Reinforced Damage Minimization in Critical Events for Self-driving Vehicles

Francesco Merola, Fabrizio Falchi, Claudio Gennaro, Marco Di Benedetto

2022

Abstract

Self-driving systems have recently received massive attention in both academic and industrial contexts, leading to major improvements in standard navigation scenarios typically identified as well-maintained urban routes. Critical events like road accidents or unexpected obstacles, however, require the execution of specific emergency actions that deviate from the ordinary driving behavior and are therefore harder to incorporate in the system. In this context, we propose a system that is specifically built to take control of the vehicle and perform an emergency maneuver in case of a dangerous scenario. The presented architecture is based on a deep reinforcement learning algorithm, trained in a simulated environment and using raw sensory data as input. We evaluate the system’s performance on several typical pre-accident scenario and show promising results, with the vehicle being able to consistently perform an avoidance maneuver to nullify or minimize the incoming damage.

Paper Citation

in Harvard Style

Merola F., Falchi F., Gennaro C. and Di Benedetto M. (2022). Reinforced Damage Minimization in Critical Events for Self-driving Vehicles. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 258-266. DOI: 10.5220/0010908000003124

in Bibtex Style

@conference{visapp22,
author={Francesco Merola and Fabrizio Falchi and Claudio Gennaro and Marco Di Benedetto},
title={Reinforced Damage Minimization in Critical Events for Self-driving Vehicles},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP},
year={2022},
pages={258-266},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010908000003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP
TI - Reinforced Damage Minimization in Critical Events for Self-driving Vehicles
SN - 978-989-758-555-5
AU - Merola F.
AU - Falchi F.
AU - Gennaro C.
AU - Di Benedetto M.
PY - 2022
SP - 258
EP - 266
DO - 10.5220/0010908000003124
PB - SciTePress