VizNav: A Modular Off-Policy Deep Reinforcement Learning Framework for Vision-Based Autonomous UAV Navigation in 3D Dynamic Environments
Drones · 27.04.2024 · 8 (5) · 173
DOI: 10.3390/drones8050173 ↗Kurz gefasst
Fachartikel in der Zeitschrift Drones, online erschienen am 27.04.2024. Verfasst von Fadi AlMahamid und 1 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSERC.
Abstract (Originalsprache)
Unmanned aerial vehicles (UAVs) provide benefits through eco-friendliness, cost-effectiveness, and reduction of human risk. Deep reinforcement learning (DRL) is widely used for autonomous UAV navigation; however, current techniques often oversimplify the environment or impose movement restrictions. Additionally, most vision-based systems lack precise depth perception, while range finders provide a limited environmental overview, and LiDAR is energy-intensive. To address these challenges, this paper proposes VizNav, a modular DRL-based framework for autonomous UAV navigation in dynamic 3D environments without imposing conventional mobility constraints. VizNav incorporates the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm with Prioritized Experience Replay and Importance Sampling (PER) to improve performance in continuous action spaces and mitigate overestimations. Additionally, VizNav employs depth map images (DMIs) to enhance visual navigation by accurately estimating objects’ depth information, thereby improving obstacle avoidance. Empirical results show that VizNav, by leveraging TD3, improves navigation, and the inclusion of PER and DMI further boosts performance. Furthermore, the deployment of VizNav across various experimental settings confirms its flexibility and adaptability. The framework’s architecture separates the agent’s learning from the training process, facilitating integration with various DRL algorithms, simulation environments, and reward functions. This modularity creates a potential to influence RL simulation in various autonomous navigation systems, including robotics control and autonomous vehicles.
Förderung
- NSERC
Zitieren
APA
AlMahamid, F., & Grolinger, K. (2024). VizNav: A Modular Off-Policy Deep Reinforcement Learning Framework for Vision-Based Autonomous UAV Navigation in 3D Dynamic Environments. Drones, 8(5), 173. https://doi.org/10.3390/drones8050173
Vancouver
AlMahamid F, Grolinger K. VizNav: A Modular Off-Policy Deep Reinforcement Learning Framework for Vision-Based Autonomous UAV Navigation in 3D Dynamic Environments. Drones. 2024;8(5):173. doi:10.3390/drones8050173
BibTeX
@article{AlMahamid2024,
author = {AlMahamid, Fadi and Grolinger, Katarina},
title = {VizNav: A Modular Off-Policy Deep Reinforcement Learning Framework for Vision-Based Autonomous UAV Navigation in 3D Dynamic Environments},
journal = {Drones},
year = {2024},
volume = {8},
number = {5},
pages = {173},
doi = {10.3390/drones8050173}
}
EUVIMED