Stroke is a leading cause of disability, with up to 80 R^2=0.81 ) with clinical motor function scores. This study demonstrates that HD-EMG can capture detailed motor unit activity and neural control characteristics across multiple forearm muscles in individuals with chronic stroke. By integrating multiple HD-EMG features, this approach provides new insights into neuromuscular alterations linked to hand motor function after stroke. These findings support the use of HD-EMG for monitoring recovery, predicting outcomes, and guiding more targeted rehabilitation, thus advancing both stroke research and patient care.

Extracting neural signals at the single motor neuron level provides an optimal control signal for neuroprosthetic applications. However, current algorithms to decompose motor units from high-density electromyography (HD-EMG) are time-consuming and inconsistent, limiting their application to controlled scenarios in a research setting. We introduce MUelim, an algorithm for efficient motor unit decomposition that uses approximate joint diagonalization with a subtractive approach to rapidly identify and refine candidate sources. The algorithm incorporates an extend-lag procedure to augment data for enhanced source separability prior to diagonalization. By systematically iterating and eliminating redundant or noisy sources, MUelim achieves high decomposition accuracy while significantly reducing computational complexity, making it well-suited for real-time applications. We validate MUelim by demonstrating its ability to extract motor units in both simulated and physiological HD-EMG grid data. Across six healthy participants performing ramp and maximum voluntary contraction paradigms, MUelim achieves up to a 36$\times$ speed increase compared to existing state-of-the-art methods while decomposing a similar number of high signal-to-noise sources. Furthermore, we showcase a real-world application of MUelim in a clinical setting in which an individual with spinal cord injury controlled an EMG-driven neuroprosthetic to perform functional tasks. We demonstrate the ability to decode motor intent in real-time using a spiking neural network trained on the decomposed motor unit spike trains to trigger functional electrical stimulation patterns that evoke hand movements during task practice therapy. We show that motor unit-based decoding enables nuanced motor control, highlighting the potential of MUelim to advance assistive neurotechnology and rehabilitation through precise, intention-driven neuroprosthetic systems.

Objectives To investigate whether hand motor coordination of stroke survivors can be explained through a combination of features extracted from a high-density electromyography (HD-EMG) sleeve. Design Standardized clinical assessments were evaluated in participants with stroke and scored by a licensed occupational therapist. Assessments included the upper extremity section of the Fugl-Meyer and the Modified Ashworth Scale test to assess finger and wrist spasticity. After clinical assessments, subjects performed 12 functional hand and wrist movements while HD-EMG was recorded using a wearable sleeve. Movements were visually evaluated based on an observed movement score (0=no movement, 1=visible movement, 2=incomplete movement, and 3=normal movement). After data collection, a variety of HD-EMG features, or views, were calculated from EMG, namely cocontraction, muscle correlation, muscle synergies, and motor unit firing coherence. Setting This study was performed at Battelle Memorial Institute. Participants This study enrolled able-bodied adults (n=7) and chronic stroke subjects with upper limb hemiparesis (n=7). Participants with stroke had hand impairment that interferes with their ability to perform activities of daily living and were classified as stage 1-6 on the hand subscale of the Chedoke McMaster Stroke assessment. Interventions Not applicable. Main Outcome Measures Main outcome measures include the correlation of HD-EMG features, or a combination of features, with the upper extremity section of the Fugl-Meyer and Modified Ashworth Scale scores. Results Stroke subjects had higher cocontraction and reduced muscle coupling when attempting to open their hand and actuate their thumb. Muscle synergies decomposed in the stroke population were relatively preserved. Alterations in synergy composition demonstrated reduced coupling between digit extensors and muscles that actuate the thumb, as well as an increase in flexor activity in the stroke group. Average synergy activations during movements revealed differences in coordination, highlighting overactivation of antagonist muscles and compensatory strategies. Motor units decomposed in the stroke population had a lower firing coherence across movements, demonstrating reduced neural drive to muscles. When combining features using canonical correlation analysis, the first latent component was correlated with upper extremity section of the Fugl-Meyer hand subscore (R2=0.85). Latent component weightings revealed interpretable measures of motor coordination and muscle coupling alterations. Conclusions These results demonstrate the feasibility of predicting motor function through features decomposed from a wearable HD-EMG sleeve, which could be leveraged to improve stroke research and clinical care. Disclaimer: This device has not been approved or cleared as safe or effective by US Food and Drug Administration. This device is limited by US federal law to investigational use. Disclosures All authors are employees of Battelle Memorial Institute, which has developed the NeuroLife Sleeve.

Objectives To investigate the feasibility of using a wearable, high-density electrode sleeve to provide intention-driven functional electrical stimulation (FES) therapy, and to evaluate the preliminary effects on recovery in 2 adult chronic stroke survivors. Design During the 8-week intervention period, therapy was administered using the intention-driven FES sleeve during three 2-hour sessions. After the 8-week intervention period, subjects were monitored in a 10-week follow-up period during which task-oriented training was not administered. However, FES was delivered during this period to enable continued engineering development of the sleeve. Setting This study was performed at Battelle Memorial Institute.. Participants This study enrolled adults with upper limb hemiparesis, stroke-related hand impairment that interferes with the ability to complete activities of daily life, and who were classified as stage 1-6 on the hand subscale of the Chedoke McMaster Stroke assessment. Individuals actively participating in stroke-related upper limb rehabilitation, co-occurring neurological or neuromuscular conditions, or implanted electronic devices were excluded. Interventions The intervention was comprised of using an investigational device composed of a high-density grid of electrodes embedded in a sleeve to deliver FES during therapist (occupational therapist)-guided therapy. FES was delivered either (1) by an operator that matched FES to the subject's intention, or (2) by the wearer's own electromyographic signals. The operator-controlled FES system was used twice per week, and the electromyographic-controlled FES system used once per week. At each session, the occupational therapist chose functional tasks, graded them to an appropriate difficulty, and administered practice for approximately 20 minutes before moving on to a new task. Main Outcome Measures Main outcome measures include the Action Research Arm Test, the Fugl-Meyer Assessment Upper Extremity, and the Box and Blocks test. Results At the conclusion of the 8-week therapy schedule, both subjects demonstrated improvements that exceeded the minimal clinically important difference on the Action Research Arm Test, Fugl-Meyer Assessment Upper Extremity, and the Box and Blocks test. These improvements were sustained during the 10-week follow-up period. Conclusions These results provide an initial, preliminary demonstration in 2 stroke survivors of using intention-driven FES therapy incorporating multiple FES-enabled movements using a wearable forearm sleeve. Larger studies are needed to validate these findings. This device has not been approved or cleared as safe or effective by US Food and Drug Administration. This device is limited by US federal law to investigational use. Disclosures All authors are employees of Battelle Memorial Institute, which has developed the described NeuroLife Sleeve.

Objective. Non-invasive, high-density electromyography (HD-EMG) has emerged as a useful tool to collect a range of neurophysiological motor information. Recent studies have demonstrated changes in EMG features that occur after stroke, which correlate with functional ability, highlighting their potential use as biomarkers. However, previous studies have largely explored these EMG features in isolation with individual electrodes to assess gross movements, limiting their potential clinical utility. This study aims to predict hand function of stroke survivors by combining interpretable features extracted from a wearable HD-EMG forearm sleeve. Approach. Here, able-bodied (N = 7) and chronic stroke subjects (N = 7) performed 12 functional hand and wrist movements while HD-EMG was recorded using a wearable sleeve. A variety of HD-EMG features, or views, were decomposed to assess alterations in motor coordination. Main Results. Stroke subjects, on average, had higher co-contraction and reduced muscle coupling when attempting to open their hand and actuate their thumb. Additionally, muscle synergies decomposed in the stroke population were relatively preserved, with a large spatial overlap in composition of matched synergies. Alterations in synergy composition demonstrated reduced coupling between digit extensors and muscles that actuate the thumb, as well as an increase in flexor activity in the stroke group. Average synergy activations during movements revealed differences in coordination, highlighting overactivation of antagonist muscles and compensatory strategies. When combining co-contraction and muscle synergy features, the first principal component was strongly correlated with upper-extremity Fugl Meyer hand sub-score of stroke participants (R2 = 0.86). Principal component embeddings of individual features revealed interpretable measures of motor coordination and muscle coupling alterations. Significance. These results demonstrate the feasibility of predicting motor function through features decomposed from a wearable HD-EMG sleeve, which could be leveraged to improve stroke research and clinical care.

Abstract Objective Seventy-five percent of stroke survivors, caregivers, and health care professionals (HCP) believe current therapy practices are insufficient, specifically calling out the upper extremity as an area where innovation is needed to develop highly usable prosthetics/orthotics for the stroke population. A promising method for controlling upper extremity technologies is to infer movement intention non-invasively from surface electromyography (EMG). However, existing technologies are often limited to research settings and struggle to meet user needs. Approach To address these limitations, we have developed the NeuroLife® EMG System, an investigational device which consists of a wearable forearm sleeve with 150 embedded electrodes and associated hardware and software to record and decode surface EMG. Here, we demonstrate accurate decoding of 12 functional hand, wrist, and forearm movements in chronic stroke survivors, including multiple types of grasps from participants with varying levels of impairment. We also collected usability data to assess how the system meets user needs to inform future design considerations. Main results Our decoding algorithm trained on historical- and within-session data produced an overall accuracy of 77.1 ± 5.6% across 12 movements and rest in stroke participants. For individuals with severe hand impairment, we demonstrate the ability to decode a subset of two fundamental movements and rest at 85.4 ± 6.4% accuracy. In online scenarios, two stroke survivors achieved 91.34 ± 1.53% across three movements and rest, highlighting the potential as a control mechanism for assistive technologies. Feedback from stroke survivors who tested the system indicates that the sleeve’s design meets various user needs, including being comfortable, portable, and lightweight. The sleeve is in a form factor such that it can be used at home without an expert technician and can be worn for multiple hours without discomfort. Significance The NeuroLife EMG System represents a platform technology to record and decode high-resolution EMG for the real-time control of assistive devices in a form factor designed to meet user needs. The NeuroLife EMG System is currently limited by U.S. federal law to investigational use.

High-density electromyography (HD-EMG) can provide a natural interface to enhance human-computer interaction (HCI). This study aims to demonstrate the capability of a novel HD-EMG forearm sleeve equipped with up to 150 electrodes to capture high-resolution muscle activity, decode complex hand gestures, and estimate continuous hand position via joint angle predictions. Ten able-bodied participants performed 37 hand movements and grasps while EMG was recorded using the HD-EMG sleeve. Simultaneously, an 18-sensor motion capture glove calculated 23 joint angles from the hand and fingers across all movements for training regression models. For classifying across the 37 gestures, our decoding algorithm was able to differentiate between sequential movements with 97.3 +/- 0.3%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$97.3 \pm 0.3\%$$\end{document} accuracy calculated on a 100 ms bin-by-bin basis. In a separate mixed dataset consisting of 19 movements randomly interspersed, decoding performance achieved an average bin-wise accuracy of 92.8 +/- 0.8%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$92.8 \pm 0.8\%$$\end{document}. When evaluating decoders for use in real-time scenarios, we found that decoders can reliably decode both movements and movement transitions, achieving an average accuracy of 93.3 +/- 0.9%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$93.3 \pm 0.9\%$$\end{document} on the sequential set and 88.5 +/- 0.9%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$88.5 \pm 0.9\%$$\end{document} on the mixed set. Furthermore, we estimated continuous joint angles from the EMG sleeve data, achieving a R2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$R<^>2$$\end{document} of 0.884 +/- 0.003\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$0.884 \pm 0.003$$\end{document} in the sequential set and 0.750 +/- 0.008\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$0.750 \pm 0.008$$\end{document} in the mixed set. Median absolute error (MAE) was kept below 10 degrees across all joints, with a grand average MAE of 1.8 +/- 0.04 degrees\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$1.8 \pm 0. 04<^>\circ$$\end{document} and 3.4 +/- 0.07 degrees\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$3.4 \pm 0.07<^>\circ$$\end{document} for the sequential and mixed datasets, respectively. We also assessed two algorithm modifications to address specific challenges for EMG-driven HCI applications. To minimize decoder latency, we used a method that accounts for reaction time by dynamically shifting cue labels in time. To reduce training requirements, we show that pretraining models with historical data provided an increase in decoding performance compared with models that were not pretrained when reducing the in-session training data to only one attempt of each movement. The HD-EMG sleeve, combined with sophisticated machine learning algorithms, can be a powerful tool for hand gesture recognition and joint angle estimation. This technology holds significant promise for applications in HCI, such as prosthetics, assistive technology, rehabilitation, and human-robot collaboration.

Wearable robots typically signify a specific solution for a specific problem or task rather than a generalized solution adaptable to different purposes, such as preventive care, health monitoring, assisting, and augmentation. We have been developing a new concept of wearable robots to assist humans in a spectrum of applications varying from highly constrained medical setups to home use. We used textile materials to build the exoskeletons, which makes them more suitable for long-wearing duration, lightweight, and cost-effective. Different control strategies were deployed to measure the wearer's in-tention and operate the exoskeleton accordingly. Furthermore, our neuro-cognitive user study shows that the exoskeleton aligns with human expectations as a sign of embodiment, Elec- troencephalography data shows that an error-related potential appears after unexpected actions of the exoskeleton; these were decodable with an average accuracy of 76.63 ± 1.73%.

Human-robot interaction (HRI) describes scenarios in which both human and robot work as partners, sharing the same environment or complementing each other on a joint task. HRI is characterized by the need for high adaptability and flexibility of robotic systems toward their human interaction partners. One of the major challenges in HRI is task planning with dynamic subtask assignment, which is particularly challenging when subtask choices of the human are not readily accessible by the robot. In the present work, we explore the feasibility of using electroencephalogram (EEG) based neuro-cognitive measures for online robot learning of dynamic subtask assignment. To this end, we demonstrate in an experimental human subject study, featuring a joint HRI task with a UR10 robotic manipulator, the presence of EEG measures indicative of a human partner anticipating a takeover situation from human to robot or vice-versa. The present work further proposes a reinforcement learning based algorithm employing these measures as a neuronal feedback signal from the human to the robot for dynamic learning of subtask-assignment. The efficacy of this algorithm is validated in a simulation-based study. The simulation results reveal that even with relatively low decoding accuracies, successful robot learning of subtask-assignment is feasible, with around 80% choice accuracy among four subtasks within 17 minutes of collaboration. The simulation results further reveal that scalability to more subtasks is feasible and mainly accompanied with longer robot learning times. These findings demonstrate the usability of EEG-based neuro-cognitive measures to mediate the complex and largely unsolved problem of human-robot collaborative task planning.

Incorporating soft materials into active exosuits has shown promise to provide assistance in a comfortable usercentric interface for the wearer. In order for individuals to be able to seamlessly operate an exosuit, user intention must be decoded so that the exosuit can move according to user expectations. Existing exosuit control methods aim to reduce an interaction torque between the wearer and exosuit inferred from the decoded intent from a high-level control scheme. Due to the non-linearity response of the soft materials, however, sophisticated methods of optimal control from robotics have not been used to minimize this interaction torque. A model predictive controller (MPC) may be able to predict future interaction conflicts between the wearer and exosuit assistance in order to preemptively reduce this interaction torque to provide assistance in line with intentions. Here, we experimentally approximate a model for our soft pneumatic elbow exosuit and demonstrate the feasibility of using a low-level MPC to reduce interaction torque determined from a gravity compensation high-level control approach. We demonstrate that in a step flexion response of the system, the MPC reduces oscillations around the target exosuit torque compared to on/off and PID controllers. These results demonstrate that using a model-based predictive approach reduces the interaction between the wearer and exosuit for a more naturalistic interface.

Background Existing assistive technologies attempt to mimic biological functions through advanced mechatronic designs. In some occasions, the information processing demands for such systems require substantial information bandwidth and convoluted control strategies, which make it difficult for the end-user to operate. Instead, a practical and intuitive semi-automated system focused on accomplishing daily tasks may be more suitable for end-user adoption. Methods We developed an intelligent prosthesis for the Cybathlon Global Edition 2020. The device was designed in collaboration with the prosthesis user (pilot), addressing her needs for the competition and aiming for functionality. Our design consists of a soft robotic-based two finger gripper controlled by a force-sensing resistor (FSR) headband interface, automatic arm angle dependent wrist flexion and extension, and manual forearm supination and pronation for a shared control system. The gripper is incorporated with FSR sensors to relay haptic information to the pilot based on the output of a neural network model that estimates geometries and objects material. Results As a student team of the Munich Institute of Robotics and Machine Intelligence, we achieved 12th place overall in the Cybathlon competition in which we competed against state-of-the-art prosthetic devices. Our pilot successfully accomplished two challenging tasks in the competition. During training sessions, the pilot was able to accomplish the remaining competition tasks except for one. Based on observation and feedback from training sessions, we adapted our developments to fit the user’s preferences. Usability ratings indicated that the pilot perceived the prosthesis to not be fully ergonomic due to the size and weight of the system, but argued that the prosthesis was intuitive to control to perform the tasks from the Cybathlon competition. Conclusions The system provides an intuitive interface to conduct common daily tasks from the arm discipline of the Cybathlon competition. Based on the feedback from our pilot, future improvements include the prosthesis’ reduction in size and weight in order to enhance its mobility. Close collaboration with our pilot has allowed us to continue with the prosthesis development. Ultimately, we developed a simple-to-use solution, exemplifying a new paradigm for prosthesis design, to help assist arm amputees with daily activities.

Soft exosuits offer promise to support users in everyday workload tasks by providing assistance. However, acceptance of such systems remains low due to the difficulty of control compared with rigid mechatronic systems. Recently, there has been progress in developing control schemes for soft exosuits that move in line with user intentions. While initial results have demonstrated sufficient device performance, the assessment of user experience via the cognitive response has yet to be evaluated. To address this, we propose a soft pneumatic elbow exosuit designed based on our previous work to provide assistance in line with user expectations utilizing two existing state-of-the-art control methods consisting of a gravity compensation and myoprocessor based on muscle activation. A user experience study was conducted to assess whether the device moves naturally with user expectations and the potential for device acceptance by determining when the exosuit violated user expectations through the neuro-cognitive and motor response. Brain activity from electroencephalography (EEG) data revealed that subjects elicited error-related potentials (ErrPs) in response to unexpected exosuit actions, which were decodable across both control schemes with an average accuracy of 76.63 ± 1.73% across subjects. Additionally, unexpected exosuit actions were further decoded via the motor response from electromyography (EMG) and kinematic data with a grand average accuracy of 68.73 ± 6.83% and 77.52 ± 3.79% respectively. This work demonstrates the validation of existing state-of-the-art control schemes for soft wearable exosuits through the proposed soft pneumatic elbow exosuit. We demonstrate the feasibility of assessing device performance with respect to the cognitive response through decoding when the device violates user expectations in order to help understand and promote device acceptance.

This paper describes the fabrication of a modular wireless IMU sensor network suit with a distributed vibrotactile motor for body postural measurements with feedback. Each sensor measures the absolute orientations then transmits them into one portable hub. The module can be connected with up to four vibration motors to provide feedback to the user. Each vibration motor is hosted by a block sliding through the elastic strap used for attaching the module. The vibration motors on the strap can be positioned to different sides of the body to indicate movement directions. The suit is used to train and evaluate various static and dynamic tasks. The distribution of vibrotactile feedback targets particular features of movement in real-time such as amplitude and velocity. Preliminary experiments show the ability to identify normal walking and limping based on metrics such as the trajectory of the center of mass, the energy of left and right legs, and the calf and thigh angles to the vertical. Online identification of gait is the primary key to trigger a wearable assistive device.