From Pixels to Percepts: Highly Robust Edge Perception and Contour Following Using Deep Learning and an Optical Biomimetic Tactile Sensor

Nathan F. Lepora*, Alex Church, Conrad De Kerckhove, Raia Hadsell, John Lloyd

*Corresponding author for this work

Research output: Contribution to journalArticle (Academic Journal)

9 Citations (Scopus)
202 Downloads (Pure)

Abstract

Deep learning has the potential to have same the impact on robot touch as it has had on robot vision. Optical tactile sensors act as a bridge between the subjects by allowing techniques from vision to be applied to touch. In this letter, we apply deep learning to an optical biomimetic tactile sensor, the TacTip, which images an array of papillae (pins) inside its sensing surface analogous to structures within human skin. Our main result is that the application of a deep convolutional neural network can give reliable edge perception, and, thus a robust policy for planning contact points to move around object contours. Robustness is demonstrated over several irregular and compliant objects with both tapping and continuous sliding, using a model trained only by tapping onto a disk. These results relied on using techniques to encourage generalization to tasks beyond which the model was trained. We expect this is a generic problem in practical applications of tactile sensing that deep learning will solve.

Original languageEnglish
Article number8641397
Pages (from-to)2101-2107
Number of pages7
JournalIEEE Robotics and Automation Letters
Volume4
Issue number2
Early online date13 Feb 2019
DOIs
Publication statusPublished - 1 Apr 2019

Keywords

  • biomimetics
  • deep learning in robotics and automation
  • Force and tactile sensing

Fingerprint Dive into the research topics of 'From Pixels to Percepts: Highly Robust Edge Perception and Contour Following Using Deep Learning and an Optical Biomimetic Tactile Sensor'. Together they form a unique fingerprint.

  • Cite this