Autonomous Trail Following using a Pre-trained Deep Neural Network

Masoud Hoveidar-Sefid, Michael Jenkin

2018

Abstract

Trails are unstructured and typically lack standard markers that characterize roadways; nevertheless, trails can provide an effective set of pathways for off-road navigation. Here we approach the problem of trail following by identifying the deviation of the robot from the heading angle of the trail through the refinement of a pretrained Inception-V3 (Szegedy et al., 2016a) Convolutional Neural Network (CNN) trained on the ImageNet dataset (Deng et al., 2009). A differential system is developed that uses a pair of cameras each providing input to its own CNN directed to the left and the right that estimate the deviation of the robot with respect to the trail direction. The resulting networks have been successfully tested on over 1 km of different trail types (asphalt, concrete, dirt and gravel).

Paper Citation

in Harvard Style

Jenkin M. (2018). Autonomous Trail Following using a Pre-trained Deep Neural Network.In Proceedings of the 15th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-989-758-321-6, pages 103-110. DOI: 10.5220/0006832301030110

in Bibtex Style

@conference{icinco18,
author={Michael Jenkin},
title={Autonomous Trail Following using a Pre-trained Deep Neural Network},
booktitle={Proceedings of the 15th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2018},
pages={103-110},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006832301030110},
isbn={978-989-758-321-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - Autonomous Trail Following using a Pre-trained Deep Neural Network
SN - 978-989-758-321-6
AU - Jenkin M.
PY - 2018
SP - 103
EP - 110
DO - 10.5220/0006832301030110