Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published October 2020 | Submitted
Book Section - Chapter Open

Human Preference-Based Learning for High-dimensional Optimization of Exoskeleton Walking Gaits

Abstract

Optimizing lower-body exoskeleton walking gaits for user comfort requires understanding users' preferences over a high-dimensional gait parameter space. However, existing preference-based learning methods have only explored low-dimensional domains due to computational limitations. To learn user preferences in high dimensions, this work presents LINECOSPAR, a human-in-the-loop preference-based framework that enables optimization over many parameters by iteratively exploring one-dimensional subspaces. Additionally, this work identifies gait attributes that characterize broader preferences across users. In simulations and human trials, we empirically verify that LINECOSPAR is a sample-efficient approach for high-dimensional preference optimization. Our analysis of the experimental data reveals a correspondence between human preferences and objective measures of dynamicity, while also highlighting differences in the utility functions underlying individual users' gait preferences. This result has implications for exoskeleton gait synthesis, an active field with applications to clinical use and patient rehabilitation.

Additional Information

© 2020 IEEE. This work was supported by NSF NRI award 1724464, NSF Graduate Research Fellowship No. DGE1745301, the Caltech Big Ideas Fund, and the ZEITLIN Fund. This work was conducted under IRB No. 16-0693. The authors would like to acknowledge the subjects who participated in exoskeleton testing, as well as the entire Wandercraft team that designed Atalante and continues to provide technical support for this project.

Attached Files

Submitted - 2003.06495.pdf

Files

2003.06495.pdf
Files (4.2 MB)
Name Size Download all
md5:19d71b3ce02795c727ac70c1dfa6c6bc
4.2 MB Preview Download

Additional details

Created:
August 19, 2023
Modified:
October 20, 2023