Physical Intelligence Article 2024

Learning Soft Millirobot Multimodal Locomotion with Sim-to-Real Transfer

Thumb ticker sm profilresmi 3
Physical Intelligence
  • Postdoctoral Researcher
Thumb ticker sm photo min
Medical Systems
Postdoctoral Researcher
Thumb ticker sm img 7713 smallfile
Physical Intelligence
Postdoctoral Researcher
Thumb ticker sm metin eth vertical small
Physical Intelligence
Guest Researcher
Figure01

With wireless multimodal locomotion capabilities, magnetic soft millirobots have emerged as potential minimally invasive medical robotic platforms. Due to their diverse shape programming capability, they can generate various locomotion modes, and their locomotion can be adapted to different environments by controlling the external magnetic field signal. Existing adaptation methods, however, are based on hand-tuned signals. Here, a learning-based adaptive magnetic soft millirobot multimodal locomotion framework empowered by sim-to-real transfer is presented. Developing a data-driven magnetic soft millirobot simulation environment, the periodic magnetic actuation signal is learned for a given soft millirobot in simulation. Then, the learned locomotion strategy is deployed to the real world using Bayesian optimization and Gaussian processes. Finally, automated domain recognition and locomotion adaptation for unknown environments using a Kullback-Leibler divergence-based probabilistic method are illustrated. This method can enable soft millirobot locomotion to quickly and continuously adapt to environmental changes and explore the actuation space for unanticipated solutions with minimum experimental cost.

Author(s): Demir, Sinan Ozgun and Tiryaki, Mehmet Efe and Karacakol, Alp Can and Sitti, Metin
Journal: Advanced Science
Year: 2024
Bibtex Type: Article (article)
DOI: https://doi.org/10.1002/advs.202308881
State: Published
Electronic Archiving: grant_archive

BibTex

@article{demir2024simtoreal,
  title = {Learning Soft Millirobot Multimodal Locomotion with Sim-to-Real Transfer},
  journal = {Advanced Science},
  abstract = {With wireless multimodal locomotion capabilities, magnetic soft millirobots have emerged as potential minimally invasive medical robotic platforms. Due to their diverse shape programming capability, they can generate various locomotion modes, and their locomotion can be adapted to different environments by controlling the external magnetic field signal. Existing adaptation methods, however, are based on hand-tuned signals. Here, a learning-based adaptive magnetic soft millirobot multimodal locomotion framework empowered by sim-to-real transfer is presented. Developing a data-driven magnetic soft millirobot simulation environment, the periodic magnetic actuation signal is learned for a given soft millirobot in simulation. Then, the learned locomotion strategy is deployed to the real world using Bayesian optimization and Gaussian processes. Finally, automated domain recognition and locomotion adaptation for unknown environments using a Kullback-Leibler divergence-based probabilistic method are illustrated. This method can enable soft millirobot locomotion to quickly and continuously adapt to environmental changes and explore the actuation space for unanticipated solutions with minimum experimental cost.},
  year = {2024},
  slug = {demir2024simtoreal},
  author = {Demir, Sinan Ozgun and Tiryaki, Mehmet Efe and Karacakol, Alp Can and Sitti, Metin}
}