Deficits in reactive balance can increase fall risk among older adults and individuals with neuromuscular impairments, motivating the need for interventions that improve balance recovery. Wearable robotic exoskeletons offer a promising approach to addressing this need by augmenting balance control. However, developing controllers that deliver appropriately timed and scaled assistance remains challenging, as evaluating each candidate strategy requires repeated exposure to destabilizing perturbations. We propose a simulation-to-real framework that combines motion imitation and reinforcement learning to develop balance-assistive ankle exoskeleton control. A muscle-driven neuromusculoskeletal model was trained using a small set of motion-capture data from a single subject to reproduce kinematic and kinetic responses to backward-translation perturbations. This model served as a virtual human for training a reinforcement-learning exoskeleton controller. The resulting controller generated bilateral ankle assistance using only inertial sensor measurements, without explicit perturbation detection. We implemented the controller on-board a bilateral ankle exoskeleton and evaluated it in five healthy subjects whose data were not used for training. Assistance increased the perturbation magnitude that subjects could withstand without stepping by 11.8% and reduced peak center-of-mass displacement and velocity by 13.5% and 28.2%, respectively. Individual benefits varied with baseline recovery strategy and body mass. These results indicate that a single virtual human can yield transferable balance assistance, and that more diverse virtual humans could further improve its effectiveness.
Figures & tables
Fig. 1: Overview of the simulation-to-real framework. (A) Stage 1: training the human policy to reproduce recorded responses to backward-translation perturbations. (B) Stage 2: training the exoskeleton controller to reduce CoM excursion and increase the balance threshold of the simulated human. (C) Deployment of the trained balance-assistive controller on an ankle exoskeleton. The policy receives on-board sensor inputs and outputs a torque command.
Fig. 2: Experimental protocol. (A) Participants wore a bilateral ankle exoskeleton while standing on a force-instrumented treadmill and experienced backward-translation perturbations. Foot placement was marked to standardize stance width across trials. (B) Treadmill perturbation profile and target belt displacement for a representative participant. (C) Perturbation-level selection by the QUEST adaptive algorithm and threshold selection for a representative participant.
Fig. 3: Simulation-to-real evaluation of the learned controller. (A) Motion-tracking performance of the Stage 1 human policy in representative trials, showing the response to a small perturbation and response variability across trials of the same larger perturbation. (B) Comparison of simulated gyroscope signals and exoskeleton torque commands with subject-averaged signals recorded during on-device deployment. (C) Comparison of simulated ankle moment offloading with experimentally measured reductions in biological ankle moment during exoskeleton assistance. Red vertical lines indicate onset of the perturbation. Shaded bands represent ± 1 standard deviation.
Fig. 4: Effect of simulation-trained exoskeleton assistance on standing balance outcomes. (A) Comparison of balance thresholds between exoskeleton-assisted (exo-on) and unassisted (exo-off) conditions. Colors represent individual participants and are consistent with those used in Fig. 5 . (B) Comparing peak forward CoM displacement and peak CoM velocity (both relative to the BoS) with and without exoskeleton assistance, evaluated at each participant’s unassisted balance threshold. Shaded bands represent ± 1 standard deviation.
Fig. 5: Relationship between baseline recovery strategy, quantified by the peak hip-to-ankle moment ratio, and the change in balance threshold with exoskeleton assistance. Colors represent individual participants and are consistent with those used in Fig. 4 A.
Developing exoskeleton controllers that generalize across diverse locomotor conditions typically requires extensive motion-capture data and biomechanical labeling, limiting scalability beyond instrumented laboratory settings. Here, we present a physics-based neuromusculoskeletal learning framework that trains a hip-exoskeleton control policy entirely in simulation, without motion-capture demonstrations, and deploys it on hardware via policy distillation. A reinforcement learning teacher policy is trained using a muscle-synergy action prior over a wide range of walking speeds and slopes through a two-stage curriculum, enabling direct comparison between assisted and no-exoskeleton conditions. In simulation, exoskeleton assistance reduces mean muscle activation by up to 3.4% and mean positive joint power by up to 7.0% on level ground and ramp ascent, with benefits increasing systematically with walking speed. On hardware, the assistance profiles learned in simulation are preserved across matched speed-slope conditions (r: 0.82, RMSE: 0.03 Nm/kg), providing quantitative evidence of sim-to-real transfer without additional hardware tuning. These results demonstrate that physics-based neuromusculoskeletal simulation can serve as a practical and scalable foundation for exoskeleton controller development, substantially reducing experimental burden during the design phase.
Ilseung Park, Changseob Song, Inseung Kang
Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA, 15213 USA.
Lower limb exoskeletons show promise to assist human movement, but their utility is limited by controllers designed for discrete, predefined actions in controlled environments, restricting their real-world applicability. We present an uncertainty-aware control framework that enables ankle exoskeletons to operate safely across diverse scenarios by automatically disengaging when encountering unfamiliar movements. Our approach uses an uncertainty estimator to classify movements as similar (in-distribution) or different (out-of-distribution) relative to actions in the training set. We evaluated three architectures (model ensembles, autoencoders, and generative adversarial networks) on an offline dataset and tested the strongest performing architecture (ensemble of gait phase estimators) online. The online test demonstrated the ability of our uncertainty estimator to turn assistance on and off as the user transitioned between in-distribution and out-of-distribution tasks (F1: 89.2). This new framework provides a path for exoskeletons to safely and autonomously support human movement in unstructured, everyday environments.
Fatima Mumtaza Tourk, Bishoy Galoaa, Sanat Shajan +3
Department of Mechanical Engineering, Northeastern University, Boston, MA 02115 USA
Designing generalizable control policies for lower-limb exoskeletons remains fundamentally constrained by exhaustive data collection or iterative optimization procedures, which limit accessibility to clinical populations. To address this challenge, we introduce a device-agnostic framework that combines physiologically plausible musculoskeletal simulation with reinforcement learning to enable scalable personalized exoskeleton assistance for both able-bodied and clinical populations. Our control policies not only generate physiologically plausible locomotion dynamics but also capture clinically observed compensatory strategies under targeted muscular deficits, providing a unified computational model of both healthy and pathological gait. Without task-specific tuning, the resulting exoskeleton control policies produce assistive torque profiles at the hip and ankle that align with state-of-the-art profiles validated in human experiments, while consistently reducing metabolic cost across walking speeds. For simulated impaired-gait models, the learned control policies yield asymmetric, deficit-specific exoskeleton assistance that improves both energetic efficiency and bilateral kinematic symmetry without explicit prescription of the target gait pattern. These results demonstrate that physiologically plausible musculoskeletal simulation via reinforcement learning can serve as a scalable foundation for personalized exoskeleton control across both able-bodied and clinical populations, eliminating the need for extensive physical trials.
Itak Choi, Ilseung Park, Eni Halilaj +1
Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA, 15213 USA.