Comprehensive Review of Reinforcement Learning for Autonomous Drone Systems: Algorithms, Simulation, and Deployment Challenges

DOI

10.2991/978-94-6239-727-9_13How to use a DOI?

Keywords

Reinforcement learning; deep reinforcement learning; unmanned aerial vehicles; autonomous drones; multi-agent reinforcement learning; simulation-to-real transfer

Abstract

Reinforcement learning (RL) is proving to be a significant enabler of intelligent autonomy in UAVs, such that perception, decision-making, and control policies can be learned within drones through their interactions with complex and uncertain environments. Overall, while traditional model-based control methods rely on accurate system models, RL offers an alternative means of realising adaptive behaviour in the context of experience optimisation. However, recent advances in Deep Reinforcement Learning (DRL) and multi-agent reinforcement learning (MARL) have significantly expanded the use of RL for various complex UAV tasks such as autonomous navigation, obstacle avoidance, trajectory planning, target tracking, agile flight and collaborative swarm.

This work presents a comprehensive systematic review of the reinforcement learning approaches applied to autonomous drone systems. The survey systematically investigates RL fundamentals, common DRL algorithms, MARL paradigms, simulators, simulation-to-real transfer techniques, application domains and deployed issues. Comparative tables are also added to sum up the algorithmic trade-offs, simulator features and application–algorithm relations. We then discuss the critical issues on safety, sample efficiency, computational constraints and evaluation procedures, followed by the potential research directions. This paper is intended to offer a well-organized and easy entry reference for those who are interested in the RL-based UAV autonomy area such as researchers or practitioners.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yogesh S. Dighe
AU  - R. A. Kapgate
AU  - P. M. Patare
AU  - Vishant Kumar
PY  - 2026
DA  - 2026/07/22
TI  - Comprehensive Review of Reinforcement Learning for Autonomous Drone Systems: Algorithms, Simulation, and Deployment Challenges
BT  - Proceedings of the International Conference on Sustainable Micro-Nano Materials & Innovative Technology (ICSUMMIT 2026)
PB  - Atlantis Press
SP  - 171
EP  - 179
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6239-727-9_13
DO  - 10.2991/978-94-6239-727-9_13
ID  - Dighe2026
ER  -