Wearable robotic devices have been shown to substantially reduce the energy expenditure of human walking. However, response variance between participants for fixed control strategies can be high, leading to the hypothesis that individualized controllers could further improve walking economy. Recent studies on human-in-the-loop (HIL) control optimization have elucidated several practical challenges, such as long experimental protocols and low signal-to-noise ratios. Here, we used Bayesian optimization-an algorithm well suited to optimizing noisy performance signals with very limited data-to identify the peak and offset timing of hip extension assistance that minimizes the energy expenditure of walking with a textile-based wearable device. Optimal peak and offset timing were found over an average of 21.4 ± 1.0 min and reduced metabolic cost by 17.4 ± 3.2% compared with walking without the device (mean ± SEM), which represents an improvement of more than 60% on metabolic reduction compared with state-of-the-art devices that only assist hip extension. In addition, our results provide evidence for participant-specific metabolic distributions with respect to peak and offset timing and metabolic landscapes, lending support to the hypothesis that individualized control strategies can offer substantial benefits over fixed control strategies. These results also suggest that this method could have practical impact on improving the performance of wearable robotic devices.
The increasing capabilities of exoskeletons and powered prosthetics for walking assistance have paved the way for more sophisticated and individualized control strategies. In response to this opportunity, recent work on human-in-the-loop optimization has considered the problem of automatically tuning control parameters based on realtime physiological measurements. However, the common use of metabolic cost as a performance metric creates significant experimental challenges due to its long measurement times and low signal-to-noise ratio. We evaluate the use of Bayesian optimization—a family of sample-efficient, noise-tolerant, and global optimization methods—for quickly identifying near-optimal control parameters. To manage experimental complexity and provide comparisons against related work, we consider the task of minimizing metabolic cost by optimizing walking step frequencies in unaided human subjects. Compared to an existing approach based on gradient descent, Bayesian optimization identified a near-optimal step frequency with a faster time to convergence (12 minutes, p < 0.01), smaller inter-subject variability in convergence time (± 2 minutes, p < 0.01), and lower overall energy expenditure (p < 0.01).
Exoskeletons can assist humans during squatting and the assistance has the potential to reduce the physical demands. Although several squat assistance methods are available, the effect of personalized assistance on physical effort has not been examined. We hypothesize that personalized assistance will reduce the physical effort of squatting. We developed a human-in-the-loop Bayesian optimization scheme to minimize the metabolic cost of squatting using a unilateral ankle exoskeleton. The optimization identified subject-specific assistance parameters for ascending and descending during squatting and took 15.8 min on average to converge. The subject-specific optimized condition reduced metabolic cost by 19.9% and rectus femoris muscle activity by 28.7% compared to the condition without the exoskeleton with a higher probability of improvement compared to a generic condition. In an additional study with two participants, the personalized condition presented higher metabolic cost reduction than the generic condition. These reductions illustrate the importance of personalized ankle assistance using an exoskeleton for squatting, a physically intensive activity, and suggest that such a method can be applied to minimize the physical effort of squatting. Future work can investigate the effect of personalized squat assistance on fatigue and the potential risk of injury. Index Terms-Squatting, human-in-the-loop, ankle-foot orthosis, and exoskeleton. I. INTRODUCTIONS QUATTING is a physically intensive and injury-prone task. Joint loading during squatting is higher than it is in other daily activities, such as walking [1], [2] and standing. Joint loads in squatting have increased contact stress and injuries in the tibiofemoral and patellofemoral joints [3]-[5].
The steady-state metabolic cost has been used to assess the performance of wearable robotic devices. Recently, real-time assessment of this metabolic cost has been employed in an objective function when optimizing robotic parameters for an individual user, thus personalizing the assistance to minimize human effort. However, the long estimation time needed for the model-based approach to metabolic cost estimation limits the optimization only to light-intensity activities. Here, we hypothesized that model-free, phase-plane estimation (PPE) would reduce the estimation time for the steady-state metabolic cost. First, we developed a phase-plane representation to classify the steady-state (where the change in metabolic rate is zero) and the transient metabolic dynamics. Second, we approximated the transient metabolic dynamics using a data-driven Gaussian mixture model and a real-time respiratory measure. We compared the performance of PPE with that of the model-based method by examining (1) walking performance assisted by a robotic prosthetic foot for individuals with and without Below Knee Amputation (BKA) and (2) squatting and running performance for individuals without BKA. PPE reduced the steady-state estimation time during walking for individuals with and without BKA by 31% and 40%, respectively. It also reduced estimation time by 56% and 24% for squatting and running conditions. These significant reductions in estimation time suggest that the data-driven PPE method can be used to rapidly estimate physical effort when personalizing the assistance from wearable robots. This expands the ability to conduct individual optimization for subjects engaged in physical intensive activities or for individuals with reduced physical strength.INDEX TERMS Rehabilitation robotics, Exoskeletons, Prosthetic limbs, Human-robot interaction, Human in the loop optimization.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.