A Comparison of Visual Navigation Approaches based on Localization and Reinforcement Learning in Virtual and Real Environments

Marco Rosano, Marco Rosano, Antonino Furnari, Luigi Gulino, Giovanni Maria Farinella

2020

Abstract

Visual navigation algorithms allow a mobile agent to sense the environment and autonomously find its way to reach a target (e.g. an object in the environment). While many recent approaches tackled this task using reinforcement learning, which neglects any prior knowledge about the environments, more classic approaches strongly rely on self-localization and path planning. In this study, we compare the performance of single-target and multi-target visual navigation approaches based on the reinforcement learning paradigm, and simple baselines which rely on image-based localization. Experiments performed on discrete-state environments of different sizes, comprised of both real and virtual images, show that the two paradigms tend to achieve complementary results, hence suggesting that a combination of the two approaches to visual navigation may be beneficial.

Paper Citation

in Harvard Style

Rosano M., Furnari A., Gulino L. and Farinella G. (2020). A Comparison of Visual Navigation Approaches based on Localization and Reinforcement Learning in Virtual and Real Environments. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 628-635. DOI: 10.5220/0008950806280635

in Bibtex Style

@conference{visapp20,
author={Marco Rosano and Antonino Furnari and Luigi Gulino and Giovanni Maria Farinella},
title={A Comparison of Visual Navigation Approaches based on Localization and Reinforcement Learning in Virtual and Real Environments},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP},
year={2020},
pages={628-635},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008950806280635},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP
TI - A Comparison of Visual Navigation Approaches based on Localization and Reinforcement Learning in Virtual and Real Environments
SN - 978-989-758-402-2
AU - Rosano M.
AU - Furnari A.
AU - Gulino L.
AU - Farinella G.
PY - 2020
SP - 628
EP - 635
DO - 10.5220/0008950806280635
PB - SciTePress