Imposing Healthy Hip Motion Pattern and Range by Exoskeleton Control for Individualized Assistance

Zhang, Qiang; Nalam, Varun; Tu, Xikai; Li, Minhan; Si, Jennie; Lewek, Michael D.; Huang, He

doi:10.1109/lra.2022.3196105

Cited by 18 publications

(12 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…T is a vector of N QBFs, and θ ∈ R N is a parameter vector. Similar to existing model-free LSPI-based RL approaches [36], [37], [42]- [45] that do not depend on the exact model knowledge about the controlled system or the optimal solution, we applied no prior knowledge about the optimal policy or more generally about good policies to address the personalization problem, called online LSPI with policy approximation [46]. Consider a linearly parameterized policy ĥ…”

Section: Solution For Online Lspi With Policy Approximationmentioning

confidence: 99%

“…Each participant wore the bilateral hip exoskeleton and practiced walking in a transparent mode (zero assistance) on an instrumented treadmill (Bertec Corp., Columbus, OH, USA) at 1.0 m/s a day before the experimental sessions to ensure the participant felt comfortable walking with the exoskeleton. [36], [37]. Given the advantages of the bilateral configuration of the hip exoskeleton, separate assistance patterns can be applied to the left and right hip joints, which facilitates the rationale of generating artificial gait asymmetry even though only healthy human subjects were included.…”

Section: A Human Participants and Experimental Protocolmentioning

confidence: 99%

“…This considerable inter-human variation emphasizes the importance of customizing the robotic assistance on the impaired hip joint, thus optimizing the user's gait symmetry improvement. To provide personalized robotic optimal assistance (OA), recent studies have developed new concepts and automatic engineering approaches, of which two representative ones are human-in-the-loop (HIL) optimization approaches [25]- [32] and reinforcement learning (RL) approaches [33]- [37]. Specifically related to hip exoskeletons, Ding et al [30] proposed to use a Bayesian optimization approach to tune the shape parameters of the hip extension assistive torque for a wearable hip exosuit with a control goal of minimizing human metabolic rate during walking.…”

Section: Introductionmentioning

confidence: 99%

“…Considering the same control goal, Gordon et al [38] developed a musculoskeletal model-based online metabolic rate estimation, which was combined with a Bayesian optimization approach to tune the shape parameters of the hip flexionextension assistive torque. Tu et al [36] and Zhang et al [37] proposed to implement a least square policy iteration (LSPI)based RL control framework to tune the shape parameters of the hip extension and hip extension-flexion assistive torque profiles, with the control goals of maximizing the transferred power and imposing targeted hip joint trajectory, respectively.…”

Section: Introductionmentioning

confidence: 99%

“…To demonstrate the feasibility of the proposed control framework for impaired individuals post-stroke, we designed a scenario-equivalent study on unimpaired human subjects with artificial imitation of hemiparesis post-stroke. The main contributions of this study include 1) the dimension reduction of tunable control parameters for providing both hip flexion and extension assistance when compared to [37], [40]; 2) the online inter-leg coordination-based assistance torque profile generation; 3) the consideration of both gait symmetry and control parameters increment as components of the cost function, 4) the time-efficient control parameters tuning procedure, and 5) the potential GRF-or FSR-free implementations for daily locomotion tasks.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Robotic Assistance Personalization Control Approach of Hip Exoskeletons for Gait Symmetry Improvement

Zhang¹,

Tu²,

Si³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>We propose a hierarchical control framework for a bilateral hip exoskeleton to provide the adaptive optimal hip joint assistance with a control objective of imposing the desired gait symmetry during walking. Three control levels are included in the hierarchical framework, including the high-level control to tune three control parameters based on a policy iteration reinforcement learning approach, the middle-level control to define the desired assistive torque profile based on a delayed output feedback control method, and the low-level control to achieve a good torque trajectory tracking performance. To evaluate the feasibility of the proposed control framework, five healthy young participants are recruited for treadmill walking experiments, where an artificial gait asymmetry is imitated as the hemiparesis post-stroke, and only the ’paretic’ hip joint is controlled with the proposed framework. The pilot experimental studies demonstrate that the hierarchical control framework for the hip exoskeleton successfully and efficiently achieved the desired gait symmetry by providing adaptive optimal assistance on the ’paretic’ hip joint. Our next step will validate the control framework’s effectiveness on individuals post-stroke during treadmill walking and overground walking.</p>

show abstract

Section: Solution For Online Lspi With Policy Approximationmentioning

confidence: 99%

Section: A Human Participants and Experimental Protocolmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Robotic Assistance Personalization Control Approach of Hip Exoskeletons for Gait Symmetry Improvement

Zhang¹,

Tu²,

Si³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Closing the Loop Between Wearable Robots and Machine Learning: A New Paradigm for Steering Assistance Personalization Control

Zhang,

Zanotto,

Sharifi

et al. 2024

Discovering the Frontiers of Human-Robot Interaction

View full text Add to dashboard Cite

Data-efficient human walking speed intent identification

Higgins,

Bresingham,

Schmiedeler

et al. 2023

Wearable Technol.

View full text Add to dashboard Cite

The ability to accurately identify human gait intent is a challenge relevant to the success of many applications in robotics, including, but not limited to, assistive devices. Most existing intent identification approaches, however, are either sensor-specific or use a pattern-recognition approach that requires large amounts of training data. This paper introduces a real-time walking speed intent identification algorithm based on the Mahalanobis distance that requires minimal training data. This data efficiency is enabled by making the simplifying assumption that each time step of walking data is independent of all other time steps. The accuracy of the algorithm was analyzed through human-subject experiments that were conducted using controlled walking speed changes on a treadmill. Experimental results confirm that the model used for intent identification converges quickly (within 5 min of training data). On average, the algorithm successfully detected the change in desired walking speed within one gait cycle and had a maximum of 87% accuracy at responding with the correct intent category of speed up, slow down, or no change. The findings also show that the accuracy of the algorithm improves with the magnitude of the speed change, while speed increases were more easily detected than speed decreases.

show abstract

Imposing Healthy Hip Motion Pattern and Range by Exoskeleton Control for Individualized Assistance

Cited by 18 publications

References 35 publications

A Robotic Assistance Personalization Control Approach of Hip Exoskeletons for Gait Symmetry Improvement

A Robotic Assistance Personalization Control Approach of Hip Exoskeletons for Gait Symmetry Improvement

Closing the Loop Between Wearable Robots and Machine Learning: A New Paradigm for Steering Assistance Personalization Control

Data-efficient human walking speed intent identification

Contact Info

Product

Resources

About