Abstract
dc:description.abstractWe have integrated intelligent technologies into our everyday lives to reduce some of the nuisances of the human experience. Intelligent robotic exoskeletons can further augment the human experience by reducing the energy expelled as we move, but integration into our daily lives requires exoskeleton control that is sufficiently adaptable to keep up with the range of activities we incur every day. Adaptation of exoskeleton control to a user and their activity has been achieved in the field, however this success is limited to niche, ideal cases of human ambulation that can be simulated in lab settings. We need to start moving towards exoskeleton control that is applicable to a wide range of human movement and can learn to seamlessly adapt as the user’s activity changes. I have studied using HILO and transfer learning to optimize exoskeleton control profiles across multiple ambulatory tasks to determine the effects of personalization and the generalizability of exoskeleton control.
Degree
thesis:*- Level thesis:degree_level
- Masters
- Department dc:contributor.department
- Mechanical Engineering
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Powell, Justine Clair
- Advisors dc:contributor.advisor
-
- Young, Aaron
- Inan, Omer T.
- Committee members dc:contributor.committeemember
-
- Sawicki, Gregory
- Mazumdar, Anirban
Subjects
dc:subject × 3Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/77753