A robot arm control method, device and storage medium

Abstract

The present invention discloses a robot control method, device and storage medium. The robot control method includes: when the robot is powered on, the control enters a reset mode, controls the motor to rotate with a preset reset current to drive the finger mechanism to extend to a maximum extension angle; detects whether the current load of the motor increases; when the current load of the motor increases, controls the motor to stop rotating, and when all motors stop rotating, controls the exit from the reset mode. By entering the reset mode, the motor is controlled to rotate with a preset reset current to drive the finger mechanism to extend to a maximum extension angle, and detects whether the current load of the motor increases, controls the motor to stop rotating when the current load of the motor is detected to increase, and controls the exit from the reset mode when all motors are detected to stop rotating, the problem that it is difficult to accurately control the reset to restore to the default gesture posture after the robot suddenly loses power or loses memory, and even damages the fingers.

Description

Technical Field

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

[0002] In the development history of robotic arm technology, in order to be closer to the functions of human limbs, the design and control strategies of robotic arms have been continuously optimized, aiming to help users achieve more comfortable and efficient use of robotic arms to grasp and hold objects and other operational activities.

[0003] The movement of the robot hand includes 6 degrees of freedom, including the flexion of 5 fingers and the abduction of the thumb. Incremental encoders are used to record the position or angle of the fingers. When the robot hand suddenly loses power due to accidentally touching the power off button or some other reasons, the encoder loses its memory function, and the position or angle information of each finger is lost, and the fingers remain in the last posture. After the robot hand is powered on, due to the loss of the current finger position or angle information, it is difficult to accurately control the reset to the default gesture posture through the control of electromyographic signals or forced reset with the normal working current and extension speed, and it may even damage the fingers. Summary of the invention

[0004] The present invention provides a robot arm control method, aiming to solve the problem that after a sudden power outage or memory loss, the robot arm is difficult to accurately control and reset to a default gesture posture, and may even damage the fingers, thereby reducing the risk of users damaging their fingers during use.

[0005] To achieve the above-mentioned object, the present invention provides a control method for a robot arm, wherein the robot arm includes a plurality of finger mechanisms, each of which has a corresponding finger joint, and the finger mechanism drives the finger joint to rotate by a motor so that the finger mechanism extends or bends. The method includes:

[0006] When the robot is powered on, the control enters a reset mode, and the motor is controlled to rotate with a preset reset current to drive the finger mechanism to extend to a maximum extension angle;

[0007] Detecting whether the current load of the motor increases;

[0008] When the current load of the motor increases, controlling the motor to stop rotating;

[0009] And, when all of the motors stop rotating, the control exits the reset mode.

[0010] Optionally, the reset mode includes a first reset mode and a second reset mode, wherein the first reset mode is used to drive the motor to rotate with a preset first reset current so that the finger mechanism is extended close to a maximum angle, and the first reset current is determined according to a default reset current; the second reset mode is used to drive the motor to rotate with a preset second reset current so that the finger mechanism is extended close to a maximum angle, and the second reset current is determined according to a default reset current and an electromyographic signal. After the robot hand is powered on, entering the reset mode includes:

[0011] Detecting whether there is access to the electromyographic signal;

[0012] If it is detected that there is no access to the electromyographic signal, the first reset mode is entered, and the motor is controlled to rotate with a preset first reset current to drive the finger mechanism to extend to a maximum extension angle, and the first reset current is determined according to a default reset current;

[0013] If the presence of the electromyographic signal is detected, the second reset mode is entered to control the motor to rotate with a preset second reset current to drive the finger mechanism to extend to the maximum extension angle, and the second reset current is determined based on the default reset current and the electromyographic signal.

[0014] Optionally, the first reset current is determined according to a default reset current.

[0015] Obtaining the reset time taken for the last entry into the first reset mode and the reset interval time between the last entry into the first reset mode and the current entry into the first reset mode;

[0016] The default reset current is adjusted based on the reset time and the reset interval time to obtain the first reset current.

[0017] Optionally, adjusting the default reset current based on the reset time and the reset interval to obtain the first reset current includes:

[0018] Determine an adjustment curve based on the size relationship between the reset time and the reset time threshold, and the size relationship between the reset interval and the reset interval threshold;

[0019] Based on the adjustment curve, the default reset current is adjusted to obtain the first reset current.

[0020] Optionally, determining the adjustment curve based on the size relationship between the reset time and the reset time threshold, and the size relationship between the reset interval and the reset interval threshold, includes:

[0021] If the reset time is less than the reset time threshold, and the reset interval is greater than or equal to the reset interval threshold, generating a first adjustment curve;

[0022] If the reset time is less than the reset time threshold, and the reset interval is less than the reset interval threshold, a second adjustment curve is generated, and the adjustment range of the second adjustment direction is less than that of the first adjustment curve;

[0023] If the reset time is greater than or equal to the reset time threshold, and the reset interval is greater than or equal to the reset interval threshold, a third adjustment curve is generated, and the adjustment amplitude of the first section of the third adjustment curve is less than the adjustment amplitude of the first section of the first adjustment curve;

[0024] If the reset time is greater than or equal to the reset time threshold, and the reset interval is less than the reset interval threshold, a fourth adjustment curve is generated, and the front adjustment amplitude of the fourth adjustment curve is greater than the front adjustment amplitude of the third adjustment curve.

[0025] Optionally, the second reset current is determined according to a default reset current and an electromyographic signal, including:

[0026] Acquire electromyographic signals;

[0027] Performing feature extraction on the electromyographic signal to obtain a feature value of the electromyographic signal;

[0028] Determining a target action category corresponding to the electromyographic signal based on a characteristic value of the electromyographic signal;

[0029] Based on the target action category, the default reset current is adjusted to obtain the second reset current.

[0030] Optionally, adjusting the default reset current based on the target action category to obtain the second reset current includes:

[0031] Based on the correspondence between the action category and the adjustment curve, determining a fifth adjustment curve corresponding to the target action category;

[0032] Based on the fifth adjustment curve, the default reset current is adjusted to obtain the second reset current.

[0033] Optionally, adjusting the default reset current based on the fifth adjustment curve to obtain the second reset current includes:

[0034] Obtaining the action category of the robot arm when it last performed work as a reference action category;

[0035] If the reference action category is the same as the target action category, increasing the adjustment amplitude of the front section of the fifth adjustment curve;

[0036] If the reference motion category is different from the target motion category, the overall adjustment amplitude of the fifth adjustment curve is reduced.

[0037] The present invention also proposes a robot arm control device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the above-mentioned robot arm control method when executed by the processor.

[0038] The present invention also proposes a robot, comprising a robotic arm and a robotic arm control device, wherein the robotic arm comprises a plurality of finger mechanisms, each finger mechanism having a corresponding finger joint, and the robotic arm control device controls a motor to drive the finger joints to rotate so that the finger mechanisms extend or bend. The robotic arm control device is the robotic arm control device described in an embodiment of the present invention.

[0039] The technical solution of the robot hand control method of the present invention controls the robot hand to enter the reset mode after it is powered on, controls the motor to rotate with a preset reset current to drive the finger mechanism to extend to the maximum extension angle, detects whether the current load of the motor increases, controls the motor to stop rotating when the current load of the motor increases, and controls the exit from the reset mode when all motors stop rotating. The present invention controls the robot hand to enter the reset mode after it is powered on, controls the motor to rotate with a preset reset current to drive the finger mechanism to extend to the maximum extension angle, detects whether the current load of the motor increases in real time, controls the motor to stop rotating when the current load of the motor increases, and controls the exit from the reset mode when all motors stop rotating. This can solve the problem that the robot hand is difficult to accurately control to reset to the default gesture posture after a sudden power outage or memory loss, and may even damage the fingers. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A schematic diagram of a flow chart of a robot arm control method provided by an embodiment of the present invention;

[0041] Figure 2 A schematic diagram of the structure of a robot arm control device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0044] It should also be noted that when an element is referred to as being "fixed on" or "disposed on" another element, it may be directly on the other element or there may be an intermediate element at the same time. When an element is referred to as being "connected to" another element, it may be directly connected to the other element or there may be an intermediate element at the same time.

[0045] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0046] See also Figure 1 , Figure 1 It is a flowchart of a robot arm control method provided by an embodiment of the present invention.

[0047] In this embodiment, the robot comprises a plurality of finger mechanisms, each of which has a corresponding finger joint. The finger mechanisms are driven by motors to rotate the finger joints so that the finger mechanisms are extended or bent. The robot control method comprises the following steps:

[0048] Step S10, when the robot is powered on, the control enters a reset mode, and the motor is controlled to rotate with a preset reset current to drive the finger mechanism to extend to a maximum extension angle.

[0049] In this embodiment, the above-mentioned robot is controlled by a robot system. The robot system may include an operation mode and a reset mode. After the user's limb is connected to the receiving cavity, in the operation mode, the user's limb makes corresponding movements and generates electromyographic signals corresponding to the movements. Then, the motor in the robot generates corresponding action instructions according to the detected electromyographic information, and the multiple finger mechanisms of the robot respond to the action instructions to perform corresponding actions. The above-mentioned electromyographic signals can be understood as electrical signals when muscle tissue contracts. The electromyographic signals reflect the degree of muscle contraction and can be collected by electromyographic induction sensors.

[0050] The above reset mode is used to drive the motor to rotate with a preset reset current so that the finger mechanism is extended to the maximum extension angle, so that the finger mechanism is restored to the default initial position, such as five fingers open. The reset mode can be understood as an operating logic for restoring the initial state of the system in order to restart or correct errors, so that the robot hand can respond to subsequent actions in the initial position again.

[0051] The above reset current can be understood as a current used to return the multiple finger mechanisms of the robot arm to their initial positions. The above reset current is a smaller current value, so that the multiple finger mechanisms of the robot arm can slowly extend and approach the maximum angle at which the finger mechanisms can extend at a smaller reset speed.

[0052] The above-mentioned preset reset current can be understood as the system preset reset current. In order to ensure that the motor can work normally, the preset reset current is a smaller current value, so that the five finger mechanisms of the robot arm can slowly extend and approach the maximum angle that the finger mechanisms can extend at a smaller reset speed.

[0053] The above reset mode can prevent the finger mechanism from entering a random state after power-on, which would cause disorder in the action response of the finger mechanism.

[0054] It should be noted that when the robot enters the reset mode after power-on, the motor is controlled to preset a reset current to drive the finger mechanism to extend to the maximum extension angle. In a possible embodiment, when the robot suddenly loses power due to accidentally touching the power off button or other reasons, the finger maintains the last posture and does not move. After the robot is powered on, it will enter the reset mode.

[0055] Step S20, detecting whether the current load of the motor increases.

[0056] In this embodiment, a current detection circuit may be added to enable real-time monitoring of the motor current.

[0057] The above current load refers to the actual load current of the motor during operation.

[0058] It should be noted that at every moment when the motor is running, the current value at that moment will be detected in real time and compared with the current value at the previous moment. If the current value increases, it means that the load on the motor has increased. By detecting the motor current load in real time, the real-time working status of the motor can be understood in real time.

[0059] Step S30, when the current load of the motor increases, the motor is controlled to stop rotating.

[0060] In this embodiment, if the motor increases the load, it means that the finger mechanism is already in the maximum angle extension state. At this time, it can be determined that the finger mechanism has been reset.

[0061] Step S40, when all motors stop rotating, the control exits the reset mode.

[0062] In this embodiment, when all motors stop rotating, it can be determined that the robot arm has been completely reset and no longer needs to adjust parameters such as position or angle. The robot arm exits the reset mode and stops extending to avoid damaging the fingers.

[0063] Specifically, the robot enters the reset mode after power-on, and controls the motor to rotate with a preset reset current to drive the finger mechanism to move to the initial position according to a certain strategy. A smaller reset current is given to the motor corresponding to each finger mechanism, and it is slowly approached to the maximum angle that the finger mechanism can extend at a smaller reset speed. When the resistance of the limiter at the maximum angle is encountered during the process, the motor load increases due to the application of the limiter resistance, and then the current load increases. If the current load suddenly increases, it is determined that the finger mechanism has reached the maximum angle at this time, and then the extension of the finger mechanism can be stopped, thereby avoiding damage to the finger mechanism and completing the reset.

[0064] Furthermore, after completing the reset, exiting the reset mode and entering the operation mode, the electromyographic signal can be used to instruct the motor to control the position / angle of the finger according to the normal working current, and to control the bending / extension of the finger according to the normal preset speed.

[0065] The robot hand control method of this embodiment is implemented by entering a reset mode after the robot hand is powered on. The reset mode is used to drive the motor to rotate with a preset reset current so that the finger mechanism can be extended and approached to the maximum angle; in the process of driving the motor to rotate, it is detected in real time whether the current load of the motor increases; if the current load of the motor increases, it is determined that the robot hand control is completed and the reset mode is exited. The present invention can solve the problem that it is difficult to accurately control the robot hand to reset to the default gesture posture after a sudden power outage or memory loss, and even damage the fingers, thereby reducing the risk of users damaging their fingers during use.

[0066] It can be understood that in the specific implementation of this application, user data, control data, action data and other related data are involved. When the embodiments in this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data, as well as the training and use of various models need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0067] Optionally, the reset mode includes a first reset mode and a second reset mode. The first reset mode is used to drive the motor to rotate with a preset first reset current so that the finger mechanism is extended close to the maximum angle, and the first reset current is determined according to a default reset current; the second reset mode is used to drive the motor to rotate with a preset second reset current so that the finger mechanism is extended close to the maximum angle, and the second reset current is determined according to the default reset current and the electromyographic signal. After the robot is powered on, in the step of entering the reset mode, it can be detected whether there is access to the electromyographic signal; if it is detected that there is no access to the electromyographic signal, the first reset mode is entered, and the motor is controlled to rotate with the preset first reset current to drive the finger mechanism to extend to the maximum extension angle; if it is detected that there is access to the electromyographic signal, the second reset mode is entered, and the motor is controlled to rotate with the preset second reset current to drive the finger mechanism to extend to the maximum extension angle.

[0068] In the embodiment of the present invention, it is possible to first detect whether there is access to the electromyographic signal, and select the most appropriate reset mode according to the access signal of the electromyographic signal, thereby improving the user experience and effect of the robot hand.

[0069] The reset current driving the motor is used to ensure that the motor can recover from an erroneous state to a current of normal operation.

[0070] The above default reset current is the default reset current of the system, which is a smaller current value to ensure that the circuit can work normally. The first reset current is determined according to the default reset current, which can make the circuit run from the default initial state to avoid entering a random state after power-on and causing circuit disorder.

[0071] The above-mentioned electromyographic signal refers to the electrical signal generated when the muscle contracts. The second reset current is determined according to the default reset current and the electromyographic signal, and the circuit can be adjusted accordingly according to the strength of the electromyographic signal to restore the default initial state operation to ensure the accurate reset of the motor.

[0072] The above-mentioned extension toward the maximum angle can be understood as the finger mechanism being able to be extended as much as possible, such as five fingers being spread out.

[0073] Furthermore, when the robot arm is turned on, if it is detected that there is no electromyographic signal connected, it will enter the first reset mode, and use the preset first reset current to drive the motor to rotate, so that the finger mechanism is extended close to the maximum angle; if it is detected that there is an electromyographic signal connected, it will enter the second reset mode, and use the preset second reset current to drive the motor to rotate, so that the finger mechanism is extended close to the maximum angle.

[0074] Optionally, in the step of determining the first reset current based on the default reset current, the reset time taken for the last time entering the first reset mode and the reset interval between the last time entering the first reset mode and the current time entering the first reset mode can be obtained; based on the reset time taken and the reset interval, the default reset current is adjusted to obtain the first reset current.

[0075] In the embodiment of the present invention, the above reset time can be understood as the time taken to complete the reset from the last time the first reset mode was entered. The above reset time and reset interval time can be obtained through log data or from a server. Each time the reset mode is entered, the corresponding reset data is recorded, and the reset data includes the reset start time, reset time, reset end time, etc. The reset data can be written into the log or uploaded to the server for storage.

[0076] The above reset interval duration can be understood as the time interval from the completion of the last reset to the triggering of the next reset.

[0077] Specifically, after determining the reset time and the reset interval time, the default reset current can be adjusted by programming according to the reset time and the reset interval time to obtain a first reset current value, so that the system can start normally even in the case of frequent resets without causing damage to the chip.

[0078] Specifically, when determining the first reset current, the system will record the reset time and reset interval time of the last time the first reset mode was entered. Next, the default reset current is adjusted based on this information to obtain a more appropriate first reset current. For example, if the reset time is short and the reset interval is long, the value of the default reset current can be appropriately reduced; vice versa. In this way, it can be ensured that the robot arm is in a relatively stable state before each use.

[0079] Optionally, in the step of adjusting the default reset current based on the reset time and the reset interval time to obtain the first reset current, an adjustment curve can be determined based on the relationship between the reset time and the reset time threshold, and the relationship between the reset interval time and the reset interval threshold; based on the adjustment curve, the default reset current is adjusted to obtain the first reset current.

[0080] In this embodiment, the above reset time threshold is a threshold preset by the system, and is a reset time set to prevent the chip from being damaged or unable to start normally due to a long reset period.

[0081] The above reset interval time threshold is a reset interval time threshold preset by the system. The reset interval time threshold is a time interval set to prevent frequent resets from damaging the chip or affecting the normal operation of the system.

[0082] The above adjustment curve is a curve used to describe how the reset current changes with the change of the reset time and the reset interval time.

[0083] Specifically, an adjustment curve may be determined according to the actual reset time and reset interval, and the reset current may be adjusted according to the adjustment curve to better meet actual needs.

[0084] Optionally, in the step of determining the adjustment curve based on the size relationship between the reset time and the reset time threshold, and the size relationship between the reset interval time and the reset interval time threshold, if the reset time is less than the reset time threshold, and the reset interval time is greater than or equal to the reset interval time threshold, a first adjustment curve can be generated; if the reset time is less than the reset time threshold, and the reset interval time is less than the reset interval time threshold, a second adjustment curve can be generated; if the reset time is greater than or equal to the reset time threshold, and the reset interval time is greater than or equal to the reset interval time threshold, a third adjustment curve can be generated; if the reset time is greater than or equal to the reset time threshold, and the reset interval time is less than the reset interval time threshold, a fourth adjustment curve can be generated.

[0085] In this embodiment, the adjustment range of the second adjustment curve is smaller than that of the first adjustment curve, the adjustment range of the first section of the third adjustment curve is larger than that of the first adjustment curve, and the adjustment range of the first section of the fourth adjustment curve is larger than that of the first adjustment curve.

[0086] If the reset time is less than the reset time threshold, and the reset interval is greater than or equal to the reset interval threshold, it means that the time required for reset is short and the interval between resets is long, indicating that the robot may have a low-frequency and short-time reset characteristic. At this time, a first adjustment curve can be generated. The first adjustment curve can be a constant curve. By adjusting the value of the default reset current through the first adjustment curve, the reset process can be carried out with a relatively stable reset current.

[0087] If the reset time is less than the reset time threshold, and the reset interval is less than the reset interval threshold, it means that the reset time is short and the interval between resets is short, indicating that the robot may have a high-frequency and short-time reset characteristic. In order to avoid increased wear of components caused by high-frequency reset, a second adjustment curve can be generated at this time, and the adjustment amplitude of the second adjustment curve is smaller than the first adjustment curve. The second adjustment curve can also be a constant curve. By adjusting the value of the default reset current through the second adjustment curve, the reset process can be carried out with a relatively stable reset current.

[0088] If the reset time is greater than or equal to the reset time threshold, and the reset interval is greater than or equal to the reset interval threshold, this means that the reset time is long and the interval between resets is long, indicating that the robot may have a low-frequency long-time reset characteristic. At this time, a third adjustment curve can be generated. The adjustment amplitude of the front section of the third adjustment curve is greater than the adjustment amplitude of the front section of the first adjustment curve. The adjustment amplitude of the front section of the third adjustment curve is larger, so that the front section of the reset process is performed with a slightly larger reset current, thereby increasing the reset speed of the front section of the reset process, and the rear section is performed with a smaller reset current, so that the rear section of the reset process is smoother.

[0089] If the reset time is greater than or equal to the reset time threshold, and the reset interval is less than the reset interval threshold, it means that the reset time is long and the interval between resets is short, indicating that the robot may have a high-frequency reset characteristic. At this time, a fourth adjustment curve can be generated. The adjustment amplitude of the front section of the fourth adjustment curve is greater than the adjustment amplitude of the front section of the third adjustment curve. The adjustment amplitude of the front section of the fourth adjustment curve is larger, so that the front section of the reset process is performed with a larger reset current, thereby improving the reset speed of the front section of the reset process, and the rear section is performed with a smaller reset current, so that the rear section of the reset process is smoother.

[0090] Optionally, in the step of determining the second reset current based on the default reset current and the electromyographic signal, the electromyographic signal can be obtained; feature extraction is performed on the electromyographic signal to obtain a characteristic value of the electromyographic signal; based on the characteristic value of the electromyographic signal, a target action category corresponding to the electromyographic signal is determined; based on the target action category, the default reset current is adjusted to obtain a second reset current.

[0091] In this embodiment, the electromyographic signal can be obtained by the electromyographic induction sensor, and the electromyographic signal is used to reflect the contraction degree and strength of the finger mechanism.

[0092] The above feature extraction can be understood as a process of extracting effective features from electromyographic signals.

[0093] The above-mentioned characteristic values ​​of the electromyographic signal are used to evaluate the muscle contraction strength and signal complexity.

[0094] The above-mentioned action categories can be understood as different actions produced by contraction of different finger muscles, for example, bending 2 fingers, bending 5 fingers, opening 3 fingers, opening 5 fingers, etc.

[0095] Furthermore, the magnitude and direction of the default reset current can be adjusted according to the current action category to ensure that the finger joints can be correctly reset to the initial position.

[0096] Optionally, in the step of adjusting the default reset current based on the target action category to obtain the second reset current, a fifth adjustment curve corresponding to the target action category can be determined based on the correspondence between the action category and the adjustment curve; based on the fifth adjustment curve, the default reset current is adjusted to obtain the second reset current.

[0097] In this embodiment, the correspondence between the above action categories and the adjustment curves can be understood as a predefined association relationship of the system, and different action categories correspond to different adjustment curves. The adjustment curve is a curve used to describe how the reset current changes with the change of the reset time and the reset interval time.

[0098] The corresponding fifth adjustment curve can be determined according to the target action category through the correspondence between the action category and the adjustment curve, and the default reset current can be adjusted using the fifth adjustment curve to obtain the second reset current.

[0099] Optionally, in the step of adjusting the default reset current based on the fifth adjustment curve to obtain the second reset current, the action category of the robot arm when it last performed an action can be obtained as a reference action category; if the reference action category is the same as the target action category, the adjustment amplitude of the front section of the fifth adjustment curve is increased; if the reference action category is different from the target action category, the overall adjustment amplitude of the fifth adjustment curve is reduced.

[0100] In this embodiment, the last execution action can be understood as the execution action of the finger keeping the last posture when the robot arm suddenly loses power due to accidentally touching the power off button or other reasons.

[0101] The above-mentioned reference action categories can be understood as known action categories that need to be compared with the target action.

[0102] Furthermore, when the action category performed by the robot last time is the same as the target action category to be performed this time, it is necessary to further increase the adjustment amplitude of the front section of the fifth adjustment curve to better adapt to the same action next time, so as to improve the performance and stability of the robot. When the action category performed by the robot last time is different from the target action category to be performed this time, it means that the default reset current in the current state may not be able to fully adapt to the requirements of the target action, so it is necessary to reduce the overall adjustment amplitude to avoid excessive or too small reset current affecting the performance of the robot and damaging the fingers.

[0103] The present invention also provides a robot control device, see Figure 2 , Figure 2 It is a schematic diagram of the structure of a robot control device in a hardware operating environment involved in an embodiment of the present invention.

[0104] The robot control device of the embodiment of the present invention can be a computing device such as a desktop computer, a notebook, a palm computer, and a server. Figure 2 As shown, the robot arm control device may include: a processor 1001 (such as a CPU), a network interface 1004, a user interface 1003, a memory 1005 and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit, such as a keyboard (Keyboard), and the user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0105] Those skilled in the art will understand that Figure 2 The structure of the robot arm control device shown in the figure does not constitute a limitation of the robot arm control device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0106] like Figure 2 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module and a computer program.

[0107] exist Figure 2In the robot arm control device shown, the network interface 1004 is mainly used to connect to the background server and communicate data with the background server; the user interface 1003 is mainly used to connect to the client (user end) and communicate data with the client; and the processor 1001 can be used to call the computer program stored in the memory 1005. When the computer program is called and executed by the processor 1001, the steps of the above-mentioned robot arm control method are implemented.

[0108] Based on the computer program proposed in the aforementioned embodiment, the present invention further proposes a robot, comprising a robot arm and a robot arm control device, the robot arm comprising a plurality of finger mechanisms, each finger mechanism having a corresponding finger joint, the finger mechanism controlling a motor through the robot arm control device to drive the finger joint to rotate so that the finger mechanism extends or bends, the robot arm control device is the robot arm control device recorded in the aforementioned embodiment, the robot stores a computer program, and when the computer program is executed by a controller, the robot arm control method recorded in the aforementioned embodiment is implemented.

[0109] Since the robot control device and robot of the present invention can implement the steps of the above-mentioned robot control method, they at least have all the beneficial effects brought by the technical solutions of the above-mentioned robot control method embodiments, which will not be described one by one here.

[0110] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0111] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0112] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0113] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0114] The above description is only a partial or preferred embodiment of the present invention. Neither the text nor the drawings can limit the scope of protection of the present invention. All equivalent structural changes made by using the contents of the present invention specification and drawings under the overall concept of the present invention, or direct / indirect application in other related technical fields are included in the scope of protection of the present invention.

Claims

1. A robot arm control method, characterized in that: The robot arm includes a plurality of finger mechanisms, each of which has a corresponding finger joint, and the finger mechanism drives the finger joint to rotate by a motor so that the finger mechanism is extended or bent. The method includes: When the robot is powered on, the control enters a reset mode, and the motor is controlled to rotate with a preset reset current to drive the finger mechanism to extend to a maximum extension angle; The reset mode includes a first reset mode and a second reset mode, wherein the first reset mode is used to drive the motor to rotate with a preset first reset current so that the finger mechanism approaches the maximum extension angle, and the first reset current is determined according to a default reset current; the second reset mode is used to drive the motor to rotate with a preset second reset current so that the finger mechanism approaches the maximum extension angle, and the second reset current is determined according to a default reset current and an electromyographic signal; after the robot is powered on, the reset mode is entered to detect whether there is access to the electromyographic signal; if it is detected that there is no access to the electromyographic signal, the first reset mode is entered to control the motor to rotate with a preset first reset current to drive the finger mechanism to extend to the maximum extension angle, and the first reset current is determined according to the default reset current; if it is detected that there is access to the electromyographic signal, the second reset mode is entered to control the motor to rotate with a preset second reset current to drive the finger mechanism to extend to the maximum extension angle, and the second reset current is determined according to the default reset current and the electromyographic signal; Detecting whether the current load of the motor increases; When the current load of the motor increases, controlling the motor to stop rotating; And, when all of the motors stop rotating, the control exits the reset mode.

2. The robot arm control method according to claim 1, characterized in that: The first reset current is determined according to a default reset current, including: Obtaining the reset time taken for the last entry into the first reset mode and the reset interval time between the last entry into the first reset mode and the current entry into the first reset mode; The default reset current is adjusted based on the reset time and the reset interval time to obtain the first reset current.

3. The robot arm control method according to claim 2, characterized in that: The adjusting the default reset current based on the reset time and the reset interval time to obtain the first reset current includes: Determine an adjustment curve based on the size relationship between the reset time and the reset time threshold, and the size relationship between the reset interval and the reset interval threshold; Based on the adjustment curve, the default reset current is adjusted to obtain the first reset current.

4. The robot arm control method according to claim 3, characterized in that: The determining of the adjustment curve based on the size relationship between the reset time and the reset time threshold, and the size relationship between the reset interval and the reset interval threshold, includes: If the reset time is less than the reset time threshold, and the reset interval is greater than or equal to the reset interval threshold, generating a first adjustment curve; If the reset time is less than the reset time threshold, and the reset interval is less than the reset interval threshold, a second adjustment curve is generated, and the adjustment range of the second adjustment curve is less than the first adjustment curve; If the reset time is greater than or equal to the reset time threshold, and the reset interval is greater than or equal to the reset interval threshold, a third adjustment curve is generated, and the adjustment amplitude of the first section of the third adjustment curve is greater than the adjustment amplitude of the first section of the first adjustment curve; If the reset time is greater than or equal to the reset time threshold, and the reset interval is less than the reset interval threshold, a fourth adjustment curve is generated, and the front adjustment amplitude of the fourth adjustment curve is greater than the front adjustment amplitude of the third adjustment curve.

5. The robot arm control method according to any one of claims 1 to 4, characterized in that: The second reset current is determined according to the default reset current and the electromyographic signal, including: Acquire electromyographic signals; Performing feature extraction on the electromyographic signal to obtain a feature value of the electromyographic signal; Determining a target action category corresponding to the electromyographic signal based on a characteristic value of the electromyographic signal; Based on the target action category, the default reset current is adjusted to obtain the second reset current.

6. The robot arm control method according to claim 5, characterized in that: The adjusting the default reset current based on the target action category to obtain the second reset current includes: Based on the correspondence between the action category and the adjustment curve, determining a fifth adjustment curve corresponding to the target action category; Based on the fifth adjustment curve, the default reset current is adjusted to obtain the second reset current.

7. The robot arm control method according to claim 6, characterized in that: The step of adjusting the default reset current based on the fifth adjustment curve to obtain the second reset current includes: Obtaining the action category of the robot arm when it last performed an action as a reference action category; If the reference action category is the same as the target action category, increasing the adjustment amplitude of the front section of the fifth adjustment curve; If the reference motion category is different from the target motion category, the overall adjustment amplitude of the fifth adjustment curve is reduced.

8. A robot arm control device, characterized in that: The robot arm control device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the robot arm control method according to any one of claims 1 to 7 are implemented.

9. A robot, characterized in that: The robot includes a robotic arm and a robotic arm control device. The robotic arm includes multiple finger mechanisms, each finger mechanism has a corresponding finger joint, and the finger mechanism controls a motor through the robotic arm control device to drive the finger joint to rotate so that the finger mechanism extends or bends. The robotic arm control device is the robotic arm control device as described in claim 8.

Images