Integration of autonomous and pattern recognition controls in hand prostheses

The pricing of high-performance hand prostheses and grasp limitations of low-cost hand prostheses indicate a need for the creation of a cost-effective upper limb prosthesis with high-performance capabilities. The need is particularly relevant for pediatric recreational applications, as it is difficult to finance multiple high-performance devices to match the growth of a child. We propose a low-cost upper limb prosthesis, the HelpingHand, to address these concerns through modification of the publicly available e-NABLE Phoenix Hand v2. Custom flexible finger modules and a user-adjustable whippletree mechanism were developed, allowing for swapping between power and precision grasp positions based on selected tension levels. The two designs were then compared through user performance tests with various common household objects and grasp positions. The HelpingHand device features wrist actuation and incorporation of various adjustable power and precision grasp patterns with a material price point of under $10. In addition, bioinspired flexible finger modules were created to improve device grasp functionality. User tests demonstrated improvements in device performance in both power and precision grasp positions over current low-cost prosthetic standards. Implementation of user-adjusted grasp positions in an upper limb prosthesis developed with accessible manufacturing methods represents a promising step forward in low-cost device development. With further optimization and validation, the HelpingHand could provide an advancement in low-cost recreational prosthetic technology.

In this paper, we discuss the potential contribution of affective touch to the user experience and robot performance in human-robot interaction, with an in-depth look into upper-limb prosthesis use as a well-suited example. Research on providing haptic feedback in human-robot interaction has worked to relay discriminative information during functional activities of daily living, like grasping a cup of tea. However, this approach neglects to recognize the affective information our bodies give and receive during social activities of daily living, like shaking hands. The discussion covers the emotional dimensions of affective touch and its role in conveying distinct emotions. In this work, we provide a human needs-centered approach to human-robot interaction design and argue for an equal emphasis to be placed on providing affective haptic feedback channels to meet the social tactile needs and interactions of human agents. We suggest incorporating affective touch to enhance user experience when interacting with and through semi-autonomous systems such as prosthetic limbs, particularly in fostering trust. Real-time analysis of trust as a dynamic phenomenon can pave the way towards adaptive shared autonomy strategies and consequently enhance the acceptance of prosthetic limbs. Here we highlight certain feasibility considerations, emphasizing practical designs and multi-sensory approaches for the effective implementation of affective touch interfaces.

A two degree-of-freedom microprocessor based controller that uses the principle of Extended Physiological Proprio- ception (EPP), was designed for the simultaneous multifunctional control of upper-limb prostheses. In an EPP system, the output is related to the input by a mechanically unbeatable position servomechanism. Use of embedded microprocessor systems in the control of upper-limb prostheses provides a high degree of control algorithm flexibility allowing different control algorithms to be downloaded and executed in the same controller circuit. In addition, control parameters can be easily adjusted and tailored to different user capabilities. In a trans-humeral or shoulder disarticulation prosthesis we envision this controller enabling EPP control of both elbow flexion-extension, and humeral rotation. In a wrist disarticulation or trans-radial prosthesis this controller, in conjunction with other similar controllers, could provide EPP control of individual digits in a multifunctional hand prosthesis.

Although significant technological advances have been made in the last forty years, natural and effortless control of upper limb prostheses is still an open issue. Commercially available myoelectric prostheses present limited Degrees of Freedom (DoF) mainly because of the lack of available and reliable independent control signals from the human body. Thus, despite the crucial role that an actuated wrist could play in a transradial prosthesis in terms of avoiding compensatory movements, commercial hand prostheses present only manually adjustable passive wrists or actuated rotators controlled by (unnatural) sequential control strategies. In the present study we investigated the synergies between the humeral orientation with respect to the trunk and the forearm pronation/supination angles during the execution of a wide range of activities of daily living, in healthy subjects. Our results showed consistent postural synergies between the two selected body segments for almost the totality of the activities of daily living under investigation. This is a promising result because these postural synergies could be exploited to automatically control the wrist rotator unit in transradial prostheses improving the fluency and the dexterity of the amputee.

The high-paced development of wireless communication technologies brought about the growing need of smart, autonomous, and ultra-high-performance network structures, and the combination of Artificial Intelligence and Machine Learning in the 6G wireless communication networks is a major research issue. The conventional network management techniques cannot support the new demands that include ultra-low latency communications, intelligent spectrum management, mass connectivity, and real-time dynamic resource provision. This paper is a systematically-conducted literature review on the recent research on AI-driven networks, edge AI, federated learning, intelligent radio access network design, and AI-native architecture in next-generation networks based on PRISMA. The review focuses on the possibilities of self-organizing networks, digital twin networks, and smart connectivity that machine learning, deep learning, and autonomous wireless systems provide to the next generation of wireless networks working in terahertz communication ranges and integrated sensing and communication landscape. The findings indicate that AI based resource allocation, intelligent surfaces of reconfigurability, massive mimo optimization and network automation are all effective towards improving spectral efficiency, reliability and energy efficiency of 6G wireless communication. Moreover, the paper has also noted the increased importance of smart security mechanisms, distributed learning, and edge computing in enabling scalable and secure AI-native architectures. The results also indicate that the next generation wireless networks will be based upon intelligent spectrum management, autonomous control, and real-time data analytics to accommodate the new applications in holographic communication, smart cities, extended reality, and connected autonomous systems.

Automation of wrist rotations in upper limb prostheses allows simplification of the human-machine interface, reducing the user's mental load and avoiding compensatory movements. This study explored the possibility of predicting wrist rotations in pick-and-place tasks based on kinematic information from the other arm joints. To do this, the position and orientation of the hand, forearm, arm, and back were recorded from five subjects during transport of a cylindrical and a spherical object between four different locations on a vertical shelf. The rotation angles in the arm joints were obtained from the records and used to train feed-forward neural networks (FFNNs) and time-delay neural networks (TDNNs) in order to predict wrist rotations (flexion/extension, abduction/adduction, and pronation/supination) based on the angles at the elbow and shoulder. Correlation coefficients between actual and predicted angles of 0.88 for the FFNN and 0.94 for the TDNN were obtained. These correlations improved when object information was added to the network or when it was trained separately for each object (0.94 for the FFNN, 0.96 for the TDNN). Similarly, it improved when the network was trained specifically for each subject. These results suggest that it would be feasible to reduce compensatory movements in prosthetic hands for specific tasks by using motorized wrists and automating their rotation based on kinematic information obtained with sensors appropriately positioned in the prosthesis and the subject's body.

Introduction Upper-limb prostheses have undergone substantial technological improvements in the last two decades, but user complaints and abandonment rates have hardly changed. This may follow from the use of laboratory-based tests when assessing new technology instead of measuring prosthesis use in at-home situations. Serious games might be used to assess prosthesis use at home. Objectives The aim of this study was to assess the feasibility, validity, and reliability of using serious games to measure myocontrol in at-home situations. Study Design The design of this study is a cohort study with repeated measurements. Methods All 10 participants (five males; seven transradial and three transhumeral defects) used pattern recognition (PR) to control their prosthesis. Two serious games were included in the PR software: Simon Says and In-The-Zone. Participants were instructed to use their prosthesis as they normally would for 2 weeks with the additional instruction to play at least 18 serious games (±90 minutes in total). Outcome measures for aspects of prosthesis use were wear time, months of prosthesis use, and user experiences, and serious games outcomes were success rate and completion time. Results For feasibility, all but one participant completed the minimum of 18 games, and user experiences were mostly positive. For validity, no relationships were found between the aspects of prosthesis use and performance in the serious games. For reliability, test-retest reliability for success rate was high (intraclass correlation [ICC], 0.79), but low for completion time (ICC, 0.18) in both games. Conclusions Feasibility and reliability of using serious games as an assessment instrument for prosthesis control in at-home situations appeared to be good; however, validity could not be established. The serious games should be improved to increase validity. Furthermore, more outcome measures that reveal aspects of prosthesis use should be considered. Clinical Relevance Statement Assessing myocontrol in at-home situations by using serious games is feasible and reliable, but validity needs further attention.

Understanding the fundamental characteristics of prosthetic movement control is imperative in improving prosthesis design and training. This study quantified how using an upper limb prosthesis affected performance during goal-directed reaching tasks. Nine prosthesis users with unilateral transradial limb absence and nine healthy controls completed a series of goal-directed reaching movements with different goals: one spatial and three temporal with different goal frequencies. We quantified end-point accuracy, smoothness, and peak speed for the spatial task and temporal accuracy, horizontal distance, and speed for the temporal task. For the temporal task, we also used a goal-equivalent manifold (GEM) approach to decompose variability in movement distance and speed into those perpendicular and tangential to the GEM. Detrended fluctuation analysis (DFA) quantified the temporal persistence of each time series. For the spatial task, movements made with prostheses were less smooth, had larger end-point errors, and had slower peak speed compared to those with control limbs (p < 0.041). For the temporal task, movements made with prostheses and intact limbs of prosthesis users and control limbs were similar in distance and speed and had similar timing errors (p > 0.138). Timing errors, distance, speed, and GEM deviations were corrected similarly between prosthetic limbs and control limbs (p > 0.091). The mean and variability of distance, speed, and perpendicular deviations decreased with increased goal frequency (p < 0.001). Our results suggest that prosthesis users have a sufficient internal model to successfully complete ballistic movements but are unable to accurately complete movements requiring substantial feedback.

Background. At the present stage, electronic communications must provide: ultra-fast data exchange between production systems, which increases productivity and safety; the use of robotic systems and artificial intelligence to support people in production processes. Reliable electronic communications ensure the security of industrial networks and personal data; intelligent factories with network sensors and automated data processing systems. In this context, new challenges are facing electronic communications and, accordingly, new problems are identified, the solution of which requires conducting promising scientific research. Objective. The purpose of this work is to generalise and highlight the key areas of development of electronic communications, which determine the current and future state of the industry. It is aimed at outlining scientific challenges and prospects associated with the digitalisation of society, the growth of demand for fast, reliable and secure data transmission. Methods. Analysis of factors and technologies that influence the growth of needs for the further development of electronic communications, the quality of telecommunications services in fifth and next generation networks, the introduction of new types of electronic communications and their integration with advanced information technologies. Results. The presented research directions determine the future of electronic communications. Research in these areas will ensure the sustainable development of the industry, taking into account the growing needs of modern society in fast, secure and reliable data transmission technologies. Conclusions. The main goal of the 6G direction and future generations of networks is to create ultra-fast, ultra-reliable and intelligent networks capable of supporting new types of services and applications, from autonomous control and remote medicine to full-scale multimedia communications. The direction of quantum communications is a revolutionary direction that promises to ensure absolute security of information transmission and open up new opportunities for communication. The direction of IoT scaling is a key direction that determines the future of many communication technologies. The research area that includes artificial intelligence (AI) and machine learning (ML) calls for further integration of AI and ML into all aspects of electronic communications, leading to smarter, more efficient and secure networks. Security and privacy in electronic communications is a dynamic area that is constantly evolving due to the growth of cyber threats and technological advancements. Edge and Fog Computing are key technologies for the future of electronic communications, and their development requires an interdisciplinary approach that combines computer science, telecommunications, AI and IoT. Research in the field of NFV and SDN is necessary to improve the performance, automation and security of networks. They play a key role in the future of 5G/6G, cloud computing, IoT and industrial networks. Green communications is an important research area that aims to improve the energy efficiency and sustainability of telecommunications networks. Networks for critical applications are a key element of modern infrastructures, and their development requires an interdisciplinary approach that combines telecommunications, cybersecurity, artificial intelligence and other fields. Holographic and tactile communication interaction technologies will become the basis of future digital communications, changing the way people and machines interact.

Although machine learning is not yet being used in clinical practice within the fields of prosthetics and orthotics, several studies on the use of prosthetics and orthotics have been conducted. We intend to provide relevant knowledge by conducting a systematic review of prior studies on using machine learning in the fields of prosthetics and orthotics. We searched the Medical Literature Analysis and Retrieval System Online (MEDLINE), Cochrane, Embase, and Scopus databases and retrieved studies published until July 18, 2021. The study included the application of machine learning algorithms to upper-limb and lower-limb prostheses and orthoses. The criteria of the Quality in Prognosis Studies tool were used to assess the methodological quality of the studies. A total of 13 studies were included in this systematic review. In the realm of prostheses, machine learning has been used to identify prosthesis, select an appropriate prosthesis, train after wearing the prosthesis, detect falls, and manage the temperature in the socket. In the field of orthotics, machine learning was used to control real-time movement while wearing an orthosis and predict the need for an orthosis. The studies included in this systematic review are limited to the algorithm development stage. However, if the developed algorithms are actually applied to clinical practice, it is expected that it will be useful for medical staff and users to handle prosthesis and orthosis.

This chapter discusses considerations for developing brain-machine interfaces (BMIs) for amputees to enhance their control of prosthetic devices. To date, very few studies have demonstrated closed-loop control of a prosthesis by amputees using a BMI. Thus, this chapter draws on concepts from other areas of BMI as they relate to prosthesis control, as well as myoelectric control schemes, which can serve as a reference for neural control of prosthetic devices. Command signals vary from discrete abstractions of limb movement to the fine control of joint angles in the mimicked limb. Given the challenges in fabricating prosthetic devices and mimicking the natural limb’s dexterity, many prosthetic developers have adopted control strategies that can reduce the number of degrees of freedom that are needed for control. We discuss recommendations on how models that predict motor intent may be calibrated and benchmarked with platforms that involve prosthetic devices. Additionally, we discuss considerations for BMIs that are specific to amputees, such as detecting motor intent, utilizing artificial sensory modalities, inducing prosthesis embodiment, and managing the phantom limb. This chapter is targeted toward developers who are aiming to develop a BMI for amputees.KeywordsBrain-machine interfaceNeuroprostheticAmputeeProsthetic limbBrain-controlled prosthesisMotor intentMotor imagerySensory feedbackEmbodimentPhantom limb

Introduction This article presents a unique case study of an individual with congenital limb loss and long-time (&gt;56 years) body-powered prosthesis use, who was able to control a sophisticated robotic upper-limb prosthesis using surface electromyography signals and pattern recognition (PR) algorithms. This case demonstrates that individuals with congenital limb amputation are able to learn unique strategies to intuitively control a dexterous prosthetic limb. Materials and Methods After completing four training sessions using a virtual integration environment, a single subject participated in 12 in-laboratory clinical training sessions using the modular prosthetic limb (MPL)—a novel multiple–degree-of-freedom dexterous upper-limb prosthesis prototype. Baseline assessments were made with her body-powered prosthesis, as well as a two-site direct-control myoelectric Bebionic she had recently received. Functional assessments with the MPL were conducted during sessions 6 and 12. Outcome measures included timed box and blocks (BB) test, Assessment of Capacity for Myoelectric Control (ACMC), Jebsen-Taylor Hand Function Test (JTHFT), Trinity Amputation and Prosthesis Experience Scale, Upper Extremity Functional Scale (UEFS), and NASA Task Load Index. Results The subject was able to control two independent wrist degrees of freedom and up to three independent hand grasps of the MPL, using an array of surface electrodes. Improvements in the BB and ACMC were observed, although the total time to complete the JTHFT stayed relatively the same from weeks 6 to 12, using the MPL. While her enpoint perceived funcitonal ability with the MPL was 58% compared with 83% with her personal myoelectric prosthesis (12 hours of use vs 4–5 weeks of use as denoted on the UEFS); the subject reported short length of training, a long-term body-powered prosthetic user with congenital limb loss was able to demonstrate objective improvements in control of a dexterous prosthetic hand over a 12-week period of in-laboratory training, achieving intuitive independent control of a variety of simultaneous individual wrist motions and grasp patterns using PR. Conclusions This case demonstrates that even individuals with congenital amputation may be considered as candidates for upper-limb PR-controlled myoelectric prosthetic devices using surface electrodes.

Many upper-limb prostheses lack proper wrist rotation functionality, leading to users performing poor compensatory strategies, leading to overuse or abandonment. In this study, we investigate the validity of creating and implementing a data-driven predictive control strategy in object grasping tasks performed in virtual reality. We propose the idea of using gaze-centered vision to predict the wrist rotations of a user and implement a user study to investigate the impact of using this predictive control. We demonstrate that using this vision-based predictive system leads to a decrease in compensatory movement in the shoulder, as well as task completion time. We discuss the cases in which the virtual prosthesis with the predictive model implemented did and did not make a physical improvement in various arm movements. We also discuss the cognitive value in implementing such predictive control strategies into prosthetic controllers. We find that gaze-centered vision provides information about the intent of the user when performing object reaching and that the performance of prosthetic hands improves greatly when wrist prediction is implemented. Lastly, we address the limitations of this study in the context of both the study itself as well as any future physical implementations.

Recently, there has been significant interest in applying machine-learning (ML) techniques to the automated analysis of X-ray scattering experiments, due to the increasing speed and size at which datasets are generated. ML-based analysis presents an important opportunity to establish a closed-loop feedback system, enabling monitoring and real-time decision-making based on online data analysis. In this study, the incorporation of a combined one-dimensional convolutional neural network (CNN) and multilayer perceptron that is trained to extract physical thin-film parameters (thickness, density, roughness) and capable of taking into account prior knowledge is described. ML-based online analysis results are processed in a closed-loop workflow for X-ray reflectometry (XRR), using the growth of organic thin films as an example. Our focus lies on the beamline integration of ML-based online data analysis and closed-loop feedback. Our data demonstrate the accuracy and robustness of ML methods for analyzing XRR curves and Bragg reflections and its autonomous control over a vacuum deposition setup.

Remote sensing (RS) is a very promising data collection tool for precision agriculture and has been widely used for many decades. However, the relative low spatial and temporal resolution are the major drawbacks for traditional RS platforms (such as satellites and piloted aircrafts). This study discusses the development of agricultural remote sensing system using autonomous unmanned helicopter to acquire the crop field image at the right time and right place with high image resolution. The helicopter was equipped with a global positioning system (GPS), an inertial measurement units (IMU) and a geomagnetic sensor to detect the position, attitude and velocity of the helicopter. An autonomous controller was used to control helicopter to reach desired positions. A multi-spectral camera was mounted on the helicopter using a pan/tilt platform which can adjust the camera posture according to attitude of the helicopter to avoid the image distortion. A ground station computer was used to communicate with the helicopter in real-time to monitor flight parameters and send out control command. The images captured from this system are suitable for multi-purpose agricultural RS research.