Manipulation of granular materials by learning particle interactions

Research output: Contribution to journalArticleScientificpeer-review

9 Citations (Scopus)
45 Downloads (Pure)

Abstract

Manipulation of granular materials such as sand or rice remains an unsolved problem due to challenges such as the difficulty of defining their configuration or modeling the materials and their particles interactions. Current approaches tend to simplify the material dynamics and omit the interactions between the particles. In this paper, we propose to use a graph-based representation to model the interaction dynamics of the material and rigid bodies manipulating it. This allows the planning of manipulation trajectories to reach a desired configuration of the material. We use a graph neural network (GNN) to model the particle interactions via message-passing. To plan manipulation trajectories, we propose to minimise the Wasserstein distance between a predicted distribution of granular particles and their desired configuration. We demonstrate that the proposed method is able to pour granular materials into the desired configuration both in simulated and real scenarios.

Original languageEnglish
Article number2
Pages (from-to)5663-5670
JournalIEEE Robotics and Automation Letters
Volume7
Issue number2
DOIs
Publication statusPublished - Apr 2022
MoE publication typeA1 Journal article-refereed

Keywords

  • Computational modeling
  • Data models
  • Deep Learning in Grasping and Manipulation
  • Machine Learning for Robot Control
  • Manipulation Planning
  • Manipulator dynamics
  • Planning
  • Trajectory

Fingerprint

Dive into the research topics of 'Manipulation of granular materials by learning particle interactions'. Together they form a unique fingerprint.

Cite this