Mechanical arm control method and device applied to mechanical arm and computer readable medium
By dynamically adjusting the admission control parameters, the problem of poor force control of the robotic arm in high-rigid environments is solved, and the smooth contact and precise force control in different environments is achieved, which improves the versatility and stability of the application.
Patent Information
- Application Number
- CN202411444539.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-16
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-10-16
AI Technical Summary
When facing an uncertain external environment, especially in high stiffness environments, it is difficult to achieve precise force control, which can easily lead to force sudden changes and system oscillation, affecting the versatility and stability of its application.
By obtaining the initial admission control parameters of the robot arm, collecting images of the items to be polished, generating space information of the items to be polished, monitoring contact force and position information in real time, dynamically adjusting the admission control parameters to generate target admission control parameters, and ensuring that the robot arm is in Maintain a stable overdamping state in different environments to avoid oscillation.
It realizes smooth contact and precise force control of the robotic arm in different stiffness environments, avoids sudden force changes and system oscillation, and improves the application versatility and stability of the robotic arm.
Smart Images

Figure CN119017391A_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present disclosure relate to the field of computer technology, and more particularly to a robot arm control method, device, and computer-readable medium applied to a robot arm. Background Art
[0002] With the development of robotics technology, the application of robotic arms in the field of manufacturing has become increasingly widespread, for example, automated object polishing based on robotic arms. At present, when a robotic arm interacts with the external environment, the usual approach is to assume that the stiffness of the external environment is known, and based on this assumption, calculate appropriate admittance control parameters to achieve the dynamic response of the robotic arm in a specific scenario.
[0003] However, the inventors have found that when the above method is adopted, the following technical problems often occur:
[0004] It has poor versatility when facing various uncertain external environments and cannot adapt to complex situations in practical applications. For example, when it comes into contact with a high-rigidity environment, it is easy to cause sudden force changes, resulting in system oscillations, which makes it impossible for the robotic arm to perform precise force control.
[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention
[0006] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.
[0007] Some embodiments of the present disclosure propose a robot arm control method, an apparatus, and a computer-readable medium applied to a robot arm to solve one or more of the technical problems mentioned in the above background technology section.
[0008] In a first aspect, some embodiments of the present disclosure provide a robot arm control method applied to a robot arm, the method comprising: obtaining initial admittance control parameters of the robot arm, wherein the robot arm comprises: a camera device, a sensor data acquisition device and a polishing device, and the initial admittance control parameters comprise: initial mass, initial damping coefficient and initial environmental stiffness. The image of the object to be polished is collected by the camera device, wherein the camera device is placed toward the position of the object to be polished when the robot arm is in an unloaded state. The spatial information of the object to be polished is generated by a pre-trained spatial information generation model and the image of the object to be polished, wherein the image of the object to be polished contains the object to be polished. According to the initial admittance control parameters and the sensor data acquisition device, the real-time contact force value of the robot arm, the real-time speed of the robot arm and the real-time position information of the robot arm are determined, wherein the real-time contact force value of the robot arm represents the real-time force magnitude of the robot arm contacting the surface of the object to be polished when polishing. According to the real-time contact force value of the robot arm, the target environmental stiffness is generated. According to the target environmental stiffness, a target admittance control parameter that satisfies the contact force control stability condition is generated, wherein the target admittance control parameter includes: a target damping coefficient and a target mass. According to the initial admittance control parameter, the target admittance control parameter, the real-time speed of the robot arm, the real-time position information of the robot arm, and the real-time contact force value of the robot arm, the desired speed information of the robot arm is generated. According to the desired speed information of the robot arm and the spatial information of the object to be polished, the polishing device included in the robot arm is controlled to polish the object to be polished.
[0009] In a second aspect, some embodiments of the present disclosure provide a robot arm control device applied to a robot arm, the device comprising: an acquisition unit, configured to acquire initial admittance control parameters of the robot arm, wherein the robot arm comprises: a camera device, a sensor data acquisition device and a polishing device, and the initial admittance control parameters include: initial mass, initial damping coefficient and initial environmental stiffness. The acquisition unit is configured to acquire an image of the object to be polished through the camera device, wherein the camera device is placed toward the position of the object to be polished when the robot arm is in an unloaded state. The first generation unit is configured to generate spatial information of the object to be polished through a pre-trained spatial information generation model and the image of the object to be polished, wherein the image of the object to be polished contains the object to be polished. The determination unit is configured to determine the real-time contact force value of the robot arm, the real-time speed of the robot arm and the real-time position information of the robot arm according to the initial admittance control parameters and the sensor data acquisition device, wherein the real-time contact force value of the robot arm represents the real-time force magnitude of the robot arm contacting the surface of the object to be polished when polishing. The second generating unit is configured to generate a target environmental stiffness according to the real-time contact force value of the above-mentioned robot arm. The third generating unit is configured to generate a target admittance control parameter that satisfies the contact force control stability condition according to the above-mentioned target environmental stiffness, wherein the above-mentioned target admittance control parameter includes: a target damping coefficient and a target mass. The fourth generating unit is configured to generate the robot arm expected speed information according to the above-mentioned initial admittance control parameter, the above-mentioned target admittance control parameter, the above-mentioned robot arm real-time speed, the above-mentioned robot arm real-time position information and the above-mentioned robot arm real-time contact force value. The control unit is configured to control the polishing device included in the above-mentioned robot arm according to the above-mentioned robot arm expected speed information and the above-mentioned space information of the object to be polished, so as to polish the above-mentioned object to be polished.
[0010] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.
[0011] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.
[0012] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the robot arm control method applied to the robot arm of some embodiments of the present disclosure, by dynamically adjusting the admittance control parameters, the generation of oscillation is avoided, and more accurate force control is achieved. Specifically, the reason for the oscillation is that the existing technology has poor versatility when facing various uncertain external environments, and cannot adapt to the complex situations in practical applications. For example, when contacting a high-rigidity environment, it is easy to cause a sudden change in force, thereby generating system oscillation, making it impossible for the robot arm to perform accurate force control. Based on this, the robot arm control method applied to the robot arm of some embodiments of the present disclosure, first, obtain the initial admittance control parameters of the robot arm, wherein the above-mentioned robot arm includes: a camera device, a sensor data acquisition device and a grinding device, and the above-mentioned initial admittance control parameters include: initial mass, initial damping coefficient and initial environmental stiffness. Secondly, the image of the object to be polished is collected by the above-mentioned camera device, wherein the above-mentioned camera device is facing the position where the object to be polished is placed when the above-mentioned robot arm is in an unloaded state. Then, the spatial information of the object to be polished is generated by the pre-trained spatial information generation model and the above-mentioned image of the object to be polished, wherein the above-mentioned image of the object to be polished contains the object to be polished. During polishing, the position information and shape information of the object to be polished are required to facilitate the subsequent control of the polishing device for polishing. Therefore, the image of the object to be polished is first photographed by a camera device, and then the position and shape are confirmed. Then, according to the above-mentioned initial admittance control parameters and the above-mentioned sensor data acquisition device, the real-time contact force value of the robot arm, the real-time speed of the robot arm and the real-time position information of the robot arm are determined, wherein the real-time contact force value of the robot arm represents the real-time force magnitude of the robot arm contacting the surface of the object to be polished during polishing. Since it is a process for the robot arm to go from never contacting to contacting the external environment, it is necessary to monitor the displacement and contact force changes of the end of the robot arm in real time to estimate the stiffness of the external environment. Further, according to the real-time contact force value of the robot arm, the target environment stiffness is generated. In addition, according to the above-mentioned target environment stiffness, the target admittance control parameters that meet the contact force control stability condition are generated, wherein the above-mentioned target admittance control parameters include: target damping coefficient and target mass. By estimating the stiffness of the external environment, the parameters of the admittance control are dynamically adjusted so that the robot arm can maintain a stable over-damped state after contact. In this way, the robot arm can achieve stable contact in environments with different stiffness, avoiding sudden force changes and system oscillations. Then, according to the above-mentioned initial admittance control parameters, the above-mentioned target admittance control parameters, the above-mentioned robot arm real-time speed, the above-mentioned robot arm real-time position information and the above-mentioned robot arm real-time contact force value, the robot arm expected speed information is generated. Finally, according to the above-mentioned robot arm expected speed information and the above-mentioned space information of the object to be polished, the polishing device included in the above-mentioned robot arm is controlled to polish the above-mentioned object to be polished.In this way, the admittance control parameters are dynamically adjusted to avoid oscillations and ensure that the robot arm can achieve precise force control during contact with the environment. BRIEF DESCRIPTION OF THE DRAWINGS
[0013] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.
[0014] Figure 1 is a flow chart of some embodiments of a robot arm control method applied to a robot arm according to the present disclosure;
[0015] Figure 2 is a schematic structural diagram of some embodiments of a robot arm control device applied to a robot arm according to the present disclosure;
[0016] Figure 3 is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure;
[0017] Figure 4 is a comparison diagram of real-time contact force values of a robotic arm corresponding to different admittance control parameters of a robotic arm control method applied to a robotic arm disclosed in the present invention;
[0018] Figure 5 It is a schematic diagram of an application scenario of a robot arm control method applied to a robot arm according to some embodiments of the present disclosure. DETAILED DESCRIPTION
[0019] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.
[0020] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.
[0021] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.
[0022] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0023] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.
[0024] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.
[0025] refer to Figure 1 , shows a process 100 of some embodiments of a robot arm control method applied to a robot arm according to the present disclosure. The robot arm control method applied to a robot arm comprises the following steps:
[0026] Step 101, obtaining the initial admittance control parameters of the robot arm.
[0027] In some embodiments, the execution subject (for example, a computing device) of the robot control method applied to the robot arm can obtain the initial admittance control parameters of the robot arm by wireless connection, wherein the robot arm includes: a camera device, a sensor data acquisition device and a grinding device, and the initial admittance control parameters include: initial mass, initial damping coefficient and initial environmental stiffness. The initial admittance control parameters are the admittance parameters in the trajectory tracking or speed tracking mode obtained by pre-adjustment. In practice, the initial admittance control parameters are used in the stage before contact when the robot arm approaches an object or a plane. As an example, the camera device can be a wide-angle camera. The sensor data acquisition device includes a first sensor data acquisition device and a second sensor data acquisition device. The first sensor data acquisition device is a device for collecting and monitoring the interaction information between the robot arm and the external environment. In practice, the first sensor data acquisition device can be a contact sensor. As an example, the first sensor data acquisition device can be a pressure sensor. The second sensor data acquisition device is a device for collecting and monitoring the position information of the robot arm. In practice, the second sensor data acquisition device can be a non-contact sensor. As an example, the second sensor data acquisition device may be an encoder sensor. The grinding device represents a tool integrated on a robot arm for grinding an object to be polished. As an example, the grinding device may be a diamond grinding head.
[0028] It should be noted that the above-mentioned wireless connection methods may include but are not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or developed in the future.
[0029] Step 102: Capture an image of the object to be polished by using a camera device.
[0030] In some embodiments, the execution entity may capture images of the object to be polished by means of the camera device, wherein the camera device is directed toward a position where the object to be polished is placed when the robot arm is in an unloaded state.
[0031] In practice, first, the execution subject may shoot a wide-angle image through the camera device, and finally, the execution subject extracts the image of the object to be polished from the captured wide-angle image, thereby obtaining the image of the object to be polished.
[0032] Step 103, generating spatial information of the object to be polished by using a pre-trained spatial information generation model and the image of the object to be polished.
[0033] In some embodiments, the execution subject may generate spatial information of the object to be polished by using a pre-trained spatial information generation model and the image of the object to be polished, wherein the image of the object to be polished contains the object to be polished. The spatial information generation model is a model for generating spatial information of the object to be polished. In practice, the spatial information generation model may be a target detection model. As an example, the spatial information generation model may be a YOLO V5 (YouOnly Look Once Version 5) model. The spatial information of the object to be polished is used to describe the position and shape of the object to be polished.
[0034] In practice, the execution entity may input the image of the object to be polished into the pre-trained spatial information generation model to generate spatial information of the object to be polished.
[0035] Optionally, the above-mentioned spatial information of the object to be polished includes: position information of the object to be polished and shape information of the object to be polished, and the above-mentioned spatial information generation model includes: position information generation model and object shape recognition model. Among them, the above-mentioned position information of the object to be polished is key point information of the object to be polished. As an example, the above-mentioned key point information of the object to be polished represents the three-dimensional coordinates of each vertex of the object to be polished. Among them, the above-mentioned shape information of the object to be polished represents the shape, size and surface characteristics of the object to be polished.
[0036] In some optional implementations of some embodiments, the execution subject generates the spatial information of the object to be polished by using the pre-trained spatial information generation model and the image of the object to be polished, which may include the following steps:
[0037] In the first step, image preprocessing is performed on the above-mentioned image of the object to be polished to obtain the preprocessed image of the object to be polished.
[0038] In practice, the execution subject may perform denoising on the image of the object to be polished to obtain a pre-processed image of the object to be polished.
[0039] In the second step, the image position of the object to be polished in the image of the object to be polished after the preprocessing is determined by using the position information generation model to generate a target image position.
[0040] Wherein, the above-mentioned position information generation model is a model that takes the image of the object to be polished after preprocessing as input and the target image position as output. In practice, the above-mentioned position information generation model can be a target detection model. As an example, the above-mentioned position information generation model can be a Faster R-CNN (Faster Region-based Convolutional Neural Network) model. Wherein, the above-mentioned target image position is the image position of the above-mentioned object to be polished in the image of the object to be polished after the above-mentioned preprocessing. In practice, the above-mentioned target image position can represent the two-dimensional coordinate point of the key point of the object to be polished that is not obstructed in the image pixel coordinate system.
[0041] In practice, the execution entity may input the preprocessed image of the object to be polished into the position information generation model to generate the target image position.
[0042] The third step is to perform spatial position transformation on the above target image position to generate a transformed target image position.
[0043] The position of the target image after the conversion can represent the three-dimensional coordinate point of the key point of the object to be polished that is not blocked in the geodetic coordinate system.
[0044] In practice, the execution subject may perform a spatial position conversion on the target image position from an image pixel coordinate system to a geodetic coordinate system to generate a converted target image position.
[0045] The fourth step is to determine the position of the occluded key point corresponding to the object to be polished according to the position of the target image after the conversion.
[0046] The above-mentioned occluded key point position may be the three-dimensional coordinate of the key point of the occluded object to be polished.
[0047] As an example, the above-mentioned occluded key point positions can be {key point A of the item to be polished (x1, y1, 0); key point B of the item to be polished (x2, y1, 0); key point C of the item to be polished (x1, y1, z1); key point D of the item to be polished (x2, y1, z1); key point E of the item to be polished (x1, y2, z1); key point F of the item to be polished (x2, y2, z1)}. Therefore, the occluded key point positions can be {key point G of the item to be polished (x1, y2, 0); key point H of the item to be polished (x2, y2, 0)}. Among them, the key point G of the item to be polished (x1, y2, 0) = key point E of the item to be polished (x1, y2, z1) - [key point C of the item to be polished (x1, y1, z1) - key point A of the item to be polished (x1, y1, 0)].
[0048] In a fifth step, the target image position and the occluded key point position are determined as the position information of the object to be polished included in the spatial information of the object to be polished.
[0049] In the sixth step, the shape information of the object to be polished included in the spatial information of the object to be polished is generated according to the object shape recognition model and the preprocessed image of the object to be polished.
[0050] The object shape recognition model is a model that takes the preprocessed image of the object to be polished as input and outputs the shape information of the object to be polished. In practice, the object shape recognition model may be a target detection model. As an example, the object shape recognition model may be a YOLO V3 (You Only Look Once Version 3) model.
[0051] In practice, the execution subject may input the preprocessed image of the object to be polished into the object shape recognition model to generate the shape information of the object to be polished included in the spatial information of the object to be polished.
[0052] Step 104, determining the real-time contact force value, real-time speed and real-time position information of the robot arm according to the initial admittance control parameters and the sensor data acquisition device.
[0053] In some embodiments, the execution subject can determine the real-time contact force value, real-time speed and real-time position information of the robot arm according to the initial admittance control parameter and the sensor data acquisition device, wherein the real-time contact force value of the robot arm represents the real-time force of the robot arm in contact with the surface of the object to be polished during polishing. The real-time speed of the robot arm is the real-time speed of the robot arm from the time when the robot arm does not touch the object to the time when the robot arm touches the object to be polished. The real-time position information of the robot arm represents the real-time position of the robot arm in contact with the surface of the object to be polished during polishing.
[0054] In practice, first, the above-mentioned execution entity can obtain the real-time contact force value of the robot arm under the initial admittance control parameters through the first sensor data acquisition device included in the above-mentioned sensor data acquisition device, and then, the above-mentioned execution entity can obtain the real-time speed and real-time position information of the robot arm under the initial admittance control parameters through the second sensor data acquisition device included in the above-mentioned sensor data acquisition device.
[0055] Step 105, generating a target environment stiffness according to the real-time contact force value of the robot arm.
[0056] In some embodiments, the execution subject may generate a target environment stiffness according to the real-time contact force value of the robot arm. The target environment stiffness is calculated by real-time monitoring of the displacement and contact force changes of the robot arm. In practice, the target environment stiffness is determined by the following formula:
[0057]
[0058] Among them, K is the target environment stiffness, F2 is the real-time contact force value of the robot arm at the second moment, F1 is the real-time contact force value of the robot arm at the first moment, x2 is the axis position of the second robot arm, and x1 is the axis position of the first robot arm.
[0059] In practice, the execution subject may use a machine learning algorithm to predict the target environment stiffness based on the real-time contact force value of the robot arm, wherein the machine learning algorithm may be a regression analysis algorithm.
[0060] In some optional implementations of some embodiments, the execution subject generates the target environment stiffness according to the real-time contact force value of the robot arm, which may include the following steps:
[0061] In the first step, in response to determining that the real-time contact force value of the robot arm is greater than the preset contact force value, the following determination steps are performed, wherein the preset contact force value is a pre-set contact force value:
[0062] Sub-step 1: determining the axial position of the first robotic arm corresponding to the real-time contact force value of the robotic arm at the first moment.
[0063] The first moment is the moment when the real-time contact force value of the robot arm is greater than the preset contact force value. The first axial position of the robot arm is the axial position of the robot arm at the first moment.
[0064] In practice, in response to determining that the real-time contact force value of the robotic arm is greater than the preset contact force value, the above-mentioned execution entity can determine the axial position of the first robotic arm corresponding to the real-time contact force value of the robotic arm at the first moment through a sensor data acquisition device.
[0065] Sub-step 2, in response to determining that the real-time contact force value of the robot arm meets a preset condition, determining the axis position of the second robot arm corresponding to the real-time contact force value of the robot arm at a second moment.
[0066] The preset condition is that the expected speed direction obtained by substituting the real-time contact force value of the robot into the trajectory tracking admittance control formula is in the reverse direction. The second moment is the moment when the real-time contact force value of the robot meets the preset condition. The second robot arm axial position is the axial position of the robot arm at the second moment.
[0067] In practice, in response to determining that the real-time contact force value of the robotic arm meets a preset condition, the above-mentioned execution entity can determine the second robotic arm axis position corresponding to the real-time contact force value of the robotic arm at the second moment through a sensor data acquisition device.
[0068] In the second step, the difference between the real-time contact force value of the robot arm at the second moment and the real-time contact force value of the robot arm at the first moment is determined as the contact force difference.
[0069] As an example, the contact force difference may be F2-F1, wherein F2 is the real-time contact force value of the robotic arm at the second moment, and F1 is the real-time contact force value of the robotic arm at the first moment.
[0070] The third step is to determine the difference between the axial position of the second robot arm and the axial position of the first robot arm as the robot arm axial position difference.
[0071] As an example, the difference in the robot arm axis position may be x2-x1, where x2 is the second robot arm axis position and x1 is the first robot arm axis position.
[0072] In the fourth step, the quotient of the contact force difference and the robot arm axis position difference is determined as the target environmental stiffness.
[0073] As an example, the target environment stiffness can be
[0074] Step 106: Generate target admittance control parameters that meet the contact force control stability condition according to the target environment stiffness.
[0075] In some embodiments, the execution subject may generate a target admittance control parameter that satisfies the contact force control stability condition according to the target environment stiffness, wherein the target admittance control parameter includes: a target damping coefficient and a target mass. The target damping coefficient is a damping coefficient that satisfies the contact force control stability condition. The target mass is a mass that satisfies the contact force control stability condition.
[0076] In practice, first, the execution subject may substitute the target environment stiffness into the contact force control stability condition, and finally, the execution subject may perform mathematical operations on the contact force control stability condition to generate the target admittance control parameters that satisfy the contact force control stability condition.
[0077] Optionally, the contact force control stability condition includes: a first control stability condition and a second control stability condition, wherein the first control stability condition is: the square of the first damping coefficient is greater than or equal to the first intermediate variable, wherein the first intermediate variable is equal to the product of a preset multiple, the target environment stiffness and the first mass, and the second control stability condition is: the quotient of the first damping coefficient and the second intermediate variable is greater than the preset value lower limit and the quotient of the first damping coefficient and the second intermediate variable is less than the preset value upper limit, wherein the second intermediate variable is equal to the product of the first mass and the above-mentioned manipulator control frequency. The above-mentioned manipulator control frequency represents the number of times the manipulator control system updates the control instruction per second. As an example, the above-mentioned preset multiple can be 4. The above-mentioned preset value upper limit can be 2. The above-mentioned preset value lower limit can be 0.
[0078] In some optional implementations of some embodiments, the execution subject generates a target admittance control parameter that satisfies a contact force control stability condition according to the target environment stiffness, which may include the following steps:
[0079] In the first step, the first quality range is determined with the first control stability condition and the second control stability condition as constraints.
[0080] In practice, the execution entity may determine the first quality range by performing mathematical operations on the first control stability condition and the second control stability condition.
[0081] As an example, the above first control stability condition is determined by the following formula:
[0082] D 2 ≥4×K×M
[0083] Wherein, D is the first damping coefficient, and M is the first mass.
[0084] The above second control stability condition is determined by the following formula:
[0085]
[0086] Where f is the control frequency of the robot arm.
[0087] Taking the square root of the first control stability condition above, we get The above second control stability condition is transformed by the formula to obtain D<2×M×f, then
[0088]
[0089] The first mass range is solved as:
[0090]
[0091] The second step is to determine the target mass included in the target admittance control parameter according to the first mass range.
[0092] As an example, the first mass range mentioned above is:
[0093]
[0094] , then the target quality included in the target admittance control parameter can be:
[0095]
[0096] The third step is to determine the damping coefficient range based on the above target mass.
[0097] As an example, the target quality above is:
[0098]
[0099] according to The above damping coefficient range can be:
[0100]
[0101] The fourth step is to determine the minimum target damping coefficient that satisfies the second control stability condition according to the damping coefficient range and the target mass.
[0102] As an example, the target quality above is:
[0103]
[0104] From D<2×M×f, we get and The minimum target damping coefficient that satisfies the second control stability condition can be:
[0105] The fifth step is to determine the minimum target damping coefficient as the target damping coefficient included in the target admittance control parameter.
[0106] As an example, in order to better demonstrate the influence of the dynamically adjusted admittance control parameters of the present application on the real-time contact force value of the robot arm, and the influence of the fixed admittance control parameters on the real-time contact force value of the robot arm, see Figure 4 The comparison diagram of the real-time contact force values of the manipulator corresponding to different admittance control parameters is shown in the figure. Specifically, Figure 4Sub-figure A in the figure is a schematic diagram showing the effect of fixed admittance control parameters on the real-time contact force of the robot. Figure 4 Sub-figure B in the figure is a schematic diagram of the effect of the dynamically adjusted admittance control parameters on the real-time contact force of the robot. Figure 4 The real-time contact force value corresponding signal shown in sub-graph A in FIG has approximately periodic oscillations, while Figure 4 The corresponding signal of the real-time contact force value shown in sub-graph B in FIG. 1 has a brief oscillation in the early stage, but compared with Figure 4 The real-time contact force value corresponding signal shown in sub-figure A can converge more quickly. In practice, the oscillation (non-convergence) of the admittance control parameters will cause the robot arm to be unable to perform stable force control. The faster the admittance control parameters converge, the faster the robot arm can achieve stable force control.
[0107] Step 107 , generating the expected speed information of the robot arm according to the initial admittance control parameter, the target admittance control parameter, the real-time speed of the robot arm, the real-time position information of the robot arm and the real-time contact force value of the robot arm.
[0108] In some embodiments, the execution entity may generate the desired speed information of the robotic arm according to the initial admittance control parameter, the target admittance control parameter, the real-time speed of the robotic arm, the real-time position information of the robotic arm and the real-time contact force value of the robotic arm.
[0109] In practice, the above-mentioned execution entity can generate the desired speed information of the robot arm through the trajectory tracking admittance control formula and the force control admittance control formula.
[0110] Optionally, the robot arm expected speed information includes: a first robot arm expected speed and a second robot arm expected speed. The first robot arm expected speed is the robot arm expected speed before the robot arm contacts the object to be polished and during trajectory tracking. The second robot arm expected speed is the robot arm expected speed when the robot arm contacts the object to be polished.
[0111] In some optional implementations of some embodiments, the execution subject generates the expected speed information of the robotic arm according to the initial admittance control parameter, the target admittance control parameter, the real-time speed of the robotic arm, the real-time position information of the robotic arm, and the real-time contact force value of the robotic arm, which may include the following steps:
[0112] The first step is to determine the preset position information of the robot arm, the preset speed of the robot arm and the preset acceleration of the robot arm.
[0113] The preset position information of the robot arm represents the reference position of the robot arm on a given motion trajectory. The preset speed of the robot arm is the preset speed of the robot arm on a given motion trajectory. The preset acceleration of the robot arm is the preset acceleration of the robot arm on a given motion trajectory.
[0114] The second step is to determine the displacement error value of the robotic arm based on the preset position information of the robotic arm and the real-time position information of the robotic arm.
[0115] As an example, the displacement error value of the above robot arm can be xx r . Among them, x is the real-time position information of the above-mentioned robot arm, x r The preset position information of the above-mentioned robot arm, r is the subscript.
[0116] The third step is to generate the expected acceleration of the first robotic arm according to the displacement error value of the robotic arm, the preset speed of the robotic arm, the preset acceleration of the robotic arm, the initial admittance control parameter, the real-time speed of the robotic arm and the real-time contact force value of the robotic arm.
[0117] In practice, the execution subject can generate the expected acceleration of the first manipulator through the trajectory tracking admittance control formula. The admittance control formula is:
[0118]
[0119] Wherein, F is the real-time contact force value of the above-mentioned robot arm, M0 is the initial mass included in the above-mentioned initial admittance control parameters, D0 is the initial damping coefficient included in the above-mentioned initial admittance control parameters, and K0 is the above-mentioned initial environmental stiffness. r is the displacement error value of the above-mentioned robot arm. Preset speeds for the above robot arms. Preset acceleration for the above robot arm. is the real-time speed of the above-mentioned robot arm. is the expected acceleration of the first robot arm, and d is the subscript.
[0120] The fourth step is to determine the first robotic arm expected speed included in the above-mentioned robotic arm expected speed information based on the above-mentioned first robotic arm expected acceleration.
[0121] In practice, the execution entity may integrate the first robotic arm expected acceleration to determine the first robotic arm expected speed included in the robotic arm expected speed information.
[0122] The fifth step is to generate the expected acceleration of the second robotic arm according to the real-time contact force value of the robotic arm, the target admittance control parameter, the real-time speed of the robotic arm and the preset expected contact force value of the robotic arm.
[0123] Among them, the above-mentioned preset expected contact force value of the robot arm is a pre-set expected contact force value of the robot arm.
[0124] In practice, the execution subject can generate the expected acceleration of the second robot arm through the force control admittance control formula, the real-time contact force value of the robot arm, the target admittance control parameter, the real-time speed of the robot arm and the preset expected contact force value of the robot arm. The force control admittance control formula is:
[0125]
[0126] Among them, F r is the expected contact force value of the preset robot arm. F is the real-time contact force value of the above robot arm. d The target quality included in the target admittance control parameters mentioned above. d is the target damping coefficient included in the above target admittance control parameters. is the real-time speed of the above-mentioned robot arm. is the expected acceleration of the second robot arm, and n is the subscript.
[0127] The sixth step is to determine the expected speed of the second robotic arm included in the expected speed information of the robotic arm based on the expected acceleration of the second robotic arm.
[0128] In practice, the execution entity may integrate the expected acceleration of the second robotic arm to determine the expected speed of the second robotic arm included in the expected speed information of the robotic arm.
[0129] Step 108 , according to the expected speed information of the robot arm and the spatial information of the object to be polished, the polishing device included in the robot arm is controlled to polish the object to be polished.
[0130] In some embodiments, the execution subject may control the grinding device included in the robot arm to grind the object to be polished according to the expected speed information of the robot arm and the spatial information of the object to be polished. As an example, the grinding device may be a diamond grinding head.
[0131] In practice, the execution subject may control the polishing device included in the robot arm through wireless connection according to the expected speed information of the robot arm and the spatial information of the object to be polished, so as to polish the object to be polished.
[0132] Optionally, the above-mentioned robotic arm also includes: a conductivity sensor, the above-mentioned grinding device includes: a flat grinding head and a curved grinding head, the above-mentioned flat grinding head includes: a flat resin-bonded grinding head, a flat chrome-steel grinding head, a flat diamond grinding head and a flat cubic boron nitride grinding head, the above-mentioned curved grinding head includes: a curved resin-bonded grinding head, a curved chrome-steel grinding head, a curved diamond grinding head and a curved cubic boron nitride grinding head.
[0133] In some optional implementations of some embodiments, the execution subject controls the polishing device included in the robot arm according to the expected speed information of the robot arm and the spatial information of the object to be polished to polish the object to be polished, which may include the following steps:
[0134] The first step is to determine the grinding trajectory of the grinding device according to the shape information of the object to be polished included in the spatial information of the object to be polished.
[0135] In practice, the execution subject may generate a grinding trajectory of the grinding device through a path planning algorithm and shape information of the object to be polished included in the spatial information of the object to be polished.
[0136] The second step is to determine the type of grinding work surface according to the shape information of the object to be polished.
[0137] In practice, the execution entity may extract geometric features from the shape information of the object to be polished to obtain the type of the polishing working surface.
[0138] The third step is to determine the metal hardness information of the object to be polished according to the conductivity sensor.
[0139] In practice, the execution subject may measure the conductivity of the object to be polished by means of the conductivity sensor, and determine the metal hardness information of the object to be polished according to the conductivity.
[0140] In the fourth step, in response to determining that the grinding working surface type is a plane type, the following plane grinding head selection steps are performed:
[0141] In the first sub-step, in response to determining that the metal hardness represented by the metal hardness information of the object to be polished is within a first metal hardness range, the planar resin-bonded grinding head included in the polishing device is controlled to perform a polishing operation according to the desired speed information of the robot arm and the polishing trajectory.
[0142] Among them, the metal type corresponding to the above-mentioned first metal hardness range is soft metal.
[0143] In practice, the execution subject may control the planar resin-bonded grinding head included in the grinding device to perform grinding operations according to the desired speed information of the robot arm and the grinding trajectory through a wireless connection.
[0144] In the second sub-step, in response to determining that the metal hardness represented by the metal hardness information of the object to be polished is in a second metal hardness range, the flat chrome steel grinding head included in the polishing device is controlled to perform a polishing operation according to the desired speed information of the robot arm and the polishing trajectory.
[0145] Among them, the metal type corresponding to the second metal hardness range is medium hardness metal.
[0146] In practice, the execution entity may control the flat chrome steel grinding head included in the grinding device to perform grinding operations according to the desired speed information of the robot arm and the grinding trajectory through a wireless connection.
[0147] The third sub-step is, in response to determining that the metal hardness represented by the metal hardness information of the object to be polished is in a third metal hardness range, controlling the planar diamond grinding head included in the polishing device to perform a polishing operation according to the expected speed information of the robot arm and the polishing trajectory.
[0148] Among them, the metal type corresponding to the third metal hardness range is high hardness metal.
[0149] In practice, the execution subject may control the planar diamond grinding head included in the grinding device through a wireless connection to perform grinding operations according to the desired speed information of the robot arm and the grinding trajectory.
[0150] The fourth sub-step, in response to determining that the metal hardness represented by the metal hardness information of the object to be polished is in a fourth metal hardness range, controls the planar cubic boron nitride grinding head included in the polishing device to perform a polishing operation according to the expected speed information of the robot arm and the polishing trajectory.
[0151] Among them, the metal type corresponding to the fourth metal hardness range is ultra-high hardness metal.
[0152] In practice, the execution subject may control the planar cubic boron nitride grinding head included in the grinding device to perform grinding operations according to the desired speed information of the robot arm and the grinding trajectory through a wireless connection.
[0153] Step 5: In response to determining that the grinding working surface type is a curved surface type, the following curved surface grinding head selection steps are performed:
[0154] In the first sub-step, in response to determining that the metal hardness represented by the metal hardness information of the object to be polished is within a first metal hardness range, the arc-surface resin-bonded grinding head included in the polishing device is controlled to perform a polishing operation according to the desired speed information of the robot arm and the polishing trajectory.
[0155] In practice, the execution subject may control the arc-surface resin-bonded grinding head included in the grinding device by wireless connection to perform grinding operations according to the desired speed information of the robot arm and the grinding trajectory.
[0156] In the second sub-step, in response to determining that the metal hardness represented by the metal hardness information of the object to be polished is in the second metal hardness range, the arc chrome steel grinding head included in the polishing device is controlled to perform a polishing operation according to the expected speed information of the robot arm and the polishing trajectory.
[0157] In practice, the execution entity may control the arc-surface chrome steel grinding head included in the grinding device by wireless connection to perform grinding operations according to the desired speed information of the robot arm and the grinding trajectory.
[0158] The third sub-step is, in response to determining that the metal hardness represented by the metal hardness information of the object to be polished is in a third metal hardness range, controlling the arcuate diamond grinding head included in the polishing device to perform a polishing operation according to the expected speed information of the robot arm and the polishing trajectory.
[0159] In practice, the execution subject may control the arc-surface diamond grinding head included in the grinding device to perform grinding operations according to the desired speed information of the robot arm and the grinding trajectory through a wireless connection.
[0160] The fourth sub-step, in response to determining that the metal hardness represented by the metal hardness information of the object to be polished is in a fourth metal hardness range, controls the arc-surface cubic boron nitride grinding head included in the polishing device to perform a polishing operation according to the expected speed information of the robot arm and the polishing trajectory.
[0161] In practice, the execution subject may control the arc-surface cubic boron nitride grinding head included in the grinding device by wireless connection to perform grinding operation according to the desired speed information of the robot arm and the grinding trajectory.
[0162] The above-mentioned content of "in some optional implementation methods of some embodiments" as an inventive point of the present disclosure solves the following technical problem, namely, "due to the different hardness of the objects to be polished, when the hardness of the polishing tool does not match that of the object to be polished, the polishing tool may be damaged and the polishing effect may be poor. "For example, when a polishing tool suitable for softer hardness contacts a part with higher hardness, the wear rate will be faster, which may shorten the tool life, thereby increasing the replacement frequency and cost. Based on this, firstly, the present disclosure determines the polishing trajectory of the above-mentioned polishing device according to the shape information of the object to be polished included in the above-mentioned spatial information of the object to be polished. Then, according to the above-mentioned shape information of the object to be polished, the type of the polishing working surface is determined. Since different types of working surfaces use different polishing tools, it is necessary to determine the type of the polishing working surface. Then, according to the above-mentioned conductivity sensor, the metal hardness information of the above-mentioned object to be polished is determined. Since the objects to be polished have different metal hardnesses, if a single polishing tool is used, the polishing tool may be damaged and the polishing effect may be poor due to the mismatch between the hardness of the polishing tool and the object to be polished. Therefore, it is necessary to determine the metal hardness information of the object to be polished, and then use different polishing tools for polishing according to different metal hardness information. Further, in response to determining that the type of the above-mentioned polishing work surface is a plane type, the following plane grinding head selection step is performed: in response to determining that the metal hardness represented by the metal hardness information of the above-mentioned object to be polished is in the first metal hardness interval, the plane resin bonded grinding head included in the above-mentioned polishing device is controlled to perform a polishing operation according to the above-mentioned robot arm expected speed information and the above-mentioned polishing trajectory. In response to determining that the metal hardness represented by the metal hardness information of the above-mentioned object to be polished is in the second metal hardness interval, the plane chrome steel grinding head included in the above-mentioned polishing device is controlled to perform a polishing operation according to the above-mentioned robot arm expected speed information and the above-mentioned polishing trajectory. In response to determining that the metal hardness represented by the metal hardness information of the above-mentioned object to be polished is in the third metal hardness interval, the plane diamond grinding head included in the above-mentioned polishing device is controlled to perform a polishing operation according to the above-mentioned robot arm expected speed information and the above-mentioned polishing trajectory. In response to determining that the metal hardness represented by the metal hardness information of the object to be polished is in the fourth metal hardness interval, the planar cubic boron nitride grinding head included in the polishing device is controlled to perform a polishing operation according to the desired speed information of the robot arm and the polishing trajectory. Secondly, in response to determining that the type of the polishing working surface is a curved surface type, the following curved surface grinding head selection step is performed: In response to determining that the metal hardness represented by the metal hardness information of the object to be polished is in the first metal hardness interval, the curved surface resin bonded grinding head included in the polishing device is controlled to perform a polishing operation according to the desired speed information of the robot arm and the polishing trajectory. In response to determining that the metal hardness represented by the metal hardness information of the object to be polished is in the second metal hardness interval, the curved surface chrome steel grinding head included in the polishing device is controlled to perform a polishing operation according to the desired speed information of the robot arm and the polishing trajectory.In response to determining that the metal hardness represented by the metal hardness information of the object to be polished is in the third metal hardness interval, the arc-surface diamond grinding head included in the polishing device is controlled to perform a polishing operation according to the expected speed information of the robot arm and the polishing trajectory. In response to determining that the metal hardness represented by the metal hardness information of the object to be polished is in the fourth metal hardness interval, the arc-surface cubic boron nitride grinding head included in the polishing device is controlled to perform a polishing operation according to the expected speed information of the robot arm and the polishing trajectory. In this way, the damage to the polishing tool and the poor polishing effect caused by the mismatch between the hardness of the polishing tool used and the object to be polished are avoided.
[0163] As an example, see Figure 5 The schematic diagram of the application scenario of the robot control method applied to the robot arm of some embodiments of the present disclosure shown, device 501 is a sensor data acquisition device embedded in the forearm of the robot arm, and device 501 collects data of the robot arm when grinding through a wired connection. Devices 502 and 503 are grinding devices installed on the head of the robot arm, wherein device 502 is a plane grinding head and device 503 is a curved grinding head. Device 504 is a camera device installed on the head of the robot arm, wherein device 504 faces the object to be polished 505 for collecting an image of the object to be polished containing the object to be polished. For example, when the grinding working surface type of the object to be polished is a plane type, the robot arm performs a grinding operation on the object to be polished 505 through the control device 502. For another example, when the grinding working surface type of the object to be polished is a curved type, the robot arm performs a grinding operation on the object to be polished 505 through the control device 503.
[0164] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the robot arm control method applied to the robot arm of some embodiments of the present disclosure, by dynamically adjusting the admittance control parameters, the generation of oscillation is avoided, and more accurate force control is achieved. Specifically, the reason for the oscillation is that the existing technology has poor versatility when facing various uncertain external environments, and cannot adapt to the complex situations in practical applications. For example, when contacting a high-rigidity environment, it is easy to cause a sudden change in force, thereby generating system oscillation, making it impossible for the robot arm to perform accurate force control. Based on this, the robot arm control method applied to the robot arm of some embodiments of the present disclosure, first, obtain the initial admittance control parameters of the robot arm, wherein the above-mentioned robot arm includes: a camera device, a sensor data acquisition device and a grinding device, and the above-mentioned initial admittance control parameters include: initial mass, initial damping coefficient and initial environmental stiffness. Secondly, the image of the object to be polished is collected by the above-mentioned camera device, wherein the above-mentioned camera device is facing the position where the object to be polished is placed when the above-mentioned robot arm is in an unloaded state. Then, the spatial information of the object to be polished is generated by the pre-trained spatial information generation model and the above-mentioned image of the object to be polished, wherein the above-mentioned image of the object to be polished contains the object to be polished. During polishing, the position information and shape information of the object to be polished are required to facilitate the subsequent control of the polishing device for polishing. Therefore, the image of the object to be polished is first photographed by a camera device, and then the position and shape are confirmed. Then, according to the above-mentioned initial admittance control parameters and the above-mentioned sensor data acquisition device, the real-time contact force value of the robot arm, the real-time speed of the robot arm and the real-time position information of the robot arm are determined, wherein the real-time contact force value of the robot arm represents the real-time force magnitude of the robot arm contacting the surface of the object to be polished during polishing. Since it is a process for the robot arm to go from never contacting to contacting the external environment, it is necessary to monitor the displacement and contact force changes of the end of the robot arm in real time to estimate the stiffness of the external environment. Further, according to the real-time contact force value of the robot arm, the target environment stiffness is generated. In addition, according to the above-mentioned target environment stiffness, the target admittance control parameters that meet the contact force control stability condition are generated, wherein the above-mentioned target admittance control parameters include: target damping coefficient and target mass. By estimating the stiffness of the external environment, the parameters of the admittance control are dynamically adjusted so that the robot arm can maintain a stable over-damped state after contact. In this way, the robot arm can achieve stable contact in environments with different stiffness, avoiding sudden force changes and system oscillations. Then, according to the above initial admittance control parameters, the above target admittance control parameters, the above real-time speed of the robot arm, the above real-time position information of the robot arm and the above real-time contact force value of the robot arm, the expected speed information of the robot arm is generated. Finally, according to the above expected speed information of the robot arm and the above spatial information of the object to be polished, the polishing device included in the above robot arm is controlled to polish the above object to be polished.In this way, the admittance control parameters are dynamically adjusted to avoid oscillations and ensure that the robot arm can achieve precise force control during contact with the environment.
[0165] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a robot arm control device, and these device embodiments are Figure 1 Corresponding to the method embodiments shown, the robot arm control device can be specifically applied to various electronic devices.
[0166] like Figure 2 As shown, the robot control device 200 of some embodiments includes: an acquisition unit 201, a collection unit 202, a first generation unit 203, a determination unit 204, a second generation unit 205, a third generation unit 206, a fourth generation unit 207 and a control unit 208. The acquisition unit 201 is configured to acquire the initial admittance control parameters of the robot, wherein the robot includes: a camera device, a sensor data acquisition device and a polishing device, and the initial admittance control parameters include: initial mass, initial damping coefficient and initial environmental stiffness. The acquisition unit 202 is configured to acquire an image of the object to be polished through the camera device, wherein the camera device is facing the position where the object to be polished is placed when the robot is in an unloaded state. The first generation unit 203 is configured to generate spatial information of the object to be polished through a pre-trained spatial information generation model and the image of the object to be polished, wherein the image of the object to be polished includes the object to be polished. The determination unit 204 is configured to determine the real-time contact force value, real-time speed and real-time position information of the manipulator according to the initial admittance control parameter and the sensor data acquisition device, wherein the real-time contact force value of the manipulator represents the real-time force magnitude of the manipulator contacting the surface of the object to be polished when polishing. The second generation unit 205 is configured to generate the target environment stiffness according to the real-time contact force value of the manipulator. The third generation unit 206 is configured to generate the target admittance control parameter that meets the contact force control stability condition according to the target environment stiffness, wherein the target admittance control parameter includes: target damping coefficient and target mass. The fourth generation unit 207 is configured to generate the expected speed information of the manipulator according to the initial admittance control parameter, the target admittance control parameter, the real-time speed of the manipulator, the real-time position information of the manipulator and the real-time contact force value of the manipulator. The control unit 208 is configured to control the polishing device included in the manipulator according to the expected speed information of the manipulator and the space information of the object to be polished, and polish the object to be polished.
[0167] It is understandable that the units described in the robot control device 200 are similar to those described in the reference Figure 1Therefore, the operations, features and beneficial effects described above for the method are also applicable to the robot arm control device 200 and the units included therein, and will not be described in detail here.
[0168] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device (eg, a computing device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
[0169] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory 302 or a program loaded from a storage device 308 into a random access memory 303. Various programs and data required for the operation of the electronic device 300 are also stored in the random access memory 303. The processing device 301, the read-only memory 302, and the random access memory 303 are connected to each other via a bus 304. An input / output interface 305 is also connected to the bus 304.
[0170] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.
[0171] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the read-only memory 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.
[0172] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
[0173] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.
[0174] The computer-readable medium may be included in the electronic device; or may exist independently without being assembled into the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains the initial admittance control parameters of the robot arm, wherein the robot arm includes: a camera device, a sensor data acquisition device and a polishing device, and the initial admittance control parameters include: initial mass, initial damping coefficient and initial environmental stiffness. The image of the object to be polished is collected by the camera device, wherein the camera device is placed toward the object to be polished when the robot arm is in an unloaded state. The spatial information of the object to be polished is generated by a pre-trained spatial information generation model and the image of the object to be polished, wherein the image of the object to be polished includes the object to be polished. According to the initial admittance control parameters and the sensor data acquisition device, the real-time contact force value of the robot arm, the real-time speed of the robot arm and the real-time position information of the robot arm are determined, wherein the real-time contact force value of the robot arm represents the real-time force magnitude of the robot arm contacting the surface of the object to be polished when polishing. According to the real-time contact force value of the robot arm, a target environmental stiffness is generated. According to the target environmental stiffness, a target admittance control parameter that satisfies the contact force control stability condition is generated, wherein the target admittance control parameter includes: a target damping coefficient and a target mass. According to the initial admittance control parameter, the target admittance control parameter, the real-time speed of the robot arm, the real-time position information of the robot arm and the real-time contact force value of the robot arm, the expected speed information of the robot arm is generated. According to the expected speed information of the robot arm and the spatial information of the object to be polished, the polishing device included in the robot arm is controlled to polish the object to be polished.
[0175] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0176] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0177] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including an acquisition unit, a collection unit, a first generation unit, a determination unit, a second generation unit, a third generation unit, a fourth generation unit and a control unit. The names of these units do not, in some cases, constitute limitations on the units themselves, for example, the acquisition unit may also be described as a "unit for acquiring initial admittance control parameters of a robotic arm".
[0178] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.
[0179] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.
Claims
1. A robot arm control method applied to a robot arm, comprising: Acquire initial admittance control parameters of the robot arm, wherein the robot arm comprises: a camera device, a sensor data acquisition device and a polishing device, and the initial admittance control parameters comprise: an initial mass, an initial damping coefficient and an initial environmental stiffness; The camera device is used to collect images of the object to be polished, wherein the camera device is oriented toward the position where the object to be polished is placed when the robot arm is in an unloaded state; Generate spatial information of the object to be polished by using a pre-trained spatial information generation model and the image of the object to be polished, wherein the image of the object to be polished includes the object to be polished; According to the initial admittance control parameter and the sensor data acquisition device, determine the real-time contact force value of the robot arm, the real-time speed of the robot arm and the real-time position information of the robot arm, wherein the real-time contact force value of the robot arm represents the real-time force magnitude of the robot arm contacting the surface of the object to be polished during polishing; generating a target environment stiffness according to the real-time contact force value of the robot arm; According to the target environmental stiffness, generating target admittance control parameters that meet the contact force control stability condition, wherein the target admittance control parameters include: a target damping coefficient and a target mass; Generate expected speed information of the robotic arm according to the initial admittance control parameter, the target admittance control parameter, the real-time speed of the robotic arm, the real-time position information of the robotic arm, and the real-time contact force value of the robotic arm; According to the expected speed information of the robot arm and the spatial information of the object to be polished, the polishing device included in the robot arm is controlled to polish the object to be polished.
2. The method according to claim 1, wherein: The spatial information of the object to be polished includes: position information of the object to be polished and shape information of the object to be polished, and the spatial information generation model includes: a position information generation model and an object shape recognition model; and The generating of spatial information of the object to be polished by using the pre-trained spatial information generating model and the image of the object to be polished includes: Performing image preprocessing on the image of the object to be polished to obtain a preprocessed image of the object to be polished; Determine the image position of the object to be polished in the image of the object to be polished after the preprocessing by generating a model based on the position information to generate a target image position; Performing spatial position transformation on the target image position to generate a transformed target image position; Determining the position of the occluded key point corresponding to the object to be polished according to the position of the converted target image; Determine the target image position and the occluded key point position as the position information of the object to be polished included in the spatial information of the object to be polished; The shape information of the object to be polished included in the spatial information of the object to be polished is generated according to the object shape recognition model and the preprocessed image of the object to be polished.
3. The method according to claim 2, wherein: Generating a target environment stiffness according to the real-time contact force value of the robot arm includes: In response to determining that the real-time contact force value of the robot arm is greater than the preset contact force value, the following determination steps are performed: Determine the axial position of the first robotic arm corresponding to the real-time contact force value of the robotic arm at the first moment; In response to determining that the real-time contact force value of the robot arm meets a preset condition, determining a second robot arm axis position corresponding to the real-time contact force value of the robot arm at a second moment; Determine the difference between the real-time contact force value of the robotic arm at the second moment and the real-time contact force value of the robotic arm at the first moment as a contact force difference; Determine the difference between the axial position of the second mechanical arm and the axial position of the first mechanical arm as the mechanical arm axial position difference; The quotient of the contact force difference and the robot arm axis position difference is determined as the target environment stiffness.
4. The method according to claim 3, wherein: The contact force control stability condition includes: a first control stability condition and a second control stability condition, wherein the first control stability condition is: the square of the first damping coefficient is greater than or equal to the first intermediate variable, wherein the first intermediate variable is equal to the product of a preset multiple, the target environment stiffness and the first mass, and the second control stability condition is: the quotient of the first damping coefficient and the second intermediate variable is greater than a preset value lower limit and the quotient of the first damping coefficient and the second intermediate variable is less than a preset value upper limit, wherein the second intermediate variable is equal to the product of the first mass and the control frequency of the manipulator; and The step of generating a target admittance control parameter satisfying a contact force control stability condition according to the target environment stiffness comprises: Determining a first mass range with the first control stability condition and the second control stability condition as constraints; Determining a target mass included in the target admittance control parameter according to the first mass range; Determining a damping coefficient range according to the target mass; Determining a minimum target damping coefficient that satisfies the second control stability condition according to the damping coefficient range and the target mass; The minimum target damping coefficient is determined as the target damping coefficient included in the target admittance control parameter.
5. The method according to claim 4, wherein: The expected speed information of the mechanical arm includes: the expected speed of the first mechanical arm and the expected speed of the second mechanical arm; and The generating the expected speed information of the robot arm according to the initial admittance control parameter, the target admittance control parameter, the real-time speed of the robot arm, the real-time position information of the robot arm and the real-time contact force value of the robot arm comprises: Determine the preset position information of the robot arm, the preset speed of the robot arm and the preset acceleration of the robot arm; Determine a displacement error value of the robotic arm according to the preset position information of the robotic arm and the real-time position information of the robotic arm; Generate a first expected acceleration of the robotic arm according to the displacement error value of the robotic arm, the preset speed of the robotic arm, the preset acceleration of the robotic arm, the initial admittance control parameter, the real-time speed of the robotic arm and the real-time contact force value of the robotic arm; Determine, based on the first mechanical arm expected acceleration, a first mechanical arm expected speed included in the mechanical arm expected speed information; Generate an expected acceleration of the second robotic arm according to the real-time contact force value of the robotic arm, the target admittance control parameter, the real-time speed of the robotic arm and a preset expected contact force value of the robotic arm; Based on the second manipulator arm expected acceleration, a second manipulator arm expected speed included in the manipulator arm expected speed information is determined.
6. A robot arm control device applied to a robot arm, comprising: An acquisition unit is configured to acquire initial admittance control parameters of a robot arm, wherein the robot arm comprises: a camera device, a sensor data acquisition device and a polishing device, and the initial admittance control parameters comprise: an initial mass, an initial damping coefficient and an initial environmental stiffness; A collection unit is configured to collect images of the object to be polished through the camera device, wherein the camera device is oriented toward a position where the object to be polished is placed when the robot arm is in an unloaded state; A first generating unit is configured to generate spatial information of the object to be polished by using a pre-trained spatial information generation model and the image of the object to be polished, wherein the image of the object to be polished includes the object to be polished; a determination unit configured to determine a real-time contact force value of the robot arm, a real-time speed of the robot arm, and real-time position information of the robot arm according to the initial admittance control parameter and the sensor data acquisition device, wherein the real-time contact force value of the robot arm represents the real-time force magnitude of the robot arm contacting the surface of the object to be polished when polishing; A second generating unit is configured to generate a target environment stiffness according to the real-time contact force value of the robot arm; A third generating unit is configured to generate a target admittance control parameter satisfying a contact force control stability condition according to the target environment stiffness, wherein the target admittance control parameter includes: a target damping coefficient and a target mass; a fourth generating unit, configured to generate expected speed information of the manipulator according to the initial admittance control parameter, the target admittance control parameter, the real-time speed of the manipulator, the real-time position information of the manipulator, and the real-time contact force value of the manipulator; The control unit is configured to control the polishing device included in the robot arm to polish the object to be polished according to the expected speed information of the robot arm and the spatial information of the object to be polished.
7. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 5.
8. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.
Citation Information
Patent Citations
Polishing robot proportional damping control method and system based on force sensor
CN116372909A
Mechanical arm control method, device and equipment and storage medium
CN116922383A
Model processing method, mechanical arm control method, device, equipment and storage medium
CN117086870A
Mechanical arm trajectory planning method and device, computer equipment and storage medium
CN118254176A
Contact force limiting with haptic feedback for a tele-operated robot
US20160229050A1
Cited By
Self-adaptive admittance control method and device for mechanical arm
CN122100159A
A robot arm adaptive admittance control method and device
CN122100159B
