Review of Ai-Based Uav Navigation in Gps-Denied Environments

DOI

10.2991/978-94-6463-864-6_51How to use a DOI?

Keywords

Unmanned Aerial Vehicles; Navigation; Reinforcement Learning; Deep Learning; Deep Reinforcement Learning

Abstract

Unmanned Aerial Vehicles (UAVs) have increasingly become vital across a wide range of industries in the past decades. However, the conventional GPS-dependent navigation systems face critical limitations in these applications, especially in GPS-denied environments. Recent advances in Artificial Intelligence (AI) offer promising solutions for autonomous navigation without GPS reliance, such as reinforcement learning (RL), deep learning (DL), and deep reinforcement learning (DRL). This study presents a comprehensive review of AI-based navigation systems in these fields, emphasizing trajectory planning, perception, and localization. The main UAV autonomous applications include Search and Rescue (SaR), surveillance, and tracking. AI plays a crucial role in these applications for modeling humans to perform fundamental interactions and decision-making processes. RL methods enable self-learning of navigation policies through environment interaction, while DRL enhances this capability by integrating deep neural networks to manage complex, high-dimensional sensor data. DL approach, notably Convolutional Neural Networks (CNNs) and their derivatives like YOLO and DCNN, further empower UAVs with robust real-time vision-based navigation. Finally, challenges and future research directions are outlined, including lightweight algorithm exploitation, hybrid onboard-cloud computation, and energy-efficient autonomous recharging strategies, aiming to bridge the gap between simulation and real-world deployment for AI-based UAV navigation systems.

Copyright

© 2025 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  - Chenxin Yang
PY  - 2025
DA  - 2025/10/23
TI  - Review of Ai-Based Uav Navigation in Gps-Denied Environments
BT  - Proceedings of the 2025 2nd International Conference on Electrical Engineering and Intelligent Control (EEIC 2025)
PB  - Atlantis Press
SP  - 583
EP  - 596
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-864-6_51
DO  - 10.2991/978-94-6463-864-6_51
ID  - Yang2025
ER  -