Skip to main navigation Skip to search Skip to main content

PINN-Based Dynamics Learning of Continuum Soft Robots with Finite-Time Stable Sliding Mode Controller

  • Linke Xu
  • , Sen Guo
  • , Dong Zhu
  • , Xiangyu Shao*
  • *Corresponding author for this work
  • Harbin Institute of Technology
  • Ltd
  • Ltd.

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

Aircrafts working with soft robotic arms aroused extensive concerns in recent years. In this paper, a physics-informed neural network (PINN) is used to learn the dynamics of continuum soft robots. In detail, we incorporate Euler Lagrange equation into the deep neural network, providing improved physical interpretability and learning efficiency. Afterwards, a finite-time stable sliding mode controller is designed to achieve fast convergence, more accurate trajectory tracking and anti-disturbance ability. Theoretical analysis proves the closed-loop stability, and comparative simulations verify its superiority in transient and steady-state performance.

Original languageEnglish
Title of host publicationSpringer Aerospace Technology
PublisherSpringer Science and Business Media Deutschland GmbH
Pages252-259
Number of pages8
DOIs
StatePublished - 2025

Publication series

NameSpringer Aerospace Technology
VolumePart F194
ISSN (Print)1869-1730
ISSN (Electronic)1869-1749

Keywords

  • DeLaN
  • Finite-time Convergence
  • PINN
  • Sliding Mode Control

Fingerprint

Dive into the research topics of 'PINN-Based Dynamics Learning of Continuum Soft Robots with Finite-Time Stable Sliding Mode Controller'. Together they form a unique fingerprint.

Cite this