Learning Physical Human–Robot Interaction With Coupled Cooperative Primitives for a Lower Exoskeleton

Huang, Rui; Cheng, Hong; Qiu, Jing; Zhang, Jianwei

doi:10.1109/tase.2018.2886376

Cited by 90 publications

(34 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, the linear reference model output (LRMO) tracking control setting is advantageous, ensuring indirect state-feedback linearization of control systems. Such linearity property of control systems is critical for higherlevel learning paradigms such as Iterative Learning Control [28][29][30][31][32][33][34] and primitive-based learning [34][35][36][37][38][39][40], as representative hierarchical learning control paradigms [41][42][43][44].…”

Section: Introductionmentioning

confidence: 99%

Virtual State Feedback Reference Tuning and Value Iteration Reinforcement Learning for Unknown Observable Systems Control

Rădac

Borlea

2021

Energies

View full text Add to dashboard Cite

In this paper, a novel Virtual State-feedback Reference Feedback Tuning (VSFRT) and Approximate Iterative Value Iteration Reinforcement Learning (AI-VIRL) are applied for learning linear reference model output (LRMO) tracking control of observable systems with unknown dynamics. For the observable system, a new state representation in terms of input/output (IO) data is derived. Consequently, the Virtual State Feedback Tuning (VRFT)-based solution is redefined to accommodate virtual state feedback control, leading to an original stability-certified Virtual State-Feedback Reference Tuning (VSFRT) concept. Both VSFRT and AI-VIRL use neural networks controllers. We find that AI-VIRL is significantly more computationally demanding and more sensitive to the exploration settings, while leading to inferior LRMO tracking performance when compared to VSFRT. It is not helped either by transfer learning the VSFRT control as initialization for AI-VIRL. State dimensionality reduction using machine learning techniques such as principal component analysis and autoencoders does not improve on the best learned tracking performance however it trades off the learning complexity. Surprisingly, unlike AI-VIRL, the VSFRT control is one-shot (non-iterative) and learns stabilizing controllers even in poorly, open-loop explored environments, proving to be superior in learning LRMO tracking control. Validation on two nonlinear coupled multivariable complex systems serves as a comprehensive case study.

show abstract

Section: Introductionmentioning

confidence: 99%

Virtual State Feedback Reference Tuning and Value Iteration Reinforcement Learning for Unknown Observable Systems Control

Rădac

Borlea

2021

Energies

View full text Add to dashboard Cite

show abstract

“…Despite the on-going trend in automation and mechanization in the industry, many workers still suffer from work-related musculoskeletal disorders due to unnatural body postures (De Looze et al, 2016;Huang et al, 2019). For example, in dynamic manufacturing and warehousing environments, the work scene made it impossible for workers to seat, so workers suffered from muscle fatigue of the lower limb caused by standing or squatting for a long period of time.…”

Section: Introductionmentioning

confidence: 99%

A Semi-active Exoskeleton Based on EMGs Reduces Muscle Fatigue When Squatting

Wang

Chen

et al. 2021

Front. Neurorobot.

View full text Add to dashboard Cite

In dynamic manufacturing and warehousing environments, the work scene made it impossible for workers to sit, so workers suffer from muscle fatigue of the lower limb caused by standing or squatting for a long period of time. In this paper, a semi-active exoskeleton used to reduce the muscle fatigue of the lower limb was designed and evaluated. (i) Background: The advantages and disadvantages of assistive exoskeletons developed for industrial purposes were introduced. (ii) Simulation: The process of squatting was simulated in the AnyBody.7.1 software, the result showed that muscle activity of the gluteus maximus, rectus femoris, vastus medialis, vastus lateralis, vastus intermedius, and erector spinae increased with increasing of knee flexion angle. (iii) Design: The exoskeleton was designed with three working modes: rigid-support mode, elastic-support mode and follow mode. Rigid-support mode was suitable for scenes where the squatting posture is stable, while elastic-support mode was beneficial for working environments where the height of squatting varied frequently.The working environments were identified intelligently based on the EMGs of the gluteus maximus, and quadriceps, and the motor was controlled to switch the working mode between rigid-support mode and elastic-support mode. In follow mode, the exoskeleton moves freely with users without interfering with activities such as walking, ascending and descending stairs. (iv) Experiments: Three sets of experiments were conducted to evaluate the effect of exoskeleton. Experiment one was conducted to measure the surface electromyography signal (EMGs) in both condition of with and without exoskeleton, the root mean square of EMGs amplitude of soleus, vastus lateralis, vastus medialis, gastrocnemius, vastus intermedius, rectus femoris, gluteus maximus, and erector spinae were reduced by 98.5, 97.89, 80.09, 77.27, 96.73, 94.17, 70.71, and 36.32%, respectively, with the assistance of the exoskeleton. The purpose of experiment two was aimed to measure the plantar pressure with and without exoskeleton. With exoskeleton, the percentage of weight through subject's feet was reduced by 63.94, 64.52, and 65.61% respectively at 60°, 90°, and 120° of knee flexion angle, compared to the condition of without exoskeleton. Experiment three was purposed to measure the metabolic cost at a speed of 4 and 5 km/h with and without exoskeleton. Experiment results showed that the average additional metabolic cost introduced by exoskeleton was 2.525 and 2.85%. It indicated that the exoskeleton would not interfere with the movement of the wearer Seriously in follow mode. (v) Conclusion: The exoskeleton not only effectively reduced muscle fatigue, but also avoided interfering with the free movement of the wearer.

show abstract

“…The Chinese University of Science and Technology designed an exoskeleton robot driven by a servo motor and developed a fuzzy algorithm for lower extremity exoskeleton (Huang et al, 2016a). The exoskeleton team of H. C. from University of Electronic Science and Technology of China have developed exoskeletons for paraplegia (Huang et al, 2018), hemiplegia patients (Peng et al, 2020), and human-power augmentation (Huang et al, 2016b(Huang et al, , 2019. The exoskeleton group at the Shenzhen Institutes of Advanced Technology of the Chinese Academy of Sciences has developed the fourth generation of the SIAT exoskeleton robot.…”

Section: Introductionmentioning

confidence: 99%

A Real-Time Stability Control Method Through sEMG Interface for Lower Extremity Rehabilitation Exoskeletons

et al. 2021

View full text Add to dashboard Cite

Herein, we propose a real-time stable control gait switching method for the exoskeleton rehabilitation robot. Exoskeleton rehabilitation robots have been extensively developed during the past decade and are able to offer valuable motor ability to paraplegics. However, achieving stable states of the human-exoskeleton system while conserving wearer strength remains challenging. The constant switching of gaits during walking may affect the center of gravity, resulting in imbalance of human–exoskeleton system. In this study, it was determined that forming an equilateral triangle with two crutch-supporting points and a supporting leg has a positive impact on walking stability and ergonomic interaction. First, the gaits planning and stability analysis based on human kinematics model and zero moment point method for the lower limb exoskeleton are demonstrated. Second, a neural interface based on surface electromyography (sEMG), which realizes the intention recognition and muscle fatigue estimation, is constructed. Third, the stability of human–exoskeleton system and ergonomic effects are tested through different gaits with planned and unplanned gait switching strategy on the SIAT lower limb rehabilitation exoskeleton. The intention recognition based on long short-term memory (LSTM) model can achieve an accuracy of nearly 99%. The experimental results verified the feasibility and efficiency of the proposed gait switching method for enhancing stability and ergonomic effects of lower limb rehabilitation exoskeleton.

show abstract

Learning Physical Human–Robot Interaction With Coupled Cooperative Primitives for a Lower Exoskeleton

Cited by 90 publications

References 24 publications

Virtual State Feedback Reference Tuning and Value Iteration Reinforcement Learning for Unknown Observable Systems Control

Virtual State Feedback Reference Tuning and Value Iteration Reinforcement Learning for Unknown Observable Systems Control

A Semi-active Exoskeleton Based on EMGs Reduces Muscle Fatigue When Squatting

A Real-Time Stability Control Method Through sEMG Interface for Lower Extremity Rehabilitation Exoskeletons

Contact Info

Product

Resources

About