Learning physics-informed simulation models for soft robotic manipulation: A case study with dielectric elastomer actuators

Manu Lahariya, Craig Innes, Chris Develder, Subramanian Ramamoorthy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Soft actuators offer a safe and adaptable approach to robotic tasks like gentle grasping and dexterous movement. Creating accurate models to control such systems, however, is challenging due to the complex physics of deformable materials. Accurate Finite Element Method (FEM) models incur prohibitive computational complexity for closed-loop use. Using a differentiable simulator is an attractive alternative, but their applicability to soft actuators and deformable materials remains under-explored. This paper presents a framework that combines the advantages of both. We learn a differentiable model consisting of a material properties neural network and an analytical dynamics model of the remainder of the manipulation task. This physics-informed model is trained using data generated from FEM and can be used for closed-loop control and inference. We evaluate our framework on a dielectric elastomer actuator (DEA) coin-pulling task. We simulate DEA coin pulling in FEM, and design experiments to evaluate the physics-informed model for simulation, control, and inference. Our model attains < 5% simulation error compared to FEM, and we use it as the basis for an MPC controller that outperforms (i.e., requires fewer iterations to converge) a model-free actor-critic policy, a heuristic policy, and a PD controller.
Original languageEnglish
Title of host publicationProceedings of the International Conference on Intelligent Robots and Systems (IROS) 2022
PublisherInstitute of Electrical and Electronics Engineers
Pages11031-11038
Number of pages8
ISBN (Electronic)978-1-6654-7927-1
ISBN (Print)978-1-6654-7928-8
DOIs
Publication statusPublished - 26 Dec 2022
EventThe 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems - Kyoto, Japan
Duration: 23 Oct 202227 Oct 2022
https://iros2022.org/

Publication series

NameIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
PublisherIEEE
ISSN (Print)2153-0858
ISSN (Electronic)2153-0866

Conference

ConferenceThe 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems
Abbreviated titleIROS 2022
Country/TerritoryJapan
CityKyoto
Period23/10/2227/10/22
Internet address

Keywords / Materials (for Non-textual outputs)

  • Dielectric elastomer actuators
  • Differentiable simulator
  • Finite element methods
  • Model predictive control
  • Neural Networks
  • Physics based machine learning
  • Soft ActorCritic
  • Soft robotics

Fingerprint

Dive into the research topics of 'Learning physics-informed simulation models for soft robotic manipulation: A case study with dielectric elastomer actuators'. Together they form a unique fingerprint.

Cite this