Color-Based Proprioception of Soft Actuators Interacting with Objects

Rob B.N. Scharff, Rens M. Doornbusch, Eugeni L. Doubrovski, Jun Wu, Jo M.P. Geraedts, Charlie C.L. Wang*

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

14 Citations (Scopus)
98 Downloads (Pure)

Abstract

Actuators using soft materials feature a large number of degrees of freedom. This tremendous flexibility allows a soft actuator to passively adapt its shape to the objects under interaction. In this paper, we propose a novel proprioception method for soft actuators during real-time interaction with previously unknown objects. First, we design a color-based sensing structure that instantly translates the inflation of a bellow into changes in color, which are subsequently detected by a miniaturized color sensor. The color sensor is small and, thus, multiple of them can be integrated into soft pneumatic actuators to reflect local deformations. Second, we make use of a feed-forward neural network to reconstruct a multivariate global shape deformation from local color signals. Our results demonstrate that deformations of the actuator during interaction, including sigmoid-like shapes, can be accurately reconstructed. The accurate shape sensing represents a significant step toward closed-loop control of soft robots in unstructured environments.

Original languageEnglish
Article number8766864
Pages (from-to)1964-1973
Number of pages10
JournalIEEE/ASME Transactions on Mechatronics
Volume24
Issue number5
DOIs
Publication statusPublished - 2019

Keywords

  • Color sensor
  • pneumatic actuator
  • sensor fusion
  • shape prediction
  • soft robotics

Fingerprint

Dive into the research topics of 'Color-Based Proprioception of Soft Actuators Interacting with Objects'. Together they form a unique fingerprint.

Cite this