Physical Intelligence

Learning of sub-optimal gait controllers for magnetic walking soft millirobots

2020

Conference Paper

ics

pi


Untethered small-scale soft robots have promising applications in minimally invasive surgery, targeted drug delivery, and bioengineering applications as they can access confined spaces in the human body. However, due to highly nonlinear soft continuum deformation kinematics, inherent stochastic variability during fabrication at the small scale, and lack of accurate models, the conventional control methods cannot be easily applied. Adaptivity of robot control is additionally crucial for medical operations, as operation environments show large variability, and robot materials may degrade or change over time,which would have deteriorating effects on the robot motion and task performance. Therefore, we propose using a probabilistic learning approach for millimeter-scale magnetic walking soft robots using Bayesian optimization (BO) and Gaussian processes (GPs). Our approach provides a data-efficient learning scheme to find controller parameters while optimizing the stride length performance of the walking soft millirobot robot within a small number of physical experiments. We demonstrate adaptation to fabrication variabilities in three different robots and to walking surfaces with different roughness. We also show an improvement in the learning performance by transferring the learning results of one robot to the others as prior information.

Author(s): Culha, Utku and Demir, Sinan O. and Trimpe, Sebastian and Sitti, Metin
Book Title: Robotics: Science and Systems XVI
Pages: P070
Year: 2020
Editors: Toussaint, Marc and Bicchi, Antonio and Hermans, Tucker
Publisher: RSS Foundation

Department(s): Intelligent Control Systems, Physical Intelligence
Research Project(s): Machine learning methods for soft millirobot design and control
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

DOI: 10.15607/RSS.2020.XVI.070
Event Name: Robotics: Science and Systems 2020 (RSS 2020)
Event Place: Corvallis, OR, USA

ISBN: 978-0-9923747-6-1
State: Published
URL: http://www.roboticsproceedings.org/rss16/p070.pdf

BibTex

@inproceedings{CulhaDemirRSS2020,
  title = {Learning of sub-optimal gait controllers for magnetic walking soft millirobots},
  author = {Culha, Utku and Demir, Sinan O. and Trimpe, Sebastian and Sitti, Metin},
  booktitle = {Robotics: Science and Systems XVI},
  pages = {P070},
  editors = {Toussaint, Marc and Bicchi, Antonio and Hermans, Tucker},
  publisher = {RSS Foundation},
  year = {2020},
  doi = {10.15607/RSS.2020.XVI.070},
  url = {http://www.roboticsproceedings.org/rss16/p070.pdf}
}