Abstract
Advances in wearable devices have led to an increased need to develop sophisticated and individualized control strategies. To address this problem, several researchers have begun exploring human-in-the-loop optimization methods that automatically adjust control parameters in a wearable device using real-time physiological measurements. A common physiological measurement, metabolic cost, poses significant experimental challenges due to its long measurement times and low signal-to-noise ratio. This study addresses the challenges by using Bayesian optimization—an algorithm well-suited to optimizing noisy performance signals with very limited data—to perform control adaptation online. When applied to a soft exosuit designed to provide hip assistance, optimized control parameters were found in 24 min with a significant reduction in metabolic cost. These results suggest that this method could have a practical impact on improving the performance of wearable robotic devices.
This material is based upon the work supported by the Defense Advanced Research Projects Agency, Warrior Web Program (contract no. W911NF-14-C-0051), the Wyss Institute, the John A. Paulson School of Engineering and Applied Science at Harvard University and the Technology for Equitable and Assessable Medicine (TEAM) initiative at Harvard.
M. Kim and Y. Ding—Contributed equally to this work.
This manuscript is a shortened version of the recently published article [1]. Most contents are excerpted from the article including figures.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Ding, Y., et. al.: Human-in-the-loop optimization of hip assistance with a soft exosuit during walking. Sci. Robot. 3(15), eaar5438 (2018)
Zhang, J., et al.: Human-in-the-loop optimization of exoskeleton assistance during walking. Science 356(6344), 1280–1284 (2017)
Lee, S., et al.: Autonomous multi-joint soft exosuit with online optimization reduces energy cost of loaded walking. JNER 15(1), 66 (2018)
Mooney, L.M., et al.: Autonomous exoskeleton reduces metabolic cost of human walking during load carriage. JNER 11(1), 80 (2014)
Ding, Y., et al.: Effect of timing of hip extension assistance during loaded walking with a soft exosuit. JNER 13(1), 87 (2016)
Kim, M., et al.: Human-in-the-loop Bayesian optimization of wearable device parameters. PLoS ONE 12(9), e0184054 (2017)
Brochu, E., et al.: A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning. arXiv preprint arXiv:1012.2599 (2010)
Awad, L., et al.: A soft robotic exosuit improves walking in patients after stroke. Sci. Transl. Med. 9(400), eaai9084 (2017)
Acknowledgment
The authors would like to thank Chih-Kang Chang, Asa Eckert-Erdheim, Maria Athanassiu, Brice Mikala Iwangou, Nicolas Menard, and Sarah Sullivan for their contributions to this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Kim, M. et al. (2019). Human-in-the-Loop Bayesian Optimization of a Tethered Soft Exosuit for Assisting Hip Extension. In: Carrozza, M., Micera, S., Pons, J. (eds) Wearable Robotics: Challenges and Trends. WeRob 2018. Biosystems & Biorobotics, vol 22. Springer, Cham. https://doi.org/10.1007/978-3-030-01887-0_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-01887-0_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01886-3
Online ISBN: 978-3-030-01887-0
eBook Packages: EngineeringEngineering (R0)