter corresponding to the deformation judgment image does not exist or is 0. If the target object is not deformed, it can be indicated that the hardness type of the target object is not easy to deform, and the driving parameters of the clamp have high accuracy. At this time, the adjustment parameters are not used for adjustment, which can ensure that the clamping force is moderate.

[0085] In some embodiments, based on the YOLO model, the target objects in the contact image and the deformation judgment image can be compared to obtain the deformation degree of the target object; the adjustment parameters can be determined according to the deformation degree of the target object; and the first target angle can be adjusted by adjusting the parameters to obtain the adjusted first target angle.

[0086] In some embodiments, the characteristics of the jaws penetrating into the target object can be detected to obtain the depth ratio of the end of the jaws entering the target object; the depth ratio is mapped to obtain an adjustment parameter; based on the adjustment parameter, the first target angle is adjusted to obtain an adjusted first target angle.

[0087] Step 508: adjusting the adjusted first target angle according to the parameter difference between the driving parameters of the gripper and the reference driving parameters to obtain a second target angle.

[0088] In some embodiments, the adjusted first target angle is adjusted according to the parameter difference between the driving parameters of the gripper and the reference driving parameters to obtain the second target angle, including: adjusting the driving parameters of the gripper according to a preset angle step until the parameter difference meets a preset condition, and taking the angle of the gripper during the rotation process when the parameter difference meets the preset condition as the second target angle.

[0089] In some embodiments, the adjusted first target angle is adjusted according to the parameter difference between the driving parameters of the gripper and the reference driving parameters to obtain the second target angle, including: determining the adjustment step according to the parameter difference between the driving parameters of the gripper and the reference driving parameters; adjusting the adjusted first target angle according to the adjustment step to obtain the second target angle.

[0090] In some embodiments, the adjusted first target angle is adjusted according to the parameter difference between the driving parameters of the gripper and the reference driving parameters to obtain the second target angle, including: when the current driving parameters of the gripper are greater than the reference driving parameters, the adjusted first target angle is reduced according to the parameter difference to obtain the second target angle; when the current driving parameters of the gripper are less than the reference driving parameters, the adjusted first target angle is increased according to the parameter difference to obtain the second target angle.

[0091] The parameter difference includes the current parameter difference, the cumulative value of the parameter difference, and the driving parameter change rate.

[0092] In this embodiment, since the clamp supports the clamping function of multiple target objects, the process of excessive image recognition will lead to a waste of resources, and there may still be the possibility of recognition errors; therefore, based on the contact image, it is determined that the clamping type of the target object belongs to an unknown type to avoid excessive resource consumption in the recognition process of the known type and ensure processing efficiency; then, based on the preset parameters corresponding to the unknown type, the initial first target angle is determined. Since the deviation between the force indicated by the preset parameters and the appropriate force is large, when the clamping type belongs to an unknown type, the clamp and the target object are imaged to obtain a deformation judgment image to reintroduce image information. Then, firstly, the adjustment parameters corresponding to the deformation judgment image are efficiently adjusted, and then the adjustment is made through the parameter difference to ensure that the clamping force of the clamp is faster and more appropriate.

[0093] In an exemplary embodiment, the first target angle is adjusted according to the adjustment parameters corresponding to the deformation judgment image to obtain the adjusted first target angle, including: when the deformation judgment image indicates that the target object is deformed, determining the first adjustment parameter corresponding to the deformation judgment image; according to the first adjustment parameter, lowering the first target angle to obtain the adjusted first target angle.

[0094] When the first target angle is lowered, the current used to adjust the angle of the clamp is reduced, and a smaller clamping force is used for clamping. The reason for this adjustment is that when the target object clamped by the clamp can be divided into easily deformed types and non-deformed types, the easily deformed type and the non-deformed type each use different mechanisms for the force applied to the clamp. In this case, the force applied to the clamp by the easily deformed type can interfere with the normal use of the clamp, so by controlling it with a relatively small first target angle, the clamping force can be relatively weak, which can ensure that the clamping force is moderate, so as to clamp the target object more stably. Easily deformable types include but are not limited to cotton, sponge and other types.

[0095] For example, based on the deformation judgment images at different times, it is possible to detect whether the shape of the target object has changed; if so, there is deformation; if not, there is no deformation. It is also possible to detect whether the relative position of the target object and the gripper has changed based on the deformation judgment images at different times; if so, there is deformation; if not, there is no deformation.

[0096] In this embodiment, the target object is deformed, which can indicate that the target object is of the easily deformable type. The force exerted on the clamp by the easily deformable type can affect the driving parameters of the clamp. In this case, by controlling the relatively small first target angle, the clamping force can be made relatively weak, which can ensure that the clamping force is moderate.

[0097] In an exemplary embodiment, the gripper is controlled to grip the target object according to a first target angle corresponding to the gripping type, including: determining, based on a contact image, that the gripping type of the target object belongs to a known type; determining the first target angle based on gripping properties corresponding to the known type to which the target object belongs; and controlling the gripper to grip the target object according to the first target angle.

[0098] The known type is used to represent the clamping type of the contact image, which is contained in the data storage system, and the first target angle of the target object can be obtained through the clamping attribute corresponding to the data storage system. In this case, the corresponding first target angle is carefully analyzed directly based on the clamping attribute corresponding to the known type.

[0099] The clamping attribute of the target object is an attribute related to the clamping force. Optionally, the clamping attribute includes but is not limited to attributes such as shape, texture, and hardness, and the first target angle can be estimated based on these clamping attributes; in this case, there is no need to set a mapping rule for each target object separately, but a universal clamping attribute is used for mapping to ensure processing efficiency. Optionally, the clamping attribute can also be the type information of the target object, and the first target angle corresponding to the type information.

[0100] In some embodiments, based on the contact image, determining that the gripping type of the target object belongs to a known type includes: when the target object matches a feature of a candidate type, determining that the gripping type of the target object belongs to the candidate type, in which case the gripping type of the candidate type belongs to a known type. For example, similarity calculations may be performed based on the features of the target object and the features of a candidate type to obtain similarities between the target object and each candidate type; if there is a target similarity greater than a preset value among the similarities, the gripping type of the target object is set according to the candidate type used to obtain the target similarity.

[0101] For example, when the gripping type of the target object is a known type, the shape, hardness and other information of the object can be retrieved from the database, and then the target object can be gripped by controlling the motor. Since the contact image may have errors or recognition errors, even if the specific content of the gripping category is reflected, the corresponding gripping steps are performed using the corresponding gripping attributes.

[0102] In this embodiment, based on the contact image, it is determined that the clamping type of the target object belongs to a known type; in this case, the specific clamping attributes can be refined to comprehensively analyze the specific attributes; then, based on the clamping attributes corresponding to the known type to which the target object belongs, a multi-dimensional analysis is formed to more accurately determine the first target angle.

[0103] In an exemplary embodiment, the first target angle is adjusted according to the parameter difference between the driving parameters of the gripper and the reference driving parameters to obtain the second target angle, including: when the current driving parameters of the gripper are greater than the reference driving parameters, the first target angle is reduced according to the parameter difference to obtain the second target angle; when the current driving parameters of the gripper are less than the reference driving parameters, the first target angle is increased according to the parameter difference to obtain the second target angle.

[0104] The current driving parameter is the driving parameter at the current moment, which can reflect the clamping force at the current moment. When the current driving parameter is greater than the reference driving parameter, the target object is clamped too tightly, and the first target angle needs to be lowered to achieve clamping; correspondingly, when the current driving parameter is less than the reference driving parameter, the target object is clamped loosely or not clamped, and the first target angle needs to be raised to clamp with a greater combined force.

[0105] Optionally, if the current driving parameter is changed to a preset value, the current driving parameter of the clamp is less than the reference driving parameter.

[0106] In this embodiment, the first target angle is adjusted according to the comparison result between the current driving parameters and the reference driving parameters, and the adjustment direction can be controlled by real-time parameters to ensure the timeliness of the processing, thereby achieving more efficient clamping.

[0107] In an exemplary embodiment, the driving parameters of the clamp include driving parameters at each moment within a preset clamping time period, the previous driving parameters, and the current driving parameters; the parameter difference includes the current parameter difference, the cumulative value of the parameter difference, and the driving parameter change rate. Before determining the parameter difference between the driving parameters of the clamp and the reference driving parameters, the method further includes: determining the current parameter difference according to the difference between the current driving parameters and the reference driving parameters; performing difference processing on the driving parameters at each moment within the preset clamping time period and the reference driving parameters to obtain the parameter differences of the preset clamping time period; accumulating the parameter differences of the preset clamping time period to obtain the cumulative value of the parameter differences; determining the driving parameter change rate based on the difference between the current driving parameters and the reference driving parameters and the difference change rate between the previous driving parameters and the reference driving parameters.

[0108] The preset gripping time period is a preset time length between the current moments, and the preset time length may be calculated from the moment when the gripper grips the target object. The preset gripping time period is used to provide a cumulative error, which helps reflect the steady-state error of the system.

[0109] The current driving parameter is the driving parameter at the current moment, and the previous driving parameter is the driving parameter at the previous moment. The previous moment is the moment before the current moment. The time period between the previous moment and the current moment can be a part of the preset clamping time period.

[0110] The current parameter difference is the difference between the current driving parameter and the reference driving parameter or the processing result of the difference, which is used to reflect the real-time error.

[0111] The parameter differences of the preset clamping time period include the results of difference calculations with the reference driving parameters at each moment in the preset clamping time period. The parameter difference cumulative value is the cumulative sum or multiplication of the parameter differences of the preset clamping time period.

[0112] The difference change rate is the difference between the current drive parameter and the reference drive parameter, and the difference between the previous drive parameter and the reference drive parameter, divided by the time between the previous moment and the current moment after the difference calculation is performed again. The difference change rate is used to indicate the rate of change of the error.

[0113] The driving parameter change rate can be the difference change rate, or a parameter positively correlated with the difference change rate, which can predict the vibration generated by the robot arm for easy regulation. The driving parameter change rate can be the difference between the current driving parameter and the reference driving parameter, and the result of differentiating the difference between the previous driving parameter and the reference driving parameter.

[0114] In this embodiment, the driving parameters of the clamp include three parameter difference dimensions: current parameter difference, cumulative parameter difference, and driving parameter change rate; the current parameter difference can reflect the adjustment direction of the clamping force, the cumulative parameter difference can reflect the corresponding error accumulation, and the driving parameter change rate can predict the change at the next moment; through these three parameter difference dimensions, this process can be controlled more accurately.

[0115] In an exemplary embodiment, the target object is the object to be gripped:

[0116] When clamping an object, the camera will first identify the type of object in the area of ​​the clamping jaws, and make a preliminary judgment on the type of the object through the yolo recognition module. If it is a known object, the shape, hardness and other information related to the object will be retrieved from the database; that is, step 402. Then, the object is clamped by controlling the motor. In the clamping process, first, the motor itself has current during the movement. When the motor reaches the target position, if the object is clamped tightly, the motor detects a relatively large current. If it is not clamped, the motor current is 0. A more appropriate force is adjusted through the feedback of the current and the detection type of the object, so that the clamp is in a state of appropriate tightness, that is, step 404, and step 406.

[0117] If it is an unknown object, the camera will identify the object outline and the contact of the gripper according to the boundary of the object and the contact of the gripper, similar to the above control method. At this time, the camera will identify the object outline and the contact of the gripper, and make an optimal gripping with the motor current, that is, step 502-step 508, and step 406. Through the above method, the robot arm can intelligently grip various objects such as hard wood blocks and soft sponges. The application of this technology enables the robot arm to adaptively grip objects of different shapes and textures without adding additional force sensors, making the gripping action of the robot arm more intelligent.

[0118] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0119] Based on the same inventive concept, the embodiment of the present application also provides a clamping control device for implementing the clamping control method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more clamping control device embodiments provided below can refer to the limitations of the clamping control method above, and will not be repeated here.

[0120] In an exemplary embodiment, Figure 6 As shown, a gripping control device is provided, a mechanical arm, the mechanical arm is provided with a gripper, and the device comprises:

[0121] A detection module 602 is used to obtain a contact image when the gripper contacts the target object, and determine the gripping type of the target object based on the contact image;

[0122] An adjustment module 604 is used to adjust the first target angle to obtain a second target angle according to a parameter difference between a driving parameter of the gripper and a reference driving parameter when controlling the gripper to grip the target object according to a first target angle corresponding to the gripping type;

[0123] The gripping module 606 is configured to control the gripper to grip the target object according to the second target angle.

[0124] In one embodiment, the adjustment module 604 is used to:

[0125] Based on the contact image, determining that the gripping type of the target object belongs to an unknown type, and based on preset parameters corresponding to the unknown type, determining a first target angle; according to the first target angle, controlling the gripper to grip the target object; according to the first target angle, controlling the gripper to grip the target object;

[0126] Correspondingly, the adjustment module 604 is used to:

[0127] When the gripping type is an unknown type, capturing images of the gripper and the target object to obtain a deformation judgment image;

[0128] adjusting the first target angle according to the adjustment parameter corresponding to the deformation judgment image to obtain an adjusted first target angle;

[0129] According to the parameter difference between the driving parameter of the clamping jaw and the reference driving parameter, the adjusted first target angle is adjusted to obtain a second target angle.

[0130] In one embodiment, the adjustment module 604 is used to:

[0131] When the deformation judgment image indicates that the target object is deformed, determining a first adjustment parameter corresponding to the deformation judgment image;

[0132] According to the first adjustment parameter, the first target angle is adjusted lower to obtain an adjusted first target angle.

[0133] In one embodiment, the adjustment module 604 is used to:

[0134] Based on the contact image, determining that the gripping type of the target object belongs to a known type;

[0135] Determining a first target angle based on a gripping property corresponding to a known type to which the target object belongs;

[0136] The gripper is controlled to grip the target object according to the first target angle.

[0137] In one embodiment, the adjustment module 604 is used to:

[0138] When the current driving parameter of the gripper is greater than the reference driving parameter, the first target angle is reduced according to the parameter difference to obtain a second target angle;

[0139] When the current driving parameter of the gripper is less than the reference driving parameter, the first target angle is increased according to the parameter difference to obtain a second target angle.

[0140] In one embodiment, the driving parameters of the clamp include the driving parameters at each moment in a preset clamping time period, the previous driving parameters, and the current driving parameters; the parameter difference includes the current parameter difference, the cumulative value of the parameter difference, and the driving parameter change rate;

[0141] Before the adjustment of the parameter difference between the driving parameter of the clamp and the reference driving parameter, the adjustment module 604 is further used to:

[0142] Determining the current parameter difference according to the difference between the current driving parameter and the reference driving parameter;

[0143] Perform difference processing on the driving parameters at each moment in the preset clamping time period and the reference driving parameters to obtain the parameter difference values ​​of the preset clamping time period; perform accumulation on the parameter difference values ​​of the preset clamping time period to obtain the parameter difference accumulation value;

[0144] The driving parameter change rate is determined based on the difference between the current driving parameter and the reference driving parameter, and the difference change rate between the difference between the previous driving parameter and the reference driving parameter.

[0145] Each module in the above-mentioned gripping control device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0146] In an exemplary embodiment, a computer device is provided, wherein a processor of the computer device is used to execute the clamping control method. The internal structure diagram of the computer device can be as follows: Figure 7 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external robotic arm in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a gripping control method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0147] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0148] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0149] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0150] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0151] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0152] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0153] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0154] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A clamping control method, characterized in that: Applied to a robotic arm, the robotic arm being provided with a gripper, the method comprising: Acquire a contact image when the clamping claw contacts the target object, and determine a clamping type of the target object based on the contact image; When the gripper is controlled to grip the target object according to a first target angle corresponding to the gripping type, the first target angle is adjusted according to a parameter difference between a driving parameter of the gripper and a reference driving parameter to obtain a second target angle; According to the second target angle, the gripper is controlled to grip the target object.

2. The method according to claim 1, characterized in that The controlling the gripper to grip the target object according to the first target angle corresponding to the gripping type includes: Based on the contact image, determining that the gripping type of the target object belongs to an unknown type, and based on preset parameters corresponding to the unknown type, determining a first target angle; and controlling the gripper to grip the target object according to the first target angle; The adjusting the first target angle according to the parameter difference between the driving parameter of the clamp and the reference driving parameter to obtain the second target angle comprises: When the gripping type is an unknown type, capturing images of the gripper and the target object to obtain a deformation judgment image; adjusting the first target angle according to the adjustment parameter corresponding to the deformation judgment image to obtain an adjusted first target angle; According to the parameter difference between the driving parameter of the clamping jaw and the reference driving parameter, the adjusted first target angle is adjusted to obtain a second target angle.

3. The method according to claim 2, characterized in that The adjusting the first target angle according to the adjustment parameter corresponding to the deformation judgment image to obtain the adjusted first target angle includes: When the deformation judgment image indicates that the target object is deformed, determining a first adjustment parameter corresponding to the deformation judgment image; According to the first adjustment parameter, the first target angle is adjusted lower to obtain an adjusted first target angle.

4. The method according to claim 1, characterized in that: The controlling the gripper to grip the target object according to the first target angle corresponding to the gripping type includes: Based on the contact image, determining that the gripping type of the target object belongs to a known type; Determining a first target angle based on a gripping property corresponding to a known type to which the target object belongs; The gripper is controlled to grip the target object according to the first target angle.

5. The method according to claim 1, characterized in that The adjusting the first target angle according to the parameter difference between the driving parameter of the clamp and the reference driving parameter to obtain the second target angle comprises: When the current driving parameter of the gripper is greater than the reference driving parameter, the first target angle is reduced according to the parameter difference to obtain a second target angle; When the current driving parameter of the gripper is less than the reference driving parameter, the first target angle is increased according to the parameter difference to obtain a second target angle.

6. The method according to claim 1, characterized in that The driving parameters of the clamping jaws include the driving parameters at each moment within the preset clamping time period, the previous driving parameters, and the current driving parameters; the parameter difference includes the current parameter difference, the cumulative value of the parameter difference, and the driving parameter change rate; Before the parameter difference between the driving parameter of the clamp and the reference driving parameter, the method further comprises: Determining the current parameter difference according to the difference between the current driving parameter and the reference driving parameter; Perform difference processing on the driving parameters at each moment in the preset clamping time period and the reference driving parameters to obtain the parameter difference values ​​of the preset clamping time period; perform accumulation on the parameter difference values ​​of the preset clamping time period to obtain the parameter difference accumulation value; The driving parameter change rate is determined based on the difference between the current driving parameter and the reference driving parameter, and the difference change rate between the difference between the previous driving parameter and the reference driving parameter.

7. A clamping control device, characterized in that: Applied to a mechanical arm, the mechanical arm is provided with a gripper, the device comprises: a detection module, configured to obtain a contact image when the clamping claw contacts a target object, and determine a clamping type of the target object based on the contact image; an adjustment module, configured to adjust the first target angle to obtain a second target angle according to a parameter difference between a driving parameter of the clamp and a reference driving parameter when controlling the clamp to clamp the target object according to a first target angle corresponding to the clamp type; The gripping module is used to control the gripper to grip the target object according to the second target angle.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images