In this paper we provide a method for identifying and temporally localizing tactile force actions from measured force signals. Our key idea is to use the Continuous wavelet transform (CWT) with the Complex Morlet wavelet to transform force signals into feature vectors amenable to machine learning algorithms. Our method uses these feature vectors to train a classifier that recognizes different actions. We demonstrate our approach in a system that records human activities with an instrumented set of tongs. Our system successfully identifies a wide range of actions based on a small set of labeled examples.

@InProceedings{SRWZG17,
  author       = "Subramani, Guru and Rakita, Daniel and Wang, Hongyi and Zinn, Michael and Gleicher, Michael",
  title        = "Recognizing Actions during Tactile Manipulations through Force Sensing",
  booktitle    = "IEEE/RSJ International Conference on Intelligent Robots and Systems",
  year         = "2017",
  url          = "http://graphics.cs.wisc.edu/Papers/2017/SRWZG17"
}