RESUMEN

The design and control of artificial hands remains a challenge in engineering. Popular prostheses are bio-mechanically simple with restricted manipulation capabilities, as advanced devices are pricy or abandoned due to their difficult communication with the hand. For social robots, the interpretation of human intention is key for their integration in daily life. This can be achieved with machine learning (ML) algorithms, which are barely used for grasping posture recognition. This work proposes an ML approach to recognize nine hand postures, representing 90% of the activities of daily living in real time using an sEMG human-robot interface (HRI). Data from 20 subjects wearing a Myo armband (8 sEMG signals) were gathered from the NinaPro DS5 and from experimental tests with the YCB Object Set, and they were used jointly in the development of a simple multi-layer perceptron in MATLAB, with a global percentage success of 73% using only two features. GPU-based implementations were run to select the best architecture, with generalization capabilities, robustness-versus-electrode shift, low memory expense, and real-time performance. This architecture enables the implementation of grasping posture recognition in low-cost devices, aimed at the development of affordable functional prostheses and HRI for social robots.

Asunto(s)

RESUMEN

Introduction: Myoelectric pattern recognition systems have shown promising control of upper limb powered prostheses and are now commercially available. These pattern recognition systems typically record from up to 8 muscle sites, whereas other control systems use two-site control. While previous offline studies have shown 8 or fewer sites to be optimal, real-time control was not evaluated. Methods: Six individuals with no limb absence and four individuals with a transradial amputation controlled a virtual upper limb prosthesis using pattern recognition control with 8 and 16 channels of EMG. Additionally, two of the individuals with a transradial amputation performed the Assessment for Capacity of Myoelectric Control (ACMC) with a multi-articulating hand and wrist prosthesis with the same channel count conditions. Results: Users had significant improvements in control when using 16 compared to 8 EMG channels including decreased classification error (p = 0.006), decreased completion time (p = 0.019), and increased path efficiency (p = 0.013) when controlling a virtual prosthesis. ACMC scores increased by more than three times the minimal detectable change from the 8 to the 16-channel condition. Discussion: The results of this study indicate that increasing EMG channel count beyond the clinical standard of 8 channels can benefit myoelectric pattern recognition users.

RESUMEN

AIM: Continuous real-time echocardiographic monitoring is essential for guidance during ASD closure. However, transthoracic echocardiography (TTE) can only be implemented intermittently during fluoroscopy. We evaluate a novel approach to provide real-time imaging during the entire procedure. FINDING: We developed a custom-made TTE monitoring apparatus using artificial hand (AH-TTE) that enables real-time TTE images during atrial septal defect (ASD) closure. Thirty-two patients underwent successful device implantation using AH-TTE monitoring without complications. The median duration for real-time AH-TTE monitoring was 22 min and the median fluoroscopy time was 7.2 min. One case of pericardial effusion and one of transient bradycardia event due to air embolism was detected. All patients had uneventful recoveries. CONCLUSIONS: Our simple and novel monitoring technique with AH-TTE provides TEE-like monitoring and may be a new alternative method for ASD closure. It gives real-time stable TTE images and minimizes radiation exposure for the interventional team during fluoroscopy.

Asunto(s)

RESUMEN

The development of underwater robotics sensitivity, which is based on the sensors of laser spectroscopy methods, have been discussed. The ways to improve Laser Induced Fluorescence (LIF) and Laser Induced Breakdown Spectroscopy (LIBS) methods were investigated in order to develop and create laser sensitivity for underwater robotics. A brief overview is done in the article, where LIF and LIBS spectroscopy in underwater robotics are used as spectroscopy sensors in order to investigate underwater environments by means of underwater vehicles. Limit of Detection (LoD) of oil and oil product solutions in the seawater have been detected by means of nanosecond and femtosecond spectroscopy LIF. All results, which had been received by laser pulses of different duration, were compared. The same experiments have been provided in order to measure concentrations of elements in the seawater and solutions by the LIBS method. It was discovered that the LoD of a group of elements was reduced when the femtosecond LIBS was used. Anthropomorphic complexes were under discussion in order to adopt laser spectroscopy sensors for underwater environments. The submersible module, which was constructed to investigate and examine laser spectroscopy sensors, has been described.

RESUMEN

This study presents the development of an innovative artificial finger-like device that provides position specific mechanical loads at the end of the long bone and induces mechanotransduction in bone. Bone cells such as osteoblasts are the mechanosensitive cells that regulate bone remodelling. When they receive gentle, periodic mechanical loads, new bone formation is promoted. The proposed device is an under-actuated multi-fingered artificial hand with 4 fingers, each having two phalanges. These fingers are connected by mechanical linkages and operated by a worm gearing mechanism. With the help of 3D printing technology, a prototype device was built mostly using plastic materials. The experimental validation results show that the device is capable of generating necessary forces at the desired frequencies, which are suitable for the stimulation of bone cells and the promotion of bone formation. It is recommended that the device be tested in a clinical study for confirming its safety and efficacy with patients.

RESUMEN

Recently, significant advances over the past decade have been made in robotics, artificial intelligence and other cognitive related fields, allowing development of highly sophisticated bio-mimetic robotics systems. In addition, enormous number of robots have been designed and assembled by explicitly realising their biological oriented behaviours. To enhance skill behaviours and adequate grasping abilities in these devices, a new phase of dexterous hands has been developed recently with bio-mimetically oriented and bio-inspired functionalities. The aim in writing this review paper is to present a detailed insight towards the development of the bio-mimetic based dexterous robotic multi-fingered artificial hand. An "ideal" upper limb prosthesis should be perceived as a part of their natural body by the amputee and should replicate sensory-motor capabilities of the amputated limb. Upper-limb amputations are most often the result of sudden trauma to the body, although they also can be caused by malignancy, congenital deficiencies and vascular diseases. This paper discusses the different bio-mimetic approaches using a framework that permits for a common description of biological and technical based hand manipulation behaviour. In particular, the review focuses on a number of developments in the inspired robotic systems. In conclusion, the study found that a huge amount of research efforts in terms of kinematics, dynamics, modelling and control methodologies are being put in to improve the present hand technology, thereby providing more functionality to the prosthetic limb of the amputee. This would improve their quality-of-life and help in performing activities of daily living (ADL) tasks with comparative ease in the near future.

Asunto(s)

RESUMEN

Objective To study the best method for myoelectric feedback training and evaluate the effectiveness of myoelectric artificial hand. Methods Fourteen cases of upper limb amputees (11 male, 3 female, aged 25?8.69 years, right side 13, left side 3,totally 16 myoelectric artificial hands) were recruited for this study. The biofeedback training process was divided into three steps: basic signal of myoelectric feedback training, visible feedback training, and ADL function training. Results After the training, 16 myoelectric artificial hands could grasp, pinch and rotate wrist, and could perform ADL such as dressing, eating, cleaning. Conclusion To achieve the goal set for the myoelectric artificial hand, emphasis should be on locating the most stronger myoelectric signal of the stump and strengthening the feedback training.

RESUMEN

Hands are an important organ with which mankind has created his civilizations. Functional reconstruction of hand defects is a difficult clinical problem. The cosmetic artificial hand has no other function than that of decoration. The tool hand and kruckenberg forearm furcate phalangisation have scarcely been utilized now because they have limited functions. The myoelectric artificial hand is the major product on the prosthese market, but its accuracy needs improving. Microsurgery can restore part of the sensory functions of the hand but can not restore its normal contour. Treatment of the lost part of the forearm with an electronic artificial hand, which is controlled by a reconstructed digit transplanted from the second toe to the forearm stump, improves the action accuracy. Wide application of this new technique is recommendable. More than 10 cases treated with allograft hand transplantation have been reported recently. Since these patients have to receive a long term therapy of immunosuppressive agents due to the immunological rejection,this method is not suitable to be a routine clinical operation. If the problems concerning transplantation immunity are solved, allograft hand transplantation will be an optimal method of functional reconstruction of hand defects.