2017
DOI: 10.1371/journal.pone.0184054
|View full text |Cite
|
Sign up to set email alerts
|

Human-in-the-loop Bayesian optimization of wearable device parameters

Abstract: 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 … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

2
85
0

Year Published

2018
2018
2024
2024

Publication Types

Select...
4
3
2
1

Relationship

0
10

Authors

Journals

citations
Cited by 103 publications
(90 citation statements)
references
References 49 publications
2
85
0
Order By: Relevance
“…Testing multiple concepts prior to the final device development could enable researchers to quickly diagnose the independent effects of design parameters on current products and test novel ideas [57]. Thus, we reason that exoskeleton testbeds have progressed exoskeleton technology by enabling researchers to optimize a high number of device parameters [58], test new ideas, and then iterate designs without having to build one-off prototypes.…”
Section: Leading Approaches and Technologies For Advancing Exoskeletonsmentioning
confidence: 99%
“…Testing multiple concepts prior to the final device development could enable researchers to quickly diagnose the independent effects of design parameters on current products and test novel ideas [57]. Thus, we reason that exoskeleton testbeds have progressed exoskeleton technology by enabling researchers to optimize a high number of device parameters [58], test new ideas, and then iterate designs without having to build one-off prototypes.…”
Section: Leading Approaches and Technologies For Advancing Exoskeletonsmentioning
confidence: 99%
“…However, there is potential to use advanced tools from image processing and machine-learning to extract real-time muscle length and velocity samples from ultrasound images 82 , and then use them in combination with EMG or a musculoskeletal model 83,84 as input to an exoskeleton controller. Access to muscle dynamics in real-time would enable application of state-of-the-art human in the loop optimization techniques 17,85,86 to individual or groups of target muscles. The possibility of 'muscle in the loop' exoskeleton control strategies opens the door to devices capable of steering neuromechanical structure and function over both short and long timescales during locomotion 87 .…”
mentioning
confidence: 99%
“…However, there is potential to use advanced tools from image processing and machine-learning to extract real-time muscle length and velocity samples from ultrasound images 82 , and then use them in combination with EMG or a musculoskeletal model 83,84 as input to an exoskeleton controller. Access to muscle dynamics in real-time would enable application of state-of-the-art human in the loop optimization techniques 17,85,86 to individual or groups of target muscles. The possibility of ‘muscle in the loop’ exoskeleton control strategies opens the door to devices capable of steering neuromechanical structure and function over both short and long timescales during locomotion 87,88 .…”
Section: Discussionmentioning
confidence: 99%