UAV Detection Using Reinforcement Learning
Unmanned Aerial Vehicles (UAVs) have gained significant popularity in both military and civilian applications due to their cost-effectiveness and flexibility. However, the increased utilization of UAVs raises concerns about the risk of illegal data gathering and potential criminal use. As a result,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/6/1870 |
| _version_ | 1797239368656617472 |
|---|---|
| author | Arwa AlKhonaini Tarek Sheltami Ashraf Mahmoud Muhammad Imam |
| author_facet | Arwa AlKhonaini Tarek Sheltami Ashraf Mahmoud Muhammad Imam |
| author_sort | Arwa AlKhonaini |
| collection | DOAJ |
| description | Unmanned Aerial Vehicles (UAVs) have gained significant popularity in both military and civilian applications due to their cost-effectiveness and flexibility. However, the increased utilization of UAVs raises concerns about the risk of illegal data gathering and potential criminal use. As a result, the accurate detection and identification of intruding UAVs has emerged as a critical research concern. Many algorithms have shown their effectiveness in detecting different objects through different approaches, including radio frequency (RF), computer vision (visual), and sound-based detection. This article proposes a novel approach for detecting and identifying intruding UAVs based on their RF signals by using a hierarchical reinforcement learning technique. We train a UAV agent hierarchically with multiple policies using the REINFORCE algorithm with entropy regularization term to improve the overall accuracy. The research focuses on utilizing extracted features from RF signals to detect intruding UAVs, which contributes to the field of reinforcement learning by investigating a less-explored UAV detection approach. Through extensive evaluation, our findings show the remarkable results of the proposed approach in achieving accurate RF-based detection and identification, with an outstanding detection accuracy of 99.7%. Additionally, our approach demonstrates improved cumulative return performance and reduced loss. The obtained results highlight the effectiveness of the proposed solution in enhancing UAV security and surveillance while advancing the field of UAV detection. |
| first_indexed | 2024-04-24T17:50:26Z |
| format | Article |
| id | doaj.art-4e2288ebc630417d9b19362e50d1b164 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-24T17:50:26Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4e2288ebc630417d9b19362e50d1b1642024-03-27T14:04:00ZengMDPI AGSensors1424-82202024-03-01246187010.3390/s24061870UAV Detection Using Reinforcement LearningArwa AlKhonaini0Tarek Sheltami1Ashraf Mahmoud2Muhammad Imam3Computer Engineering Department, Interdisciplinary Research Center of Smart Mobility and Logistics, King Fahd University of Petroleum and Minerals, Dhahran 31261, Saudi ArabiaComputer Engineering Department, Interdisciplinary Research Center of Smart Mobility and Logistics, King Fahd University of Petroleum and Minerals, Dhahran 31261, Saudi ArabiaComputer Engineering Department, Interdisciplinary Research Center of Smart Mobility and Logistics, King Fahd University of Petroleum and Minerals, Dhahran 31261, Saudi ArabiaComputer Engineering Department, Interdisciplinary Research Center for Intelligent Secure Systems, King Fahd University of Petroleum and Minerals, Dhahran 31261, Saudi ArabiaUnmanned Aerial Vehicles (UAVs) have gained significant popularity in both military and civilian applications due to their cost-effectiveness and flexibility. However, the increased utilization of UAVs raises concerns about the risk of illegal data gathering and potential criminal use. As a result, the accurate detection and identification of intruding UAVs has emerged as a critical research concern. Many algorithms have shown their effectiveness in detecting different objects through different approaches, including radio frequency (RF), computer vision (visual), and sound-based detection. This article proposes a novel approach for detecting and identifying intruding UAVs based on their RF signals by using a hierarchical reinforcement learning technique. We train a UAV agent hierarchically with multiple policies using the REINFORCE algorithm with entropy regularization term to improve the overall accuracy. The research focuses on utilizing extracted features from RF signals to detect intruding UAVs, which contributes to the field of reinforcement learning by investigating a less-explored UAV detection approach. Through extensive evaluation, our findings show the remarkable results of the proposed approach in achieving accurate RF-based detection and identification, with an outstanding detection accuracy of 99.7%. Additionally, our approach demonstrates improved cumulative return performance and reduced loss. The obtained results highlight the effectiveness of the proposed solution in enhancing UAV security and surveillance while advancing the field of UAV detection.https://www.mdpi.com/1424-8220/24/6/1870radio frequencyUnmanned Aerial Vehicleshierarchical reinforcement learningdetection and identificationREINFORCE |
| spellingShingle | Arwa AlKhonaini Tarek Sheltami Ashraf Mahmoud Muhammad Imam UAV Detection Using Reinforcement Learning Sensors radio frequency Unmanned Aerial Vehicles hierarchical reinforcement learning detection and identification REINFORCE |
| title | UAV Detection Using Reinforcement Learning |
| title_full | UAV Detection Using Reinforcement Learning |
| title_fullStr | UAV Detection Using Reinforcement Learning |
| title_full_unstemmed | UAV Detection Using Reinforcement Learning |
| title_short | UAV Detection Using Reinforcement Learning |
| title_sort | uav detection using reinforcement learning |
| topic | radio frequency Unmanned Aerial Vehicles hierarchical reinforcement learning detection and identification REINFORCE |
| url | https://www.mdpi.com/1424-8220/24/6/1870 |
| work_keys_str_mv | AT arwaalkhonaini uavdetectionusingreinforcementlearning AT tareksheltami uavdetectionusingreinforcementlearning AT ashrafmahmoud uavdetectionusingreinforcementlearning AT muhammadimam uavdetectionusingreinforcementlearning |