An underactuated bionic dexterous hand, system and control method thereof

Abstract

The application provides an underactuated bionic dexterous hand, a system and a control method thereof. The underactuated bionic dexterous hand comprises a palm, five fingers, a control plate and a steering engine installed on the back of the palm through a threaded hole. The thumb comprises a joint, a tendon rope for driving the bending of the finger, a metacarpal bone, a proximal phalanx and a distal phalanx connected through a cylindrical pin in sequence. The index finger, the middle finger, the ring finger and the little finger have the same structure and each comprises a joint, a tendon rope for driving the bending of the finger, a distal phalanx, a middle phalanx and a proximal phalanx connected through a cylindrical pin in sequence. A finger root stroke limiter is arranged at the metacarpophalangeal joint of the thumb and the palm, and the metacarpophalangeal joint of the index finger, the middle finger, the ring finger and the little finger and the palm, the middle phalanx and the distal phalanx are each provided with a finger root stroke limiter. The application has high human simulation degree, is light and flexible, and solves the technical problems of the overlarge size, the overly complex structure, the rigid motion and the low human simulation degree of the dexterous hand.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent mechanical engineering, in particular to an underactuated bionic dexterous hand, a system and a control method thereof. BACKGROUND

[0002] The current development of the robot field presents the trends of diversification and intelligence, and the robot is composed of an execution mechanism, a driving device, a sensing device and a control system. Among the many components of the robot, the efficiency of the end effector directly affects the overall work efficiency of the robot. The traditional end effector is mostly a clamping type or a suction type end effector, and when facing some extreme environments and complex working conditions, the work efficiency is not high and the adaptability to complex extreme working environments is insufficient. The dexterous hand as a new type of end effector combined with bionics not only has high dexterity and strong adaptability, but also can complete various types of complex operations, making up for the defects of the traditional end effector such as single function.

[0003] The anthropomorphic dexterous hand can be divided into two categories according to different driving modes, one is a fully driven anthropomorphic dexterous hand, and the other is an underactuated anthropomorphic dexterous hand. It has gradually evolved from the past characteristics of large size, heavy weight and low sensitivity to the present characteristics of small size, light weight and high sensitivity. In recent years, in order to meet the higher demand for anthropomorphism, scholars and laboratories at home and abroad have made great progress in the research of underactuated dexterous hands. Most of the dexterous hand driving modes developed by them use underactuation to replace full drive, and most of the underactuated dexterous hands use tendon control to move the joints.

[0004] For the realization of human-computer interaction of the dexterous hand, its equipment has developed from the initial operation of the complex knob button remote control, to the configuration of the multi-sensor data glove, to the feedback sensitive, small volume and light weight somatosensory gesture sensor device, which is developing towards simplicity and lightness. However, the existing dexterous hand has problems such as too large size, too complex structure, rigid motion and low degree of anthropomorphism. SUMMARY

[0005] Therefore, it is necessary to provide an underactuated bionic dexterous hand, a system and a control method thereof, to solve the technical problems of the existing dexterous hand, such as too large size, too complex structure, rigid motion and low degree of anthropomorphism.

[0006] On the one hand, the present application provides an underactuated bionic dexterous hand, which comprises a palm, five fingers, a control plate and a rudder installed on the back of the palm through a threaded hole, wherein the five fingers are a thumb, an index finger, a middle finger, a ring finger and a little finger connected with the palm.

[0007] The thumb comprises a joint, a tendon rope for driving the bending of the finger, metacarpal bones connected in sequence through a cylindrical pin, a proximal phalanx and a distal phalanx; the index finger, the middle finger, the ring finger and the little finger are the same in structure, and each comprises a joint, a tendon rope for driving the bending of the finger, a distal phalanx, a middle phalanx and a proximal phalanx connected in sequence through the cylindrical pin; a finger root stroke limiter is arranged at the metacarpophalangeal joint of the thumb and the metacarpophalangeal joint of the index finger, the middle finger, the ring finger and the little finger, and the middle phalanx and the distal phalanx.

[0008] Optionally, the axis at the metacarpophalangeal joint of the thumb rotates at a preset angle relative to the axis at the rotation of the carpometacarpal joint.

[0009] Optionally, the winding mode of the tendon rope is a da Vinci type matching pulley type.

[0010] In another aspect, the application further provides an underactuated bionic dexterous hand system, comprising the underactuated bionic dexterous hand, and further comprising a sensing module and a master control module.

[0011] The master control module is connected with the underactuated bionic dexterous hand and the sensing module respectively.

[0012] The sensing module is used for detecting the gesture action made by a human hand, obtaining gesture motion data and storing the gesture motion data.

[0013] The master control module is used for extracting and analyzing the gesture motion data, optimizing the gesture motion data through a preset gesture recognition algorithm, obtaining control parameters, and outputting the control parameters after being converted into control signals.

[0014] The underactuated bionic dexterous hand is used for receiving the control signals, generating corresponding driving signals according to the control signals, driving the steering engine to operate, and controlling the fingers of the underactuated bionic dexterous hand to operate correspondingly.

[0015] Optionally, the sensing module comprises two high-frame-rate depth cameras, three infrared emitters and an infrared filter.

[0016] Optionally, the master control module is an upper computer.

[0017] In another aspect, the application further provides an underactuated bionic dexterous hand control method applied to the underactuated bionic dexterous hand system, and the underactuated bionic dexterous hand control method comprises the following steps:

[0018] The sensing module is used for detecting the gesture action made by a human hand, obtaining gesture motion data and storing the gesture motion data.

[0019] The gesture motion data is extracted and analyzed by the master control module, and the gesture motion data is optimized by a preset gesture recognition algorithm model to obtain control parameters;

[0020] The control parameters are converted into control signals;

[0021] The control signals are received by the underactuated bionic dexterous hand, and corresponding driving signals are generated according to the control signals to drive the steering engine to operate and control the fingers of the underactuated bionic dexterous hand to perform corresponding operations.

[0022] Optionally, the step of detecting the gesture action made by the human hand based on the sensing module to obtain gesture motion data and storing the gesture motion data includes:

[0023] The gesture action made by the human hand is detected based on the sensing module to obtain coordinate data, hand motion speed data, and hand motion acceleration data of the hand motion;

[0024] The coordinate data, the hand motion data, and the hand motion acceleration data are stored in an SDK file of the sensing module.

[0025] Optionally, the step of converting the control parameters into control signals and outputting includes:

[0026] The virtual dexterous hand is driven to move according to the control parameters;

[0027] Corresponding control signals are output according to the driver parameters required by the action of the virtual dexterous hand.

[0028] Optionally, the virtual dexterous hand and the underactuated bionic dexterous hand maintain a mapping relationship.

[0029] The beneficial effects of the above embodiment are that the underactuated bionic dexterous hand provided by the application comprises a palm, five fingers, a control plate and a steering engine installed on the back of the palm through a threaded hole, the five fingers are a thumb, an index finger, a middle finger, a ring finger and a little finger connected with the palm, wherein the thumb comprises a joint, a tendon rope for driving the bending of the finger, metacarpal bones, proximal phalanges and distal phalanges connected in sequence through a cylindrical pin, the index finger, the middle finger, the ring finger and the little finger have the same structure and comprise a joint, a tendon rope for driving the bending of the finger, distal phalangeal joints, middle phalangeal joints and proximal phalangeal joints connected in sequence through the cylindrical pin, a finger root stroke limiter is arranged at the metacarpophalangeal joint of the thumb connected with the palm, and the finger root stroke limiter is arranged at the metacarpophalangeal joint of the index finger, the middle finger, the ring finger and the little finger connected with the palm, the middle phalangeal joint and the distal phalangeal joint. The application is designed and manufactured in the tendon rope transmission mode, conforms to the lightweight and simple principles, compared with the gear and connecting rod driven dexterous hand of the traditional control mode, the application can complete human flexible work, the selected steering engine is small in size, so that the dexterous hand itself is more portable and flexible, and the technical problems of the current developed industrial robot loaded dexterous hand, such as large size, too complex structure, rigid motion and low human degree, are solved. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0031] Figure 1 An embodiment structure schematic diagram of the underactuated bionic dexterous hand provided by the application;

[0032] Figure 2 An embodiment structure schematic diagram of the underactuated bionic dexterous hand system provided by the application;

[0033] Figure 3 An embodiment flow schematic diagram of the underactuated bionic dexterous hand control method provided by the application;

[0034] Figure 4 An embodiment flow schematic diagram of step S310 in the application; Figure 3 An embodiment flow schematic diagram of step S330 in the application.

[0035] Figure 5 An embodiment flow schematic diagram of step S330 in the application. Figure 3 An embodiment flow schematic diagram of step S330 in the application. DETAILED DESCRIPTION

[0036] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be clearly and completely described in the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person skilled in the art without creative work fall within the protection scope of the present application.

[0037] It should be understood that the schematic drawings are not drawn according to the actual proportions. The flowchart used in the present application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented in no order, the steps without logical context relationship can be reversed in order or implemented simultaneously. In addition, one or more other operations can be added to the flowchart or one or more operations can be removed from the flowchart by a person skilled in the art under the guidance of the content of the present application.

[0038] In the present application, the phrase "embodiment" means that the specific features, structures or characteristics described in combination with the embodiment can be contained in at least one embodiment of the present application. The phrase appears in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment to other embodiments. A person skilled in the art explicitly and implicitly understands that the embodiments described herein can be combined with other embodiments.

[0039] The embodiments of the present application provide an underactuated bionic dexterous hand, a system and a control method thereof, which are described below respectively.

[0040] Figure 1 An embodiment structure diagram of the underactuated bionic dexterous hand provided by the present application is shown in FIG. 1, which includes a palm, five fingers, a control board and a steering wheel 5 installed on the back of the palm through a threaded hole, the five fingers are a thumb, an index finger, a middle finger, a ring finger and a little finger connected with the palm; Figure 1

[0041] Among them, the thumb includes a joint, a tendon rope driving the finger to bend, a metacarpal bone 11, a proximal phalanx 22 and a distal phalanx 13 connected in turn through a cylindrical pin 4; the index finger, the middle finger, the ring finger and the little finger have the same structure, and each includes a joint, a tendon rope driving the finger to bend, a distal phalanx 23, a middle phalanx 22 and a proximal phalanx 21 connected in turn through a cylindrical pin; a finger root stroke limiter 1 is arranged at the metacarpophalangeal joint of the thumb connected with the palm, and a finger root stroke limiter 2 is arranged at the metacarpophalangeal joint of the index finger, the middle finger, the ring finger and the little finger connected with the palm, the middle phalanx and the distal phalanx.

[0042] ​It should be noted that the steering engine 5 in the embodiment of the present application adopts a micro serial bus digital steering engine, which is small in mass and volume, and is directly installed on the palm of the dexterous hand, so that the kinetic energy loss of the tendon due to long distance transmission can be greatly reduced, and the dexterous hand has higher sensitivity; the cylindrical pin 4 is used to connect the individual knuckles of the fingers, so as to ensure the stability of the transmission between the joints; the longitudinal arched curved surface structure is used for the shape of the palm, which conforms to the shape of the human hand and ensures that the movement of the steering engine 5 in the palm does not interfere with the hand movement.

[0043] It can be understood that, considering that there is a limit position when the human finger is relaxed and stretched, the finger root stroke limiter 1 is arranged at the metacarpophalangeal joint connecting the thumb and the palm, the finger root stroke limiter 2 is arranged at the metacarpophalangeal joint connecting the index finger, the middle finger, the ring finger and the little finger and the middle knuckle and the distal knuckle, for controlling the relaxed limit position of the whole finger, so as to prevent the finger from being excessively stretched into an uncontrollable rotation angle.

[0044] Compared with the prior art, the underactuated bionic dexterous hand provided by the embodiment of the present application is designed and manufactured by adopting a tendon transmission mode, conforms to the lightweight and simple principles, and can complete human flexible work compared with the gear and connecting rod driven dexterous hand of the traditional control mode, the selected steering engine is small in size, so that the dexterous hand itself is more portable and flexible, and the technical problems of the current developed industrial robot loaded dexterous hand, such as large size, too complex structure, rigid motion and low human degree, are solved.

[0045] In some embodiments of the present application, the axis of the metacarpophalangeal joint of the thumb is rotated at a preset angle relative to the axis of the rotation of the carpometacarpal joint 3.

[0046] It can be understood that, in the specific implementation, the metacarpophalangeal joint axis of the thumb of the dexterous hand is rotated at a space of 47.09° (a preset angle) relative to the axis of the rotation of the carpometacarpal joint 3, so that the dexterous hand has higher human nature.

[0047] In some embodiments of the present application, the winding mode of the tendon is a da Vinci type with a pulley type.

[0048] It should be noted that the tendon material in the embodiment of the present application is PBO fiber rope, which has higher strength and modulus, is fire-resistant and non-combustible, and will not produce excessive creep.

[0049] On the other hand, on the basis of the underactuated bionic dexterous hand, the embodiment of the present application also provides an underactuated bionic dexterous hand system, which refers to Figure 2 The underactuated bionic dexterous hand system comprises the underactuated bionic dexterous hand 21, the sensing module 22 and the main control module 23 in any one of the above embodiments;

[0050] The main control module 23 is connected with the underactuated bionic dexterous hand 21 and the sensing module 22 respectively.

[0051] The sensing module 22 is used for detecting the gesture action made by the human hand, obtaining gesture motion data and storing the gesture motion data.

[0052] The main control module 23 is used for extracting and analyzing the gesture motion data, optimizing the gesture motion data through a preset gesture recognition algorithm model, obtaining control parameters, and outputting the control parameters after being converted into control signals.

[0053] The underactuated bionic dexterous hand 21 is used for receiving the control signals and generating corresponding driving signals according to the control signals to drive the steering engine to operate and control the fingers of the underactuated bionic dexterous hand to operate correspondingly.

[0054] It should be understood that in the embodiment of the application, specifically, the sensing module 22 is a depth vision sensor, which is used for detecting the gesture action made by the human hand in the field of view, obtaining gesture motion data (coordinate data, speed and acceleration of hand motion and other physical states) and storing them into the SDK file built-in the sensor. The data packets in the SDK file are extracted and analyzed by the main control module in the background, the gesture is optimized through the gesture recognition algorithm (g-CNN-kNN algorithm model), the optimized gesture data is converted into the parameters of the steering angle, direction and speed in the background, and the control signals are transmitted to the wireless serial port module of the underactuated bionic dexterous hand 21 through the data interface constructed by text in the main control module 23, and finally the data is sent to the driver through the wireless serial port module to complete the control instruction, so as to realize the precise motion from the human gesture to the underactuated bionic dexterous hand 21.

[0055] It should be noted that in the embodiment of the application, the sensing module 22 includes two high-frame-rate depth cameras, three infrared emitters and an infrared filter. The infrared emitters emit infrared light, and the two cameras obtain images and positions captured at two different points by reflecting the infrared light of the identified human hand. The spatial relative position of the cameras is determined, and then the position relationship between the projection point of the coordinates of the identified human hand on the camera plane and the coordinate point of the identified human hand is determined. The data feature extraction is performed on the data obtained by the camera shooting, such as point feature, boundary feature and line feature, image matching is performed to obtain the parallax, and the spatial point cloud analysis operation is performed on the point position information, physical information, parallax and camera physical parameters to reconstruct the three-dimensional model of the human hand. The gesture motion data is the gesture motion image data of the three-dimensional model.

[0056] It also needs to be explained that the master module 23 in the embodiment of the application is realized by a host computer, and the g-CNN-kNN algorithm model in the embodiment is a model constructed based on a k-Nearest Neighbor (k-NN) algorithm, and the construction of the g-CNN-kNN algorithm model includes: (1) input layer preprocessing, input gesture dataset images in the input layer, a part as a training dataset and a part as a test dataset, and the input images are preprocessed by mean removal and normalization; (2) convolutional neural network feature extraction, first, the image is in the military base by the convolution kernel and the weight sharing of the visual field, second, the dimensionality of the last convolution image is reduced and the data volume is compressed through the pooling layer, and the overfitting is reduced, finally, the obtained all feature neurons are re-fitted and linearly calculated in the linear layer, and the image features are output; (3) k-Nearest Neighbor algorithm classification and identification, the image features are input into the KNN, the distances between each feature point and the identified feature point are calculated, and the selected k value is used to select the k nearest feature points from all distances, finally, the feature space of the new test sample is judged by using a judgment formula and according to a classification decision principle; (4) output sample judgment result.

[0057] On the other hand, on the basis of the underactuated bionic dexterous hand system, the application further provides an underactuated bionic dexterous hand control method, which is applied to the underactuated bionic dexterous hand system described in any one of the above embodiments, and refers to Figure 3 The underactuated bionic dexterous hand control method comprises the following steps:

[0058] S310, detecting the gesture action made by the human hand based on the sensing module, obtaining gesture motion data and storing the gesture motion data;

[0059] S320, extracting and analyzing the gesture motion data by using the master control module, and optimizing the gesture motion data by using a preset gesture recognition algorithm model to obtain control parameters;

[0060] S330, converting the control parameters into control signals;

[0061] S340, receiving the control signals by the underactuated bionic dexterous hand, and generating corresponding driving signals according to the control signals to drive the servo to operate and control the fingers of the underactuated bionic dexterous hand to perform corresponding operations.

[0062] It should be noted that in the embodiment of the application, the sensing module is a depth vision sensor, and the host control module is an upper computer, in the specific implementation, the gesture action made by the human hand in the field of view is detected by using the depth vision sensor, gesture motion data (coordinate data, speed and acceleration of hand motion and other physical states) are obtained and stored in the SDK file built in the sensor, the data packet in the SDK file is extracted and analyzed in the background by the host control module, gesture optimization is performed through a gesture recognition algorithm (g-CNN-kNN algorithm model), the optimized gesture data is converted into driver rotation angle, direction and speed and other parameters in the background, and the parameters are transmitted to the wireless serial port module of the underactuated dexterous hand in the form of control signals through the data interface constructed by text in the host control module, finally, the data is sent to the driver through the wireless serial port module to complete the control instruction, and precise motion from human gesture to underactuated dexterous hand is realized.

[0063] Compared with the prior art, the underactuated dexterous hand in the embodiment of the application is designed by imitating the structure of the human hand according to the modular design idea, the whole machine follows the principles of small size, light weight and reliable control, tendon transmission is adopted, and a finger root stroke limiter is added to avoid motion failure caused by excessive stretching of the finger joints, and the motion angle of the finger meets the demand of the angle of joint motion according to human bionics; compared with the traditional k-neighbor algorithm, the g-CNN-kNN algorithm model adopted by the host control module in the embodiment of the application has higher gesture recognition accuracy and speed, and the embodiment of the application further builds a virtual-real fusion gesture recognition dexterous hand control system, which organically combines gesture recognition, a virtual reality platform and a dexterous hand prototype, and constitutes an "real-virtual-real" control chain, so that the human hand, the virtual dexterous hand and the dexterous hand prototype can make synchronous gestures, the complex control of the traditional dexterous hand is simplified, and the visualization performance of the control system is improved.

[0064] In some embodiments of the application, with reference to Figure 4 , step S310 comprises:

[0065] S410, detecting the gesture action made by the human hand based on the sensing module to obtain coordinate data of hand motion, hand motion speed data and hand motion acceleration data;

[0066] S420, storing the coordinate data, hand motion data and hand motion acceleration data into the SDK file of the sensing module.

[0067] It can be understood that in the embodiment of the application, the gesture motion data includes coordinate data, speed, acceleration and other physical quantity characteristic data of hand motion, which is collected by the depth vision sensor and stored in the SDK file.

[0068] In some embodiments of the application, with reference to Figure 5The step S330 comprises:

[0069] S510, driving the virtual dexterous hand according to the control parameter;

[0070] S520, outputting corresponding control signals according to the driver parameters required by the action of the virtual dexterous hand.

[0071] It should be noted that the virtual dexterous hand is pre-constructed by the host computer in the embodiment of the present application, and the virtual dexterous hand maintains a mapping relationship with the underactuated bionic dexterous hand; the construction of the virtual dexterous hand is performed according to the above-mentioned underactuated bionic dexterous hand, and the assembly of three-dimensional parts of each part of the dexterous hand is combined with the degrees of freedom of the actual human hand to prevent errors in the motion logic of the subsequent control model motion caused by excessive cooperation or accurate cooperation. After the preliminary model is constructed, some physical properties need to be added to it, the mass, resistance, constraint, gravity and other related parameters in the compiled component are mounted, so as to achieve the purpose of simulating the physical properties and dynamic properties of the real dexterous hand.

[0072] It can be understood that the embodiment of the present application also builds a gesture data extraction system based on a depth vision sensor, and the gesture data (i.e. control parameters) obtained by the gesture data extraction system is used to drive the virtual dexterous hand to make the same motion as the gesture, and then the driver parameters (such as driver rotation angle, direction and speed, etc.) required by the motion of the virtual dexterous hand are used to control the underactuated bionic dexterous hand to make the same action as the virtual dexterous hand through a serial data interface.

[0073] It should be noted that the steps in the method in the above embodiment can be increased or expanded according to each module or unit in the underactuated bionic dexterous hand system, and the specific details are described in the embodiment of the underactuated bionic dexterous hand system, which will not be repeated here.

[0074] The underactuated bionic dexterous hand, system and control method thereof provided by the present application are described in detail above, and the principles and implementation modes of the present application are described by applying specific examples; the above embodiment is only used to help understand the method and core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will be changed, and the above description should not be understood as limiting the present application.

Claims

1. An underactuated bionic dexterous hand, characterized in that: It includes a palm, five fingers, a control panel, and a servo mounted on the back of the palm through threaded screw holes, wherein the five fingers are a thumb, an index finger, a middle finger, a ring finger, and a little finger connected to the palm; Among them, the thumb includes a joint, a tendon that drives the bending of the fingers, a metacarpal bone, a proximal phalanx and a distal phalanx connected in sequence by cylindrical pins; the index finger, the middle finger, the ring finger and the little finger have the same structure, all including a joint, a tendon that drives the bending of the fingers, a distal phalanx, an intermediate phalanx and a proximal phalanx connected in sequence by the cylindrical pins; a finger base travel limiter is provided at the metacarpophalangeal joint where the thumb is connected to the palm, and the finger base travel limiter is provided at the metacarpophalangeal joint where the index finger, the middle finger, the ring finger and the little finger are connected to the palm, the intermediate phalanx and the distal phalanx.

2. The underactuated bionic dexterous hand according to claim 1, characterized in that: The axis of the metacarpophalangeal joint of the thumb rotates at a preset angle relative to the axis of the rotation of the carpometacarpal joint.

3. The underactuated bionic dexterous hand according to claim 1, characterized in that: The winding method of the tendon rope is a Da Vinci type combined with a pulley type.

4. An underactuated bionic dexterous hand system, characterized in that: The under-actuated bionic dexterous hand according to any one of claims 1 to 3 further comprises a sensing module and a main control module; Wherein, the main control module is connected to the under-actuated bionic dexterous hand and the sensor module respectively; The sensing module is used to detect gestures made by a person's hand, obtain gesture motion data and store the gesture motion data; The main control module is used to extract and analyze the gesture motion data, optimize the gesture motion data through a preset gesture recognition algorithm, obtain control parameters, convert the control parameters into control signals and output them; The underactuated bionic dexterous hand is used to receive the control signal and generate a corresponding drive signal according to the control signal to drive the servo to operate and control the fingers of the underactuated bionic dexterous hand to perform corresponding operations.

5. The underactuated bionic dexterous hand system according to claim 4, characterized in that: The sensing module includes two high-frame-rate depth cameras, three infrared emitters and an infrared filter.

6. The underactuated bionic dexterous hand system according to claim 5, characterized in that: The main control module is a host computer.

7. A control method for an underactuated bionic dexterous hand, applied to the underactuated bionic dexterous hand system according to any one of claims 4 to 6, characterized in that: The underactuated bionic dexterous hand control method comprises the following steps: Detecting hand gestures made by a person based on a sensing module, obtaining gesture motion data and storing the gesture motion data; A main control module is used to extract and analyze the gesture motion data, and the gesture motion data is optimized through a preset gesture recognition algorithm model to obtain control parameters; converting the control parameter into a control signal; The underactuated bionic dexterous hand is used to receive the control signal and generate a corresponding drive signal according to the control signal to drive the servo to operate and control the fingers of the underactuated bionic dexterous hand to perform corresponding operations.

8. The underactuated bionic dexterous hand control method according to claim 7, characterized in that: The step of detecting a hand gesture performed by a human hand based on a sensing module, obtaining gesture motion data, and storing the gesture motion data includes: Detecting hand gestures based on the sensor module to obtain hand motion coordinate data, hand motion speed data, and hand motion acceleration data; The coordinate data, the hand movement speed data, and the hand movement acceleration data are stored in the SDK file of the sensor module.

9. The underactuated bionic dexterous hand control method according to claim 8, characterized in that: The step of converting the control parameter into a control signal and then outputting the signal comprises: driving the virtual dexterous hand to move according to the control parameters; The corresponding control signal is output according to the driver parameters required for the movement of the virtual dexterous hand.

10. The underactuated bionic dexterous hand control method according to claim 9, characterized in that: The virtual dexterous hand maintains a mapping relationship with the under-actuated bionic dexterous hand.

Images