• R Esther Priya
• Aabheshek P
• Arun T N
• Garrepelli Varshini
• Sasikumar S.

The rapid advancement of drone technology has sparked significant interest in the development of autonomous navigation systems. This project focuses on creating a robust model designed to enable unmanned aerial vehicles (UAVs) to operate independently in dynamic environments. By leveraging advanced algorithms for real-time decision-making, path planning, and obstacle detection, this allows UAVs to navigate without human intervention. Utilizing Deep Reinforcement Learning (DRL), specifically the Soft Actor-Critic (SAC) model, and LiDAR for obstacle detection, the system is designed to learn and adapt in real-time while avoiding both static and dynamic obstacles. The project employs the AirSim simulation platform to train models in various simulated environments, ensuring adaptability and robustness. Key outcomes include efficient collision avoidance, adaptive learning across diverse terrains, and improved navigation performance compared to traditional methods.

Artificial Intelligence, Automated Navigation, Computer Vision, UAV, Object Detection.

"AUTOMATED UAV NAVIGATION IN SIMULATED ENVIRONMENTS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.f143-f148, March-2025, Available :http://www.jetir.org/papers/JETIR2503544.pdf

"AUTOMATED UAV NAVIGATION IN SIMULATED ENVIRONMENTS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppf143-f148, March-2025, Available at : http://www.jetir.org/papers/JETIR2503544.pdf