CaltechAUTHORS
  A Caltech Library Service

ROIAL: Region of Interest Active Learning for Characterizing Exoskeleton Gait Preference Landscapes

Li, Kejun and Tucker, Maegan and Bıyık, Erdem and Novoseller, Ellen and Burdick, Joel W. and Sui, Yanan and Sadigh, Dorsa and Yue, Yisong and Ames, Aaron D. (2020) ROIAL: Region of Interest Active Learning for Characterizing Exoskeleton Gait Preference Landscapes. . (Unpublished) https://resolver.caltech.edu/CaltechAUTHORS:20210120-165248789

[img] PDF - Submitted Version
See Usage Policy.

3161Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20210120-165248789

Abstract

Characterizing what types of exoskeleton gaits are comfortable for users, and understanding the science of walking more generally, require recovering a user's utility landscape. Learning these landscapes is challenging, as walking trajectories are defined by numerous gait parameters, data collection from human trials is expensive, and user safety and comfort must be ensured. This work proposes the Region of Interest Active Learning (ROIAL) framework, which actively learns each user's underlying utility function over a region of interest that ensures safety and comfort. ROIAL learns from ordinal and preference feedback, which are more reliable feedback mechanisms than absolute numerical scores. The algorithm's performance is evaluated both in simulation and experimentally for three able-bodied subjects walking inside of a lower-body exoskeleton. ROIAL learns Bayesian posteriors that predict each exoskeleton user's utility landscape across four exoskeleton gait parameters. The algorithm discovers both commonalities and discrepancies across users' gait preferences and identifies the gait parameters that most influenced user feedback. These results demonstrate the feasibility of recovering gait utility landscapes from limited human trials.


Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription
http://arxiv.org/abs/2011.04812arXivDiscussion Paper
ORCID:
AuthorORCID
Tucker, Maegan0000-0001-7363-6809
Novoseller, Ellen0000-0001-5263-0598
Sui, Yanan0000-0002-9480-627X
Yue, Yisong0000-0001-9127-1989
Ames, Aaron D.0000-0003-0848-3177
Additional Information:This research was supported by NIH grant EB007615, NSF NRI award 1924526 and CMMI award 1923239, NSF Graduate Research Fellowship No. DGE-1745301, and the Caltech Big Ideas and ZEITLIN Funds. This work was conducted under IRB No. 16-0693. The authors would like to thank the experiment volunteers and the entire Wandercraft team that designed Atalante and continues to provide technical support for this project.
Funders:
Funding AgencyGrant Number
NIHEB007615
NSFECCS-1924526
NSFCMMI-1923239
NSF Graduate Research FellowshipDGE-1745301
Caltech Big Ideas FundUNSPECIFIED
Zeitlin Family Discovery FundUNSPECIFIED
Record Number:CaltechAUTHORS:20210120-165248789
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20210120-165248789
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:107615
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:21 Jan 2021 16:16
Last Modified:21 Jan 2021 16:16

Repository Staff Only: item control page