Towards latent space based manipulation of elastic rods using autoencoder models and robust centerline extractions

Jiaming Qi, Guangfu Ma, Peng Zhou, Haibo Zhang, Yueyong Lyu, David Navarro-Alarcon

Research output: Journal article publicationJournal articleAcademic researchpeer-review

Abstract

The automatic shape control of deformable objects is a challenging (and currently hot) manipulation problem due to their high-dimensional geometric features and complex physical properties. In this study, a new methodology to manipulate elastic rods automatically into 2D desired shapes is presented. An efficient vision-based controller that uses a deep autoencoder network is designed to compute a compact representation of the object's infinite-dimensional shape. An online algorithm that approximates the sensorimotor mapping between the robots configuration and the object's shape features is used to deal with the latters (typically unknown) mechanical properties. The proposed approach computes the rods centerline from raw visual data in real-time by introducing an adaptive algorithm on the basis of a self-organizing network. Its effectiveness is thoroughly validated with simulations and experiments.

Original languageEnglish
Pages (from-to)101-115
Number of pages15
JournalAdvanced Robotics
Volume36
Issue number3
DOIs
Publication statusPublished - 2022

Keywords

  • autoencoder
  • deformable objects
  • Robotics
  • self-organizing network
  • visual servoing

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Human-Computer Interaction
  • Hardware and Architecture
  • Computer Science Applications

Cite this