Body-machine Interface Research Articles

SoftBoMI: a non-invasive wearable body-machine interface for mapping movement of shoulder to commands

Objective.Customized human-machine interfaces for controlling assistive devices are vital in improving the self-help ability of upper limb amputees and tetraplegic patients. Given that most of them possess residual shoulder mobility, using it to generate commands to operate assistive devices can serve as a complementary approach to brain-computer interfaces.Approach.We propose a hybrid body-machine interface prototype that integrates soft sensors and an inertial measurement unit. This study introduces both a rule-based data decoding method and a user intent inference-based decoding method to map human shoulder movements into continuous commands. Additionally, by incorporating prior knowledge of the user's operational performance into a shared autonomy framework, we implement an adaptive switching command mapping approach. This approach enables seamless transitions between the two decoding methods, enhancing their adaptability across different tasks.Main results.The proposed method has been validated on individuals with cervical spinal cord injury, bilateral arm amputation, and healthy subjects through a series of center-out target reaching tasks and a virtual powered wheelchair driving task. The experimental results show that using both the soft sensors and the gyroscope exhibits the most well-rounded performance in intent inference. Additionally, the rule-based method demonstrates better dynamic performance for wheelchair operation, while the intent inference method is more accurate but has higher latency. Adaptive switching decoding methods offer the best adaptability by seamlessly transitioning between decoding methods for different tasks. Furthermore, we discussed the differences and characteristics among the various types of participants in the experiment.Significance.The proposed method has the potential to be integrated into clothing, enabling non-invasive interaction with assistive devices in daily life, and could serve as a tool for rehabilitation assessment in the future.

Remapping Movement of Shoulder With Soft Sensors: A Noninvasive Wearable Body–Machine Interface

Remapping Movement of Shoulder With Soft Sensors: A Noninvasive Wearable Body–Machine Interface

Learning to Control Complex Robots Using High-Dimensional Body-Machine Interfaces.

When individuals are paralyzed from injury or damage to the brain, upper body movement and function can be compromised. While the use of body motions to interface with machines has shown to be an effective noninvasive strategy to provide movement assistance and to promote physical rehabilitation, learning to use such interfaces to control complex machines is not well understood. In a five session study, we demonstrate that a subset of an uninjured population is able to learn and improve their ability to use a high-dimensional Body-Machine Interface (BoMI), to control a robotic arm. We use a sensor net of four inertial measurement units, placed bilaterally on the upper body, and a BoMI with the capacity to directly control a robot in six dimensions. We consider whether the way in which the robot control space is mapped from human inputs has any impact on learning. Our results suggest that the space of robot control does play a role in the evolution of human learning: specifically, though robot control in joint space appears to be more intuitive initially, control in task space is found to have a greater capacity for longer-term improvement and learning. Our results further suggest that there is an inverse relationship between control dimension couplings and task performance.

A novel virtual robotic platform for controlling six degrees of freedom assistive devices with body-machine interfaces

Body-machine interfaces (BoMIs)—systems that control assistive devices (e.g., a robotic manipulator) with a person’s movements—offer a robust and non-invasive alternative to brain-machine interfaces for individuals with neurological injuries. However, commercially-available assistive devices offer more degrees of freedom (DOFs) than can be efficiently controlled with a user’s residual motor function. Therefore, BoMIs often rely on nonintuitive mappings between body and device movements. Learning these mappings requires considerable practice time in a lab/clinic, which can be challenging. Virtual environments can potentially address this challenge, but there are limited options for high-DOF assistive devices, and it is unclear if learning with a virtual device is similar to learning with its physical counterpart. We developed a novel virtual robotic platform that replicated a commercially-available 6-DOF robotic manipulator. Participants controlled the physical and virtual robots using four wireless inertial measurement units (IMUs) fixed to the upper torso. Forty-three neurologically unimpaired adults practiced a target-matching task using either the physical (sample size n = 25) or virtual device (sample size n = 18) involving pre-, mid-, and post-tests separated by four training blocks. We found that both groups made similar improvements from pre-test in movement time at mid-test (Δvirtual: 9.9 ± 9.5 s; Δphysical: 11.1 ± 9.9 s) and post-test (Δvirtual: 11.1 ± 9.1 s; Δphysical: 11.8 ± 10.5 s) and in path length at mid-test (Δvirtual: 6.1 ± 6.3 m/m; Δphysical: 3.3 ± 3.5 m/m) and post-test (Δvirtual: 6.6 ± 6.2 m/m; Δphysical: 3.5 ± 4.0 m/m). Our results indicate the feasibility of using virtual environments for learning to control assistive devices. Future work should determine how these findings generalize to clinical populations.

A Non-Linear Body Machine Interface for Controlling Assistive Robotic Arms.

Body machine interfaces (BoMIs) enable individuals with paralysis to achieve a greater measure of independence in daily activities by assisting the control of devices such as robotic manipulators. The first BoMIs relied on Principal Component Analysis (PCA) to extract a lower dimensional control space from information in voluntary movement signals. Despite its widespread use, PCA might not be suited for controlling devices with a large number of degrees of freedom, as because of PCs' orthonormality the variance explained by successive components drops sharply after the first. Here, we propose an alternative BoMI based on non-linear autoencoder (AE) networks that mapped arm kinematic signals into joint angles of a 4D virtual robotic manipulator. First, we performed a validation procedure that aimed at selecting an AE structure that would allow to distribute the input variance uniformly across the dimensions of the control space. Then, we assessed the users' proficiency practicing a 3D reaching task by operating the robot with the validated AE. All participants managed to acquire an adequate level of skill when operating the 4D robot. Moreover, they retained the performance across two non-consecutive days of training. While providing users with a fully continuous control of the robot, the entirely unsupervised nature of our approach makes it ideal for applications in a clinical context since it can be tailored to each user's residual movements. We consider these findings as supporting a future implementation of our interface as an assistive tool for people with motor impairments.

NeuroSuitUp: System Architecture and Validation of a Motor Rehabilitation Wearable Robotics and Serious Game Platform

This article presents the system architecture and validation of the NeuroSuitUp body-machine interface (BMI). The platform consists of wearable robotics jacket and gloves in combination with a serious game application for self-paced neurorehabilitation in spinal cord injury and chronic stroke. The wearable robotics implement a sensor layer, to approximate kinematic chain segment orientation, and an actuation layer. Sensors consist of commercial magnetic, angular rate and gravity (MARG), surface electromyography (sEMG), and flex sensors, while actuation is achieved through electrical muscle stimulation (EMS) and pneumatic actuators. On-board electronics connect to a Robot Operating System environment-based parser/controller and to a Unity-based live avatar representation game. BMI subsystems validation was performed using exercises through a Stereoscopic camera Computer Vision approach for the jacket and through multiple grip activities for the glove. Ten healthy subjects participated in system validation trials, performing three arm and three hand exercises (each 10 motor task trials) and completing user experience questionnaires. Acceptable correlation was observed in 23/30 arm exercises performed with the jacket. No significant differences in glove sensor data during actuation state were observed. No difficulty to use, discomfort, or negative robotics perception were reported. Subsequent design improvements will implement additional absolute orientation sensors, MARG/EMG based biofeedback to the game, improved immersion through Augmented Reality and improvements towards system robustness.

Re-corporealising MRI Data

MRI is a non-invasive biomedical imaging technology that visualizes tissues within the body. Corporeal matter as perceived by MRI straddles definitions of substance, organism, subject, and object. MRI interacts with the body through nuclear magnetic resonance and creates biomedical images using electrodynamics, signal analysis, and mathematics. MRI brings us into contact with the body as a patient, a person, a biological environment, pathology, and as an assemblage of biochemical reactions charted by a medical geography. It reminds us that we contain autonomic organs, tissues, cells, molecules, and that we are atomic, and composed molecularly. In other words, the body acts beyond us. Here, I explore MRI through creative practice, using pan.able to create an embedded and relational assemblage of my practice, and how it interacts with MRI. My point of departure is to identify interfaces in MRI as “places”, sites or moments where separate entities become connected and where a change in force or informational transfer occurs. During an MRI scan, a powerful magnetic field moves across the body-machine interface, interacting with bodily matter on the subatomic level. The interactions of the scanner result in the protons within the subject emitting radio frequency pulses which are detected and transformed into a digital biomedical image using computational processes. Through a practice of “re-corporealisation”, the art practice described in this article explores corporeality and the philosophical concept of the abject as crucial to our subjectivity. This art project examines the MRI process as partly composed of the body-machine and analogue-digital interfaces resulting in artworks that interact with and emerge from MRI. I created sculptures called phantoms using tissue-mimicking materials (TMMs), named after scientific devices of the same name. Phantoms are used in biomedical imaging as stand-ins for human tissue, and used to calibrate, test, and verify scanning protocols. My sculptural phantoms are materials-led objects made to interact at the body-machine interface and be sensed by MRI. They are recognized and treated as semi-figurative body proxies and came to inform my understanding of my personal experience of cancer and medical treatment. I scanned my phantoms at the Francis Crick Institute, London and the Future Technology Centre, Portsmouth, where I was able to explore the potential of an art object as a scientific device and create further parity between them and my medical subjectivity. At the analogue-digital interface, I use weaving (also a body-machine interface) to explore how the signals from the body become biomedical images. I analyze and visually represent the different mathematical properties needed to make an MRI image: frequency, amplitude, phase, sequence, precession, signal-to-noise ratio, real and imaginary numbers. By translating these into images, weave drafts, and weaving them into textural patternings, I create re-corporealised, hand-woven deconstructed reconfigurations of the informational transfers that take place at the analogue-digital interface. The shared lineage of the computer and loom helps me to understand and enact how weaving and computational technologies operate. Part of the process or re-coporealisation was to make MRI processes knowable through my own body and my woven work. MRI makes us aware of different kinds of entanglements: MRI emerges with the body which charts both self and health. Electrons, textiles, signals, TMMs, and movements through the loom are entangled with the phenomenon of corporeal matter, my experience of cancer, and cancer treatment. These entanglements are visualized in my pan.able article through interacting layers, transparencies and opacities, overlapping photographic records of my work, photos of the lab, phantom-making, computer screens, stages of weaving, handwritten notes, sketches, and illustrations. Linking and relinking multiple concepts through patches of transparency helped me to convey how multi-scalar entities and systems in my research and practice are entangled, embodied, and embedded.

Neurorehabilitation Through Synergistic Man-Machine Interfaces Promoting Dormant Neuroplasticity in Spinal Cord Injury: Protocol for a Nonrandomized Controlled Trial.

BackgroundSpinal cord injury (SCI) constitutes a major sociomedical problem, impacting approximately 0.32-0.64 million people each year worldwide; particularly, it impacts young individuals, causing long-term, often irreversible disability. While effective rehabilitation of patients with SCI remains a significant challenge, novel neural engineering technologies have emerged to target and promote dormant neuroplasticity in the central nervous system.ObjectiveThis study aims to develop, pilot test, and optimize a platform based on multiple immersive man-machine interfaces offering rich feedback, including (1) visual motor imagery training under high-density electroencephalographic recording, (2) mountable robotic arms controlled with a wireless brain-computer interface (BCI), (3) a body-machine interface (BMI) consisting of wearable robotics jacket and gloves in combination with a serious game (SG) application, and (4) an augmented reality module. The platform will be used to validate a self-paced neurorehabilitation intervention and to study cortical activity in chronic complete and incomplete SCI at the cervical spine.MethodsA 3-phase pilot study (clinical trial) was designed to evaluate the NeuroSuitUp platform, including patients with chronic cervical SCI with complete and incomplete injury aged over 14 years and age-/sex-matched healthy participants. Outcome measures include BCI control and performance in the BMI-SG module, as well as improvement of functional independence, while also monitoring neuropsychological parameters such as kinesthetic imagery, motivation, self-esteem, depression and anxiety, mental effort, discomfort, and perception of robotics. Participant enrollment into the main clinical trial is estimated to begin in January 2023 and end by December 2023.ResultsA preliminary analysis of collected data during pilot testing of BMI-SG by healthy participants showed that the platform was easy to use, caused no discomfort, and the robotics were perceived positively by the participants. Analysis of results from the main clinical trial will begin as recruitment progresses and findings from the complete analysis of results are expected in early 2024.ConclusionsChronic SCI is characterized by irreversible disability impacting functional independence. NeuroSuitUp could provide a valuable complementary platform for training in immersive rehabilitation methods to promote dormant neural plasticity.Trial RegistrationClinicalTrials.gov NCT05465486; https://clinicaltrials.gov/ct2/show/NCT05465486International Registered Report Identifier (IRRID)PRR1-10.2196/41152

Fostering Social Interaction Through Sound Feedback: Sentire

Sentire is a body–machine interface that sonifies motor behaviour in real time and a participatory, interactive performance in which two people use their physical movements to collaboratively create sound while constantly being influenced by the results. Based on our informal observation that basal social behaviours emerge during Sentire performances, the present article investigates our principal hypothesis that Sentire can foster basic mechanisms underlying non-verbal social interaction. We illustrate how coordination serves as a crucial basic mechanism for social interaction, and consider how it is addressed by various therapeutic approaches, including therapeutic use of real-time auditory feedback. Then we argue that the implementation of Sentire may be fruitful in healthcare contexts and in promoting general well-being. We describe how the Sentire system has been developed further within the scope of the research project ‘Social interaction through sound feedback–Sentire’ that combines human–computer interaction, sound design and real-world research, against the background of the relationship between sound, sociality and therapy. The question concerning how interaction is facilitated through Sentire is addressed through the first results of behavioural analysis using structured observation, which allows for a quasi-quantitative sequential analysis of interactive behaviour.

Personalized Human-Swarm Interaction Through Hand Motion

The control of collective robotic systems, such as drone swarms, is often delegated to autonomous navigation algorithms due to their high dimensionality. However, like other robotic entities, drone swarms can still benefit from being teleoperated by human operators, whose perception and decision-making capabilities are still out of the reach of autonomous systems. Drone swarm teleoperation is only at its dawn, and a standard human-swarm interface (HSI) is missing to date. In this study, we analyzed the spontaneous interaction strategies of naive users with a swarm of drones. We implemented a machine-learning algorithm to define a personalized Body-Machine Interface (BoMI) based only on a short calibration procedure. During this procedure, the human operator is asked to move spontaneously as if they were in control of a simulated drone swarm. We assessed that hands are the most commonly adopted body segment, and thus we chose a LEAP Motion controller to track them to let the users control the aerial drone swarm. This choice makes our interface portable since it does not rely on a centralized system for tracking the human body. We validated our HSIs generation algorithm on a set of participants in a realistic simulated environment, showing a positive user feedback and performance comparable with a remote controller after training. Our method leaves the user free to choose between position and velocity control only based on their body motion preferences.

A Framework for Optimizing Co-adaptation in Body-Machine Interfaces.

The operation of a human-machine interface is increasingly often referred to as a two-learners problem, where both the human and the interface independently adapt their behavior based on shared information to improve joint performance over a specific task. Drawing inspiration from the field of body-machine interfaces, we take a different perspective and propose a framework for studying co-adaptation in scenarios where the evolution of the interface is dependent on the users' behavior and that do not require task goals to be explicitly defined. Our mathematical description of co-adaptation is built upon the assumption that the interface and the user agents co-adapt toward maximizing the interaction efficiency rather than optimizing task performance. This work describes a mathematical framework for body-machine interfaces where a naïve user interacts with an adaptive interface. The interface, modeled as a linear map from a space with high dimension (the user input) to a lower dimensional feedback, acts as an adaptive “tool” whose goal is to minimize transmission loss following an unsupervised learning procedure and has no knowledge of the task being performed by the user. The user is modeled as a non-stationary multivariate Gaussian generative process that produces a sequence of actions that is either statistically independent or correlated. Dependent data is used to model the output of an action selection module concerned with achieving some unknown goal dictated by the task. The framework assumes that in parallel to this explicit objective, the user is implicitly learning a suitable but not necessarily optimal way to interact with the interface. Implicit learning is modeled as use-dependent learning modulated by a reward-based mechanism acting on the generative distribution. Through simulation, the work quantifies how the system evolves as a function of the learning time scales when a user learns to operate a static vs. an adaptive interface. We show that this novel framework can be directly exploited to readily simulate a variety of interaction scenarios, to facilitate the exploration of the parameters that lead to optimal learning dynamics of the joint system, and to provide an empirical proof for the superiority of human-machine co-adaptation over user adaptation.

Recovery of Distal Arm Movements in Spinal Cord Injured Patients with a Body-Machine Interface: A Proof-of-Concept Study.

Background: The recovery of upper limb mobility and functions is essential for people with cervical spinal cord injuries (cSCI) to maximize independence in daily activities and ensure a successful return to normality. The rehabilitative path should include a thorough neuromotor evaluation and personalized treatments aimed at recovering motor functions. Body-machine interfaces (BoMI) have been proven to be capable of harnessing residual joint motions to control objects like computer cursors and virtual or physical wheelchairs and to promote motor recovery. However, their therapeutic application has still been limited to shoulder movements. Here, we expanded the use of BoMI to promote the whole arm’s mobility, with a special focus on elbow movements. We also developed an instrumented evaluation test and a set of kinematic indicators for assessing residual abilities and recovery. Methods: Five inpatient cSCI subjects (four acute, one chronic) participated in a BoMI treatment complementary to their standard rehabilitative routine. The subjects wore a BoMI with sensors placed on both proximal and distal arm districts and practiced for 5 weeks. The BoMI was programmed to promote symmetry between right and left arms use and the forearms’ mobility while playing games. To evaluate the effectiveness of the treatment, the subjects’ kinematics were recorded while performing an evaluation test that involved functional bilateral arms movements, before, at the end, and three months after training. Results: At the end of the training, all subjects learned to efficiently use the interface despite being compelled by it to engage their most impaired movements. The subjects completed the training with bilateral symmetry in body recruitment, already present at the end of the familiarization, and they increased the forearm activity. The instrumental evaluation confirmed this. The elbow motion’s angular amplitude improved for all subjects, and other kinematic parameters showed a trend towards the normality range. Conclusion: The outcomes are preliminary evidence supporting the efficacy of the proposed BoMI as a rehabilitation tool to be considered for clinical practice. It also suggests an instrumental evaluation protocol and a set of indicators to assess and evaluate motor impairment and recovery in cSCI.

Building an adaptive interface via unsupervised tracking of latent manifolds

In human–machine interfaces, decoder calibration is critical to enable an effective and seamless interaction with the machine. However, recalibration is often necessary as the decoder off-line predictive power does not generally imply ease-of-use, due to closed loop dynamics and user adaptation that cannot be accounted for during the calibration procedure. Here, we propose an adaptive interface that makes use of a non-linear autoencoder trained iteratively to perform online manifold identification and tracking, with the dual goal of reducing the need for interface recalibration and enhancing human–machine joint performance. Importantly, the proposed approach avoids interrupting the operation of the device and it neither relies on information about the state of the task, nor on the existence of a stable neural or movement manifold, allowing it to be applied in the earliest stages of interface operation, when the formation of new neural strategies is still on-going.In order to more directly test the performance of our algorithm, we defined the autoencoder latent space as the control space of a body–machine interface. After an initial offline parameter tuning, we evaluated the performance of the adaptive interface versus that of a static decoder in approximating the evolving low-dimensional manifold of users simultaneously learning to perform reaching movements within the latent space. Results show that the adaptive approach increased the representational efficiency of the interface decoder. Concurrently, it significantly improved users’ task-related performance, indicating that the development of a more accurate internal model is encouraged by the online co-adaptation process.

Analyzing Dilemmas Posed by Artificial Intelligence and 4IR Technologies Requires using all Available Models, Including the Existing International Human Rights Framework and Principles of AI Ethics

We are living in the epoch referred to as the ‘4th industrial revolution'. The 4th industrial Revolution (4IR) is a development characterized by a fusion of technologies that blur the digital, physical, and biological spheres (e.g., cyberspace, virtual and augmented reality, body-machine interface and robotics). Certain is the guaranteed ubiquitous adoption of these technologies, and futurism. Where the former is a reference to the increasing use and normalization of such technologies in everyday life, government service provision and industry. The latter is a reference to the philosophical/science fiction discussions that are emerging as a result of these changes (e.g. debates around the ‘singularity’, transhumanism, and posthumanism – often presented in utopian/dystopia terms). As such, the definition of digital ethics can be expanded and expressed in terms of the impacts of new digital technologies, through analysis of potential opportunities and risks in contemporary and future contexts. Many are working on forward‑looking policy frameworks and governance protocols, with broad multistakeholder engagement and buy‑in, to accelerate the adoption of emerging technologies in the global public interest, such as artificial intelligence (AI) and machine learning (ML) blockchain, 5G, data analytics, quantum computing, autonomous vehicles, synthetic biology, the internet of things (IoT), and killer robots or autonomous weapons systems (AWS). We have gained insight into the unequal distribution of the positive and negative impacts of AI on human rights throughout society, and have begun to explore the power of the human rights framework to address these disparate impacts. Although internationally recognized laws and standards on human rights provide a common standard of achievement for all people in all countries, more work is needed to understand how they can be best applied in the context of disruptive technology. AI systems raise myriad questions for society and democracy, only some of which are covered or addressed by existing laws. In order to fill these perceived gaps, a vocal group of governments, industry players, academics, and civil society actors have been promoting principles or frameworks for ethical AI. COVID-19 accelerated the use of AI in all countries and all fields. The pandemic accelerated the transition to a society that is increasingly based on the use of AI. This also increased the threats new risks related to human rights in the context of AI deployment. The human rights implications of governments' aggressive measures targeting the spread of COVID-19-related misinforation is also discussed. The question of whether corporations can act ethically is particularly relevant for Big Tech. Many of these firms are oligopolies that individuals and governments alike depend on completely, though they have little to no capacity to independently remedy issues when they arise, as Project Maven showed. Artificial intelligence and automated decision-making tools are increasing in power and centrality, and technology companies retain large troves of private data that it sells. These companies are at the forefront of technological innovation and may be caught up with the factual question of what can be done rather than the normative question of whether it should be done. All these issues arise in a field where there is little to no government regulation or intervention. The threats AI poses to society are so new, that the legal system is struggling to impose sufficient values and restrictions. Thus, a coherent approach to addressing AI ethics, values and consequences is, indeed, urgently needed. In May 2019, 42 countries adopted the Organization for Economic Co-operation and Development (OECD) AI Principles, a legal recommendation that includes five principles and five recommendations related to the use of AI. To ensure the successful implementation of the Principles, the OECD launched the AI Policy Observatory in February 2020. The Observatory publishes practical guidance about how to implement the AI Principles, and supports a live database of AI policies and initiatives globally. It also compiles metrics and measurement of global AI development and uses its convening power to bring together the private sector, governments, academia, and civil society. The AI ethics and governance initiatives discussed are cause for optimism that the global community will use all available models and brainpower for analysis and ultimately global governance of AI.

A hybrid Body-Machine Interface integrating signals from muscles and motions

Objective. Body-Machine Interfaces (BoMIs) establish a way to operate a variety of devices, allowing their users to extend the limits of their motor abilities by exploiting the redundancy of muscles and motions that remain available after spinal cord injury or stroke. Here, we considered the integration of two types of signals, motion signals derived from inertial measurement units (IMUs) and muscle activities recorded with electromyography (EMG), both contributing to the operation of the BoMI. Approach. A direct combination of IMU and EMG signals might result in inefficient control due to the differences in their nature. Accordingly, we used a nonlinear-regression-based approach to predict IMU from EMG signals, after which the predicted and actual IMU signals were combined into a hybrid control signal. The goal of this approach was to provide users with the possibility to switch seamlessly between movement and EMG control, using the BoMI as a tool for promoting the engagement of selected muscles. We tested the interface in three control modalities, EMG-only, IMU-only and hybrid, in a cohort of 15 unimpaired participants. Participants practiced reaching movements by guiding a computer cursor over a set of targets. Main results. We found that the proposed hybrid control led to comparable performance to IMU-based control and significantly outperformed the EMG-only control. Results also indicated that hybrid cursor control was predominantly influenced by EMG signals. Significance. We concluded that combining EMG with IMU signals could be an efficient way to target muscle activations while overcoming the limitations of an EMG-only control.

Personalized Telerobotics by Fast Machine Learning of Body-Machine Interfaces

Human-Robot Interfaces (HRIs) can be hard to master for inexperienced users, making the teleoperation of mobile robots a difficult task. The development of Body-Machine Interfaces (BoMIs) represents a promising approach to making a user more proficient, by exploiting the natural control they can exert on their own body motion. Since human motion presents individual traits due to several factors, including physical condition, age, and experience, generic BoMIs still require a significant learning time and effort to reach adequate ability in teleoperation. In this work, we present a novel approach which provides a Body-Machine Interface tailored on the specific user. Our method autonomously learns from the user their preferred strategy to control the robot, and provide a personalized body-machine mapping. We show that the proposed method can significantly reduce the duration of the training phase in teleoperation, thus allowing faster skill acquisition. We validated our approach by performing both simulation and real-world experiments with human subjects. The first involved the teleoperation of a fixed-wing simulated drone, while the second consisted in controlling a real quadrotor. We used our framework to extrapolate common and peculiar features of movements among individuals. Observing reoccurring strategies, we provide insights on how humans would naturally interface with a distal machine.

Vibration Propagation on the Skin of the Arm.

Vibrotactile interfaces are an inexpensive and non-invasive way to provide performance feedback to body-machine interface users. Interfaces for the upper extremity have utilized a multi-channel approach using an array of vibration motors placed on the upper extremity. However, for successful perception of multi-channel vibrotactile feedback on the arm, we need to account for vibration propagation across the skin. If two stimuli are delivered within a small distance, mechanical propagation of vibration can lead to inaccurate perception of the distinct vibrotactile stimuli. This study sought to characterize vibration propagation across the hairy skin of the forearm. We characterized vibration propagation by measuring accelerations at various distances from a source vibration of variable intensities (100–240 Hz). Our results showed that acceleration from the source vibration was present at a distance of 4 cm at intensities >150 Hz. At distances greater than 8 cm from the source, accelerations were reduced to values substantially below vibrotactile discrimination thresholds for all vibration intensities. We conclude that in future applications of vibrotactile interfaces, stimulation sites should be separated by a distance of at least 8 cm to avoid potential interference in vibration perception caused by propagating vibrations.

Age-related deficits in motor learning are associated with altered motor exploration strategies

How is motor learning affected by aging? Although several experimental paradigms have been used to address this question, there has been limited focus on the early phase of motor learning, which involves motor exploration and the need to coordinate multiple degrees of freedom in the body. Here, we examined motor learning in a body-machine interface where we measured both age-related differences in task performance as well as the coordination strategies underlying this performance. Participants (N = 65; age range 18–72 years) wore wireless inertial measurement units on the upper body, and learned to control a cursor on a screen, which was controlled by motions of the trunk. Results showed that, consistent with prior studies, there was an age-related effect on movement time, with middle-aged and older adults taking longer to perform the task than young adults. However, we also found that these changes were associated with limited exploration in older adults. Moreover, when considering data across a majority of the lifespan (including children), longer movement times were associated with greater inefficiency of the coordination pattern, producing more task-irrelevant motion. These results suggest exploration behaviors during motor learning are affected with aging, and highlight the need for different practice strategies with aging.

Deep Learning in the Biomedical Applications: Recent and Future Status

Deep neural networks represent, nowadays, the most effective machine learning technology in biomedical domain. In this domain, the different areas of interest concern the Omics (study of the genome—genomics—and proteins—transcriptomics, proteomics, and metabolomics), bioimaging (study of biological cell and tissue), medical imaging (study of the human organs by creating visual representations), BBMI (study of the brain and body machine interface) and public and medical health management (PmHM). This paper reviews the major deep learning concepts pertinent to such biomedical applications. Concise overviews are provided for the Omics and the BBMI. We end our analysis with a critical discussion, interpretation and relevant open challenges.

Age-dependent differences in learning to control a robot arm using a body-machine interface

Body-machine interfaces, i.e. interfaces that rely on body movements to control external assistive devices, have been proposed as a safe and robust means of achieving movement and mobility; however, how children learn these novel interfaces is poorly understood. Here we characterized the learning of a body-machine interface in young unimpaired adults, two groups of typically developing children (9-year and 12-year olds), and one child with congenital limb deficiency. Participants had to control the end-effector of a robot arm in 2D using movements of the shoulder and torso. Results showed a striking effect of age - children had much greater difficulty in learning the task compared to adults, with a majority of the 9-year old group unable to even complete the task. The 12-year olds also showed poorer task performance compared to adults (as measured by longer movement times and greater path lengths), which were associated with less effective search strategies. The child with congenital limb deficiency showed superior task performance compared to age-matched children, but had qualitatively distinct coordination strategies from the adults. Taken together, these results imply that children have difficulty learning non-intuitive interfaces and that the design of body-machine interfaces should account for these differences in pediatric populations.