Sorted by DateClassified by Publication TypeClassified by Research Category

Bioinspired Vision-only UAV Attitude Rate Estimation using Machine Learning

Macarena Mérida-Floriano, Fernando Caballero, Diana Garc\'i-Morales, Fernando Casares, and Luis Merino. Bioinspired Vision-only UAV Attitude Rate Estimation using Machine Learning. In Proceedings of the International Conference on Unmanned Aircraft Systems, ICUAS, pp. 1–6, 2017.

Download

[PDF] 

Abstract

This paper presents a bioinspired system for attitude rate estimation using visual sensors for aerial vehicles. The sensorial system consists of three small low-resolution cameras (10x8 pixels), and is based on insect ocelli, a set of three simple eyes related to flight stabilization. Most previous approaches inspired by the ocellar system use model-based techniques and consider different assumptions, like known light source direction. Here, a learning approach is employed, using Artificial Neural Networks, in which the system is trained to recover the angular rates in different illumination scenarios with unknown light source direction. We present an study using real data in an indoor setting, in which we evaluate different network architectures and inputs.

BibTeX Entry

  @INPROCEEDINGS{icuas17,
  author = {Macarena M\'{e}rida-Floriano and Fernando Caballero and Diana Garc\'{i}-Morales and Fernando Casares and Luis Merino},
  title = {{Bioinspired Vision-only UAV Attitude Rate Estimation using Machine Learning}},
  booktitle = {Proceedings of the International Conference on Unmanned Aircraft Systems, ICUAS},
  year = {2017},
  pages = {1--6},
  abstract={This paper presents a bioinspired system for attitude rate estimation using visual sensors for aerial vehicles. The sensorial system consists of three small low-resolution cameras (10x8 pixels), and is based on insect ocelli, a set of three simple eyes related to flight stabilization. Most previous approaches inspired by the ocellar system use model-based techniques and consider different assumptions, like known light source direction. Here, a learning approach is employed, using Artificial Neural Networks, in which the system is trained to recover the angular rates in different illumination scenarios with unknown light source direction. We present an study using real data in an indoor setting, in which we evaluate different network architectures and inputs.},
}

Generated by bib2html.pl (written by Patrick Riley ) on Thu Feb 01, 2018 17:59:02