Adaptive Learning and Central AI Analysis of UAV Navigation Systems Using Multiple Sensors in Complex Terrain
DOI:
https://doi.org/10.61173/3jae3007Keywords:
UAV, sensor fusion, reinforcement learning, experience replay, dynamic optimization, autonomous navigation, extreme environments, disaster relief, precision agricultureAbstract
This paper explores the application of artificial intelligence (AI) in the field of unmanned aerial vehicle (UAV) navigation in complex terrains. Traditional navigation systems like GPS often fail in extreme environments due to their limitations. AI techniques, such as reinforcement learning, enhance the UAV’s adaptability, offering a solution to these challenges. By applying continuous optimization methods, including experience replay and dynamic model adjustments, UAVs improve their decision-making capabilities. This results in a more powerful ability to operate effectively in various applications, such as disaster relief and precision agriculture. The integration of AI enables drones to autonomously learn and adapt to new conditions, reducing the need for human intervention and lowering costs. As a result, UAVs are becoming increasingly vital in our daily lives, providing innovative solutions in challenging environments where traditional methods fall short.References
[1] Zahran S., Moussa A., El-Sheimy N. Enhanced UAV navigation in GNSS denied environment using repeated dynamics pattern recognition. IEEE/ION Position, Location and Navigation Symposium, 2018, 1135-1142.
[2] Yijing Z., Zheng Z., Xiaoyi Z. Q learning algorithm based UAV path learning and obstacle avoidance approach. Chinese Control Conference (CCC), 2017, 3397-3402.
[3] Chriki A., Touati H., Snoussi H. Centralized cognitive radio based frequency allocation for UAVs communication. IWCMC, 2019, 1674-1679.
[4] Hung G. L., Sahimi M. S. B., Samma H. Faster R-CNN deep learning model for pedestrian detection from drone images. SN Comput Sci., 2020, 1:1-9.
[5] Bithas P. S., Michailidis E. T., Nomikos N. A survey on machine-learning techniques for UAV-based communications. Sensors, 2019, 19(23): 5170.
[6] Australia’s Bushfire Disaster: How Drones are Supporting Emergency Responders. Wildfire Today, 2020.
[7] Virnodkar S. S., Pachghare V. K., Patil V., Jha S. K. Remote sensing and machine learning for crop water stress determination in various crops: A critical review. Precis Agric., 2020, 21(5): 1121-1155.
[8] Precision Agriculture Research at Lancaster University. Lancaster University, 2019.
[9] Khan N. A., Jhanjhi N. Z., Brohi S. N. UAV’s applications, architecture, security issues and attack scenarios: A survey. Springer, 2020, 753-760.
[10] Zahran S., Moussa A., El-Sheimy N. Enhanced UAV navigation in GNSS denied environment using repeated dynamics pattern recognition. IEEE/ION Position, Location, and Navigation Symposium, 2018, 1135-1142.
[11] Yijing Z., Zheng Z., Xiaoyi Z. Q learning algorithm based UAV path learning and obstacle avoidance approach. Chinese Dean&Francis ISSN 2959-6157 Control Conference (CCC), 2017, 3397-3402.
[12] Chriki A., Touati H., Snoussi H. Centralized cognitive radio-based frequency allocation for UAVs communication. IWCMC, 2019, 1674-1679.
[13] Hung G. L., Sahimi M. S. B., Samma H. Faster R-CNN deep learning model for pedestrian detection from drone images. SN Comput Sci., 2020, 1:1-9.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
