Terrain Classification For Ground Robots Based On Acoustic Features

Bernd Kiefer, Abraham Gebru Tesfay, Dietrich KlakowZenodo 2017 · DOI

Abstract

The motivation of our work is to detect different<br> terrain types traversed by a robot based on acoustic data from the<br> robot-terrain interaction. Different acoustic features and classifiers<br> were investigated, such as Mel-frequency cepstral coefficient and<br> Gamma-tone frequency cepstral coefficient for the feature extraction,<br> and Gaussian mixture model and Feed forward neural network for the<br> classification. We analyze the system’s performance by comparing<br> our proposed techniques with some other features surveyed from<br> distinct related works. We achieve precision and recall values between<br> 87% and 100% per class, and an average accuracy at 95.2%. We also<br> study the effect of varying audio chunk size in the application phase<br> of the models and find only a mild impact on performance.
BibTeX
@inproceedings{kiefer2017terrain,
  author = {Bernd Kiefer and Abraham Gebru Tesfay and Dietrich Klakow},
  title = {{Terrain Classification For Ground Robots Based On Acoustic Features}},
  booktitle = {Zenodo},
  year = {2017},
  doi = {10.5281/zenodo.1130636},
}

Loading related content...

Figure