Iterative Learning of Human Behavior for Adaptive Gait Pattern Adjustment of a Powered Exoskeleton

Park, Kyeong-Won; Choi, Jungsu; Kong, Kyoungchul

doi:10.1109/tro.2022.3144955

Cited by 14 publications

(4 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Adaptive control [13] is unable to overcome highly nonlinear uncertainties and disturbances with varying parameters, resulting in limited accuracy. A recent control strategy is timebased iterative learning control (ILC), which can achieve the best accuracy among the aforementioned strategies [14], [15] thanks to its ability to handle periodical disturbance in time. [14] proposed an ILC to improve the ankle exoskeleton's average and real-time torque tracking performance in steadystate walking by optimizing the parameters of ILC.…”

Section: Introductionmentioning

confidence: 99%

“…[14] proposed an ILC to improve the ankle exoskeleton's average and real-time torque tracking performance in steadystate walking by optimizing the parameters of ILC. [15] designed a gait parameter adjustment method based on ILC for paraplegic wearers with powered exoskeletons. However, ILC [14], [15] requires a fixed learning speed with a fixed iteration period, making unsteady-state walking difficult to handle, and is only suitable to handle periodic disturbance.…”

Section: Introductionmentioning

confidence: 99%

“…[15] designed a gait parameter adjustment method based on ILC for paraplegic wearers with powered exoskeletons. However, ILC [14], [15] requires a fixed learning speed with a fixed iteration period, making unsteady-state walking difficult to handle, and is only suitable to handle periodic disturbance. In addition to temporal periodicity, the motor control system of the exoskeleton has spatial periodicity due to the cyclic angle displacement according to [16], [17].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Spatial Iterative Learning Torque Control of Robotic Exoskeletons for High Accuracy and Rapid Convergence Assistance

Xing,

Zhang,

Huang

et al. 2024

IEEE/ASME Trans. Mechatron.

View full text Add to dashboard Cite

High-performance torque tracking is crucial for accurate control of the magnitude and timing of exoskeleton assistive torque profiles. However, state-of-the-art torque control methods, e.g., iterative learning control (ILC), applied to exoskeletons cannot achieve satisfying accuracy and convergence speed. This paper aims to design a spatial iterative learning (sIL)-based torque control strategy for exoskeletons to achieve accurate and fast torque assistance, which includes a high-level controller for torque planning, a mid-level one for reference trajectory generation, and a low-level one for trajectory tracking. Compared with ILC, our proposed sIL-based control method can estimate and compensate for spatial uncertainties (e.g., joint-angle-related uncertain dynamics of the human-exoskeleton interaction system) and spatial disturbances (e.g., joint-anglerelated disturbances caused by physical interaction with the human limb) that commonly exist in exoskeletons for highly accurate torque assistance. Furthermore, our control can ensure accurate torque tracking during unsteady-state gaits with fast convergence thanks to its spatial learning capability that enables varying iterative learning speeds to deal with varying walking speeds of users for different iterations, which is not feasible by ILC methods. Experiments showed that compared with the state-of-the-art torque control methods, our sIL-based control method significantly improved the torque tracking accuracy and shortened the convergence time for both steady-state walking and unsteady-state walking (with sudden or gradual changes in gait speeds), which demonstrates its effectiveness.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spatial Iterative Learning Torque Control of Robotic Exoskeletons for High Accuracy and Rapid Convergence Assistance

Xing,

Zhang,

Huang

et al. 2024

IEEE/ASME Trans. Mechatron.

View full text Add to dashboard Cite

show abstract

“…Due to the differences of individual physiological properties of wearers, identical stiffness coefficient is not suitable for all the wearers. In recent years, the control parameters or assistive strategies, such as in force control (Huo et al , 2020), impedance control (Li et al , 2017) or assistance strategy (Agarwal and Deshpande, 2019) for exoskeletons, are commonly tuned by iterative learning method (Park et al , 2022) or human-in-the-loop (HIL) optimization framework (Zhang et al , 2017). To use this effective and automatic tuning method for PWAEs, one of the important issues that is required to be discussed is that how to select the objective function given the circumstance of stoop lifting task (Han et al , 2021).…”

Section: Introductionmentioning

confidence: 99%

Stiffness optimization based on muscle fatigue and muscle synergy for passive waist assistive exoskeleton

Pang

Ding

et al. 2023

RIA

View full text Add to dashboard Cite

Purpose This paper aims to optimize the stiffness coefficient of the elastic element for a passive waist assistive exoskeleton (WAE). There is a tradeoff between stiffness coefficient of elastic element of the exoskeleton and work efficiency of the wearer, because elastic element affects original bending motion of the wearer and the force requirement of erector spinae is compensated by the other muscles. However, there is no accepted conclusion on how to determine the proper stiffness coefficient, especially with respected to the effort of groups of muscles, not only erector spinae. Design/methodology/approach In this study, a consumption indicator based on muscle fatigue of seven muscles is proposed and a Bayesian-based human-in-the-loop optimization approach is adopted to optimize the stiffness coefficient. Pneumatic artificial muscles are used to replace the mechanical elastic part to adjust the assistive force automatically. The proposed optimization method is verified by the way of load-lifting experiments with three different conditions: without exoskeleton, with fixed air pressure and with optimized air pressure. Six subjects participated in the experiment and each experiment is performed in different day. Findings Compared with No-Exo condition and static assistance condition, the parameter-optimized waist exoskeleton averagely reduces muscle fatigue of the six subjects by 45.30 ± 29.14% and 30.94 ± 30.29%, respectively. The experimental results indicate that the proposed method is effective to reduce muscle fatigue during stoop lifting task. Originality/value This paper provides a novel cost function construction method based on muscle fatigue and muscle synergy for passive WAE stiffness optimization.

show abstract

Forward dynamics simulation of a simplified neuromuscular-skeletal-exoskeletal model based on the CMA-ES optimization algorithm: framework and case studies

Jin,

Liu,

Zhang

et al. 2024

Multibody Syst Dyn

View full text Add to dashboard Cite

Iterative Learning of Human Behavior for Adaptive Gait Pattern Adjustment of a Powered Exoskeleton

Cited by 14 publications

References 42 publications

Spatial Iterative Learning Torque Control of Robotic Exoskeletons for High Accuracy and Rapid Convergence Assistance

Spatial Iterative Learning Torque Control of Robotic Exoskeletons for High Accuracy and Rapid Convergence Assistance

Stiffness optimization based on muscle fatigue and muscle synergy for passive waist assistive exoskeleton

Forward dynamics simulation of a simplified neuromuscular-skeletal-exoskeletal model based on the CMA-ES optimization algorithm: framework and case studies

Contact Info

Product

Resources

About