Bionic hand control method, device, electronic device and storage medium

Abstract

The present disclosure provides a bionic hand control method, device, electronic device and storage medium, wherein an inertial measurement unit and an electromyographic sensor are provided in the bionic hand. The bionic hand control method of the present disclosure embodiment comprises: when the wearer of the bionic hand is in motion, obtaining the motion data of the bionic hand measured by the inertial measurement unit; using the motion data of the bionic hand to obtain the shaking characteristics of the bionic hand and the motion characteristics of the wearer; judging whether the shaking characteristics of the bionic hand and the motion characteristics of the wearer meet the predetermined shaking conditions; if the predetermined shaking conditions are met, controlling the bionic hand to lock and maintain a first preset posture, and lowering the sampling frequency of the electromyographic sensor. The present disclosure can effectively avoid erroneous operations caused by shaking of the bionic hand when the wearer is in motion.

Description

Technical Field

[0001] The present disclosure relates to the field of robotics technology, and in particular to a bionic hand control method, device, electronic device and storage medium. Background Art

[0002] Bionic hands are hand-assistive devices designed to mimic the structure and function of a biological hand. They typically include multiple degrees of freedom, are capable of performing a variety of grasping and manipulation tasks, and are designed to mimic the look and feel of a real hand. Bionic hands may include advanced technologies such as myoelectric control, tactile feedback, or use lightweight materials to mimic the weight and movement of a real hand. Such hand devices are intended to provide not only basic functionality, but also a more natural and intuitive user experience.

[0003] At present, the control of the bionic hand is mainly achieved by building myoelectric sensors into the bionic hand. After the user wears the bionic hand, the myoelectric sensors built into the bionic hand come into contact with the user's skin to collect the myoelectric signals of the user's skin, and the movements of the fingers of the bionic hand are controlled by analyzing the myoelectric signals. However, when the wearer of the bionic hand is doing activities such as running, brisk walking, strolling, etc., the bionic hand will shake, and the contact between the myoelectric sensors and the user's skin is likely to be insufficient, and the myoelectric signals are of poor quality and disorder, resulting in the bionic hand being unable to make movements or operations that meet the wearer's intentions, affecting the user experience. Summary of the invention

[0004] In view of this, the present disclosure provides a bionic hand control method, device, electronic device and storage medium.

[0005] According to a first aspect of the present disclosure, a bionic hand control method is provided, wherein an inertial measurement unit is provided in the bionic hand, and an electromyographic sensor is provided in an inner cavity of the bionic hand, and the method comprises:

[0006] When the wearer of the bionic hand is in motion, acquiring motion data of the bionic hand measured by the inertial measurement unit;

[0007] Using the motion data of the bionic hand to obtain the shaking characteristics of the bionic hand and the motion characteristics of the wearer;

[0008] Determining whether the shaking characteristics of the bionic hand and the movement characteristics of the wearer meet a predetermined shaking condition;

[0009] If the predetermined shaking condition is met, the bionic hand is controlled to lock and maintain the first preset posture, and the sampling frequency of the electromyographic sensor is lowered.

[0010] In some embodiments of the first aspect of the present disclosure, the method further includes: if the predetermined shake condition is not met, entering a shake protection mode, in which the current posture of the bionic hand is locked and the electromyographic sensor is controlled to stop collecting electromyographic signals.

[0011] In some embodiments of the first aspect of the present disclosure, the method also includes: after entering the shake protection mode, determining whether the current posture of the bionic hand is a second preset posture; if the current posture of the bionic hand is the second preset posture, adjusting the input signal of the drive motor in the bionic hand to enhance the gripping force of the bionic hand, the drive motor being arranged inside the bionic hand and connected to the finger joints of the bionic hand.

[0012] In some implementations of the first aspect of the present disclosure, the step of acquiring the shaking characteristics of the bionic hand and the motion characteristics of the wearer by using the motion data of the bionic hand includes:

[0013] Processing the motion data of the bionic hand using a pre-trained motion analysis model to obtain motion characteristics of the bionic hand, wherein the motion characteristics include the motion frequency and motion type of the wearer;

[0014] The motion data of the bionic hand is processed using a pre-trained jitter analysis model to obtain jitter characteristics of the bionic hand, wherein the jitter characteristics include the jitter type, jitter frequency and jitter peak value of the bionic hand.

[0015] In some implementations of the first aspect of the present disclosure, the predetermined jitter condition includes one or more of the following:

[0016] The motion type of the wearer and the shaking type of the bionic hand are both periodic motion, and the shaking peak value of the bionic hand does not exceed a preset shaking threshold;

[0017] The motion type of the wearer and the shaking type of the bionic hand are both periodic motions, and the difference between the shaking frequency of the bionic hand and the motion frequency of the wearer is less than a preset frequency threshold.

[0018] In some implementations of the first aspect of the present disclosure, the method further includes: unlocking the bionic hand in response to a first operation of a user on a physical key.

[0019] In some embodiments of the first aspect of the present disclosure, the method further comprises:

[0020] Receiving electromyographic signals collected in real time by the electromyographic sensor of the bionic hand;

[0021] Determining a desired action according to the electromyographic signal, wherein the desired action is the action that the wearer expects the bionic hand to perform;

[0022] When the expected action is a preset action, the bionic hand is unlocked and controlled to perform the expected action.

[0023] According to a second aspect of the present disclosure, there is provided a bionic hand control device, comprising:

[0024] A data acquisition unit, used for acquiring the motion data of the bionic hand measured by the inertial measurement unit when the wearer of the bionic hand is in motion;

[0025] A feature extraction unit, used for acquiring the shaking features of the bionic hand and the motion features of the wearer by using the motion data of the bionic hand;

[0026] A shaking verification unit, used to determine whether the shaking characteristics of the bionic hand and the movement characteristics of the wearer meet a predetermined shaking condition;

[0027] The first locking unit is used to control the bionic hand to lock and maintain a first preset posture and lower the sampling frequency of the electromyographic sensor when the predetermined shaking condition is met.

[0028] According to a third aspect of the present disclosure, an electronic device is provided, comprising: one or more processors and a memory storing a program, wherein the program comprises instructions, and when the instructions are executed by the processor, the processor executes the above method.

[0029] According to a fourth aspect of the present disclosure, a computer-readable storage medium storing a program is provided, wherein the program includes instructions, which, when executed by one or more processors of a computing device, cause the computing device to execute the above method.

[0030] It can be seen from the above technical solutions that, through the disclosed embodiment, the motion data of the bionic hand is detected in real time through the inertial measurement unit, the shaking characteristics of the bionic hand and the motion characteristics of the wearer are obtained according to the motion data, and when the shaking characteristics of the bionic hand and the motion characteristics of the wearer meet the predetermined shaking conditions, the bionic hand is controlled to lock and maintain the first preset posture, and the sampling frequency of the electromyographic sensor is lowered. The method of the disclosed embodiment can effectively avoid erroneous operation caused by the shaking of the bionic hand during the wearer's movement, and the sampling frequency of the electromyographic sensor is lowered while locking the bionic hand. It can also reduce power consumption without affecting the work of the bionic hand, save electricity, and extend the use time of the bionic hand, thereby significantly improving the user experience of the bionic hand while meeting the actual application needs of the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 A schematic diagram of the structure of a bionic hand control system provided in an embodiment of the present disclosure;

[0033] Figure 2 A flow chart of a bionic hand control method provided by an embodiment of the present disclosure;

[0034] Figure 3 Another flow chart of the bionic hand control method provided by the embodiment of the present disclosure;

[0035] Figure 4 A schematic diagram of the structure of a bionic hand control device provided in an embodiment of the present disclosure;

[0036] Figure 5 A schematic structural block diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0038] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments, and are not intended to limit the present disclosure. The singular forms "a", "said" and "the" used in the embodiments of the present disclosure and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0039] As used herein, the words "if," "if," and the like may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0040] As described in the background technology, when the wearer of the bionic hand is doing activities such as running, brisk walking, or strolling, the bionic hand will shake, and the contact between the electromyographic sensor and the user's skin is likely to be insufficient. The electromyographic signal quality is poor and disordered, resulting in the bionic hand being unable to make movements or operations that are consistent with the wearer's intentions, affecting the user experience.

[0041] When the bionic hand is in an unstable state such as shaking, the myoelectric sensor does not have sufficient contact with the user's skin, and the collected myoelectric signals are of poor quality and disordered, causing the bionic hand's fingers to make incorrect movements or even misoperations, affecting the user experience. For example, when controlling the bionic hand to grasp a heavy object, if misoperations occur due to the above problems, the object may slip due to insufficient gripping force, random finger movements, and other problems.

[0042] In view of this, the embodiments of the present disclosure provide the following bionic hand control method, device, electronic device and storage medium, which detect the motion data of the bionic hand in real time through an inertial measurement unit, obtain the shaking characteristics of the bionic hand and the motion characteristics of the wearer according to the motion data, and when the shaking characteristics of the bionic hand and the motion characteristics of the wearer meet the predetermined shaking conditions, control the bionic hand to lock and maintain the first preset posture, and lower the sampling frequency of the electromyographic sensor. The method of the embodiment of the present disclosure can effectively avoid erroneous operation caused by the shaking of the bionic hand during the wearer's movement, lower the sampling frequency of the electromyographic sensor while locking the bionic hand, and can also reduce power consumption without affecting the work of the bionic hand, save electricity, and extend the use time of the bionic hand, thereby significantly improving the user experience of the bionic hand while meeting the actual application needs of the user.

[0043] To facilitate understanding, the bionic hand control system provided in the embodiment of the present disclosure is first exemplarily described below.

[0044] Figure 1 FIG. 2 shows a schematic diagram of the structure of a bionic hand control system provided by an embodiment of the present disclosure. Figure 1 The bionic hand control system provided by the embodiment of the present disclosure includes: an electromyographic sensor 110, an inertial measurement unit (IMU) 120 and an electronic device 130. The electromyographic sensor 110 and the inertial measurement unit 120 are both arranged in a bionic hand 140. When worn, the electromyographic sensor 110 in the bionic hand 140 can contact the wearer's skin. The electromyographic sensor 110 and the inertial measurement unit 120 can communicate with the electronic device 130 respectively. The electronic device 130 can be used to control the bionic hand to make movements through the bionic hand control method described below.

[0045] Figure 1 An example of a bionic hand is also shown. Figure 1In the example of , the bionic hand 140 includes five fingers 141, a palm 142, a wrist 143, and a receiving cavity 144. In a specific application, the IMU 120 can be arranged in the palm 142, the wrist 143 and / or the receiving cavity 144 of the bionic hand, and the myoelectric sensor 110 can be arranged in the receiving cavity 144 so that the myoelectric sensor can fully contact the user's skin to collect myoelectric signals.

[0046] In a specific application, a driving motor is provided inside the bionic hand 140, and the driving motor is connected to the finger joints of the bionic hand 140. The driving motor drives the fingers 141 of the bionic hand 140 to move under the control of an input signal. The driving motor is electrically connected to the electronic device 130, and the input signal of the driving motor can be provided by the electronic device 130.

[0047] It should be noted that Figure 1 The structure of the bionic hand 140 is only used as an example. Those skilled in the art should understand that the structure of the bionic hand is different in different application scenarios. For example, in other examples, the bionic hand may have fewer or more than five fingers, and the wrist may be designed as a hollow structure to be used as a receiving cavity at the same time. The embodiments of the present disclosure are applicable to bionic hands of any structure.

[0048] The myoelectric sensor 110 generates an electromyographic signal by sensing the contraction of the wearer's skin or muscles. In some examples, the myoelectric sensor 110 may be, but is not limited to, a surface electromyographic sensor, and the electromyographic signal may be, but is not limited to, a surface electromyography (sEMG).

[0049] The inertial measurement unit 120 can measure the motion data of the bionic hand 140 in real time. In specific applications, the inertial measurement unit 120 may include but is not limited to a gyroscope, an accelerometer, a magnetometer, etc., and the motion data collected by the inertial measurement unit 120 may include but is not limited to angular velocity, linear acceleration, magnetic field strength, etc. In some examples, the inertial measurement unit 120 can be arranged in different areas of the bionic hand, such as the palm, back of the hand, wrist, fingers, etc., so as to capture the motion data of each part of the bionic hand.

[0050] See also Figure 1 The electronic device 130 may include a controller 131 and a communication module 132. The communication module 132 is electrically connected to the controller 131. The communication module 132 may communicate with the myoelectric sensor 110 to obtain myoelectric signals generated by the contraction of muscles (e.g., arms, wrists, or hands) of a user wearing a bionic hand 140. The communication module 132 may communicate with the inertial measurement unit 120 to obtain motion data of the bionic hand 140. The controller 131 may be used to execute the bionic hand control method described below.

[0051] In a specific application, the electronic device 130 can be implemented as a microcontroller or other control device that can be built into the bionic hand. Alternatively, the electronic device 130 can be implemented as a device such as a computer or a server that is arranged outside the bionic hand.

[0052] In specific applications, the communication module 132 can be implemented as but not limited to a Bluetooth module, a short-range communication module, an Ethernet communication interface or other similar modules to communicate wirelessly. In addition, the communication module 132 can also be implemented as a communication data serial port or other electrical connection interface to communicate by wire.

[0053] The above system architecture of the embodiment of the present disclosure is only an example. Those skilled in the art should understand that in specific applications, the bionic hand control system may also adopt any other applicable architecture, and the embodiment of the present disclosure does not limit this.

[0054] The bionic hand control method provided by the embodiment of the present disclosure is described in detail below.

[0055] Figure 2 FIG. 1 is a flow chart of a bionic hand control method provided by an embodiment of the present disclosure. The bionic hand control method provided by an embodiment of the present disclosure can be executed by the aforementioned electronic device 130. Figure 2 , the method of the embodiment of the present disclosure may include:

[0056] Step 201, when the wearer of the bionic hand is in motion, obtaining motion data of the bionic hand measured by an inertial measurement unit;

[0057] Step 202, using the motion data of the bionic hand to obtain the shaking characteristics of the bionic hand and the motion characteristics of the wearer;

[0058] Step 203, determining whether the shaking characteristics of the bionic hand and the movement characteristics of the wearer meet a predetermined shaking condition;

[0059] Step 204: If the predetermined shaking condition is met, the bionic hand is controlled to lock and maintain the first preset posture, and the sampling frequency of the electromyographic sensor is lowered.

[0060] Figure 3 Another schematic diagram of the flow chart of the bionic hand control method provided by the embodiment of the present disclosure is shown. Figure 3The method of the disclosed embodiment may further include: step 205, if the predetermined shaking condition is not met, then entering the shaking protection mode, in which the current posture of the bionic hand is locked, and the electromyographic sensor is controlled to stop collecting electromyographic signals. Thus, when the bionic hand shakes abnormally during the wearer's movement, the posture of the bionic hand can be locked and the electromyographic signal collection can be stopped, so as to prevent the bionic hand from being misoperated due to abnormal shaking, and at the same time avoid affecting the posture stability of the bionic hand due to the disorder of the electromyographic signal.

[0061] The specific implementation of the bionic hand control method provided by the embodiment of the present disclosure is described in detail below.

[0062] In step 201, if there are a large number of inertial measurement units installed in the bionic hand and they are distributed in different parts of the bionic hand, all motion data measured by all inertial measurement units within a predetermined time (for example, 1 minute, 5 minutes or 10 minutes, etc.) can be obtained simultaneously. The motion data collected by each inertial measurement unit includes angular velocity, acceleration, etc. Here, the predetermined time can be set by the wearer, or it can be flexibly configured according to different application scenarios.

[0063] In step 201, the motion state of the wearer is not restricted. For example, the motion state of the wearer may be, but is not limited to, walking, running, rotating, or other various motions. The motion state may be set by the wearer, or may not be set, or may be set to a default value. The method of the disclosed embodiment may be triggered upon detecting that the wearer of the bionic hand is in a motion state, that is, the bionic hand control method of the disclosed embodiment may be triggered upon determining that the wearer of the bionic hand is in a motion state based on the motion data of the bionic hand measured in real time by the inertial measurement unit. Thus, the bionic hand control method of the disclosed embodiment may be automatically triggered, thereby further improving the user experience.

[0064] In step 202, the motion data of the bionic hand may be processed using a pre-trained motion analysis model to obtain motion features of the bionic hand. The motion features may include but are not limited to the wearer's motion frequency and motion type.

[0065] Here, the motion type includes periodic motion such as walking, running, rotating, etc., and the motion frequency represents the frequency of the wearer's periodic motion.

[0066] Specifically, a motion analysis model can be constructed using a machine learning model, using pre-collected bionic hand motion data annotated with the wearer's motion type and motion frequency as the first sample, using a large number of collected first samples to form a first training set, a first test set and a first validation set, using the first training set to train the motion analysis model so that the motion analysis model can identify the motion type and obtain the motion frequency, and then evaluating the performance of the motion analysis model through the first validation set and the first test set until the performance of the motion analysis model meets the requirements. In step 202, the motion data of the bionic hand is input into the motion analysis model for processing to obtain the wearer's motion type and motion frequency.

[0067] In step 202, the motion data of the bionic hand may be processed using a pre-trained jitter analysis model to obtain jitter characteristics of the bionic hand, which may include but are not limited to the jitter type, jitter frequency, and jitter peak value of the bionic hand.

[0068] Here, the shaking type may include but is not limited to periodic motions such as swinging and rotating, the shaking frequency represents the frequency of the bionic hand shaking, and the shaking peak represents the amplitude of the bionic hand shaking.

[0069] Specifically, a machine learning model such as a convolutional neural network, a recurrent neural network, a variational encoder, etc. can be used to construct a jitter model, collect bionic hand motion data marked with jitter values ​​as a second sample, use a large number of collected second samples to form a second training set, a second test set, and a second validation set, use the second training set to train the jitter model so that the jitter model can obtain the jitter value of the bionic hand, and then evaluate the performance of the jitter model through the second validation set and the second test set until the performance of the jitter model meets the requirements. In step 202, the motion data of the bionic hand is input into the jitter model for processing to obtain the jitter value of the bionic hand, and the jitter value can indicate the degree of jitter of the bionic hand when the wearer is in motion.

[0070] Furthermore, the jitter model can also be trained as a model for extracting jitter characteristics of bionic hand fingers, and the training method is the same as the above method. The jitter value obtained using the jitter model can more accurately reflect the degree of finger jitter of the bionic hand.

[0071] Furthermore, before or during step 202, the motion data may be pre-processed to remove noise, thereby improving the data quality of the motion data and further improving the accuracy of the jitter feature and the motion feature.

[0072] In addition, motion features and jitter features can also be obtained through other implementation methods. In some examples, the motion data of the bionic hand can be Fourier transformed to implement frequency domain analysis to obtain motion features and jitter features. In some examples, features such as peak values, valley values, average values, and periodic patterns of acceleration and angular velocity can be extracted from the motion data of the bionic hand to obtain motion features and jitter features.

[0073] The specific implementation of step 202 is not limited in the embodiment of the present disclosure.

[0074] In step 203, the predetermined shaking conditions may include but are not limited to one or more of the following: 1) the wearer's movement type and the bionic hand's shaking type are both periodic movements, and the bionic hand's shaking peak value does not exceed a preset shaking threshold; 2) the wearer's movement type and the bionic hand's shaking type are both periodic movements, and the difference between the wearer's movement frequency and the wearer's shaking frequency is less than a preset frequency threshold.

[0075] In step 203, it is determined whether it is a periodic motion according to the type of motion of the wearer and the type of shaking of the bionic hand. If the type of motion of the wearer and the type of shaking of the bionic hand are both periodic motions, the above-mentioned conditions can be further verified for the shaking peak value and / or shaking frequency of the bionic hand. If the type of motion of the wearer and the type of shaking of the bionic hand meet the predetermined shaking conditions, it means that the shaking of the bionic hand is normal, and the step 204 can be continued to avoid misoperation caused by the shaking of the bionic hand caused by the motion of the wearer. If the type of motion of the wearer and the type of shaking of the bionic hand meet the predetermined shaking conditions, it means that the shaking of the bionic hand is abnormal, and the step 205 can be continued to enter the shaking protection mode to prevent misoperation caused by abnormal shaking of the bionic hand during the motion of the wearer.

[0076] It should be noted that the predetermined jitter condition in the embodiment of the present disclosure may also include other contents, and the predetermined jitter condition may be flexibly adjusted according to different specific application scenarios and actual application requirements.

[0077] Taking into account that different people have different hand swing frequencies and swing amplitudes when walking, running, and other motion states, in some implementations, the jitter threshold and frequency threshold can be calibrated based on the motion data collected when the wearer wears the bionic hand. In this way, the jitter threshold and frequency threshold are more in line with the characteristics of the specific wearer, thereby further improving the effectiveness of the wearer's bionic hand posture control when in motion, thereby further improving the user experience.

[0078] In addition, the jitter threshold and the frequency threshold may also be set to empirical values ​​as default settings. The embodiments of the present disclosure do not limit the specific values ​​and configurations of the jitter threshold and the frequency threshold.

[0079] In step 204, the finger posture of the bionic hand can be locked by sending a first control signal to the drive motor in the bionic hand. Specifically, when it is determined that the motion characteristics and the shaking characteristics meet the predetermined shaking conditions, it means that the shaking of the bionic hand belongs to normal shaking. At this time, the first locking mechanism will be automatically triggered. Under the first locking mechanism, a first control signal will be sent to the drive motor in the bionic hand. The drive motor reads the pre-configured parameter value of the first preset posture in response to the first control signal, and uses the parameter value of the first preset posture to control the bionic hand to execute and maintain the first preset posture, thereby locking the bionic hand in the first preset posture. The parameter value of the first preset posture may include the values ​​of the posture type, joint angle, finger position, finger direction (for example, flexion / extension, adduction / abduction, rotation, etc.) of the first preset posture, etc.

[0080] In step 204, the first preset posture can be set by the wearer himself or by default configuration. For example, when the wearer A is stationary or in motion, the wearer A wears the bionic hand, and the wearer A operates the bionic hand to enter the preset posture setting mode. In the preset posture setting mode, the electromyographic sensor collects the electromyographic signal generated by the contraction of the wearer A's skin, identifies the desired posture of the wearer A through the electromyographic signal, controls the bionic hand to make the desired posture, and saves the posture parameters of the desired posture in response to the operation of the wearer A (for example, pressing a physical button, etc.), thereby setting the desired posture of the wearer A as the first preset posture. In this way, different first preset postures can be set for different wearers, and the personalized needs of the wearers can be met at the same time.

[0081] In step 204, the low-power sampling frequency of the electromyographic sensor in motion can be pre-configured. When the shaking characteristics of the bionic hand and the motion characteristics of the wearer meet the predetermined shaking conditions, the sampling frequency of the electromyographic sensor can be adjusted to the low-power sampling frequency, thereby reducing power consumption, saving electricity, and extending the use time of the bionic hand. Here, the low-power sampling frequency of the electromyographic sensor can be freely set as needed, and can also be flexibly modified according to the actual needs of different scenarios.

[0082] In step 205, the current posture of the bionic hand can be locked by sending a second control signal to the drive motor in the bionic hand. Specifically, after entering the shake protection mode, the second locking mechanism is automatically triggered, and the second control signal instructing the drive motor to control the bionic hand to maintain the current posture is sent to the drive motor in the bionic hand to lock the current posture of the bionic hand. In specific applications, the first control signal can be calculated by, for example, a PID (i.e., proportional integral differential) control algorithm, an adaptive control algorithm, or any other applicable control algorithm.

[0083] The current posture of the bionic hand can be determined in the following manner: in step 201, the electromyographic signals collected by the electromyographic sensors are simultaneously acquired, the desired posture of the wearer is identified using the electromyographic signals, and the bionic hand is controlled to execute the desired posture.

[0084] In step 205, the electromyographic sensor can be controlled to stop collecting electromyographic signals in one of the following ways: 1) a status flag can be set for the electromyographic sensor. When the value of the status flag is "stop", the electromyographic sensor interrupts the collection of electromyographic signals. If the status flag is "start", the electromyographic sensor will work in a state of real-time collection of electromyographic signals. In this example, after entering the jitter protection mode, the status flag of the electromyographic sensor can be automatically updated to "stop" to control the electromyographic sensor to stop collecting electromyographic signals; 2) an interrupt event can be set to trigger the electromyographic sensor to stop collecting, and the trigger condition of the interrupt event is set to "entering jitter protection mode". In this way, once the bionic hand enters the jitter protection mode, the first event is triggered, and the electromyographic sensor will automatically stop collecting electromyographic signals.

[0085] Further, see Figure 3 After step 205, the following steps 206 to 208 may also be included:

[0086] Step 206, after entering the shake protection mode, determining whether the current posture of the bionic hand is a second preset posture;

[0087] Step 207: if the current posture of the bionic hand is the second preset posture, the input signal of the drive motor in the bionic hand is adjusted to enhance the gripping force of the bionic hand, the drive motor being arranged inside the bionic hand and connected to the finger joints of the bionic hand.

[0088] Step 208: If the current posture of the bionic hand is not the second preset posture, no action is performed.

[0089] This can prevent objects from slipping due to a loose grip caused by abnormal shaking of the bionic hand.

[0090] In step 206, various applicable methods may be used to determine whether the current posture of the bionic hand is the second preset posture.

[0091] In some examples, it is possible to determine whether the finger posture is the second preset posture by the type of posture. Specifically, a second preset posture list can be pre-set, and the second preset posture list contains type information of the second preset posture. The second preset posture can be, but is not limited to, grasping, grabbing, pinching, pinching, and other postures that are sensitive to misoperation. After determining the posture type of the current finger of the bionic hand using the electromyographic signal collected by the electromyographic sensor, it is determined whether the type of the current posture of the bionic hand is included in the second preset posture list. If so, it is determined that the current posture of the bionic hand is the second preset posture, otherwise the current posture of the bionic hand is not the second preset posture.

[0092] In some examples, it is possible to determine whether the finger posture of the bionic hand is the second preset posture by the posture parameter. Specifically, the second preset posture list can be preconfigured, and the second preset posture list includes one or more parameter values ​​of the second preset posture and their difference thresholds. The posture parameters include but are not limited to joint angles, finger positions, and finger directions, and the difference thresholds include but are not limited to joint angle thresholds, finger position thresholds, and finger direction thresholds. After determining the parameter values ​​of the current posture of the bionic hand using the electromyographic signal collected by the electromyographic sensor, the difference between each parameter value of the current posture of the bionic hand and the corresponding parameter value of the second preset posture is calculated (for example, absolute difference, variance, relative difference rate, percentage difference rate, etc.). If the difference of all parameters is not greater than the difference threshold of the corresponding parameter, the current posture of the bionic hand is the second preset posture. After the difference between the current posture of the bionic hand and each second preset posture in the second preset posture list is judged, if no second preset posture meets the condition of "the difference is not greater than the corresponding threshold", the current posture of the bionic hand is not the second preset posture.

[0093] Of course, the specific implementation methods of judging whether the current posture of the bionic hand is the preset posture are not limited to the above two. Those skilled in the art should understand that any applicable method can be used in specific applications to judge whether the current posture of the bionic hand is the preset posture. This embodiment of the disclosure does not limit this.

[0094] In step 207, adjusting the input signal of the driving motor in the bionic hand to enhance the gripping force of the bionic hand may include: determining the target gripping force of the bionic hand according to the current gripping force and / or jitter value of the bionic hand, and adjusting the input signal of the driving motor to increase the torque output of the driving motor so that the gripping force of the bionic hand reaches the target gripping force; wherein the current gripping force of the bionic hand is determined according to the electromyographic signal collected by the electromyographic sensor.

[0095] In some examples, the input signal of the drive motor in the bionic hand can be adjusted in the following manner to enhance the gripping force of the bionic hand: determine the current gripping force, calculate the target gripping force based on the current gripping force and a predetermined ratio, and adjust the input signal of the drive motor according to the target gripping force to increase the torque of the drive motor until the current gripping force detected by the force sensor is close to or equal to the target gripping force or until the gripping force corresponding to the torque of the drive motor is close to or equal to the target gripping force. Among them, the current gripping force can be detected by a force sensor, or calculated by the torque of the drive motor and the transmission ratio. For example, if it is necessary to increase the current gripping force by 50%, the target gripping force can be equal to the product of the current gripping force and 150%. Thus, during the shaking process, when the bionic hand is still locked in the gripping state, the required ratio can be increased on the basis of the current gripping force by adjusting the input signal of the drive motor to avoid the occurrence of situations such as objects slipping during shaking.

[0096] In some examples, the input signal of the drive motor in the bionic hand can be adjusted in the following manner to enhance the gripping force of the bionic hand: calculate the difference between the current jitter value and the predetermined jitter threshold value, determine the gripping force increase ratio based on the difference, determine the current gripping force, calculate the target gripping force based on the current gripping force and the gripping force increase ratio, and adjust the input signal of the drive motor according to the target gripping force to increase the torque of the drive motor until the current gripping force detected by the force sensor is close to or equal to the target gripping force or until the gripping force corresponding to the drive motor torque is close to or equal to the target gripping force. The current gripping force can be detected by a force sensor or calculated by the drive motor torque and the transmission ratio. Thus, the gripping force can be increased according to the degree of jitter. The greater the degree of jitter, the greater the gripping force increase, thereby better avoiding situations such as objects slipping.

[0097] In specific applications, any other applicable methods may be used to enhance the gripping force of the bionic hand, and the embodiments of the present disclosure do not limit this.

[0098] In the disclosed embodiment, unlocking of the bionic hand can be achieved in a variety of ways.

[0099] In some implementations, the bionic hand control method of the disclosed embodiment may further include: unlocking the bionic hand in response to a first operation of the user on a physical button. Thus, the user can unlock the bionic hand by pressing the physical button when unlocking is required.

[0100] In a specific application, the first operation on the physical key may be, but is not limited to, pressing, long pressing, tapping, or other operation forms. The specific form of the first operation is not limited in the embodiment of the present disclosure.

[0101] In some embodiments, the bionic hand control method of the disclosed embodiment may further include: receiving electromyographic signals collected in real time by the electromyographic sensor of the bionic hand, determining a desired action according to the electromyographic signals, the desired action being the action that the wearer expects the bionic hand to perform, unlocking the bionic hand and controlling the bionic hand to perform the desired action when the desired action is a preset action. Thus, the wearer can unlock the bionic hand by actively trying to perform a specific action (such as opening five fingers, etc.).

[0102] In a specific application, the method for determining whether the expected action is a preset action is the same as the method for determining the aforementioned posture, and will not be described in detail.

[0103] In specific applications, the preset action can be set by the wearer or by default. The implementation method of the preset action set by the wearer is similar to the setting method of the first preset posture mentioned above, and will not be repeated. In this way, the bionic hand can be unlocked while meeting the personalized needs of the wearer.

[0104] The above-mentioned bionic hand control method of the disclosed embodiment can evaluate the shaking condition of the bionic hand in real time while the wearer is moving, and lock the posture of the bionic hand in time to prevent the bionic hand from making misoperations due to shaking when the wearer is in motion, thereby effectively improving the user experience.

[0105] Figure 4 FIG. 2 shows a schematic diagram of the structure of a bionic hand control device provided by an embodiment of the present disclosure. Figure 4 , the bionic hand control device 400 may include:

[0106] The data acquisition unit 401 is used to acquire the motion data of the bionic hand measured by the inertial measurement unit when the wearer of the bionic hand is in motion;

[0107] A feature extraction unit 402 is used to obtain the shaking characteristics of the bionic hand and the motion characteristics of the wearer using the motion data of the bionic hand;

[0108] The shaking verification unit 403 is used to determine whether the shaking characteristics of the bionic hand and the movement characteristics of the wearer meet the predetermined shaking conditions;

[0109] The first locking unit 404 is used to control the bionic hand to lock and maintain a first preset posture when a predetermined shaking condition is met, and to lower the sampling frequency of the electromyographic sensor.

[0110] Furthermore, the bionic hand control device 400 may also include: a second locking unit 405, which is used to enter a shake protection mode when a predetermined shake condition is not met. In the shake protection mode, the current posture of the bionic hand is locked, and the electromyographic sensor is controlled to stop collecting electromyographic signals.

[0111] Furthermore, the bionic hand control device 400 may also include: an adjustment unit 406, which is used to determine whether the current posture of the bionic hand is the second preset posture after entering the shake protection mode, and if the current posture of the bionic hand is the second preset posture, adjust the input signal of the drive motor in the bionic hand to enhance the gripping force of the bionic hand, and the drive motor is arranged inside the bionic hand and connected to the finger joints of the bionic hand.

[0112] Furthermore, the bionic hand control device 400 may further include: an unlocking unit 407, configured to unlock the bionic hand in response to a first operation of the user on a physical key.

[0113] Furthermore, the data acquisition unit 401 can also be used to receive electromyographic signals collected in real time by the electromyographic sensors of the bionic hand; the bionic hand control device 400 can also include: a posture recognition unit 408, used to determine the expected action based on the electromyographic signals, the expected action being the action that the wearer expects the bionic hand to perform; the unlocking unit 407 can also be used to unlock the bionic hand and control the bionic hand to perform the expected action when the expected action is a preset action.

[0114] For other technical details about the bionic hand control device 400 , please refer to the above-mentioned part of the bionic hand control method, which will not be repeated here.

[0115] In addition, an embodiment of the present disclosure further provides a computer-readable storage medium on which a computer program is stored. The program includes instructions, and when the instructions are executed by one or more processors of a computing device, the steps of the aforementioned bionic hand control method are executed.

[0116] Figure 5 FIG. 1 is a schematic diagram showing the structure of an electronic device provided by an embodiment of the present disclosure. Figure 5 The electronic device 500 may include: one or more processors 501, and a memory 502 storing one or more programs, which are executed by the one or more processors 501 to implement the method flow shown in the above embodiments of the present disclosure and / or program units corresponding to each unit in the device.

[0117] The various components are interconnected using different buses and can be mounted on a common motherboard or in other ways as needed. The processor 501 can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of the user interface on an external input / output device (such as a display device coupled to the interface). In other embodiments, if necessary, multiple processors and / or multiple buses can be used with multiple memories and multiple memories.

[0118] The processor 501 may include one or more single-core processors or multi-core processors. The processor 501 may include any combination of general-purpose processors or dedicated processors (such as image processors, application processors, baseband processors, etc.).

[0119] The memory 502 is a computer-readable storage medium provided by the present disclosure, which can be used to store non-transient software programs, non-transient computer executable programs and units, such as the following in the embodiments of the present disclosure: Figure 3 The processor 501 executes the non-transient software programs, instructions and units stored in the memory 502 to perform the above method embodiments. Figure 3 The programs, instructions and units corresponding to the bionic hand control method shown.

[0120] The electronic device 500 may further include: an input device 503 and an output device 504. The processor 501, the memory 502, the input device 503 and the output device 504 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0121] The input device 503 can receive input digital or character information, and generate signal input related to user settings and function control, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick and other input devices. The output device 505 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device may be a touch screen.

[0122] The above-mentioned programs (also referred to as software, software applications, or codes) include machine instructions for programmable processors, and these computer programs may be implemented using object-oriented programming languages, assembly or machine languages.

[0123] With the development of time and technology, the meaning of medium is becoming more and more extensive, and the dissemination path of computer programs is no longer limited to tangible media, but can also be downloaded directly from the Internet. Any combination of one or more computer-readable storage media can be used. Computer-readable storage media can be used, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, computer-readable storage media can be any tangible medium that contains or stores a program that can be used by or in combination with an instruction execution system, device or device.

[0124] The technical solution provided by the present disclosure is described in detail above. The principles and implementation methods of the present disclosure are described in detail using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present disclosure. At the same time, for those skilled in the art, according to the idea of ​​the present disclosure, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present disclosure.

[0125] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A bionic hand control method, characterized in that: The bionic hand is provided with an inertial measurement unit, and the inner cavity of the bionic hand is provided with an electromyographic sensor. The method comprises: When the wearer of the bionic hand is in motion, acquiring motion data of the bionic hand measured by the inertial measurement unit; Using the motion data of the bionic hand to obtain the shaking characteristics of the bionic hand and the motion characteristics of the wearer; Determining whether the shaking characteristics of the bionic hand and the movement characteristics of the wearer meet a predetermined shaking condition; If the predetermined shaking condition is met, the bionic hand is controlled to lock and maintain a first preset posture, and the sampling frequency of the electromyographic sensor is lowered; Among them, the method of using the motion data of the bionic hand to obtain the jitter characteristics of the bionic hand and the motion characteristics of the wearer includes: using a pre-trained motion analysis model to process the motion data of the bionic hand to obtain the motion characteristics of the bionic hand; using a pre-trained jitter analysis model to process the motion data of the bionic hand to obtain the jitter characteristics of the bionic hand.

2. The method according to claim 1, characterized in that The method further comprises: If the predetermined shaking condition is not met, a shaking protection mode is entered, in which the current posture of the bionic hand is locked, and the myoelectric sensor is controlled to stop collecting myoelectric signals.

3. The method according to claim 2, characterized in that: The method further comprises: After entering the shake protection mode, determining whether the current posture of the bionic hand is a second preset posture; If the current posture of the bionic hand is the second preset posture, the input signal of the drive motor in the bionic hand is adjusted to enhance the gripping force of the bionic hand. The drive motor is arranged inside the bionic hand and connected to the finger joints of the bionic hand.

4. The method according to claim 1, characterized in that The motion characteristics include the wearer's motion frequency and motion type; the jitter characteristics include the jitter type, jitter frequency and jitter peak value of the bionic hand.

5. The method according to claim 4, characterized in that The predetermined jitter condition includes one or more of the following: The motion type of the wearer and the shaking type of the bionic hand are both periodic motion, and the shaking peak value of the bionic hand does not exceed a preset shaking threshold; The motion type of the wearer and the shaking type of the bionic hand are both periodic motions, and the difference between the shaking frequency of the bionic hand and the motion frequency of the wearer is less than a preset frequency threshold.

6. The method according to claim 1, characterized in that The method further includes: unlocking the bionic hand in response to a first operation of a user on a physical key.

7. The method according to claim 1, characterized in that The method further comprises: Receiving electromyographic signals collected in real time by the electromyographic sensor of the bionic hand; Determine a desired action according to the electromyographic signal, wherein the desired action is the action that the wearer expects the bionic hand to perform; When the expected action is a preset action, the bionic hand is unlocked and controlled to perform the expected action.

8. A bionic hand control device, characterized in that: The bionic hand is provided with an inertial measurement unit, and the inner cavity of the bionic hand is provided with an electromyographic sensor; the bionic hand control device comprises: A data acquisition unit, used for acquiring the motion data of the bionic hand measured by the inertial measurement unit when the wearer of the bionic hand is in motion; A feature extraction unit, used for acquiring the shaking features of the bionic hand and the motion features of the wearer by using the motion data of the bionic hand; A shaking verification unit, used to determine whether the shaking characteristics of the bionic hand and the movement characteristics of the wearer meet a predetermined shaking condition; A first locking unit, used for controlling the bionic hand to lock and maintain a first preset posture and lowering the sampling frequency of the electromyographic sensor when the predetermined shaking condition is met; The feature extraction unit is used to: process the motion data of the bionic hand using a pre-trained motion analysis model to obtain the motion features of the bionic hand; and process the motion data of the bionic hand using a pre-trained jitter analysis model to obtain the jitter features of the bionic hand.

9. An electronic device, characterized in that: include: One or more processors and a memory storing a program, wherein the program includes instructions, and when the instructions are executed by the processor, the processor executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a program, wherein the program comprises instructions, and when the instructions are executed by one or more processors of a computing device, the instructions cause the computing device to execute the method according to any one of claims 1 to 7.

Images