A robot arm control method, device, electronic device and storage medium

Abstract

The present invention discloses a method, device, electronic device and storage medium for controlling a robotic arm. The method comprises: obtaining the operation data of the robotic arm at the current moment; classifying the operation data based on a pre-constructed operation intention database, determining the intention classification result corresponding to the operation data, and determining the joint operation type of each joint of the robotic arm based on the intention classification result; wherein the joint operation type includes an intended operation joint type and an unintended operation joint type; and suppressing the movement of the joints of the unintended operation joint type. This scheme realizes a method for classifying the operation data in real time through a pre-constructed operation intention database, and suppressing the movement of unintended operation joints in time. It can detect unintended operation joints in time and suppress them, avoiding the problem of positioning errors of the robotic arm caused by positioning unintended operation joints during the robotic arm control process, and improving the accuracy and safety of the robotic arm control.

Description

Technical Field

[0001] The present invention relates to the field of robot control technology, and in particular to a robot arm control method, device, electronic equipment and storage medium. Background Art

[0002] With the development of intelligent medical technology, the application of laparoscopic surgical robots has become more and more extensive. They can not only avoid the traditional large incision surgery method, reduce surgical trauma and intraoperative bleeding of patients, but also provide high-precision surgical manipulation and field of view.

[0003] In existing clinical surgeries, doctors use their hands to drag the surgical arm to achieve pre-operative and intra-operative positioning intentions based on their operating experience and intra-operative needs of the multi-arm surgical robot system. The positioning control of the surgical arm mainly depends on the preset control program or the doctor's control instructions, which to a certain extent achieves smooth control of the surgical arm, but the process depends on the doctor's experience and operation. For example, physiological tremors in human hands will cause positioning of unintended joints in the surgical arm, resulting in positioning errors. At present, it is usually done through manual inspection methods, which rely too much on the doctor's experience and operation, and lack intelligent recognition and intelligent processing methods for the positioning control of the surgical arm, resulting in poor accuracy of robotic arm control. Summary of the invention

[0004] The present invention provides a robot arm control method, device, electronic device and storage medium to solve the problem of lack of intelligent recognition and intelligent processing in the positioning control of the surgical arm and the problem of poor control accuracy of the robot arm.

[0005] According to one aspect of the present invention, there is provided a robot arm control method, comprising:

[0006] Get the operation data of the robot arm at the current moment;

[0007] Classify the operation data based on the pre-built operation intention database, determine the intention classification result corresponding to the operation data, and determine the joint operation type of each joint of the robot arm based on the intention classification result; wherein the joint operation type includes the intended operation joint type and the non-intended operation joint type;

[0008] Movement inhibition is performed on joints of non-intended joint types.

[0009] Optionally, a pre-built operation intention database includes multiple intention classes, wherein an intention class includes operation data that satisfies the intention class; the operation data of the robotic arm includes torque data and acceleration data of each joint of the robotic arm; the operation data is classified based on the pre-built operation intention database to determine the intention classification result corresponding to the operation data, including: traversing the pre-built operation intention database to determine the distance data between the operation data and the operation data corresponding to each intention class in the operation intention database; and determining the intention classification result corresponding to the operation data based on the distance data.

[0010] Optionally, the joint operation type of each joint of the robotic arm is determined based on the intention classification result, including: determining the joint operation type information corresponding to the intention classification result based on a mapping relationship between the intention class and the joint operation type information, the joint operation type information including at least one joint operation type and a corresponding joint identification set, the joint identification set including at least one joint identifier; determining the joint operation type of each joint of the robotic arm based on the joint operation type information.

[0011] Optionally, inhibiting movement of joints of the non-intentional operation joint type includes: determining a joint inhibition current of the non-intentional operation joint type, and inhibiting movement of the joints of the non-intentional operation joint type based on the joint inhibition current.

[0012] Optionally, determining the joint inhibition current of an unintentional operation joint type includes: for any joint of the unintentional operation joint type, collecting external control force data of the joint of the unintentional operation joint type at each moment; determining the joint inhibition current of the joint of the unintentional operation joint type at each moment based on a pre-built mapping relationship between the joint inhibition current and the external control force and the external control force data of the joint of the unintentional operation joint type at each moment.

[0013] Optionally, constructing an operation intention database includes: obtaining a sample data set, preprocessing the sample data set to obtain a preprocessed sample data set, wherein the sample data set includes intention operation information and historical operation data of each joint of the robotic arm; clustering the preprocessed sample data set to determine multiple intention classes, and forming an operation intention database based on the multiple intention classes.

[0014] Optionally, the method also includes: dividing the sample data set into subsets according to surgical information to obtain multiple sample data subsets, wherein the surgical information includes one or more information of surgical type, department information and operator information; constructing a corresponding operation intention database based on each sample data subset; accordingly, the method also includes: obtaining current surgical information and calling the corresponding operation intention database.

[0015] According to another aspect of the present invention, there is provided a robot arm control device, comprising:

[0016] An operation data acquisition module is used to obtain the operation data of the robot arm at the current moment;

[0017] A joint operation type determination module is used to classify the operation data based on a pre-built operation intention database, determine the intention classification result corresponding to the operation data, and determine the joint operation type of each joint of the robot arm based on the intention classification result; wherein the joint operation type includes the intended operation joint type and the non-intended operation joint type;

[0018] The joint movement inhibition control module is used to inhibit the movement of joints of unintended operation joint types.

[0019] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0020] at least one processor; and

[0021] a memory communicatively connected to at least one processor; wherein,

[0022] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by at least one processor so that the at least one processor can execute the robot arm control method of any embodiment of the present invention.

[0023] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the robot arm control method of any embodiment of the present invention when executed.

[0024] The technical solution of the embodiment of the present invention is to obtain the operation data of the robot arm at the current moment; classify the operation data based on a pre-constructed operation intention database, determine the intention classification result corresponding to the operation data, and determine the joint operation type of each joint of the robot arm based on the intention classification result; wherein the joint operation type includes the intended operation joint type and the unintended operation joint type; and suppress the movement of the joints of the unintended operation joint type. This solution classifies the operation data in real time through a pre-constructed operation intention database, determines the unintended operation joints according to the intention classification result, and then promptly suppresses the detected unintended operation joints, thereby realizing intelligent recognition and intelligent processing of the robot arm's positioning operation intention, avoiding the problem of positioning errors of the robot arm caused by positioning operations on unintended operation joints during the robot arm control process, and improving the accuracy, stability and safety of the robot arm control.

[0025] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0027] Figure 1 is a flow chart of a robot arm control method provided in Embodiment 1 of the present invention;

[0028] Figure 2 is a flow chart of a robot arm control method provided by Embodiment 2 of the present invention;

[0029] Figure 3 is a schematic diagram of the structure of a robot arm control device provided in Embodiment 3 of the present invention;

[0030] Figure 4 It is a structural schematic diagram of an electronic device for implementing the robot arm control method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] Embodiment 1

[0034] Figure 1 This is a flow chart of a robot arm control method provided in Example 1 of the present invention. This embodiment is applicable to situations where a robot arm is controlled. The method can be executed by a robot arm control device. The robot arm control device can be implemented in the form of hardware and / or software. The robot arm control device can be configured in electronic devices such as computers, servers, and control terminals.

[0035] It should be noted that, when one or more joints of the robotic arm are controlled to move by applying a control force externally, there may be errors in the positioning of the robotic arm due to misoperation or physiological tremors of the doctor's hands. In this embodiment, taking the surgical robot as an example, for abdominal surgery, the use of the abdominal surgical robot can not only avoid the traditional large incision method, reduce surgical trauma and intraoperative bleeding of the patient, but also provide high-precision surgical manipulation and vision. However, the operating accuracy requirements of the surgical robot are extremely high, and the control accuracy requirements of each joint of the robotic arm are also extremely high. The surgical robotic arm is controlled by a preset control program or the doctor's control instructions, and the smooth control of the surgical arm is achieved to a certain extent. When the doctor controls the movement of the surgical arm, it is necessary to avoid operating the unintended joints. The unintended joints can be subjected to motion suppression processing to suppress the changes in the joint postures of the unintended joints caused by factors such as human hand tremors, so as to eliminate the positioning errors of the robotic arm caused by misoperation and improve the control accuracy and stability of the robotic arm.

[0036] like Figure 1 As shown, the method includes:

[0037] S110, obtaining the operation data of the robot arm at the current moment.

[0038] The operation data specifically represents the data fed back by each joint of the robot arm during the movement process. In this embodiment, the operation data specifically represents the data fed back by each joint during the positioning operation of the robot arm. The operation data includes but is not limited to the torque data and acceleration data of each joint. The data can be collected by the sensor equipment set at each joint.

[0039] Specifically, the operation data of each joint of the robotic arm is collected in real time by setting sensor devices at each joint of the robotic arm. When the doctor performs positioning operations before and during surgery, he sets a sampling window of an appropriate period as the operation intention recognition period at the current moment, and then collects the operation data of the robotic arm at the current moment in real time according to the operation intention recognition period. The setting of the appropriate period can be set according to the sampling frequency of the device, and a fixed sampling period can also be set. Preferably, the sampling period is set to 1ms, which is specifically set according to the actual situation. The sampling period can be set as small as possible to improve the real-time performance of obtaining the operation data, and then improve the real-time performance of the recognition and processing of the joint operation type.

[0040] S120. Classify the operation data based on a pre-built operation intention database, determine the intention classification result corresponding to the operation data, and determine the joint operation type of each joint of the robotic arm based on the intention classification result; wherein the joint operation type includes the intended operation joint type and the non-intended operation joint type.

[0041] Among them, the operation intention database can be specifically understood as a storage space for storing multiple intention classes and their associated data. The intention class can be understood as the doctor's intended positioning operation. The number of joints corresponding to different doctors' intended positioning operations is different. The associated data includes but is not limited to the operation data and joint operation type information corresponding to the intention class, which is specifically used to classify the real-time collected operation data and determine the joint operation type of each joint of the robot arm. The corresponding operation intention database can be constructed by clustering a large amount of surgery-related data of the robot arm. It can also be classified according to different surgery types, scene information and doctor information to obtain the corresponding operation intention database, which is helpful to realize the personalized construction of the operation intention database and intelligently match the intention operations of different doctors and various surgery types. The classification processing can match the operation data with the pre-constructed operation intention database, and use the matched information as the intention classification result corresponding to the operation data. The pre-constructed operation intention database and the operation data can also be processed as a pre-constructed classification network model to output the intention classification result corresponding to the operation data. It is not limited here, and the corresponding classification processing method is called according to the actual situation. The intention classification result represents the intention class to which the operation data belongs. The intended operation joint type and the unintended operation joint type are specifically used to characterize the type of operation object during the doctor's positioning operation. The operation object can be any joint of the robotic arm. It should be noted that for different positioning behaviors of the doctor, the number of joints that the doctor intends to operate will be different. Therefore, it is necessary to classify the operation data to obtain the intended operation joints and unintended operation joints in the positioning behavior corresponding to the operation data, so as to avoid errors caused by positioning operations on unintended operation joints and reduce surgical risks.

[0042] Specifically, a pre-built operation intention database is called, and the operation data at the current moment is matched with the operation intention database to obtain the intention classification result corresponding to the operation data. The intention classification result corresponding to the operation data can be determined by a pre-built classification algorithm. The pre-built classification algorithm includes but is not limited to the Euclidean distance algorithm and a pre-built classification model. After determining the intention classification result corresponding to the operation data, the corresponding joint operation type information is determined according to the intention classification result, and the joint operation type of each joint of the robotic arm is determined according to the joint operation type information. Among them, the intention classification result and the joint operation type information have a mapping relationship, and the mapping relationship can be stored in the pre-built operation intention database, or it can be other storage space that has an association relationship with the pre-built operation intention database. It is only necessary to match the corresponding storage space according to the association relationship based on the intention classification result, and then determine the corresponding joint operation type information.

[0043] In this embodiment, a pre-built operation intention database classifies the operation data to determine the intention classification result corresponding to the operation data. This can determine the doctor's intended operation corresponding to the operation data, and then accurately judge the joints of non-intentional operation types and the joints of intended operation types, which helps to subsequently perform targeted inhibition of motion operations on the joints of non-intentional operation types, thereby improving the accuracy and safety of robotic arm operations.

[0044] Optionally, the joint operation type of each joint of the robotic arm is determined based on the intention classification result, including: determining the joint operation type information corresponding to the intention classification result based on a mapping relationship between the intention class and the joint operation type information, the joint operation type information including at least one joint operation type and a corresponding joint identification set, the joint identification set including at least one joint identifier; determining the joint operation type of each joint of the robotic arm based on the joint operation type information.

[0045] Among them, the mapping relationship between the intention class and the joint operation type information can be determined in the process of building the operation intention database. When applied, the mapping relationship between the intention class and the joint operation type information can be directly read from the operation intention database.

[0046] Specifically, the mapping relationship between the intention class and the joint operation type information is called, and the intention classification result is matched with the mapping relationship to obtain the joint operation type information corresponding to the intention classification result. The joint operation type information includes at least one joint operation type and a corresponding joint identification set. Each joint identification set includes at least one joint identifier. For the joint identification set corresponding to each joint operation type in the joint operation type information, the joint identification of each joint of the robotic arm is matched with the joint identification set, and the corresponding joint operation type is set to the joint operation type of the successfully matched joint. After the joint identification matching of each joint of the robotic arm is completed, the joint operation type of each joint of the robotic arm is obtained.

[0047] Optionally, constructing an operation intention database includes: obtaining a sample data set, preprocessing the sample data set to obtain a preprocessed sample data set, wherein the sample data set includes intention operation information and historical operation data of each joint of the robotic arm; clustering the preprocessed sample data set to determine multiple intention classes, and forming an operation intention database based on the multiple intention classes.

[0048] Specifically, a sample data set can be obtained from a target storage space, and the target storage space includes but is not limited to a server, a local storage device, and an external storage device. The sample data set includes intended operation information and historical operation data of each joint of the robotic arm; the intended operation information represents the intended operation joint information corresponding to the doctor's positioning operation. The sample data set is preprocessed by a preset preprocessing method to obtain a preprocessed sample data set, wherein the preprocessing method includes but is not limited to data cleaning, outlier detection, and filtering and noise reduction processing. Then, the preprocessed sample data set is clustered by a clustering algorithm to obtain multiple intent classes, and an operation intention database is formed based on multiple intent classes, wherein the clustering algorithm includes but is not limited to the K-means clustering algorithm, the Mean-Shift clustering algorithm, and the K-medians clustering algorithm.

[0049] In a specific embodiment, the preprocessed sample data set is clustered by a K-means clustering algorithm. First, the number of joints of various doctor operation intentions is determined according to the doctor's intended operation joint information in the sample data set. The number of categories is determined according to the number of joints of various doctor operation intentions, that is, the classification K value is determined. The calculation formula of the classification number is as follows:

[0050] ;

[0051] in, is the total number of intent categories, is the number of joints of the robot arm, and the function is defined as According to the preprocessed sample data and the number of classifications, iterative training is performed to obtain the centroid of each cluster. When the centroid of each cluster remains unchanged, the clustering results are stopped and output to obtain the classification results of the operation intention. Intent Classes and The centroid of an intention class includes the operation data of each joint of the corresponding intention class.

[0052] In this embodiment, the number of categories is determined by the number of joints of the doctor's operation intention, and then clustering is performed according to the number of categories to obtain corresponding clustering results. This can achieve accurate correspondence between the intention class and the doctor's intended control behavior, and help to construct an intention operation database that is more in line with the doctor's intended operation behavior, thereby making the classification of operation data more accurate, thereby improving the accuracy of non-intentional operation joint types.

[0053] Optionally, the method also includes: dividing the sample data set into subsets according to surgical information to obtain multiple sample data subsets, wherein the surgical information includes one or more information of surgical type, department information and operator information; and constructing a corresponding operation intention database based on each sample data subset.

[0054] Specifically, data can be filtered from the sample data set according to one or more pieces of information in the surgical information. The various pieces of information in the surgical information can be arranged and combined to obtain a variety of information combinations, and sample data subsets corresponding to different information combinations can be obtained. For example, the data filtered out from the sample data set based on the surgical type can be used as a sample data subset, or the data filtered out from the sample data set based on the surgical type and department information can be used as a subset, wherein the surgical information includes but is not limited to the surgical type, department information, and operator information. For each sample data subset, the sample data subset is clustered using a clustering algorithm to obtain multiple intent classes, and an operation intent database is formed based on the multiple intent classes. It should be noted that the sample data subset can also be pre-processed before clustering.

[0055] In this embodiment, different sample data subsets are determined according to the surgical information and clustered to obtain the corresponding operation intention database. This realizes the construction of a personalized operation intention database based on the surgical information and the intelligent identification of positioning operations. The corresponding operation intention database can be intelligently matched according to the surgical information to improve the efficiency of determining the intention class results corresponding to the operating data.

[0056] Correspondingly, the method also includes: obtaining current surgery information and calling a corresponding operation intention database.

[0057] Specifically, when calling pre-built operation intention data, the current surgical information is obtained, and then the operation intention database matching the surgical information is called. There is no need to obtain the entire operation intention database, which reduces the amount of data processing and thus improves the speed of determining the intention classification results corresponding to the operation data.

[0058] S130. Perform motion inhibition on joints of non-intended operation joint types.

[0059] Among them, the joint motion suppression can be specifically understood as reducing or eliminating the vibration and instability of the robot arm during the movement, especially at the joints, through a specific control strategy, so as to improve the movement accuracy and stability of the robot arm. In this embodiment, the movement of the joints of the non-intentional operation joint type is specifically suppressed to ensure that the position of the joints of the non-intentional operation joint type remains unchanged. For determining the control strategy, a corresponding control strategy can be set according to the associated information of the joints of the non-intentional operation joint type, and the associated information includes but is not limited to the torque information and the joint expected position information that cause the joint vibration of the non-intentional operation joint type. The control strategy can set a corresponding inhibition current for different associated information, and the joint motion is suppressed according to the inhibition current.

[0060] Specifically, the motion of the joint of the non-intentional operation joint type can be inhibited by generating an inhibitory current to overcome the torque that causes joint vibration applied to the joint of the non-intentional operation joint type, and the inhibitory current that overcomes the external torque can be determined by a preset inhibitory current determination method. The preset inhibitory current determination method can be to determine the inhibitory current that matches the external torque according to the mapping relationship between the torque and the inhibitory current, or to determine the inhibitory current that matches the external torque by a pre-trained inhibitory current determination network model, which is not limited here. It should be noted that the motion inhibition of the joint of the non-intentional operation joint type is to ensure that the joint of the non-intentional operation joint type cannot be moved due to the external torque. Therefore, the expected position change of the joint of the non-intentional operation joint type can be used as a parameter for determining the inhibitory current. Exemplarily, a mapping relationship between the torque, the expected position change and the inhibitory current can be constructed. For the pre-trained inhibitory current determination network model, during the training process, the expected position change is also used as a training parameter of the model. In this embodiment, since it is to control the non-intentional operation joint not to move due to the external control force, the expected position change of the non-intentional operation joint is 0. To achieve precise control of the motion inhibition process of joints of unintended joint types.

[0061] Optionally, inhibiting movement of joints of the non-intentional operation joint type includes: determining a joint inhibition current of the non-intentional operation joint type, and inhibiting movement of the joints of the non-intentional operation joint type based on the joint inhibition current.

[0062] Specifically, the movement inhibition of the joints of the non-intentional operation joint type is performed by determining the joint inhibition current of the non-intentional operation joint type, specifically by calling the pre-constructed mapping relationship between the joint inhibition current and the external control force, matching the external control force corresponding to the joint of the non-intentional operation joint type with the pre-constructed mapping relationship between the joint inhibition current and the external control force, and determining the joint inhibition current of the non-intentional operation joint type. Optionally, determining the joint inhibition current of the non-intentional operation joint type includes: for any joint of the non-intentional operation joint type, collecting the external control force data of the joint of the non-intentional operation joint type at each moment; determining the joint inhibition current of the joint of the non-intentional operation joint type at each moment based on the pre-constructed mapping relationship between the joint inhibition current and the external control force and the external control force data of the joint of the non-intentional operation joint type at each moment.

[0063] It should be noted that the external control force applied to the joint is often continuous, so it is necessary to continuously detect the external control force of the joints of the non-intentional operation joint type, and continuously collect the external control force at multiple moments in the whole process of applying the external control force on the joint. For any joint of the non-intentional operation joint type, collect the external control force data of the joint of the non-intentional operation joint type at each moment, call the pre-built mapping relationship between the joint inhibition current and the external control force, match the external control force data of the joint of the non-intentional operation joint type at each moment with the mapping relationship, and determine the joint inhibition current of the joint of the non-intentional operation joint type at each moment.

[0064] In this embodiment, by continuously collecting the external control force at multiple moments during the entire process of applying the external control force on the joints of the non-intentional operation joint type, the inhibition current corresponding to the external control force at multiple moments is determined to achieve continuous control of the joints of the non-intentional operation joint type for motion inhibition, overcome the continuously applied external control force, avoid changes in the posture of the joints of the non-intentional operation joint type, eliminate the positioning error of the robotic arm caused by misoperation, and improve the control accuracy and stability of the robotic arm.

[0065] The technical solution of this embodiment is to obtain the operation data of the robot arm at the current moment; classify the operation data based on a pre-constructed operation intention database, determine the intention classification result corresponding to the operation data, and determine the joint operation type of each joint of the robot arm based on the intention classification result; wherein the joint operation type includes the intended operation joint type and the unintended operation joint type; and inhibit the movement of the joints of the unintended operation joint type. This solution classifies the operation data in real time through a pre-constructed operation intention database, determines the unintended operation joints according to the intention classification results, and then promptly inhibits the detected unintended operation joints, thereby realizing the intelligent recognition and intelligent processing of the robot arm's positioning operation intention, avoiding the problem of error in the positioning of the robot arm caused by mistakenly performing positioning operations on unintended operation joints during the robot arm control process, and improving the accuracy, stability and safety of the robot arm control.

[0066] Embodiment 2

[0067] Figure 2 is a flowchart of a robot arm control method provided in the second embodiment of the present invention. This embodiment is a further optimization of the method of the above embodiment. Optionally, traverse the pre-built operation intention database to determine the distance data between the operation data and the operation data corresponding to each intention class in the operation intention database; determine the intention classification result corresponding to the operation data based on the distance data. Figure 2 As shown, the method includes:

[0068] S210, obtaining the operation data of the robot arm at the current moment.

[0069] S220 , traverse the pre-built operation intention database to determine distance data between the operation data and the operation data corresponding to each intention class in the operation intention database.

[0070] The pre-built operation intention database includes multiple intention classes, wherein the intention class includes operation data that satisfies the intention class; the operation data of the robotic arm includes torque data and acceleration data of each joint of the robotic arm.

[0071] Specifically, call the pre-built operation intention database, traverse the pre-built operation intention database, obtain multiple intention classes and corresponding operation data, calculate the distance data between the actual operation data of the robot arm and the operation data corresponding to each intention class in the operation intention database, and the distance calculation can be performed by the following formula:

[0072] ;

[0073] Among them, A is the operation data corresponding to the intention class in the operation intention database, , They represent the operating data of the corresponding joints. B is the actual operating data of the robot arm. , They represent the operation data of the corresponding joints respectively. n is the number of joints of the robot arm. It is any positive integer and can be set according to actual conditions.

[0074] S230. Determine the intention classification result corresponding to the operation data based on the distance data.

[0075] Specifically, after determining the distance data, the operation data corresponding to the minimum value of the distance data is selected, and the intention class corresponding to the operation data is used as the intention classification result.

[0076] S240: Determine the joint operation type of each joint of the robotic arm based on the intention classification result.

[0077] S250. Perform motion inhibition on joints of non-intended operation joint types.

[0078] The technical solution of this embodiment is to obtain the operation data of the robot arm at the current moment; traverse the pre-constructed operation intention database to determine the distance data between the operation data and the operation data corresponding to each intention class in the operation intention database; determine the intention classification result corresponding to the operation data based on the distance data; determine the joint operation type of each joint of the robot arm based on the intention classification result; and inhibit the movement of the joints of the non-intentional operation joint type. This solution classifies the operation data in real time through the pre-constructed operation intention database, quickly determines the intention classification result according to the distance data between the operation data and the operation data corresponding to each intention class in the operation intention database, determines the non-intentional operation joint according to the intention classification result, and then promptly inhibits the detected non-intentional operation joints, thereby realizing the intelligent recognition and intelligent processing of the positioning operation intention of the robot arm, avoiding the problem of positioning errors of the robot arm caused by positioning operations on non-intentional operation joints during the control process of the robot arm, and improving the accuracy, stability and safety of the robot arm control.

[0079] Embodiment 3

[0080] Figure 3 Schematic diagram of the structure of a robot arm control device provided by the third embodiment of the present invention. Figure 3 As shown, the device comprises:

[0081] The operation data acquisition module 310 is used to acquire the operation data of the robot arm at the current moment;

[0082] The joint operation type determination module 320 is used to classify the operation data based on the pre-built operation intention database, determine the intention classification result corresponding to the operation data, and determine the joint operation type of each joint of the robot arm based on the intention classification result; wherein the joint operation type includes the intended operation joint type and the non-intended operation joint type;

[0083] The joint movement inhibition control module 330 is used to inhibit the movement of joints of non-intended operation joint types.

[0084] The technical solution of this embodiment is to obtain the operation data of the robot arm at the current moment through the operation data acquisition module; the joint operation type determination module classifies the operation data based on the pre-constructed operation intention database, determines the intention classification result corresponding to the operation data, and determines the joint operation type of each joint of the robot arm based on the intention classification result; wherein the joint operation type includes the intended operation joint type and the unintended operation joint type; the joint movement inhibition control module inhibits the movement of the joints of the unintended operation joint type. This solution classifies the operation data in real time through the pre-constructed operation intention database, determines the unintended operation joints according to the intention classification result, and then promptly inhibits the detected unintended operation joints, thereby realizing the intelligent recognition and intelligent processing of the positioning operation intention of the robot arm, avoiding the problem of positioning errors of the robot arm caused by positioning the unintended operation joints during the control process of the robot arm, and improving the accuracy, stability and safety of the robot arm control.

[0085] On the basis of the above embodiment, optionally, the pre-built operation intention database includes multiple intention classes, wherein the intention class includes operation data that satisfies the intention class; the operation data of the robotic arm includes torque data and acceleration data of each joint of the robotic arm; the joint operation type determination module 320 is specifically used to traverse the pre-built operation intention database, determine the distance data between the operation data and the operation data corresponding to each intention class in the operation intention database; and determine the intention classification result corresponding to the operation data based on the distance data.

[0086] Optionally, the joint operation type determination module 320 is specifically used to determine the joint operation type information corresponding to the intention classification result based on the mapping relationship between the intention class and the joint operation type information, the joint operation type information includes at least one joint operation type and a corresponding joint identification set, the joint identification set includes at least one joint identifier; based on the joint operation type information, determine the joint operation type of each joint of the robotic arm.

[0087] Optionally, the joint movement inhibition control module 330 is specifically used to determine the joint inhibition current of the non-intentional operation joint type, and to inhibit the movement of the joints of the non-intentional operation joint type based on the joint inhibition current.

[0088] Optionally, the joint motion inhibition control module 330 is also specifically used to collect the external control force data of the joints of the non-intentional operation joint type at each moment for any joint of the non-intentional operation joint type; and determine the joint inhibition current of the joints of the non-intentional operation joint type at each moment based on a pre-built mapping relationship between the joint inhibition current and the external control force and the external control force data of the joints of the non-intentional operation joint type at each moment.

[0089] Optionally, the joint operation type determination module 320 includes an operation intention database construction unit, which is used to obtain a sample data set, preprocess the sample data set to obtain a preprocessed sample data set, wherein the sample data set includes intended operation information and historical operation data of each joint of the robotic arm; cluster the preprocessed sample data set to determine multiple intention classes, and form an operation intention database based on the multiple intention classes.

[0090] Optionally, the operation intention database construction unit is specifically used to subset the sample data set according to the surgical information to obtain multiple sample data subsets, wherein the surgical information includes one or more information of the surgical type, department information and operator information; and to construct a corresponding operation intention database based on each sample data subset. Accordingly, the method also includes: obtaining the current surgical information and calling the corresponding operation intention database.

[0091] Optionally, the joint operation type determination module 320 is further specifically used to obtain current surgical information and call a corresponding operation intention database.

[0092] The robot arm control device provided in the embodiment of the present invention can execute the robot arm control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0093] Embodiment 4

[0094] Figure 4 1 is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0095] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11 in communication, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the random access memory (RAM) 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the read-only memory (ROM) 12, and the random access memory (RAM) 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0096] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0097] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a robotic arm control method.

[0098] In some embodiments, the robot arm control method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via a read-only memory (ROM) 12 and / or a communication unit 19. When the computer program is loaded into a random access memory (RAM) 13 and executed by the processor 11, one or more steps of the robot arm control method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the robot arm control method in any other appropriate manner (e.g., by means of firmware).

[0099] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0100] The computer program for implementing the robot arm control method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0101] Embodiment 5

[0102] Embodiment 5 of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to execute a robot arm control method, the method comprising:

[0103] Get the operation data of the robot arm at the current moment;

[0104] Classify the operation data based on the pre-built operation intention database, determine the intention classification result corresponding to the operation data, and determine the joint operation type of each joint of the robot arm based on the intention classification result; wherein the joint operation type includes the intended operation joint type and the non-intended operation joint type;

[0105] Movement inhibition is performed on joints of non-intended joint types.

[0106] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 foregoing.

[0107] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0108] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by 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), a blockchain network, and the Internet.

[0109] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0110] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0111] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A robot arm control method, characterized in that: include: Get the operation data of the robot arm at the current moment; Classify the operation data based on a pre-built operation intention database, determine the intention classification result corresponding to the operation data, and determine the joint operation type of each joint of the robotic arm based on the intention classification result; wherein the joint operation type includes an intended operation joint type and a non-intended operation joint type; Performing motion inhibition on the joint of the non-intended operation joint type; The pre-built operation intention database includes a plurality of intention classes, wherein the intention class includes operation data satisfying the intention class; the operation data of the robotic arm includes torque data and acceleration data of each joint of the robotic arm; The classifying the operation data based on the pre-built operation intention database to determine the intention classification result corresponding to the operation data includes: Traversing the pre-built operation intention database, determining distance data between the operation data and the operation data corresponding to each intention class in the operation intention database; Determine, based on the distance data, an intention classification result corresponding to the operation data; The determining the joint operation type of each joint of the robot arm based on the intention classification result includes: Determine, based on a mapping relationship between the intention class and the joint operation type information, the joint operation type information corresponding to the intention classification result, wherein the joint operation type information includes at least one joint operation type and a corresponding joint identification set, and the joint identification set includes at least one joint identifier; The joint operation type of each joint of the robot arm is determined based on the joint operation type information.

2. The method according to claim 1, characterized in that The step of inhibiting the movement of the joint of the non-intended operation joint type comprises: A joint inhibition current of the non-intended operation joint type is determined, and movement inhibition is performed on the joint of the non-intended operation joint type based on the joint inhibition current.

3. The method according to claim 2, characterized in that The determining of the joint inhibition current of the unintended operation joint type comprises: For any joint of the non-intentional operation joint type, collecting external control force data of the joint of the non-intentional operation joint type at each moment; The joint inhibition current of the joint of the non-intentional operation joint type at each moment is determined based on the pre-constructed mapping relationship between the joint inhibition current and the external manipulation force and the external manipulation force data of the joint of the non-intentional operation joint type at each moment.

4. The method according to claim 1, characterized in that: Constructing the operation intention database includes: Acquire a sample data set, and preprocess the sample data set to obtain a preprocessed sample data set, wherein the sample data set includes intended operation information and historical operation data of each joint of the robotic arm; The preprocessed sample data set is clustered to determine a plurality of intention classes, and the operation intention database is formed based on the plurality of intention classes.

5. The method according to claim 4, characterized in that The method also includes: Dividing the sample data set into subsets according to the surgical information to obtain a plurality of sample data subsets, wherein the surgical information includes one or more information of surgical type, department information and operator information; and constructing a corresponding operation intention database based on each of the sample data subsets; Accordingly, the method further includes: Get the current surgery information and call the corresponding operation intention database.

6. A robot arm control device, characterized in that: include: An operation data acquisition module is used to obtain the operation data of the robot arm at the current moment; a joint operation type determination module, configured to classify the operation data based on a pre-built operation intention database, determine the intention classification result corresponding to the operation data, and determine the joint operation type of each joint of the robotic arm based on the intention classification result; wherein the joint operation type includes an intended operation joint type and a non-intended operation joint type; A joint motion inhibition control module, used for inhibiting the motion of the joints of the non-intended operation joint type; The pre-built operation intention database includes a plurality of intention classes, wherein the intention class includes operation data satisfying the intention class; the operation data of the robotic arm includes torque data and acceleration data of each joint of the robotic arm; the joint operation type determination module is specifically used to traverse the pre-built operation intention database, determine the distance data between the operation data and the operation data corresponding to each intention class in the operation intention database; and determine the intention classification result corresponding to the operation data based on the distance data; The joint operation type determination module is specifically used to determine the joint operation type information corresponding to the intention classification result based on the mapping relationship between the intention class and the joint operation type information, the joint operation type information includes at least one joint operation type and a corresponding joint identification set, and the joint identification set includes at least one joint identifier; based on the joint operation type information, determine the joint operation type of each joint of the robotic arm.

7. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the robot arm control method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the robot arm control method according to any one of claims 1 to 5 when executed.

Images