Revisiting End-to-end Deep Learning for Obstacle Avoidance: Replication and Open Issues
Alexander Seewald
2020
Abstract
Obstacle avoidance is an essential feature for autonomous robots. It is usually addressed with specialized sensors and Simultaneous Localization and Mapping algorithms (SLAM, Cadena et al. (2016)). Muller et al. (2006) have demonstrated that it can also be addressed using end-to-end deep learning. They proposed a convolutional neural network that maps raw stereo pair input images to steering outputs and is trained by a human driver in an outdoor setting. Using the ToyCollect open source hardware and software platform, we replicate their main findings, compare several variants of their network that differ in the way steering angles are represented, and extend their system to indoor obstacle avoidance. We discuss several issues for further work concerning the automated generation of training data and the quantitative evaluation of such systems.
DownloadPaper Citation
in EndNote Style
TY - CONF
JO - Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Revisiting End-to-end Deep Learning for Obstacle Avoidance: Replication and Open Issues
SN - 978-989-758-395-7
AU - Seewald A.
PY - 2020
SP - 652
EP - 659
DO - 10.5220/0008979706520659
in Harvard Style
Seewald A. (2020). Revisiting End-to-end Deep Learning for Obstacle Avoidance: Replication and Open Issues. In Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-395-7, pages 652-659. DOI: 10.5220/0008979706520659
in Bibtex Style
@conference{icaart20,
author={Alexander Seewald},
title={Revisiting End-to-end Deep Learning for Obstacle Avoidance: Replication and Open Issues},
booktitle={Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2020},
pages={652-659},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008979706520659},
isbn={978-989-758-395-7},
}