Bionic Hand Research Articles

Bionic Hand Movements Recognition: A Unified Framework with Attention-Guided ROI Identification and the Bionic Fusion Net Approach

Bionic Hand Movements Recognition: A Unified Framework with Attention-Guided ROI Identification and the Bionic Fusion Net Approach

Analysis of the Structure and Working Principle of Intelligent Bionic Hand

Intelligent bionic prosthetic hand controlled by intelligent neural networks with perceptual feedback function is a hot topic of research for scientists around the world. This article analyzes the development status of electromyographic prosthetic hands both domestically and internationally over the years, and provides a detailed introduction to the structure of intelligent bionic hands. The intelligent bionic hand consists of three important components: 3D printed bionic hand bone structure, sensors, and intelligent neural network algorithm control system. Among them, the intelligent neural network algorithm control system is its core. The focus is on the working principle of an intelligent bionic hand, where sensors collect electromyography and neural electrical signals generated by human muscle movements. Through the intelligent neural network algorithm control system, the data information obtained is continuously optimized and adjusted to achieve motion control of the prosthetic hand. This article analyzes some problems of intelligent bionic hands and provides development ideas and suggestions. It is pointed out that the reconstruction of the sensing function of the intelligent bionic hand should focus on multimodal feedback, using diverse stimuli and more sensitive sensors for human-machine interaction, so that the intelligent bionic hand can move flexibly and freely, benefiting most disabled patients.

The second clinical study investigating the surgical method for the kineticomyographic control implementation of the bionic hand

In 2018, during our first clinical study on the kineticomyographic (KMG)-controlled bionic hand, we implanted three magnetic tags inside the musculotendinous junction of three paired extensor-flexor transferred tendons. However, the post-operative tissue adhesions affected the independent movements of the implanted tags and consequently the distinct patterns of the obtained signals. To overcome this issue, we modified our surgical procedure from a one-stage tendon transfer to a two-stage. During the first surgery, we created three tunnels using silicon rods for the smooth tendon gliding. In the second stage, we transferred the same three pairs of the forearm agonist–antagonist tendons through the tunnels and implanted the magnetic tags inside the musculotendinous junction. Compared to our prior clinical investigation, fluoroscopy and ultrasound evaluations revealed that the surgical modification in the current study yielded more pronounced independent movements in two specific magnetic tags associated with fingers (maximum 5.7 mm in the first trial vs. 28 mm in the recent trial with grasp and release) and thumb (maximum 3.2 mm in the first trial vs. 9 mm in the current trial with thumb flexion–extension). Furthermore, we observed that utilizing the flexor digitorum superficialis (FDS) tendons for the flexor component in finger and thumb tendon transfer resulted in more independent movements of the implanted tags, compared with the flexor digitorum profundus (FDP) in the prior research. This study can help us plan for our future five-channel bionic limb design by identifying the gestures with the most significant independent tag displacement.

A highly integrated bionic hand with neural control and feedback for use in daily life.

Restoration of sensorimotor function after amputation has remained challenging because of the lack of human-machine interfaces that provide reliable control, feedback, and attachment. Here, we present the clinical implementation of a transradial neuromusculoskeletal prosthesis-a bionic hand connected directly to the user's nervous and skeletal systems. In one person with unilateral below-elbow amputation, titanium implants were placed intramedullary in the radius and ulna bones, and electromuscular constructs were created surgically by transferring the severed nerves to free muscle grafts. The native muscles, free muscle grafts, and ulnar nerve were implanted with electrodes. Percutaneous extensions from the titanium implants provided direct skeletal attachment and bidirectional communication between the implanted electrodes and a prosthetic hand. Operation of the bionic hand in daily life resulted in improved prosthetic function, reduced postamputation, and increased quality of life. Sensations elicited via direct neural stimulation were consistently perceived on the phantom hand throughout the study. To date, the patient continues using the prosthesis in daily life. The functionality of conventional artificial limbs is hindered by discomfort and limited and unreliable control. Neuromusculoskeletal interfaces can overcome these hurdles and provide the means for the everyday use of a prosthesis with reliable neural control fixated into the skeleton.

PH and temperature dual-responsive hydrogel actuator with bidirectional bending behavior and ultra large bending angle

Smart hydrogels have received attentions for the great potentials in biomedical and robots applications. However, the deformation performance of hydrogels still needs to be improved, especially for the pH and thermal dual responsive hydrogels. In this study, a pH and temperature dual-responsive poly(acrylamide-acrylic acid-3-acrylamidophenylboronic acid)/Poly(N-isopropylacrylamide) (P(AAm-AAc-3-AAPBA)/PNIPAM) bilayer structures have been prepared by UV polymerization. The PNIPAM layer shrinks/swells when the temperature is higher/lower than the low critical solution temperature, while P(AAm-AAc-3-AAPBA) layer will swell/shrink when pH is too high/low. The volume change trend of the two layer is different, resulting in the bending behaviors of P(AAm-AAc-3-AAPBA)/PNIPAM hydrogel actuator. The bidirectional bending performance can be reversibly, repeatedly, and precisely controlled by pH and temperature-induced cooperative swelling-shrinking properties from both layers. The bending angle of the bilayer structure achieves about 1420° at the environment of pH 2 and 55 ℃. It takes about 70 s to convert the bending angle of the bilayer structures from 355° (10 ℃, pH 2) to −360° (55 ℃, pH 12). In addition, three kinds of biomimetic hydrogel structures, such as mechanical gripper, bionic flower and bionic hand, have been prepared and demonstrated good performance. The obtained P(AAm-AAc-3-AAPBA)/PNIPAM hydrogels exhibit excellent pH and thermal responsive bending properties, which enable them as an ideal smart hydrogel system.

A 3D Printed, Bionic Hand Powered by EMG Signals and Controlled by an Online Neural Network.

About 8% of the Ecuadorian population suffers some type of amputation of upper or lower limbs. Due to the high cost of a prosthesis and the fact that the salary of an average worker in the country reached 248 USD in August 2021, they experience a great labor disadvantage and only 17% of them are employed. Thanks to advances in 3D printing and the accessibility of bioelectric sensors, it is now possible to create economically accessible proposals. This work proposes the design of a hand prosthesis that uses electromyography (EMG) signals and neural networks for real-time control. The integrated system has a mechanical and electronic design, and the latter integrates artificial intelligence for control. To train the algorithm, an experimental methodology was developed to record muscle activity in upper extremities associated with specific tasks, using three EMG surface sensors. These data were used to train a five-layer neural network. the trained model was compressed and exported using TensorflowLite. The prosthesis consisted of a gripper and a pivot base, which were designed in Fusion 360 considering the movement restrictions and the maximum loads. It was actuated in real time thanks to the design of an electronic circuit that used an ESP32 development board, which was responsible for recording, processing and classifying the EMG signals associated with a motor intention, and to actuate the hand prosthesis. As a result of this work, a database with 60 electromyographic activity records from three tasks was released. The classification algorithm was able to detect the three muscle tasks with an accuracy of 78.67% and a response time of 80 ms. Finally, the 3D printed prosthesis was able to support a weight of 500 g with a safety factor equal to 15.

Hand Grasp Pose Prediction Based on Motion Prior Field.

Shared control of bionic robot hands has recently attracted much research attention. However, few studies have performed predictive analysis for grasp pose, which is vital for the pre-shape planning of robotic wrists and hands. Aiming at shared control of dexterous hand grasp planning, this paper proposes a framework for grasp pose prediction based on the motion prior field. To map the hand-object pose to the final grasp pose, an object-centered motion prior field is established to learn the prediction model. The results of motion capture reconstruction show that, with the input of a 7-dimensional pose and cluster manifolds of dimension 100, the model performs best in terms of prediction accuracy (90.2%) and error distance (1.27 cm) in the sequence. The model makes correct predictions in the first 50% of the sequence during hand approach to the object. The outcomes of this study enable prediction of the grasp pose in advance as the hand approaches the object, which is very important for enabling the shared control of bionic and prosthetic hands.

Finger Kinematics during Human Hand Grip and Release.

A bionic robotic hand can perform many movements similar to a human hand. However, there is still a significant gap in manipulation between robot and human hands. It is necessary to understand the finger kinematics and motion patterns of human hands to improve the performance of robotic hands. This study aimed to comprehensively investigate normal hand motion patterns by evaluating the kinematics of hand grip and release in healthy individuals. The data corresponding to rapid grip and release were collected from the dominant hands of 22 healthy people by sensory glove. The kinematics of 14 finger joints were analyzed, including the dynamic range of motion (ROM), peak velocity, joint sequence and finger sequence. The results show that the proximal interphalangeal (PIP) joint had a larger dynamic ROM than metacarpophalangeal (MCP) and distal interphalangeal (DIP) joints. Additionally, the PIP joint had the highest peak velocity, both in flexion and extension. For joint sequence, the PIP joint moved prior to the DIP or MCP joints during flexion, while extension started in DIP or MCP joints, followed by the PIP joint. Regarding the finger sequence, the thumb started to move before the four fingers, and stopped moving after the fingers during both grip and release. This study explored the normal motion patterns in hand grip and release, which provided a kinematic reference for the design of robotic hands and thus contributes to its development.

Speech Recognition pada Kontrol Gerak Tangan Bionik berbasis Raspberry Pi dan Arduino

<p><em>The bionic hand is a broad bio-mechatronic device that incorporates various concepts involving biology and mechatronics. In this journal, the authors research finger movements in bionic hands using voice commands. In designing this bionic hand, the author made a mechanical design using a 3D printing machine. The hardware design used by the Raspberry Pi to process voice data is then transmitted to Arduino to carry out servo movement commands so that it can move bionic fingers. Software design uses the Python language using the Google text-to-speech API. From this research, data was generated with 100% accuracy. The movement of bionic fingers moves according to the commands spoken.</em></p>

A Future Realistic Model of Bionic Limbs with High Accuracy

Bionic limb achievements in the last 10 years have primarily focused on breakthroughs to improve accuracy with new materials and concepts that are unlikely to be used when producing an entire upper bionic limb. For example, studies on bionic limbs with new materials, such as pneumatic bionic flexible arms, which cannot meet the needs of amputees in terms of using comfortably and accurately interpreting users' intentions. Though the future development of bionic limbs has many possibilities, this paper summarizes and analyzes the functions and drawbacks of three most important structures in bionic hands and compares them to the most widely used sensory feedback realization methods. The paper then designed a future model based on the perspectives discussed above in order to meet the requirements of high accuracy, flexibility, a comfortable feeling, and real-time sensory feedback. Finally, the paper contrasts the BCI technique with the newly developed model.

Biorealistic hand prosthesis with compliance control and noninvasive somatotopic sensory feedback

Significant advances have been made to improve control and to provide sensory functions for bionic hands. However, great challenges remain, limiting wide acceptance of bionic hands due to inadequate bidirectional neural compatibility with human users. Recent research has brought to light the necessity for matching neuromechanical behaviors between the prosthesis and the sensorimotor system of amputees. A novel approach to achieving greater neural compatibility leverages the technology of biorealistic modeling with real-time computation. These studies have demonstrated a promising outlook that this unique approach may transform the performance of hand prostheses. Simultaneously, a noninvasive technique of somatotopic sensory feedback has been developed based on evoked tactile sensation (ETS) for conveying natural, intuitive, and digit-specific tactile information to users. This paper reports the recent work on these two important aspects of sensorimotor functions in prosthetic research. A background review is presented first on the state of the art of bionic hand and the various techniques to deliver tactile sensory information to users. Progress in developing the novel biorealistic hand prosthesis and the technique of noninvasive ETS feedback is then highlighted. Finally, challenges to future development of the biorealistic hand prosthesis and implementing the ETS feedback are discussed with respect to shaping a next-generation hand prosthesis.

Cross-Modal Integration and Transfer Learning Using Fuzzy Logic Techniques for Intelligent Upper Limb Prosthesis

The integration and interaction of proprioception and exteroception in the human multisensory network facilitate high-level cognitive functionalities, such as cross-modal integration, recognition, and imagination for accurate evaluation and comprehensive understanding of the multimodal world. In this article, we propose a novel cross-modal integration framework for the upper limb prosthesis based on type-2 fuzzy logic system (FLS), which can facilitate the high-level cognitive and dexterous manipulation of the prosthesis by combing human's surface electromyography (sEMG) with the computer vision. First, a transfer learning approach is proposed to improve the decoding of human's intent and enhance the effectiveness of skill transition. Then the sEMG signals and image information are integrated to jointly determine the grasp posture of the bionic hand based on fuzzy decision strategy. Fusing multisensory data and using cross-modal integration, the system is capable of crossmodally recognizing multimodal information. In order to realize the prosthesis automatically reaching the target position under the guidance of computer vision, an interval type-2 fuzzy logic controller considering uncertain dynamic parameters and disturbance is designed. Experiments are performed in some typical 3C assembly scenarios, and results show that our proposed strategy can obviously improve the accuracy of grasp posture selection and trajectory tracking effect, which brings more potential job opportunities with hope to amputees, and provides a promising approach toward robotic sensing and perception.

Realization of a Bionic Hand Controlled via Bluetooth Communication Utilizing a Microcontroller

The ability of people without limbs to do their own work and their adaptation to life can be achieved with bionic hands. The aim of this study is to realize the design and application of bionic hand that can be controlled by mobile application for handicapped individuals. The aerobic designs necessary to solve this problem were made and a prototype was produced and controlled with Arduino Mega 2560 microcontroller. For the five fingers of the bionic hand designed with the work carried out, the independent movement of the five fingers from the fingertip to all the other joints has been successfully performed using five SG90 model mini servomotors. The movement of the servomotors is provided by the software developed with the MIT AI2 Companion program on the mobile phone. The software algorithm has been fulfilled separately for each finger and each joint. Microcontroller and mobile phone communication is done with HC-06 Bluetooth module. Servomotor fin connections are made with fishing line with the tip of each finger. The two joints of the thumb and three joints of the other four fingers are controlled by winding the fishing line, which is connected to the servomotor, according to the determined rotation angle. Thus, the control of the fingers on the hand was realized through the mobile application. Ultimately, the effective use of the bionic hand will have an impact on every individual's participation in society. Every individual who is brought into the society has the potential to be an individual who enters the business life at the same time. For this reason, this will allow for an increase in employment and working power. It is also more sustainable because it raises people's living standards.

Study on the methods of feature extraction based on electromyographic signal classification.

Electromyography (EMG) is a form of biological information, which is used in many fields to help people study human muscle movement, especially in the study of bionic hands. EMG signals can be used to explain the activity at a certain moment through the signal changes of human muscles, and it is a very complex signal, so processing it is very important. The process of EMG signals can be divided into acquisition, pre-processing, feature extraction, and classification. Not all signal channels are useful in EMG acquisition, and it is important to select useful signals among them. Therefore, this study proposes a feature extraction method to extract the most representative two-channel signals from the eight-channel signals. In this paper, the traditional principal component analysis method and support vector machine feature elimination are used to extract signal channels. At the same time, a new method, correlation heat map, is proposed to implement feature extraction method by using three methods, and three classification algorithms of K-nearest neighbor, random forest, and support vector machine are used to verify. The results show that the classification accuracy of the proposed method is better than that of the other two traditional methods.

A self-sensing intelligent soft pneumatic actuator with soft magnetic structures

Many achievements for soft pneumatic actuators (SPAs) are made in the structure design and application demonstration. However, few studies focus on their mechanical sensing which is significant toward autonomous and intelligent soft robots. Herein, a self-sensing intelligent soft pneumatic actuator (SISPA) is developed by integrating a sensing layer that is silicone rubber/NdFeB composite twined with a varnished wire. The induced voltage is generated with the bending deformation of the sensing layer. Experimental results show that the induced voltage rises with the increasing mass fraction of magnetic powders, turns of the varnished wire, and thicknesses and widths of the composite. The bending deformation of the SISPA is also investigated experimentally and numerically. The bending angle of the SISPA reaches 225.5° with an applied pressure of 40 kPa, which is 92.68% of that of the SPA without embedding the sensing layer. The effect of the four parameters of the sensing layer on the bending deformation is investigated as well. In conclusion, the sensing layer has a slight effect on the bending deformation of the SISPA. Based on the experimental data, we find that there is a linear relationship between the bending angle and magnetic flux change. So the relation of the bending deformation and output voltage is formulated approximatively. Finally, an intelligent bionic hand is developed by utilizing the SISPA, which outputs different signals according to diverse gestures. Therefore, the proposed SISPA can be an attractive candidate involving accuracy control and intelligent soft robots.

A bioinspired 3D-printable flexure joint with cellular mechanical metamaterial architecture for soft robotic hands.

Compliant flexure joints have been widely used for cable-driven soft robotic hands and grippers due to their safe interaction with humans and objects. This paper presents a soft and compliant revolute flexure joint based on the auxetic cellular mechanical metamaterials with a heterogeneous structure. The heterogeneous architecture of the proposed metamaterial flexure joint (MFJ), which is inspired by the human finger joints, provides mechanically tunable multi-stiffness bending motion and large range of bending angle in comparison to conventional flexure joints. The multi-level variation of the joint stiffness over the range of bending motion can be tuned through the geometrical parameters of the cellular mechanical metamaterial unit cells. The proposed flexure joints are 3D printed with single flexible material in monolithic fashion using a standard benchtop 3D printer. The application of the MFJ is demonstrated in robotic in-hand manipulation and grasping thin and deformable objects such as wires and cables. The results show the capability and advantages of the proposed MFJ in soft robotic grippers and highly functional bionic hands.

Controlling Upper Limb Prostheses Using Sonomyography (SMG): A Review.

This paper presents a critical review and comparison of the results of recently published studies in the fields of human-machine interface and the use of sonomyography (SMG) for the control of upper limb prothesis. For this review paper, a combination of the keywords "Human Machine Interface", "Sonomyography", "Ultrasound", "Upper Limb Prosthesis", "Artificial Intelligence", and "Non-Invasive Sensors" was used to search for articles on Google Scholar and PubMed. Sixty-one articles were found, of which fifty-nine were used in this review. For a comparison of the different ultrasound modes, feature extraction methods, and machine learning algorithms, 16 articles were used. Various modes of ultrasound devices for prosthetic control, various machine learning algorithms for classifying different hand gestures, and various feature extraction methods for increasing the accuracy of artificial intelligence used in their controlling systems are reviewed in this article. The results of the review article show that ultrasound sensing has the potential to be used as a viable human-machine interface in order to control bionic hands with multiple degrees of freedom. Moreover, different hand gestures can be classified by different machine learning algorithms trained with extracted features from collected data with an accuracy of around 95%.

Design and control of intelligent bionic artificial hand based on image recognition.

At present, the popular control method for intelligent bionic prosthetic hands is EMG control. However, the control accuracy of this method is low. It is a trend to integrate computer vision into the prosthetic hand. The purpose of this paper is to design an intelligent prosthetic hand based on image recognition, improve the control accuracy and the quality of life of the disabled. Convolutional neural network is used to recognize the object to be grasped, and the recognition result is used as a trigger signal to control our intelligent prosthetic hand. We have designed a four-bar linkage mechanism and a side swing mechanism in the structure, which can not only achieve the flexion and extension of fingers but also realize the adduction and abduction of the four fingers and the lateral swing of the thumb. Through the method of image recognition, the new intelligent bionic hand can achieve five kinds of Human action. Including grasp, side pinch, three-finger pinch, two-finger pinch, and pinch between fingers. The experiment result proves that the precision of image recognition control is very excellent, the intelligent prosthetic hand can be completed the corresponding task.

Flexible pressure/temperature sensing system based on Te-PEDOT:PSS composite thermoelectric material

<p indent="0mm">With the rapid development of artificial intelligence, the demand for new flexible tactile sensors for human-machine interaction technology is increasing sharply. As an essential medium for intelligent bionic systems to obtain external information, such as intelligent manipulators and bionic prosthetic hands, flexible tactile sensors are significant for realizing bionic tactile perception and improving system intelligence. Recently, fabricating multimodal tactile sensors through theoptimal design of functional material and structure has become a key challenge in the field of flexible electronics. Herein, a thermoelectric sensing material composited of Te-poly (3,4-ethylenedioxythiophene)-poly(styrene sulfonic acid) (Te-PEDOT:PSS) was prepared via a hydrothermal method, which was compounded within a three-dimensional porous dense amine foam framework and subsequently coated by a thin polyvinyl alcohol layer for encapsulation. The controllable preparation of sensitive composite materials with high interfacial stability was realized. Thus, the assembled flexible tactile sensor with a thermoelectric effect and capacitance performance can achieve the perception ability of pressure/temperature in contact/noncontact mode, respectively. Further, an intelligent manipulator sensory feedback system is constructed, and its performance in tactile perception is explored.

Novel Bionic Soft Robotic Hand With Dexterous Deformation and Reliable Grasping

Bionic soft robotic hand has been developed rapidly, as it can achieve considerable flexibility and mimic human hand to perform actions such as grasping. This study develops a novel bionic soft robotic hand, which consists of a palm and five fingers that can operate independently. Unlike other soft hands, the fingers of the developed soft robotic hand are capable of stretching and bending. The thumb can mimic the joint activities of human thumb. An air chamber is placed on the back of robotic hand to mimic the elongation of muscles on the back of human hand. As such, the curvature of the palm can be changed. A particle jamming method is used in the hand palm to achieve passive variable stiffness during grasping, which improves the grasping stability of the bionic hand and the ability of wrapping target objects. Grasping experiments are conducted to evaluate and validate the grasping performance of the developed soft robotic hand. The experimental results show that the developed soft hand can effectively grasp sheet, columnar, and irregular objects when the driving pressure of finger and hand back are 50 kPa and 40 kPa, respectively. The maximum grasping mass is comparable to the mass of the soft robotic hand.