Using Deep RL to Improve the ACAS-Xu Policy: Concept Paper

Filipo Perotto

2024

Abstract

ACAS-Xu is the future collision avoidance system for UAVs, responsible for generating evasive maneuvers in case of imminent risk of collision with another aircraft. In this concept paper, we summarize drawbacks of its current specification, particularly: (a) the fact that the resolution policy, calculated through dynamic programming over a stochastic process, is stored as a huge Q-table; (b) the need of forcing a correspondence between the continuous observations and the artificially discretized space of states; and (c) the consideration of a single aircraft crossing the drone’s trajectory, whereas the anti-collision system must potentially deal with multiple intruders. We suggest the use of recent deep reinforcement learning techniques to simultaneously approximate a compact representation of the problem in their continuous dimensions, as well as a near-optimal policy directly from simulation, in addition extending the set of observations and actions.

Paper Citation

in Harvard Style

Perotto F. (2024). Using Deep RL to Improve the ACAS-Xu Policy: Concept Paper. In Proceedings of the 2nd International Conference on Cognitive Aircraft Systems - Volume 1: ICCAS; ISBN 978-989-758-724-5, SciTePress, pages 110-117. DOI: 10.5220/0013023200004562

in Bibtex Style

@conference{iccas24,
author={Filipo Perotto},
title={Using Deep RL to Improve the ACAS-Xu Policy: Concept Paper},
booktitle={Proceedings of the 2nd International Conference on Cognitive Aircraft Systems - Volume 1: ICCAS},
year={2024},
pages={110-117},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013023200004562},
isbn={978-989-758-724-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Cognitive Aircraft Systems - Volume 1: ICCAS
TI - Using Deep RL to Improve the ACAS-Xu Policy: Concept Paper
SN - 978-989-758-724-5
AU - Perotto F.
PY - 2024
SP - 110
EP - 117
DO - 10.5220/0013023200004562
PB - SciTePress