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 $$97.3 \pm 0.3\%$$ 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 $$92.8 \pm 0.8\%$$ . 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 $$93.3 \pm 0.9\%$$ on the sequential set and $$88.5 \pm 0.9\%$$ on the mixed set. Furthermore, we estimated continuous joint angles from the EMG sleeve data, achieving a $$R^2$$ of $$0.884 \pm 0.003$$ in the sequential set and $$0.750 \pm 0.008$$ in the mixed set. Median absolute error (MAE) was kept below 10° across all joints, with a grand average MAE of $$1.8 \pm 0.04^\circ$$ and $$3.4 \pm 0.07^\circ$$ 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.
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.
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.
Prosthetics and orthotics have been recognized for decades as a potential means to restore hand function and independence to individuals living with impairment due to stroke. However, 75% of stroke survivors, caregivers, and health care professionals (HCP) believe current 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 limb technologies is to infer movement intent non-invasively from surface electromyography (EMG) activity. While this approach has garnered significant attention in the literature, existing technologies are often limited to research settings and struggle to meet stated user needs. To address these limitations, we have developed the NeuroLife ® EMG System, 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, including multiple types of grasps from participants with varying levels of chronic impairment from stroke, with an overall accuracy of 77.1±5.6%. Importantly, we demonstrate the ability to decode a subset of 3 fundamental movements in individuals with severe hand impairment at 85.4±6.4% accuracy, 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. Taken together, the NeuroLife EMG System represents a platform technology to record and decode high-definition EMG for the eventual real-time control of assistive devices in a form factor designed to meet user needs.
8 January 2026 in Journal of NeuroEngineering and Rehabilitation
Stroke is a leading cause of disability, with up to 80% of survivors experiencing motor impairments. These impairments are attributed to various factors, i
Background Functional electrical stimulation (FES) has been recognized for decades as a method to retrain the motor system after stroke. Benefits of FES rehabilitation can be enhanced by combining task-oriented therapy, dubbed FES therapy (FEST). Furthermore, by synchronizing FES with the user’s volitional motor intention and incorporating multiple trained tasks FES can be better integrated into common task-oriented rehabilitation practice. Using wearable FES technology, we tested therapy incorporating these elements in two chronic stroke survivors. Methods Our group has developed the NeuroLife® Sleeve, a wearable forearm sleeve that contains a high-density grid of embedded FES electrodes, that may be controlled by an operator or by the wearer’s own electromyographic (EMG) signals. During eight weeks of FEST, intention-driven FES enabling multiple movements was delivered via operator control twice weekly and EMG control once weekly. Results At the end of the therapy period, subjects A and B had both improved their scores: Box and Blocks Test (A: +5, B: +7), the Action Arm Research Test (A: +7, B: +12), the Fugl Meyer Upper Extremity section (A: +11, B: +9), and the 9-Hole Peg Test (A: 158 sec, B: 54 sec, both previously unable). All score improvements persisted over the 10-week follow-up period despite greatly reduced (>80%) effective dose of FES. Conclusions This case series provides additional evidence that intention-driven FEST drives long-lasting motor recovery in chronic stroke survivors. The NeuroLife Sleeve enabled this therapy through the easily donned wearable sleeve interface, control schemes for pairing FES with motor intention, and efficient transitions between tasks with programmable FES placement and parameters.