Experiment-free exoskeleton assistance via learning in simulation

Exoskeletons have enormous potential to improve human locomotive performance1-3. However, their development and broad dissemination are limited by the requirement for lengthy human tests and handcrafted control laws2. Here we show an experiment-free method to learn a versatile control policy in simulation. Our learning-in-simulation framework leverages dynamics-aware musculoskeletal and exoskeleton models and data-driven reinforcement learning to bridge the gap between simulation and reality without human experiments. The learned controller is deployed on a custom hip exoskeleton that automatically generates assistance across different activities with reduced metabolic rates by 24.3%, 13.1% and 15.4% for walking, running and stair climbing, respectively. Our framework may offer a generalizable and scalable strategy for the rapid development and widespread adoption of a variety of assistive robots for both able-bodied and mobility-impaired individuals.

Evaluation of controllers for augmentative hip exoskeletons and their effects on metabolic cost of walking: explicit versus implicit synchronization

Background: Efficient gait assistance by augmentative exoskeletons depends on reliable control strategies. While numerous control methods and their effects on the metabolic cost of walking have been explored in the literature, the use of different exoskeletons and dissimilar protocols limit direct comparisons. In this article, we present and compare two controllers for hip exoskeletons with different synchronization paradigms. Methods: The implicit-synchronization-based approach, termed the Simple Reflex Controller (SRC), determines the assistance as a function of the relative loading of the feet, resulting in an emerging torque profile continuously assisting extension during stance and flexion during swing. On the other hand, the Hip-Phase-based Torque profile controller (HPT) uses explicit synchronization and estimates the gait cycle percentage based on the hip angle, applying a predefined torque profile consisting of two shorter bursts of assistance during stance and swing. We tested the controllers with 23 naïve healthy participants walking on a treadmill at 4 km ⋅ h-1, without any substantial familiarization. Results: Both controllers significantly reduced the metabolic rate compared to walking with the exoskeleton in passive mode, by 18.0% (SRC, p < 0.001) and 11.6% (HPT, p < 0.001). However, only the SRC led to a significant reduction compared to walking without the exoskeleton (8.8%, p = 0.004). The SRC also provided more mechanical power and led to bigger changes in the hip joint kinematics and walking cadence. Our analysis of mechanical powers based on a whole-body analysis suggested a reduce in ankle push-off under this controller. There was a strong correlation (Pearson's r = 0.778, p < 0.001) between the metabolic savings achieved by each participant with the two controllers. Conclusion: The extended assistance duration provided by the implicitly synchronized SRC enabled greater metabolic reductions compared to the more targeted assistance of the explicitly synchronized HPT. Despite the different assistance profiles and metabolic outcomes, the correlation between the metabolic reductions with the two controllers suggests a difference in individual responsiveness to assistance, prompting more investigations to explore the person-specific factors affecting assistance receptivity.

NSF DARE-transforming modeling in neurorehabilitation: a patient-in-the-loop framework

In 2023, the National Science Foundation (NSF) and the National Institute of Health (NIH) brought together engineers, scientists, and clinicians by sponsoring a conference on computational modelling in neurorehabiilitation. To facilitate multidisciplinary collaborations and improve patient care, in this perspective piece we identify where and how computational modelling can support neurorehabilitation. To address the where, we developed a patient-in-the-loop framework that uses multiple and/or continual measurements to update diagnostic and treatment model parameters, treatment type, and treatment prescription, with the goal of maximizing clinically-relevant functional outcomes. This patient-in-the-loop framework has several key features: (i) it includes diagnostic and treatment models, (ii) it is clinically-grounded with the International Classification of Functioning, Disability and Health (ICF) and patient involvement, (iii) it uses multiple or continual data measurements over time, and (iv) it is applicable to a range of neurological and neurodevelopmental conditions. To address the how, we identify state-of-the-art and highlight promising avenues of future research across the realms of sensorimotor adaptation, neuroplasticity, musculoskeletal, and sensory & pain computational modelling. We also discuss both the importance of and how to perform model validation, as well as challenges to overcome when implementing computational models within a clinical setting. The patient-in-the-loop approach offers a unifying framework to guide multidisciplinary collaboration between computational and clinical stakeholders in the field of neurorehabilitation.

Electromyography-driven musculoskeletal models with time-varying fatigue dynamics improve lumbosacral joint moments during lifting

Muscle fatigue is prevalent across different aspects of daily life. Tracking muscle fatigue is useful to understand muscle overuse and possible risk of injury leading to musculoskeletal disorders. Current fatigue models are not suitable for real-world settings as they are either validated using simulations or non-functional tasks. Moreover, models that capture the changes to muscle activity due to fatigue either assume a linear relationship between muscle activity and muscle force or utilize a simple muscle model. Personalised electromygraphy (EMG)-driven musculoskeletal models (pEMS) offer person-specific approaches to model muscle and joint kinetics during a wide repertoire of daily life tasks. These models utilize EMG, thus capturing central fatigue-dependent changes in multi-muscle bio-electrical activity. However, the peripheral muscle force decay is missing in these models. Thus, we studied the influence of fatigue on a large scale pEMS of the trunk. Eleven healthy participants performed functional asymmetric lifting task. Average peak body-weight normalized lumbosacral moments (BW-LM) were estimated to be 2.55 ± 0.26 Nm/kg by reference inverse dynamics. After complete exhaustion of the lower back, the pEMS overestimated the peak BW-LM by 0.64 ± 0.37 Nm/kg. Then, we developed a time-varying muscle force decay model resulting in a time-varying pEMS (t-pEMS). This reduced the difference between BW-LM estimated by the t-pEMS and reference to 0.49 ± 0.14 Nm/kg. We also showed that five fatiguing contractions are sufficient to calibrate the t-pEMS. Thus, this study presents a person and muscle specific model to track fatigue during functional tasks.

Single-Channel sEMG-Based Estimation of Knee Joint Angle Using a Decomposition Algorithm With a State-Space Model

Accurate human motion estimation is crucial for effective and safe human-robot interaction when using robotic devices for rehabilitation or performance enhancement. Although surface electromyography (sEMG) signals have been widely used to estimate human movements, conventional sEMG-based methods, which need sEMG signals measured from multiple relevant muscles, are usually subject to some limitations, including interference between sEMG sensors and wearable robots/environment, complicated calibration, as well as discomfort during long-term routine use. Few methods have been proposed to deal with these limitations by using single-channel sEMG (i.e., reducing the sEMG sensors as much as possible). The main challenge for developing single-channel sEMG-based estimation methods is that high estimation accuracy is difficult to be guaranteed. To address this problem, we proposed an sEMG-driven state-space model combined with an sEMG decomposition algorithm to improve the accuracy of knee joint movement estimation based on single-channel sEMG signals measured from gastrocnemius. The effectiveness of the method was evaluated via both single- and multi-speed walking experiments with seven and four healthy subjects, respectively. The results showed that the normal root-mean-squared error of the estimated knee joint angle using the method could be limited to 15%. Moreover, this method is robust with respect to variations in walking speeds. The estimation performance of this method was basically comparable to that of state-of-the-art studies using multi-channel sEMG.

Tapping Into Skeletal Muscle Biomechanics for Design and Control of Lower Limb Exoskeletons: A Narrative Review

Lower limb exoskeletons and exosuits ("exos") are traditionally designed with a strong focus on mechatronics and actuation, whereas the "human side" is often disregarded or minimally modeled. Muscle biomechanics principles and skeletal muscle response to robot-delivered loads should be incorporated in design/control of exos. In this narrative review, we summarize the advances in literature with respect to the fusion of muscle biomechanics and lower limb exoskeletons. We report methods to measure muscle biomechanics directly and indirectly and summarize the studies that have incorporated muscle measures for improved design and control of intuitive lower limb exos. Finally, we delve into articles that have studied how the human-exo interaction influences muscle biomechanics during locomotion. To support neurorehabilitation and facilitate everyday use of wearable assistive technologies, we believe that future studies should investigate and predict how exoskeleton assistance strategies would structurally remodel skeletal muscle over time. Real-time mapping of the neuromechanical origin and generation of muscle force resulting in joint torques should be combined with musculoskeletal models to address time-varying parameters such as adaptation to exos and fatigue. Development of smarter predictive controllers that steer rather than assist biological components could result in a synchronized human-machine system that optimizes the biological and electromechanical performance of the combined system.

Consistent control information driven musculoskeletal model for multiday myoelectric control

Objective.Musculoskeletal model (MM)-based myoelectric interface has aroused great interest in human-machine interaction. However, the performance of electromyography (EMG)-driven MM in long-term use would be degraded owing to the inherent non-stationary characteristics of EMG signals. Here, to improve the estimation performance without retraining, we proposed a consistent muscle excitation extraction approach based on an improved non-negative matrix factorization (NMF) algorithm for MM when applied to simultaneous hand and wrist movement prediction.Approach.We added constraints andL2-norm regularization terms to the objective function of classic NMF regarding muscle weighting matrix and time-varying profiles, through which stable muscle synergies across days were identified. The resultant profiles of these synergies were then used to drive the MM. Both offline and online experiments were conducted to evaluate the performance of the proposed method in inter-day scenarios.Main results.The results demonstrated significantly better and more robust performance over several competitive methods in inter-day experiments, including machine learning methods, EMG envelope-driven MM, and classic NMF-based MM. Furthermore, the analysis of control information on different days revealed the effectiveness of the proposed method in obtaining consistent muscle excitations.Significance.The outcomes potentially provide a novel and promising pathway for the robust and zero-retraining control of myoelectric interfaces.

Effects of a soft robotic exosuit on the quality and speed of overground walking depends on walking ability after stroke

BACKGROUND

Soft robotic exosuits can provide partial dorsiflexor and plantarflexor support in parallel with paretic muscles to improve poststroke walking capacity. Previous results indicate that baseline walking ability may impact a user's ability to leverage the exosuit assistance, while the effects on continuous walking, walking stability, and muscle slacking have not been evaluated. Here we evaluated the effects of a portable ankle exosuit during continuous comfortable overground walking in 19 individuals with chronic hemiparesis. We also compared two speed-based subgroups (threshold: 0.93 m/s) to address poststroke heterogeneity.

METHODS

We refined a previously developed portable lightweight soft exosuit to support continuous overground walking. We compared five minutes of continuous walking in a laboratory with the exosuit to walking without the exosuit in terms of ground clearance, foot landing and propulsion, as well as the energy cost of transport, walking stability and plantarflexor muscle slacking.

RESULTS

Exosuit assistance was associated with improvements in the targeted gait impairments: 22% increase in ground clearance during swing, 5° increase in foot-to-floor angle at initial contact, and 22% increase in the center-of-mass propulsion during push-off. The improvements in propulsion and foot landing contributed to a 6.7% (0.04 m/s) increase in walking speed (R2 = 0.82). This enhancement in gait function was achieved without deterioration in muscle effort, stability or cost of transport. Subgroup analyses revealed that all individuals profited from ground clearance support, but slower individuals leveraged plantarflexor assistance to improve propulsion by 35% to walk 13% faster, while faster individuals did not change either.

CONCLUSIONS

The immediate restorative benefits of the exosuit presented here underline its promise for rehabilitative gait training in poststroke individuals.

Subject-Specific and COM Acceleration-Enhanced Reflex Neuromuscular Model to Predict Ankle Responses in Perturbed Gait

Subject-specific musculoskeletal models generate more accurate joint torque estimates from electromyography (EMG) inputs in relation to experimentally obtained torques. Similarly, reflex Neuromuscular Models (NMMs) that employ COM states in addition to musculotendon information generate muscle activations to musculoskeletal models that better predict ankle torques during perturbed gait. In this study, the reflex NMM of locomotion of one subject is identified by employing an EMG-calibrated musculoskeletal model in unperturbed and perturbed gait. A COM acceleration-enhanced reflex NMM is identified. Subject-specific musculoskeletal models improve torque tracking of the ankle joint in unperturbed and perturbed conditions. COM acceleration-enhanced reflex NMM improves ankle torque tracking especially in early stance and during backward perturbation. Results found herein can guide the implementation of reflex controllers in active prosthetic and orthotic devices.

Real-time lumbosacral joint loading estimation in exoskeleton-assisted lifting conditions via electromyography-driven musculoskeletal models

Lumbar joint compression forces have been linked to the development of chronic low back pain, which is specially present in occupational environments. Offline methodologies for lumbosacral joint compression force estimation are not commonly integrated in occupational or medical applications due to the highly time-consuming and complex post-processing procedures. Hence, applications such as real-time adjustment of assistive devices (i.e., back-support exoskeletons) for optimal modulation of compression forces remains unfeasible. Here, we present a real-time electromyography (EMG)-driven musculoskeletal model, capable of estimating accurate lumbosacral joint moments and plausible compression forces. Ten participants performed box-lifting tasks (5 and 15 kg) with and without the Laevo Flex back-support exoskeleton using squat and stoop lifting techniques. Lumbosacral kinematics and EMGs from abdominal and thoracolumbar muscles were used to drive, in real-time, subject-specific EMG-driven models, and estimate lumbosacral joint moments and compression forces. Real-time EMG-model derived moments showed high correlations (R2 = 0.76 - 0.83) and estimation errors below 30% with respect to reference inverse dynamic moments. Compared to unassisted lifting conditions, exoskeleton liftings showed mean lumbosacral joint moments and compression forces reductions of 11.9 - 18.7 Nm (6 - 12% of peak moment) and 300 - 450 N (5 - 10%), respectively. Our modelling framework was capable of estimating in real-time, valid lumbosacral joint moments and compression forces in line with in vivo experimental data, as well as detecting the biomechanical effects of a passive back-support exoskeleton. Our presented technology may lead to a new class of bio-protective robots in which personalized assistance profiles are provided based on subject-specific musculoskeletal variables.

Advances on mechanical designs for assistive ankle-foot orthoses

Assistive ankle-foot orthoses (AAFOs) are powerful solutions to assist or rehabilitate gait on humans. Existing AAFO technologies include passive, quasi-passive, and active principles to provide assistance to the users, and their mechanical configuration and control depend on the eventual support they aim for within the gait pattern. In this research we analyze the state-of-the-art of AAFO and classify the different approaches into clusters, describing their basis and working principles. Additionally, we reviewed the purpose and experimental validation of the devices, providing the reader with a better view of the technology readiness level. Finally, the reviewed designs, limitations, and future steps in the field are summarized and discussed.

Use of Lower Limb Exoskeletons as an Assessment Tool for Human Motor Performance: A Systematic Review

Exoskeletons are a promising tool to support individuals with a decreased level of motor performance. Due to their built-in sensors, exoskeletons offer the possibility of continuously recording and assessing user data, for example, related to motor performance. The aim of this article is to provide an overview of studies that rely on using exoskeletons to measure motor performance. Therefore, we conducted a systematic literature review, following the PRISMA Statement guidelines. A total of 49 studies using lower limb exoskeletons for the assessment of human motor performance were included. Of these, 19 studies were validity studies, and six were reliability studies. We found 33 different exoskeletons; seven can be considered stationary, and 26 were mobile exoskeletons. The majority of the studies measured parameters such as range of motion, muscle strength, gait parameters, spasticity, and proprioception. We conclude that exoskeletons can be used to measure a wide range of motor performance parameters through built-in sensors, and seem to be more objective and specific than manual test procedures. However, since these parameters are usually estimated from built-in sensor data, the quality and specificity of an exoskeleton to assess certain motor performance parameters must be examined before an exoskeleton can be used, for example, in a research or clinical setting.

Recent advances in wearable actuated ankle-foot orthoses: Medical effects, design, and control

This paper presents a survey on recent advances of wearable actuated ankle-foot orthoses (AAFOs). First of all, their medical functions are investigated. From the short-term aspect, they lead to rectification of pathological gaits, reduction of metabolic cost, and improvement of gait performance. After AAFO-based walking training with sufficient time, free walking performance can be enhanced. Then, key design factors are studied. First, primary design parameters are investigated. Second, common actuators are analysed. Third, human-robot interaction (HRI), ergonomics, safety, and application places, are considered. In the following section, control technologies are reviewed from the aspects of rehabilitation stages, gait feature quantities, and controller characteristics. Finally, existing problems are discussed; development trends are prospected.

Opportunities and challenges in the development of exoskeletons for locomotor assistance

Exoskeletons can augment the performance of unimpaired users and restore movement in individuals with gait impairments. Knowledge of how users interact with wearable devices and of the physiology of locomotion have informed the design of rigid and soft exoskeletons that can specifically target a single joint or a single activity. In this Review, we highlight the main advances of the past two decades in exoskeleton technology and in the development of lower-extremity exoskeletons for locomotor assistance, discuss research needs for such wearable robots and the clinical requirements for exoskeleton-assisted gait rehabilitation, and outline the main clinical challenges and opportunities for exoskeleton technology.

sEMG-Based Continuous Hand Action Prediction by Using Key State Transition and Model Pruning

Conventional classification of hand motions and continuous joint angle estimation based on sEMG have been widely studied in recent years. The classification task focuses on discrete motion recognition and shows poor real-time performance, while continuous joint angle estimation evaluates the real-time joint angles by the continuity of the limb. Few researchers have investigated continuous hand action prediction based on hand motion continuity. In our study, we propose the key state transition as a condition for continuous hand action prediction and simulate the prediction process using a sliding window with long-term memory. Firstly, the key state modeled by GMM-HMMs is set as the condition. Then, the sliding window is used to dynamically look for the key state transition. The prediction results are given while finding the key state transition. To extend continuous multigesture action prediction, we use model pruning to improve reusability. Eight subjects participated in the experiment, and the results show that the average accuracy of continuous two-hand actions is 97% with a 70 ms time delay, which is better than LSTM (94.15%, 308 ms) and GRU (93.83%, 300 ms). In supplementary experiments with continuous four-hand actions, over 85% prediction accuracy is achieved with an average time delay of 90 ms.