Using tactile sensation for learning contact knowledge: Discriminate collision from physical interaction

Saskia Golz; Christian Osendorfer; Sami Haddadin

ICRA 2015poster82 citations

Using tactile sensation for learning contact knowledge: Discriminate collision from physical interaction

Saskia Golz, Christian Osendorfer, Sami Haddadin

Abstract

Detecting and interpreting contacts is a crucial aspect of physical Human-Robot Interaction. In order to discriminate between intended and unintended contact types, we derive a set of linear and non-linear features based on physical contact model insights and from observing real impact data that may even rely on proprioceptive sensation only. We implement a classification system with a standard non-linear Support Vector Machine and show empirically both in simulations and on a real robot the high accuracy in off- as well as on-line settings of the system. We argue that these successful results are based on our feature design derived from first principles.

BibTeX

@inproceedings{icra2015_usingtactilesens,
  title = {Using tactile sensation for learning contact knowledge: Discriminate collision from physical interaction},
  author = {Saskia Golz and Christian Osendorfer and Sami Haddadin},
  booktitle = {ICRA 2015},
  year = {2015}
}