Comparing optimized exoskeleton assistance of the hip, knee, and ankle in single and multi-joint configurations

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.

Estimating human joint moments unifies exoskeleton control, reducing user effort

Robotic lower-limb exoskeletons can augment human mobility, but current systems require extensive, context-specific considerations, limiting their real-world viability. Here, we present a unified exoskeleton control framework that autonomously adapts assistance on the basis of instantaneous user joint moment estimates from a temporal convolutional network (TCN). When deployed on our hip exoskeleton, the TCN achieved an average root mean square error of 0.142 newton-meters per kilogram across 35 ambulatory conditions without any user-specific calibration. Further, the unified controller significantly reduced user metabolic cost and lower-limb positive work during level-ground and incline walking compared with walking without wearing the exoskeleton. This advancement bridges the gap between in-lab exoskeleton technology and real-world human ambulation, making exoskeleton control technology viable for a broad community.

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.

AI-based methodologies for exoskeleton-assisted rehabilitation of the lower limb: a review

Over the past few years, there has been a noticeable surge in efforts to design novel tools and approaches that incorporate Artificial Intelligence (AI) into rehabilitation of persons with lower-limb impairments, using robotic exoskeletons. The potential benefits include the ability to implement personalized rehabilitation therapies by leveraging AI for robot control and data analysis, facilitating personalized feedback and guidance. Despite this, there is a current lack of literature review specifically focusing on AI applications in lower-limb rehabilitative robotics. To address this gap, our work aims at performing a review of 37 peer-reviewed papers. This review categorizes selected papers based on robotic application scenarios or AI methodologies. Additionally, it uniquely contributes by providing a detailed summary of input features, AI model performance, enrolled populations, exoskeletal systems used in the validation process, and specific tasks for each paper. The innovative aspect lies in offering a clear understanding of the suitability of different algorithms for specific tasks, intending to guide future developments and support informed decision-making in the realm of lower-limb exoskeleton and AI applications.

Lower limb biomechanics of fully trained exoskeleton users reveal complex mechanisms behind the reductions in energy cost with human-in-the-loop optimization

Exoskeletons that assist in ankle plantarflexion can improve energy economy in locomotion. Characterizing the joint-level mechanisms behind these reductions in energy cost can lead to a better understanding of how people interact with these devices, as well as to improved device design and training protocols. We examined the biomechanical responses to exoskeleton assistance in exoskeleton users trained with a lengthened protocol. Kinematics at unassisted joints were generally unchanged by assistance, which has been observed in other ankle exoskeleton studies. Peak plantarflexion angle increased with plantarflexion assistance, which led to increased total and biological mechanical power despite decreases in biological joint torque and whole-body net metabolic energy cost. Ankle plantarflexor activity also decreased with assistance. Muscles that act about unassisted joints also increased activity for large levels of assistance, and this response should be investigated over long-term use to prevent overuse injuries.

Optimizing exoskeleton assistance to improve walking speed and energy economy for older adults

BACKGROUND

Walking speed and energy economy tend to decline with age. Lower-limb exoskeletons have demonstrated potential to improve either measure, but primarily in studies conducted on healthy younger adults. Promising techniques like optimization of exoskeleton assistance have yet to be tested with older populations, while speed and energy consumption have yet to be simultaneously optimized for any population.

METHODS

We investigated the effectiveness of human-in-the-loop optimization of ankle exoskeletons with older adults. Ten healthy adults > 65 years of age (5 females; mean age: 72 ± 3 yrs) participated in approximately 240 min of training and optimization with tethered ankle exoskeletons on a self-paced treadmill. Multi-objective human-in-the-loop optimization was used to identify assistive ankle plantarflexion torque patterns that simultaneously improved self-selected walking speed and metabolic rate. The effects of optimized exoskeleton assistance were evaluated in separate trials.

RESULTS

Optimized exoskeleton assistance improved walking performance for older adults. Both objectives were simultaneously improved; self-selected walking speed increased by 8% (0.10 m/s; p = 0.001) and metabolic rate decreased by 19% (p = 0.007), resulting in a 25% decrease in energetic cost of transport (p = 8e-4) compared to walking with exoskeletons applying zero torque. Compared to younger participants in studies optimizing a single objective, our participants required lower exoskeleton torques, experienced smaller improvements in energy use, and required more time for motor adaptation.

CONCLUSIONS

Our results confirm that exoskeleton assistance can improve walking performance for older adults and show that multiple objectives can be simultaneously addressed through human-in-the-loop optimization.

Predicting Neuromuscular Engagement to Improve Gait Training with a Robotic Ankle Exoskeleton

The clinical efficacy of robotic rehabilitation interventions hinges on appropriate neuromuscular recruitment from the patient. The first purpose of this study was to evaluate the use of supervised machine learning techniques to predict neuromuscular recruitment of the ankle plantar flexors during walking with ankle exoskeleton resistance in individuals with cerebral palsy (CP). The second goal of this study was to utilize the predictive models of plantar flexor recruitment in the design of a personalized biofeedback framework intended to improve (i.e., increase) user engagement when walking with resistance. First, we developed and trained multilayer perceptrons (MLPs), a type of artificial neural network (ANN), utilizing features extracted exclusively from the exoskeleton's onboard sensors, and demonstrated 85-87% accuracy, on average, in predicting muscle recruitment from electromyography measurements. Next, our participants completed a gait training session while receiving audio-visual biofeedback of their personalized real-time planar flexor recruitment predictions from the online MLP. We found that adding biofeedback to resistance elevated plantar flexor recruitment by 24 16% compared to resistance alone. This study highlights the potential for online machine learning frameworks to improve the effectiveness and delivery of robotic rehabilitation systems in clinical populations.

An impairment-specific hip exoskeleton assistance for gait training in subjects with acquired brain injury: a feasibility study

This study was designed to investigate the feasibility and the potential effects on walking performance of a short gait training with a novel impairment-specific hip assistance (iHA) through a bilateral active pelvis orthosis (APO) in patients with acquired brain injury (ABI). Fourteen subjects capable of independent gait and exhibiting mild-to-moderate gait deficits, due to an ABI, were enrolled. Subjects presenting deficit in hip flexion and/or extension were included and divided into two groups based on the presence (group A, n = 6) or absence (group B, n = 8) of knee hyperextension during stance phase of walking. Two iHA-based profiles were developed for the groups. The protocol included two overground gait training sessions using APO, and two evaluation sessions, pre and post training. Primary outcomes were pre vs. post-training walking distance and steady-state speed in the 6-min walking test. Secondary outcomes were self-selected speed, joint kinematics and kinetics, gait symmetry and forward propulsion, assessed through 3D gait analysis. Following the training, study participants significantly increased the walked distance and average steady-state speed in the 6-min walking tests, both when walking with and without the APO. The increased walked distance surpassed the minimal clinically important difference for groups A and B, (respectively, 42 and 57 m > 34 m). In group A, five out of six subjects had decreased knee hyperextension at the post-training session (on average the peak of the knee extension angle was reduced by 36%). Knee flexion during swing phase increased, by 16% and 31%, for A and B groups respectively. Two-day gait training with APO providing iHA was effective and safe in improving walking performance and knee kinematics in ABI survivors. These preliminary findings suggest that this strategy may be viable for subject-specific post-ABI gait rehabilitation.

Comparing walking with knee-ankle-foot orthoses and a knee-powered exoskeleton after spinal cord injury: a randomized, crossover clinical trial

Recovering the ability to stand and walk independently can have numerous health benefits for people with spinal cord injury (SCI). Wearable exoskeletons are being considered as a promising alternative to conventional knee-ankle-foot orthoses (KAFOs) for gait training and assisting functional mobility. However, comparisons between these two types of devices in terms of gait biomechanics and energetics have been limited. Through a randomized, crossover clinical trial, this study compared the use of a knee-powered lower limb exoskeleton (the ABLE Exoskeleton) against passive orthoses, which are the current standard of care for verticalization and gait ambulation outside the clinical setting in people with SCI. Ten patients with SCI completed a 10-session gait training program with each device followed by user satisfaction questionnaires. Walking with the ABLE Exoskeleton improved gait kinematics compared to the KAFOs, providing a more physiological gait pattern with less compensatory movements (38% reduction of circumduction, 25% increase of step length, 29% improvement in weight shifting). However, participants did not exhibit significantly better results in walking performance for the standard clinical tests (Timed Up and Go, 10-m Walk Test, and 6-min Walk Test), nor significant reductions in energy consumption. These results suggest that providing powered assistance only on the knee joints is not enough to significantly reduce the energy consumption required by people with SCI to walk compared to passive orthoses. Active assistance on the hip or ankle joints seems necessary to achieve this outcome.

Exploring surface electromyography (EMG) as a feedback variable for the human-in-the-loop optimization of lower limb wearable robotics

Human-in-the-loop (HITL) optimization with metabolic cost feedback has been proposed to reduce walking effort with wearable robotics. This study investigates if lower limb surface electromyography (EMG) could be an alternative feedback variable to overcome time-intensive metabolic cost based exploration. For application, it should be possible to distinguish conditions with different walking efforts based on the EMG. To obtain such EMG data, a laboratory experiment was designed to elicit changes in the effort by loading and unloading pairs of weights (in total 2, 4, and 8 kg) in three randomized weight sessions for 13 subjects during treadmill walking. EMG of seven lower limb muscles was recorded for both limbs. Mean absolute values of each stride prior to and following weight loading and unloading were used to determine the detection rate (100% if every loading and unloading is detected accordingly) for changing between loaded and unloaded conditions. We assessed the use of multiple consecutive strides and the combination of muscles to improve the detection rate and estimated the related acquisition times of diminishing returns. To conclude on possible limitations of EMG for HITL optimization, EMG drift was evaluated during the Warmup and the experiment. Detection rates highly increased for the combination of multiple consecutive strides and the combination of multiple muscles. EMG drift was largest during Warmup and at the beginning of each weight session. The results suggest using EMG feedback of multiple involved muscles and from at least 10 consecutive strides (5.5 s) to benefit from the increases in detection rate in HITL optimization. In combination with up to 20 excluded acclimatization strides, after changing the assistance condition, we advise exploring about 16.5 s of walking to obtain reliable EMG-based feedback. To minimize the negative impact of EMG drift on the detection rate, at least 6 min of Warmup should be performed and breaks during the optimization should be avoided. Future studies should investigate additional feedback variables based on EMG, methods to reduce their variability and drift, and should apply the outcomes in HITL optimization with lower limb wearable robots.

The Effects of Incline Level on Optimized Lower-Limb Exoskeleton Assistance: a Case Series

For exoskeletons to be successful in real-world settings, they will need to be effective across a variety of terrains, including on inclines. While some single-joint exoskeletons have assisted incline walking, recent successes in level-ground assistance suggest that greater improvements may be possible by optimizing assistance of the whole leg. To understand how exoskeleton assistance should change with incline, we used human-in-the-loop optimization to find whole-leg exoskeleton assistance torques that minimized metabolic cost on a range of grades. We optimized assistance for three able-bodied, expert participants on 5 degree, 10 degree, and 15 degree inclines using a hip-knee-ankle exoskeleton emulator. For all assisted conditions, the cost of transport was reduced by at least 50% relative to walking in the device with no assistance, which is a large improvement to walking comparable to the benefits of whole-leg assistance on level-ground (N = 3). Optimized extension torque magnitudes and exoskeleton power increased with incline. Hip extension, knee extension and ankle plantarflexion often grew as large as allowed by comfort-based limits. Applied powers on steep inclines were double the powers applied during level-ground walking, indicating that greater exoskeleton power may be optimal in scenarios where biological powers and costs are higher. Future exoskeleton devices could deliver large improvements in walking performance across a range of inclines if they have sufficient torque and power capabilities.

Current developments of robotic hip exoskeleton toward sensing, decision, and actuation: A review

The aging population is now a global challenge, and impaired walking ability is a common feature in the elderly. In addition, some occupations such as military and relief workers require extra physical help to perform tasks efficiently. Robotic hip exoskeletons can support ambulatory functions in the elderly and augment human performance in healthy people during normal walking and loaded walking by providing assistive torque. In this review, the current development of robotic hip exoskeletons is presented. In addition, the framework of actuation joints and the high-level control strategy (including the sensors and data collection, the way to recognize gait phase, the algorithms to generate the assist torque) are described. The exoskeleton prototypes proposed by researchers in recent years are organized to benefit the related fields realizing the limitations of the available robotic hip exoskeletons, therefore, this work tends to be an influential factor with a better understanding of the development and state-of-the-art technology.

Reducing the energy cost of walking with low assistance levels through optimized hip flexion assistance from a soft exosuit

As we age, humans see natural decreases in muscle force and power which leads to a slower, less efficient gait. Improving mobility for both healthy individuals and those with muscle impairments/weakness has been a goal for exoskeleton designers for decades. In this work, we discover that significant reductions in the energy cost required for walking can be achieved with almost 50% less mechanical power compared to the state of the art. This was achieved by leveraging human-in-the-loop optimization to understand the importance of individualized assistance for hip flexion, a relatively unexplored joint motion. Specifically, we show that a tethered hip flexion exosuit can reduce the metabolic rate of walking by up to 15.2 ± 2.6%, compared to locomotion with assistance turned off (equivalent to 14.8% reduction compared to not wearing the exosuit). This large metabolic reduction was achieved with surprisingly low assistance magnitudes (average of 89 N, ~ 24% of normal hip flexion torque). Furthermore, the ratio of metabolic reduction to the positive exosuit power delivered was 1.8 times higher than ratios previously found for hip extension and ankle plantarflexion. These findings motivated the design of a lightweight (2.31 kg) and portable hip flexion assisting exosuit, that demonstrated a 7.2 ± 2.9% metabolic reduction compared to walking without the exosuit. The high ratio of metabolic reduction to exosuit power measured in this study supports previous simulation findings and provides compelling evidence that hip flexion may be an efficient joint motion to target when considering how to create practical and lightweight wearable robots to support improved mobility.