Exploiting Human and Robot Muscle Synergies for Human-in-the-loop Optimization of EMG-based Assistive Strategies

Hamaya, Masashi; Matsubara, Takamitsu; Furukawa, Jun-ichiro; Sun, Yi; Yagi, Satoshi; Teramae, Tatsuya; Noda, Tomoyuki; Morimoto, Jun

doi:10.1109/icra.2019.8794082

Cited by 4 publications

(13 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…User preference [61] Energetic cost [57] Energetic cost [19] cost [14], [18] Synergy [59], [62] Ankle Gradient descent/ascent…”

Section: Bayesian Optimizationmentioning

confidence: 99%

“…In this case, mostly muscle activity [63], [67], [68], [69] or muscle synergy [58], [59], [62] are used as an objective function. Hamaya et al [61] was the only study that aimed at maximizing user preference by asking the participant preference level in each trial given the controller parameters.…”

Section: Reinforcement Learningmentioning

confidence: 99%

“…Other optimization strategies that are getting attention in the field are Bayesian optimization (BO) and particle swarm optimization (PSO). BO has high efficiency in finding the minima of objective functions that are noisy and expensive to evaluate [14], [18], [19], [57], [61]. It has two main phases that required a trade-off: exploration (of uncertain regions) and exploitation (of regions that offer improvement over the current best value) [61].…”

Section: Reinforcement Learningmentioning

confidence: 99%

“…BO has high efficiency in finding the minima of objective functions that are noisy and expensive to evaluate [14], [18], [19], [57], [61]. It has two main phases that required a trade-off: exploration (of uncertain regions) and exploitation (of regions that offer improvement over the current best value) [61]. BO can become time consuming as dimension and number of iterations increase, but that is not the case for HILO studies with low sets of parameters.…”

Section: Reinforcement Learningmentioning

confidence: 99%

See 3 more Smart Citations

Human-in-the-Loop Optimization of Wearable Robotic Devices to Improve Human–Robot Interaction: A Systematic Review

Díaz

Voss

Dillen

et al. 2023

IEEE Trans. Cybern.

View full text Add to dashboard Cite

show abstract

“…User preference [61] Energetic cost [57] Energetic cost [19] cost [14], [18] Synergy [59], [62] Ankle Gradient descent/ascent…”

Section: Bayesian Optimizationmentioning

confidence: 99%

Section: Reinforcement Learningmentioning

confidence: 99%

Section: Reinforcement Learningmentioning

confidence: 99%

Section: Reinforcement Learningmentioning

confidence: 99%

See 2 more Smart Citations

Human-in-the-Loop Optimization of Wearable Robotic Devices to Improve Human–Robot Interaction: A Systematic Review

Díaz

Voss

Dillen

et al. 2023

IEEE Trans. Cybern.

View full text Add to dashboard Cite

show abstract

“…Typically this process is used to optimize a parameterised control law [26]- [28], though other objectives have included step frequency [29], [30], parameterised design variables [31], and the energetic profile of assisted locomotion [32]. Most commonly, device performance is evaluated by quantifying metabolic rate via respiratory gas analysis [26]- [30], however, other physiological signals such as EMG activity [31], [33], or subject feedback [34], [35] have successfully been used as a performance criterion. A critical Fig.…”

mentioning

confidence: 99%

Human-in-the-Loop Optimization of Exoskeleton Assistance Via Online Simulation of Metabolic Cost

et al. 2022

View full text Add to dashboard Cite

Many assistive robotic devices have been developed to augment or assist human locomotion. Despite advancements in design and control algorithms, this task remains challenging. Human walking strategies are unique and complex, and assistance strategies based on the dynamics of unassisted locomotion typically offer only modest reductions to the metabolic cost of walking. Recently, human-in-the-loop (HIL) methodologies have been used to identify subject-specific assistive strategies, which offer significant improvements to energy savings. However, current implementations suffer from long measurement times, necessitating the use of low-dimensional control parameterizations, and possibly requiring multiday collection protocols to avoid subject fatigue. We present a HIL methodology, which optimizes the assistive torques provided by a powered hip exoskeleton. Using musculoskeletal modeling, we are able to evaluate simulated metabolic rate online. We applied our methodology to identify assistive torque profiles for seven subjects walking on a treadmill, and found greater reductions to metabolic cost when compared to generic or off-the-shelf controllers. In a secondary investigation, we directly compare simulated and measured metabolic rate for three subjects experiencing a range of assistance levels. The time investment required to identify assistance strategies via our protocol is significantly lower when compared to existing protocols relying on calorimetry. In the future, frameworks such as these could be used to enable shorter HIL protocols or exploit more complex control parameterizations for greater energy savings.

show abstract

An EMG-Based Objective Function for Human-in-the-Loop Optimization

Díaz,

De Bock,

Beckerle

et al. 2023

2023 International Conference on Rehabilitation Robotics (ICORR)

View full text Add to dashboard Cite

Exploiting Human and Robot Muscle Synergies for Human-in-the-loop Optimization of EMG-based Assistive Strategies

Cited by 4 publications

References 27 publications

Human-in-the-Loop Optimization of Wearable Robotic Devices to Improve Human–Robot Interaction: A Systematic Review

Human-in-the-Loop Optimization of Wearable Robotic Devices to Improve Human–Robot Interaction: A Systematic Review

Human-in-the-Loop Optimization of Exoskeleton Assistance Via Online Simulation of Metabolic Cost

An EMG-Based Objective Function for Human-in-the-Loop Optimization

Contact Info

Product

Resources

About