Human Preference-Based Learning for High-dimensional Optimization of Exoskeleton Walking Gaits
| Autor: | Maegan Tucker, Joel W. Burdick, Richard Cheng, Aaron D. Ames, Myra Cheng, Ellen Novoseller, Yisong Yue |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning 0209 industrial biotechnology Rehabilitation Computer science medicine.medical_treatment Work (physics) Computer Science - Human-Computer Interaction 02 engineering and technology Gait Field (computer science) Preference Human-Computer Interaction (cs.HC) Machine Learning (cs.LG) Exoskeleton Computer Science - Robotics 020901 industrial engineering & automation Human–computer interaction 0202 electrical engineering electronic engineering information engineering medicine High dimensional optimization 020201 artificial intelligence & image processing Robotics (cs.RO) |
| Zdroj: | IROS |
| DOI: | 10.1109/iros45743.2020.9341416 |
| Popis: | 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. Comment: 8 pages, 9 figures, 2 tables, to appear at IROS 2020 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|