AI-Powered Flight Path Planning: Transforming Drone Navigation and Autonomy

Madan H T; Aruna Kumara B; Vishwanath B R; Pramodh H K; Manjunatha H M

doi:10.5935/jetia.v12i59.3853

Authors

Madan H T Nitte (Deemed to be University), NMAM Institute of Technology (NMAMIT), Department of Electronics and Communication (Advanced Communication Technology), Nitte, Karkala Taluk, Udupi – 574110,Karnataka, India. http://orcid.org/0000-0002-3126-9737 (unauthenticated)
Aruna Kumara B Department of Computer Science and Technology, School of Engineering, Dayananda Sagar University, Bangalore, Karnataka, India. http://orcid.org/0000-0001-5044-2972 (unauthenticated)
Vishwanath B R Department of Electronics and Communication Engineering, Rajeev Institute of Technology, Hassan-573201, Visvesvaraya Technological University, Belagavi, Karnataka, India. https://orcid.org/0000-0002-2722-9775 (unauthenticated)
Pramodh H K Department of Electrical and Electronics Engineering, Malnad college of Engineering, Hassan - 573202, Karnataka, India. http://orcid.org/0009-0003-0833-7644 (unauthenticated)
Manjunatha H M Electrical and Electronics Engineering, Bapuji Institute of Engineering and Technology, Davanagere-577004, Karnataka, India https://orcid.org/0000-0001-6651-7131 (unauthenticated)

DOI:

https://doi.org/10.5935/jetia.v12i59.3853

Abstract

This paper examines the integration of advanced AI technologies with traditional navigation systems, revolutionizing flight path planning for drones. It covers key navigation technologies such as Global Navigation Satellite Systems (GNSS), Inertial Measurement Units (IMUs), and Lidar, demonstrating how these systems provide the foundation for precise geolocation, stability control, and obstacle detection through 3D spatial mapping. The paper delves into sophisticated AI techniques, including Simultaneous Localization and Mapping (SLAM) and Convolutional Neural Networks (CNNs), which enable drones to navigate autonomously in complex environments without human intervention. Emphasis is placed on dynamic AI algorithms that optimize flight paths in real time, addressing challenges such as air traffic, unpredictable weather, and environmental constraints. Path planning algorithms, such as A* and Rapidly-Exploring Random Trees (RRT), are discussed alongside machine learning and reinforcement learning models that allow drones to continuously learn and adapt for enhanced safety and efficiency. Additionally, the paper explores the integration of multi-agent communication systems, demonstrating how fleets of drones can operate collaboratively to optimize airspace usage and task execution. Case studies across industries, including commercial delivery and environmental monitoring, are presented to highlight practical applications. The role of real-time data exchange technologies like 5G and RF in improving communication and control is also examined. The paper concludes by addressing the future of AI in drone path planning, discussing ethical considerations and the need for regulatory frameworks to ensure safe, responsible AI utilization. Through a comprehensive review of current technologies and forward-looking trends, this paper provides valuable insights into the evolution of drone navigation systems in the AI era.