Gripping force correction method, device, equipment and medium applied to robot
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
- Filing Date
- 2023-12-11
- Publication Date
- 2026-06-23
Smart Images
Figure CN117621065B_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present invention relate to the field of automatic control technology, and in particular to a method, device, equipment and medium for correcting the gripping force of a robotic arm. Background Technology
[0002] With the continuous development of automated equipment, the demand for replacing human hands in various scenarios is also increasing, which has led to the continuous development of various humanoid five-fingered dexterous hands.
[0003] As a device that closely resembles the human hand, the humanoid five-fingered dexterous hand has a relatively complex mechanical structure and is capable of performing more complex tasks similar to those performed by the human hand. To ensure the effectiveness of the humanoid five-fingered dexterous hand, the design of the five-finger gripping strategy (i.e., the strategy for correcting the gripping force of the five fingers) is crucial.
[0004] However, the current grip strength correction scheme is not effective and needs improvement. Summary of the Invention
[0005] This invention provides a method, device, equipment, and medium for correcting the gripping force of a robotic arm, so as to control the robotic arm to grip the target object without damaging it.
[0006] According to one aspect of the present invention, a method for correcting the gripping force of a robotic arm is provided, which may include:
[0007] For a target object being grasped by a robotic arm, detect the surface strain force generated on the surface of the target object due to the robotic arm grasping the target object;
[0008] Obtain the critical strain force, where the critical strain force is the strain force generated on the surface of the target object by the critical gripping force that critically damages the target object;
[0009] Based on the surface strain and critical strain, if the applied gripping force of the robot arm on the target object needs to be adjusted, the applied gripping force is adjusted to obtain the target gripping force, so as to control the robot arm to grip the target object based on the target gripping force.
[0010] According to another aspect of the present invention, a gripping force correction device for a robotic arm is provided, which may include:
[0011] The surface strain detection module is used to detect the surface strain generated on the surface of the target object due to the robotic arm gripping the target object.
[0012] The critical strain force acquisition module is used to acquire the critical strain force, wherein the critical strain force is the strain force generated on the surface of the target object by the critical gripping force that causes critical damage to the target object;
[0013] The gripping force correction module is used to correct the applied gripping force when it is determined that the gripping force applied by the robot arm to the target object needs to be corrected based on the surface strain force and critical strain force, so as to obtain the target gripping force and control the robot arm to grip the target object based on the target gripping force.
[0014] According to another aspect of the present invention, an electronic device is provided, which may include:
[0015] At least one processor; and
[0016] A memory that is communicatively connected to at least one processor; wherein,
[0017] The memory stores a computer program that can be executed by at least one processor, such that when the at least one processor executes the program, it implements the grip strength correction method for robotic arms provided in any embodiment of the present invention.
[0018] According to another aspect of the present invention, a computer-readable storage medium is provided having computer instructions stored thereon for causing a processor to execute and implement the gripping force correction method for a robotic arm provided in any embodiment of the present invention.
[0019] The technical solution of this invention addresses a target object being grasped by a robotic arm. It detects the surface strain force generated on the target object's surface due to the robotic arm's grasp; obtains the critical gripping force at which the target object is at risk of damage, and the critical strain force generated on the target object's surface; and, based on the surface strain force and the critical strain force, determines that the applied gripping force needs to be adjusted, thereby obtaining a target gripping force. This allows the robotic arm to grasp the target object based on the target gripping force. By detecting the surface strain force on the target object's surface and comparing it with the critical strain force, this technical solution can determine whether the current gripping force applied by the robotic arm will damage the target object. If so, it adjusts the applied gripping force to ensure the robotic arm can grasp the target object without damaging it, thus guaranteeing the safety of the target object.
[0020] It should be understood that the description in this section is not intended to identify key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description
[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0022] Figure 1 This is a flowchart of a gripping force correction method for a robotic arm according to an embodiment of the present invention;
[0023] Figure 2 This is a schematic diagram illustrating an example of force closed-loop control in a gripping force correction method for a robotic arm according to an embodiment of the present invention;
[0024] Figure 3 This is a flowchart of another method for correcting the gripping force of a robotic arm according to an embodiment of the present invention;
[0025] Figure 4 This is a flowchart of another method for correcting the gripping force of a robotic arm according to an embodiment of the present invention;
[0026] Figure 5 This is a schematic diagram illustrating an example of target size calculation in another method for correcting the gripping force of a robotic arm, provided by an embodiment of the present invention.
[0027] Figure 6 This is a schematic diagram of a proportional-derivative control example in another gripping force correction method for a robotic arm provided by an embodiment of the present invention;
[0028] Figure 7a This is a schematic diagram of another optional example of a gripping force correction method for a robotic arm provided by an embodiment of the present invention;
[0029] Figure 7b This is a flowchart of an optional example of a gripping force correction method for a robotic arm provided by an embodiment of the present invention;
[0030] Figure 8 This is a structural block diagram of a gripping force correction device for a robotic arm provided according to an embodiment of the present invention;
[0031] Figure 9 This is a schematic diagram of the structure of an electronic device that implements the gripping force correction method for a robotic arm according to an embodiment of the present invention. Detailed Implementation
[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. The same applies to "target," "original," etc., and will not be repeated here. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0034] Figure 1 This is a flowchart illustrating a method for correcting the gripping force of a robotic arm, as provided in this embodiment of the invention. This embodiment can be applied to correct the gripping force exerted by a robotic arm on a target object to prevent damage. This method can be executed by a gripping force correction device for a robotic arm provided in this embodiment of the invention. This device can be implemented in software and / or hardware and can be integrated into an electronic device, which can be various user terminals or servers.
[0035] See Figure 1 The method of this invention specifically includes the following steps:
[0036] S110. For a target object being grasped by a robotic arm, detect the surface strain force generated on the surface of the target object due to the robotic arm grasping the target object.
[0037] In this invention, a robotic arm can be understood as an automated operating device capable of mimicking certain movements and functions of a human hand and arm to grasp and move objects. In this embodiment, it may be, for example, a humanoid five-fingered dexterous hand or a two-fingered robotic arm, depending on the specific circumstances, and is not specifically limited here. The target object can be understood as the object currently being grasped by the robotic arm, i.e., the robotic arm has already grasped the target object.
[0038] It should be noted that the surface of the target object (i.e., the surface of the target object) will generate strain due to the gripping of the robotic arm (or the gripping force applied by the robotic arm to the target object). In this embodiment of the invention, in order to distinguish it from the gripping forces and strain forces in subsequent steps, the gripping force applied by the robotic arm to the target object can be referred to as the applied gripping force, and the strain force generated on the surface of the target object due to the applied gripping force can be referred to as the surface strain force.
[0039] Detecting surface strain. Considering the potential application scenarios of this invention, optionally, a non-contact full-field strain measurement system (VIC-3D) can be used to detect surface strain. VIC-3D is a powerful, visualized strain and motion measurement system capable of measuring full-field displacement, strain, and amplitude, and its measurement is not limited to a single point, allowing for observation across the entire range.
[0040] S120. Obtain the critical strain force, wherein the critical strain force is the strain force generated on the surface of the target object by the critical gripping force that causes critical damage to the target object.
[0041] Critical gripping force can be understood as the gripping force that is just enough to damage the target object. Critical strain force can be understood as the strain force generated on the surface of the target object when the critical gripping force is applied. In practical applications, the critical strain force can optionally be obtained through experimental pre-measurement.
[0042] Obtain the critical strain force.
[0043] S130. If it is determined that the applied gripping force of the robot arm on the target object needs to be modified based on the surface strain force and the critical strain force, the applied gripping force is modified to obtain the target gripping force, so as to control the robot arm to grip the target object based on the target gripping force.
[0044] To ensure that the robotic arm does not damage the target object during grasping, the need to adjust the applied gripping force can be determined based on the surface strain and critical strain. Specifically, the gripping force can be adjusted to determine whether it will damage the target object. For example, if the surface strain is greater than or equal to the critical strain, the applied gripping force will damage the target object, thus requiring adjustment. Another example is when the surface strain is less than the critical strain and the absolute value of the difference between the surface strain and the critical strain is less than or equal to a preset first absolute value threshold (which is infinitely small). This indicates that while the applied gripping force will not damage the target object initially, a slight increase in force will cause damage; therefore, the gripping force needs adjustment to better protect the target object. Of course, other methods can also be used to determine whether the gripping force needs adjustment, which are not specifically limited here.
[0045] If, based on surface strain and critical strain, it is determined that the applied gripping force needs to be adjusted, the applied gripping force can be adjusted to obtain the target gripping force (i.e., the adjusted applied gripping force). Typically, the target gripping force is less than the applied gripping force. Furthermore, the robotic arm is controlled to grip the target object based on the target gripping force to prevent damage to the object.
[0046] The technical solution of this invention addresses a target object being grasped by a robotic arm. It detects the surface strain force generated on the target object's surface due to the robotic arm's grasp; obtains the critical gripping force at which the target object is at risk of damage, and the critical strain force generated on the target object's surface; and, based on the surface strain force and the critical strain force, determines that the applied gripping force needs to be adjusted, thereby obtaining a target gripping force. This allows the robotic arm to grasp the target object based on the target gripping force. By detecting the surface strain force on the target object's surface and comparing it with the critical strain force, this technical solution can determine whether the current gripping force applied by the robotic arm will damage the target object. If so, it adjusts the applied gripping force to ensure the robotic arm can grasp the target object without damaging it, thus guaranteeing the safety of the target object.
[0047] An optional technical solution, the above-mentioned grip strength correction method, further includes:
[0048] Determine the numerical relationship between surface strain and critical strain;
[0049] When the numerical relationship characterizes the surface strain force as being greater than or equal to the critical strain force, it is determined that the gripping force needs to be adjusted.
[0050] Adjust the applied gripping force to obtain the target gripping force, including:
[0051] Determine the first corrected gripping force, and based on the first corrected gripping force, adjust the applied gripping force with the goal of reducing the applied gripping force to obtain the target gripping force.
[0052] The numerical relationship characterizes the numerical relationship between surface strain and critical strain, such as a magnitude relationship, a multiple relationship, or a degree of difference, which depends on the actual situation and is not specifically limited here. The numerical relationship is then determined. Furthermore, if the numerical relationship indicates that the surface strain is greater than or equal to the critical strain, this means that applying a gripping force at this point will damage the target object. Therefore, to ensure the safety of the target object, the applied gripping force needs to be adjusted.
[0053] The first corrected gripping force can be understood as the force applied to correct the applied gripping force due to the target item potentially being damaged or already damaged. The first corrected gripping force is determined. In practical applications, the first corrected gripping force can optionally be a preset corrected gripping force; it can also be a corrected gripping force determined based on factors such as historically applied corrected gripping forces (i.e., historical corrected gripping forces) and / or the initial gripping force; etc. This can be set according to the actual situation and is not specifically limited here.
[0054] Based on the first corrected gripping force, the applied gripping force is corrected with the goal of reducing the applied gripping force to obtain the target gripping force. For example, if the first corrected gripping force is negative, the target gripping force τ can optionally be... h =First Correction Grip Strength τ r + Apply gripping force; alternatively, τ h =τ r +Initial grip strength τ d In this example, τ r Historical adjustments to grip strength; of course, τ can also be determined based on other methods. h No specific limitation is made here. As another example, if the first corrected grip strength is positive, optionally, the target grip strength τ... h =Applied grip strength - First corrected grip strength τ r Alternatively, τ h =Initial grip strength τ d -τ r +, in this example, τ r > Historical adjustments to grip strength; of course, τ can also be determined based on other methods. h No specific limitations are specified here.
[0055] The above technical solution indicates that when the surface strain force is greater than or equal to the critical strain force, the applied gripping force will damage the target item. Therefore, the applied gripping force can be reduced, thereby ensuring the safety of the target item.
[0056] Based on this, the above-mentioned grip strength correction method may optionally include:
[0057] Before the robotic arm grasps the target object, the estimated initial grasping force for the target object is obtained, and the robotic arm is controlled to grasp the target object based on the initial grasping force.
[0058] Determine the first corrective grip strength, including:
[0059] Obtain the historical correction grip force applied when applying the historical correction grip force, and determine the first correction grip force based on the historical correction grip force, the initial grip force, and the first ratio.
[0060] The initial gripping force can be understood as the estimated gripping force that is unlikely to damage the target item. In practical applications, optionally, based on experiments, the corresponding initial gripping force can be estimated for candidate items of different item types, and the mapping relationship between each item type and each initial gripping force can be recorded. In this way, the initial gripping force corresponding to the target item can be obtained based on the item type and the mapping relationship. Furthermore, controlling the robotic arm to grip the target item based on the initial gripping force can avoid the situation where the robotic arm grips the target item with a large initial gripping force, causing damage to the target item, thereby ensuring the safety of the target item.
[0061] In this technical solution, a better target gripping force can be obtained by iteratively correcting the applied gripping force. Based on this, the historical corrected gripping force can be understood as the corrected gripping force applied in the past (i.e., before the current correction). The first ratio can be understood as the ratio applied to correct the applied gripping force due to the target item potentially being damaged or already damaged. A first corrected gripping force is determined based on the historical corrected gripping force, the initial gripping force, and the first ratio. For example, the initial gripping force can be adjusted based on the first ratio, and then the first corrected gripping force can be determined based on the historical corrected gripping force and the adjusted initial gripping force, for example, m >= M, τ. r =τ r -K1τ d K1 > 0, where m is the surface strain force, M is the critical strain force, and τ is the value on the left side of the equation. r It is the first corrective grip strength, τ on the right side of the equals sign. r It is a historical correction of grip strength, K1 is the first ratio, τ dIt is the initial grip strength; for example, the historical corrected grip strength can be adjusted based on a first ratio, and the first corrected grip strength can be determined based on the initial grip strength and the adjusted historical corrected grip strength; and so on, without specific limitations here.
[0062] The above technical solution effectively determines the first corrected gripping force by applying historical corrected gripping force, initial gripping force, and a first ratio.
[0063] Another alternative technical solution involves mounting force sensors and a force controller on the robotic arm to control the robotic arm to grasp the target object based on the target gripping force, including:
[0064] The interaction force between the robotic arm and the target object is obtained by force sensor, and the force difference between the target gripping force and the interaction force is determined.
[0065] The force difference is input into the force controller, which performs proportional-integral-derivative control based on the force difference to output a corresponding gripping force that corresponds to the target gripping force, so that the robot arm can grip the target object based on the corresponding gripping force.
[0066] The robotic arm is equipped with force sensors to detect the interaction force between the robotic arm and the target object. In practical applications, optionally, force sensors can be installed on each finger of the robotic arm to detect the interaction force between each finger and the target object, which helps to ensure the safety of the target object with finer granularity. A force controller is installed on the robotic arm to control the gripping force output by the robotic arm. In this technical solution, this gripping force corresponds to the target gripping force and is therefore referred to as the corresponding gripping force.
[0067] Force sensors detect the interaction force between the robotic arm and the target object, determining the force difference between the target gripping force and the interaction force. This force difference reflects the difference between the actual gripping force applied by the robotic arm to the target object (i.e., the interaction force) and the expected gripping force applied to the target object (i.e., the target gripping force). Furthermore, during the gripping process, to ensure the interaction force stabilizes at the target gripping force—that is, to allow the robotic arm to output a stable corresponding gripping force—the force difference can be input into a force controller. The force controller then performs proportional-integral-derivative (PID) control based on the force difference, outputting a corresponding gripping force that matches the target gripping force, enabling the robotic arm to grip the target object based on this corresponding gripping force.
[0068] The above technical solution, through PID control, can ensure that the robotic arm outputs a stable corresponding gripping force, thereby achieving stable gripping of the target object.
[0069] Based on this, to better understand the various technical solutions described above, specific examples will be provided below for illustrative purposes. For example,... Figure 2 As shown, the target gripping force τ h =First Correction Grip Strength τ r +Initial grip strength τ d First corrected grip strength τ r The initial value is 0. The robot arm is controlled based on τ. h Grasping the target object, specifically using the index finger as an example, involves detecting the interaction force between the index finger and the target object using a force sensor mounted on the index finger, and then calculating τ. h The force difference err(t) between the interaction force with the index finger, i.e., err(t) = τ h - Index finger interaction force; furthermore, using a force controller installed on the index finger, PID closed-loop control is performed based on err(t) to obtain the corresponding gripping force. Control the output τ(t) of the index finger, iterate repeatedly, until the interaction force of the index finger stabilizes at τ. h Where Kp is the proportional coefficient, Ki is the integral coefficient, and Kd is the differential coefficient. The above constitutes the inner loop.
[0070] Meanwhile, based on VIC-3D detection, the surface strain force *m* and relative displacement *Δx* between the robotic arm and the target object are measured. Here, *Δx* is detected to prevent the target object from slipping, which will be explained in detail later. Furthermore, a gripping force correction controller is used, based on... Calculate the first corrected grip strength τ r (K2 is the second ratio), and iterative processes are repeated to ensure stable gripping of the target object without damaging it during the grasping process. This is the outer loop.
[0071] In this example, τ r The update frequency of can be lower than the update frequency of τ(t), i.e., τ r Each update can be performed multiple times to make the interaction force continuously approach the value based on τ. r The determined τ h .
[0072] Figure 3This is a flowchart of another method for correcting the gripping force of a robotic arm, provided in this embodiment of the invention. This embodiment is an optimization based on the above-described technical solutions. Optionally, in this embodiment, the gripping force correction method further includes: if it is determined, based on surface strain and critical strain, that no correction of the applied gripping force is needed, controlling the robotic arm to move, and detecting the relative displacement between the robotic arm and the target object during the movement of the robotic arm; if it is determined, based on the relative displacement, that the applied gripping force needs to be corrected, correcting the applied gripping force to obtain a target gripping force, so as to control the robotic arm to grip the target object based on the target gripping force. The explanations of terms that are the same as or corresponding to those in the above embodiments are not repeated here.
[0073] See Figure 3 The method in this embodiment may specifically include the following steps:
[0074] S210. For a target object being grasped by a robotic arm, detect the surface strain force generated on the surface of the target object due to the robotic arm grasping the target object.
[0075] S220. Obtain the critical strain force, wherein the critical strain force is the strain force generated on the surface of the target object by the critical gripping force that causes critical damage to the target object.
[0076] S230. If it is determined that the applied gripping force of the robot arm on the target object needs to be modified based on the surface strain force and the critical strain force, the applied gripping force is modified to obtain the target gripping force, so as to control the robot arm to grip the target object based on the target gripping force.
[0077] S240. Based on the surface strain force and critical strain force, if it is determined that no correction is needed to the applied gripping force, control the robot arm to move, and detect the relative displacement between the robot arm and the target object during the movement of the robot arm.
[0078] In cases where no adjustment to the applied gripping force is required based on two strain forces, it indicates that the applied gripping force will not damage the target object; that is, there is no need to adjust the applied gripping force to avoid damaging the target object. Based on this, to ensure the robotic arm can stably grip the target object, it can be controlled to move, and during this movement, the relative displacement between the robotic arm and the target object can be detected. This relative displacement reflects whether the robotic arm has firmly grasped the target object.
[0079] S250. If it is determined that the applied gripping force needs to be corrected based on the relative displacement, the applied gripping force is corrected to obtain the target gripping force, so as to control the robot arm to grasp the target object based on the target gripping force.
[0080] As explained above, relative displacement reflects whether the robotic arm has firmly grasped the target object, thus determining whether the gripping force needs to be adjusted based on the relative displacement. For example, when the relative displacement is 0, it indicates that the robotic arm has firmly grasped the target object, so there is no need to adjust the gripping force. When the absolute value of the relative displacement is less than or equal to a preset second absolute value threshold, which is infinitely small, it indicates that although there is some slippage between the robotic arm and the target object, this slippage will not cause the target object to fall off the robotic arm, so there is no need to adjust the gripping force. Of course, the need to adjust the gripping force can also be determined based on other methods in conjunction with the relative displacement, without specific limitations here.
[0081] Based on the relative displacement, if it is determined that the applied gripping force needs to be adjusted, the applied gripping force is adjusted to obtain the target gripping force (i.e., the adjusted applied gripping force). Typically, the target gripping force is greater than the applied gripping force. Furthermore, the robotic arm is controlled to grip the target object based on the target gripping force to secure it, thereby preventing the target object from slipping off the robotic arm.
[0082] The technical solution of this invention embodiment, under the condition that the robotic arm will not damage the target item, can control the robotic arm to move, and detect the relative displacement between the robotic arm and the target item during the movement to determine whether the robotic arm has firmly grasped the target item; if it has not firmly grasped, the gripping force is adjusted to ensure stable gripping of the target item, thereby preventing the target item from falling.
[0083] An optional technical solution, the above-mentioned grip strength correction method, further includes:
[0084] When the relative displacement characterizes the target object slipping relative to the robotic arm, it is determined that the applied gripping force needs to be adjusted.
[0085] Adjusting the applied gripping force to obtain the desired gripping force includes:
[0086] Determine the second corrected gripping force, and based on the second corrected gripping force, adjust the applied gripping force to increase the applied gripping force, thereby obtaining the target gripping force.
[0087] In the case where relative displacement indicates that the target object is slipping off the robotic arm, it means that applying a gripping force at this time may cause the target object to slip. Therefore, in order to prevent the target object from slipping, the applied gripping force needs to be adjusted.
[0088] The second corrected gripping force can be understood as the force applied to adjust the gripping force in case the target object slips. The second corrected gripping force is determined. In practical applications, the second corrected gripping force can optionally be a preset corrected gripping force; it can also be a corrected gripping force determined based on historically applied corrected gripping forces (i.e., historical corrected gripping forces) and / or factors such as relative displacement; etc. This can be set according to the actual situation and is not specifically limited here.
[0089] Based on the second corrected gripping force, the applied gripping force is adjusted to increase the applied gripping force, resulting in the target gripping force. For example, when the second corrected gripping force is a positive number, the target gripping force τ can optionally be... h =Second Corrected Grip Strength τ r + Apply gripping force; alternatively, τ h =τ r +Initial grip strength τ d In this example, τ r > Historical adjustments to grip strength; of course, τ can also be determined based on other methods. h No specific limitation is made here. As another example, when the second corrected grip strength is negative, optionally, the target grip strength τ... h =Applied grip strength - Second modified grip strength τ r Alternatively, τ h =Initial grip strength τ d -τ r +, in this example, τ r Historical adjustments to grip strength; of course, τ can also be determined based on other methods. h No specific limitations are specified here.
[0090] The above technical solution indicates that when the target object slips off the robotic arm due to relative displacement, the applied gripping force is insufficient to hold the target object firmly. Therefore, the applied gripping force should be increased to prevent the target object from slipping off.
[0091] Based on this, optionally, a second corrective grip strength can be determined, including:
[0092] Obtain the historical correction grip force applied when applying the grip force in the historical correction, and determine the second correction grip force based on the historical correction grip force, relative displacement, and second ratio.
[0093] In this technical solution, a better target gripping force can be obtained by iteratively refining the applied gripping force. Based on this, the historical refined gripping force can be understood as the refined gripping force applied in the past (i.e., before the current refinement). The second ratio can be understood as the ratio applied to refine the applied gripping force due to the possibility of the target object slipping. The second refined gripping force is determined based on the historical refined gripping force, relative displacement, and the second ratio. For example, the relative displacement can be adjusted based on the second ratio, and then the second refined gripping force can be determined based on the historical refined gripping force and the adjusted relative displacement, for example, m < M, τ. r =τ r -K2|Δx|K2<0, where m is the surface strain force, M is the critical strain force, and τ is the value on the left side of the equation. r It is the second corrective grip strength, τ on the right side of the equals sign. r K2 is the historical correction grip strength, K2 is the second ratio, and Δx is the relative displacement. For example, the historical correction grip strength can be adjusted based on the second ratio, and then the second correction grip strength can be determined based on the relative displacement and the adjusted historical correction grip strength. And so on, without specific limitations here.
[0094] The above technical solution effectively determines the second corrected gripping force by applying historical correction gripping force, relative displacement, and second ratio.
[0095] Figure 4 This is a flowchart of another gripping force correction method for a robotic arm provided in this embodiment of the invention. This embodiment is an optimization based on the above-mentioned technical solutions. Optionally, in this embodiment, the gripping force correction method further includes: before the robotic arm grips the target object, acquiring images obtained by acquiring a reference object and the target object, and acquiring a reference size of the reference object; analyzing the acquired images to obtain the target number of pixels covered by the target object in the acquired images and the reference number of pixels covered by the reference object in the acquired images; obtaining the target size of the target object based on the target number, the reference number, and the reference size, and determining the target opening of the robotic arm based on the target size, so as to control the robotic arm to grip the target object based on the target opening. The explanations of terms that are the same as or corresponding to those in the above embodiments are not repeated here.
[0096] See Figure 4 The method in this embodiment may specifically include the following steps:
[0097] S310. For the target object to be grasped by the robotic arm, acquire images obtained by acquiring reference objects and the target object, and acquire reference dimensions of the reference objects.
[0098] Here, image acquisition can be understood as the acquisition of images of a reference object and a target object located on the same plane using an image acquisition device. The image acquisition device can be, for example, a camera, video camera, or webcam, which can be set according to the actual situation and is not specifically limited here. The reference object can be understood as an object whose actual size is known and used to help determine the actual size of the target object.
[0099] Before the robotic arm grasps the target object, it acquires images and the actual dimensions of a reference object. In this embodiment, to distinguish between the actual dimensions of the reference object and the actual dimensions of the target object, the actual dimensions of the reference object are referred to as the reference dimensions, and the actual dimensions of the target object are referred to as the target dimensions.
[0100] S320. Analyze the acquired image to obtain the target number of pixels covered by the target item in the acquired image and the reference number of pixels covered by the reference item in the acquired image.
[0101] This process involves analyzing the acquired images to determine the target number of pixels covered by the target object and the reference number of pixels covered by the reference object. For example, the target outline of the target object and the reference outline of the reference object can be extracted from the acquired image, and then the target number and the reference number can be determined based on the target outline and the reference outline, respectively. Of course, other methods can also be used to determine the target number and the reference number; no specific limitations are made here.
[0102] S330. Based on the target quantity, reference quantity, and reference size, obtain the target size of the target item, and based on the target size, determine the target opening of the robotic arm, so as to control the robotic arm to grasp the target item based on the target opening.
[0103] The target size is obtained based on the target quantity, reference quantity, and reference size. For example, see [link to example]. Figure 5 The coin is the reference item, with actual dimensions of 0.9 inches (in) * 1.0 inch (in). In practical applications, either 0.9 in or 1.0 in can be chosen as the reference size. The pill is the target item. The conversion ratio K3 is calculated based on the reference quantity N1 and the reference size L1 (e.g., 0.9 in or 1.0 in), where... This represents that each inch corresponds to K3 pixels in the acquired image, which can then be based on... The target size L2 is obtained, where N2 represents the number of targets.
[0104] Furthermore, before the robotic arm grasps the current object, the target opening angle of the robotic arm can be determined based on the target size, and then the robotic arm can be controlled to open to that target opening angle. In this way, the robotic arm can grasp the target object precisely based on the target opening angle, eliminating the need to adjust its opening angle according to the shape of the target object when grasping it, thereby shortening the grasping time and improving the grasping efficiency.
[0105] S340. Detect the surface strain force generated on the surface of the target object due to the robotic arm gripping the target object.
[0106] S350. Obtain the critical strain force, wherein the critical strain force is the strain force generated on the surface of the target object by the critical gripping force that causes critical damage to the target object.
[0107] S360. If it is determined that the applied gripping force of the robot arm on the target object needs to be adjusted based on the surface strain force and the critical strain force, the applied gripping force is adjusted to obtain the target gripping force, so as to control the robot arm to grip the target object based on the target gripping force.
[0108] The technical solution of this invention uses image recognition to determine the target size of the target item based on the reference size of the reference item, and then controls the robotic arm to open to the target size to assist the robotic arm in grasping the target item, thereby improving the grasping efficiency.
[0109] An alternative technical solution involves a position controller mounted on the robotic arm, and position sensors mounted on each finger of the robotic arm. The aforementioned gripping force correction method further includes:
[0110] Based on the finger positions detected by the position sensors corresponding to each finger, the current opening degree of the robotic arm is determined, and the opening degree difference between the target opening degree and the current opening degree is determined.
[0111] The opening difference is input into the position controller, which then performs proportional-derivative control based on the opening difference. Position commands are output to each finger to control the movement of each finger, so that the robotic arm opens to the target opening.
[0112] The robotic arm is equipped with a position controller, which sends position commands to each finger to move it to its corresponding position. Each finger is also equipped with a position sensor to detect its absolute position.
[0113] For each finger of the robotic arm, its position can be detected using a position sensor mounted on that finger. Then, based on the position of each finger, the current opening degree of the robotic arm is determined. Furthermore, to open the robotic arm to a target opening degree, the difference between the target and current opening degrees can be determined. This difference is then input into a position controller, which performs proportional-differential (PD) control based on the opening difference to output position commands to each finger, controlling their movement so that the robotic arm opens to the target opening degree.
[0114] For example, see Figure 6 The robot arm detects the finger positions using position sensors installed on each finger, determines the current opening degree based on this, and calculates the opening difference e(t) between the target opening degree and the current opening degree. Then, e(t) is input to the position controller, which, based on the formula... PD control is performed (Kp is the proportional coefficient and Kd is the derivative coefficient) to obtain u(t), and position commands are sent to each finger based on u(t) so that the robot arm opens to the target opening degree.
[0115] The above technical solution, through the cooperation of position sensors, position controllers and PD control, achieves precise control of finger position, thereby assisting the robotic arm to open to the target opening degree.
[0116] To better understand the various technical solutions described above, specific examples are provided below for illustration. For examples, see [link to example]. Figure 7a Image acquisition equipment is used to acquire images to calculate the target size of the target object, and then the humanoid five-fingered dexterous hand (hereinafter referred to as the dexterous hand) is controlled to grasp the target object based on the target opening degree corresponding to the target size. It should be noted that the 485 communication shown in the figure is used to send corresponding position commands to each finger during the process of the dexterous hand opening to the target opening degree. After the dexterous hand grasps the target object, a non-contact full-field strain measurement system (VIC-3D) is used to detect the surface strain force and relative displacement, and based on this, the gripping force applied by the dexterous hand to the target object is adjusted. This allows the dexterous hand to be controlled to use an appropriate gripping force to grasp the target object, so as not to damage the target object and to firmly grasp it.
[0117] For another example, see Figure 7bThe process involves acquiring images of a target object and a reference object located on the same plane, obtaining acquired images; extracting the target contour of the target object and the reference contour of the reference object from the acquired images; calculating the conversion ratio based on the reference size of the reference object and the reference number of pixels enclosed by the reference contour; calculating the target size of the target object based on the conversion ratio and the target number of pixels enclosed by the target contour, thus obtaining the target opening; sending position commands to each finger of the dexterous hand based on the finger position of each finger, so that the dexterous hand opens to the target opening, and then grasping the target object based on the initial gripping force, which is the applied gripping force of the dexterous hand on the target object.
[0118] Based on this, further determine if the surface strain of the target object is greater than or equal to the critical strain. If so, reduce the applied gripping force and control the dexterous hand to grasp the target object accordingly. Then, again determine if the surface strain is greater than or equal to the critical strain. This process is repeated until the surface strain is less than the critical strain. In practical applications, optionally, if the surface strain is still greater than or equal to the critical strain after multiple reductions in the applied gripping force, this can be addressed by adjusting the first ratio to quickly reduce the applied gripping force.
[0119] When the surface strain is less than the critical strain, move the dexterous hand and determine if there is a relative displacement between the dexterous hand and the target object. If so, the target object is successfully grasped; otherwise, increase the applied gripping force and control the dexterous hand to grasp the target object accordingly, then re-determine if the surface strain is greater than or equal to the critical strain, until the target object is successfully grasped. In practical applications, optionally, if increasing the applied gripping force results in the surface strain being greater than or equal to the critical strain, but decreasing the applied gripping force results in relative displacement, the first ratio applied during the decrease in gripping force and / or the second ratio applied during the increase in gripping force can be adjusted to allow the dexterous hand to quickly and firmly grasp the target object without damaging it.
[0120] The above example integrates the grip opening (i.e. target opening), the grip strength of the five fingers, and the surface strain applied to the target object. By taking into account all aspects, it achieves effective gripping of the target object.
[0121] Figure 8 This is a structural block diagram of a gripping force correction device for a robotic arm provided in an embodiment of the present invention. This device is used to execute the gripping force correction method for a robotic arm provided in any of the above embodiments. This device and the gripping force correction methods for robotic arms in the above embodiments belong to the same inventive concept. Details not described in detail in the embodiments of the gripping force correction device for robotic arms can be found in the embodiments of the gripping force correction methods for robotic arms described above. See also... Figure 8Specifically, the device may include: a surface strain detection module 410, a critical strain acquisition module 420, and an applied gripping force correction module 430.
[0122] Among them, the surface strain detection module 410 is used to detect the surface strain generated on the surface of the target object due to the robotic arm grasping the target object.
[0123] The critical strain force acquisition module 420 is used to acquire the critical strain force, wherein the critical strain force is the strain force generated on the surface of the target object by the critical gripping force that causes critical damage to the target object;
[0124] The gripping force correction module 430 is used to correct the applied gripping force when it is determined that the gripping force applied by the robot arm to the target object needs to be corrected based on the surface strain force and the critical strain force, so as to obtain the target gripping force and control the robot arm to grip the target object based on the target gripping force.
[0125] Optionally, the aforementioned grip strength correction device further includes:
[0126] The numerical relationship determination module is used to determine the numerical relationship between surface strain and critical strain.
[0127] The first determination module for applying gripping force correction is used to determine the gripping force that needs to be corrected when the surface strain force, as characterized by numerical relationship, is greater than or equal to the critical strain force.
[0128] The grip strength correction module 430 includes:
[0129] The target grip strength obtaining submodule is used to determine the first corrected grip strength, and based on the first corrected grip strength, to reduce the applied grip strength as the target corrected applied grip strength, thus obtaining the target grip strength.
[0130] Optionally, the aforementioned grip strength correction device may also include:
[0131] The first control module of the robotic arm is used to obtain the estimated initial gripping force for the target object before the robotic arm grasps the target object, and to control the robotic arm to grasp the target object based on the initial gripping force.
[0132] The target grip strength acquisition submodule includes:
[0133] The first corrected grip strength determination unit is used to obtain the historical corrected grip strength applied when the historical corrected grip strength is applied, and to determine the first corrected grip strength based on the historical corrected grip strength, the initial grip strength and the first ratio.
[0134] Optionally, the aforementioned grip strength correction device further includes:
[0135] The relative displacement detection module is used to control the movement of the robotic arm when it is determined that no correction of the applied gripping force is required based on the surface strain force and critical strain force, and to detect the relative displacement between the robotic arm and the target object during the movement of the robotic arm.
[0136] The second control module of the robotic arm is used to adjust the applied gripping force when it is determined that the gripping force needs to be adjusted based on the relative displacement, so as to obtain the target gripping force and control the robotic arm to grasp the target object based on the target gripping force.
[0137] Optionally, the aforementioned grip strength correction device may also include:
[0138] The second determination module for applying gripping force correction is used to determine the gripping force that needs to be corrected when the target object slips relative to the robotic arm due to relative displacement.
[0139] The second control module of the robotic arm includes:
[0140] The target grip strength acquisition submodule is used to determine the second modified grip strength, and based on the second modified grip strength, to modify the applied grip strength with the aim of increasing the applied grip strength, thus obtaining the target grip strength.
[0141] Based on this, an optional submodule for determining the desired grip strength includes:
[0142] The second correction gripping force determination unit is used to obtain the historical correction gripping force applied when the historical correction gripping force is applied, and to determine the second correction gripping force based on the historical correction gripping force, relative displacement, and second ratio.
[0143] Optionally, a force sensor and force controller are installed on the robotic arm to apply a gripping force correction module 430, including:
[0144] The force difference determination unit is used to acquire the interaction force between the robotic arm and the target object detected by the force sensor, and to determine the force difference between the target gripping force and the interaction force.
[0145] The robotic arm control unit is used to input the force difference into the force controller, so that the force controller can perform proportional-integral-derivative control based on the force difference and output the corresponding gripping force corresponding to the target gripping force, so that the robotic arm can grip the target object based on the corresponding gripping force.
[0146] Optionally, the aforementioned grip strength correction device further includes:
[0147] The reference size acquisition module is used to acquire images obtained by acquiring reference objects and target objects, and to acquire reference dimensions of reference objects before the robotic arm grasps the target object.
[0148] The reference quantity acquisition module is used to analyze the acquired image and obtain the target number of pixels covered by the target item in the acquired image and the reference number of pixels covered by the reference item in the acquired image.
[0149] The third control module of the robotic arm is used to obtain the target size of the target item based on the target quantity, reference quantity and reference size, and determine the target opening of the robotic arm based on the target size, so as to control the robotic arm to grasp the target item based on the target opening.
[0150] Optionally, a position controller is installed on the robotic arm, and position sensors are installed on each finger of the robotic arm. The aforementioned gripping force correction device also includes:
[0151] The opening difference determination module is used to determine the current opening of the robot hand based on the finger positions detected by the position sensors corresponding to each finger, and to determine the opening difference between the target opening and the current opening.
[0152] The fourth control module of the robotic arm is used to input the opening difference to the position controller. The position controller then performs proportional-derivative control based on the opening difference, outputting position commands to each finger to control the movement of each finger, so that the robotic arm opens to the target opening degree.
[0153] The gripping force correction device for robotic arms provided in this invention uses a surface strain detection module to detect the surface strain generated on the surface of a target object being gripped by the robotic arm; a critical strain acquisition module to acquire the critical gripping force at which the target object is at risk of damage; and a gripping force correction module to adjust the gripping force applied by the robotic arm to the target object based on the surface strain and critical strain, thus obtaining a target gripping force to control the robotic arm to grip the target object based on the target gripping force. This device, by detecting the surface strain of the target object and comparing it with the critical strain, can determine whether the current gripping force applied by the robotic arm will damage the target object. If so, it adjusts the gripping force to ensure the robotic arm grips the target object without damaging it, thereby guaranteeing the safety of the target object.
[0154] The gripping force correction device for robotic arms provided in this embodiment of the invention can execute the gripping force correction method for robotic arms provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.
[0155] It is worth noting that in the above embodiments of the gripping force correction device applied to robotic arms, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.
[0156] Figure 9 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.
[0157] like Figure 9 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0158] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0159] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the gripping force correction method applied to a robotic hand.
[0160] In some embodiments, the grip strength correction method for a robotic arm can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the grip strength correction method for a robotic arm described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the grip strength correction method for a robotic arm by any other suitable means (e.g., by means of firmware).
[0161] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0162] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0163] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0164] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0165] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.
[0166] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.
[0167] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.
[0168] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.
Claims
1. A method for correcting the gripping force of a robotic arm, characterized in that, include: The system obtains the estimated initial gripping force for the target item, controls the robotic arm to grip the target item based on the initial gripping force, and detects the surface strain force generated on the surface of the target item due to the robotic arm gripping the target item. Obtain the critical strain force, wherein the critical strain force is the strain force generated on the surface of the target item by the critical gripping force that would cause critical damage to the target item; If it is determined that the gripping force applied by the robotic arm to the target item needs to be corrected based on the surface strain being greater than or equal to the critical strain, the historical corrected gripping force applied when correcting the applied gripping force is obtained. Based on the historical corrected gripping force, the initial gripping force, and the first ratio, a first corrected gripping force is determined. Based on the first corrected gripping force, the applied gripping force is corrected with the goal of reducing the applied gripping force to obtain a target gripping force, so as to control the robotic arm to grip the target item based on the target gripping force.
2. The method according to claim 1, characterized in that, Also includes: Based on the surface strain and the critical strain, if it is determined that no correction is needed to the applied gripping force, the robotic arm is controlled to move, and the relative displacement between the robotic arm and the target object is detected during the movement of the robotic arm. If it is determined that the applied gripping force needs to be corrected based on the relative displacement, the applied gripping force is corrected to obtain the target gripping force, so as to control the robotic arm to grasp the target item based on the target gripping force.
3. The method according to claim 2, characterized in that, Also includes: When the relative displacement indicates that the target item has slipped relative to the robotic arm, it is determined that the applied gripping force needs to be adjusted. The modification of the applied gripping force to obtain the target gripping force includes: A second corrected gripping force is determined, and based on the second corrected gripping force, the applied gripping force is modified to increase the applied gripping force, thereby obtaining the target gripping force.
4. The method according to claim 3, characterized in that, Determining the second corrected grip strength includes: Obtain the historically corrected grip force applied when the grip force is applied in the historical correction, and determine the second corrected grip force based on the historically corrected grip force, the relative displacement, and the second ratio.
5. The method according to claim 1, characterized in that, The robotic arm is equipped with a force sensor and a force controller. Controlling the robotic arm to grasp the target object based on the target gripping force includes: The interaction force between the robotic arm and the target object detected by the force sensor is obtained, and the force difference between the target gripping force and the interaction force is determined. The force difference is input into the force controller so that the force controller can perform proportional-integral-derivative control based on the force difference and output a corresponding gripping force corresponding to the target gripping force, so that the robotic arm can grip the target object based on the corresponding gripping force.
6. The method according to claim 1, characterized in that, Also includes: Before the robotic arm grasps the target object, acquire images obtained by capturing a reference object and the target object, and acquire reference dimensions of the reference object; Analyze the acquired image to obtain the target number of pixels covered by the target item in the acquired image and the reference number of pixels covered by the reference item in the acquired image; Based on the target quantity, the reference quantity, and the reference size, the target size of the target item is obtained, and based on the target size, the target opening of the robotic arm is determined so as to control the robotic arm to grasp the target item based on the target opening.
7. The method according to claim 6, characterized in that, The robotic arm is equipped with a position controller, and each finger of the robotic arm is equipped with a position sensor. The method further includes: Based on the finger positions detected by the position sensors corresponding to each finger, the current opening degree of the robotic hand is determined, and the opening degree difference between the target opening degree and the current opening degree is determined. The opening difference is input to the position controller, which then performs proportional-derivative control based on the opening difference to output position commands to each finger to control the movement of each finger, so that the robotic arm opens to the target opening.
8. A gripping force correction device for use in robotic arms, characterized in that, include: The first control module of the robotic arm is used to obtain the estimated initial gripping force for the target object, and control the robotic arm to grip the target object based on the initial gripping force; A surface strain detection module is used to detect the surface strain generated on the surface of the target object due to the robotic arm gripping the target object; A critical strain force acquisition module is used to acquire critical strain force, wherein the critical strain force is the strain force generated on the surface of the target object by the critical gripping force that would cause critical damage to the target object; The gripping force correction module is used to correct the applied gripping force when it is determined that the gripping force applied by the robot arm to the target item needs to be corrected based on the surface strain force and the critical strain force, so as to obtain the target gripping force and control the robot arm to grip the target item based on the target gripping force. The grip strength correction device further includes: A numerical relationship determination module is used to determine the numerical relationship between the surface strain force and the critical strain force; The first determination module for applying gripping force correction is used to determine that the applied gripping force needs to be corrected when the numerical relationship characterizes that the surface strain is greater than or equal to the critical strain. The applied grip strength correction module includes: The target grip strength obtaining submodule is used to obtain the historically corrected grip strength applied when the applied grip strength is historically corrected, to determine a first corrected grip strength based on the historically corrected grip strength, the initial grip strength and a first ratio, and to correct the applied grip strength based on the first corrected grip strength with the goal of reducing the applied grip strength, so as to obtain the target grip strength.
9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to cause the at least one processor to perform the grip strength correction method for a robotic arm as described in any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the gripping force correction method for a robotic arm as described in any one of claims 1-7.