A ROS2-Based Autonomous UAV Software Framework with YOLO-Driven Multi-Sensor Surveillance for Law Enforcement: A Simulation Study

Year : 2026 | Volume : 04 | Issue : 02 | Page : 1 10
By

Shivam Kumar,

Bhoomi Roy,

Mohammad Shahrookh Husain,

Abhijeet Das,

Rahul Verma,

Digant Mondal,

  1. Student, Department of Computer Science and Engineering, Greater Noida Institute of Technology (GGSIPU), Greater Noida, Uttar Pradesh, India
  2. Student, Department of Computer Science and Engineering, Greater Noida Institute of Technology (GGSIPU), Greater Noida, Uttar Pradesh, India
  3. Student, Department of Computer Science and Engineering, Greater Noida Institute of Technology (GGSIPU), Greater Noida, Uttar Pradesh, India
  4. Student, Department of Computer Science and Engineering, Greater Noida Institute of Technology (GGSIPU), Greater Noida, Uttar Pradesh, India
  5. Student, Department of Computer Science and Engineering, Greater Noida Institute of Technology (GGSIPU), Greater Noida, Uttar Pradesh, India
  6. Assistant Professor, Department of Computer Science and Engineering, Greater Noida Institute of Technology (GGSIPU), Greater Noida, Uttar Pradesh, India

Abstract

The rapid proliferation of drone technology in India and worldwide has presented new opportunities to law enforcement agencies to enhance the methods used to monitor and patrol, and respond to threats to security. This paper introduces a full software system for a ROS2-based autonomous unnamed aerial vehicle (UAV) system for law enforcement surveillance. The system, validated entirely via high-fidelity simulation using Gazebo Classic and PX4 Software-in-the-Loop (SITL), uses a combination of YOLO-based real-time object detection with a three-sensor perception stack of RGB, thermal, and depth cameras. Navigation is implemented with an ORB-SLAM3 based environments. The framework is based on a modular ROS2 node architecture where clean separation between perception, navigation, control, and security modules is possible. Encrypted DDS communication and a human-in-the-loop supervisory interface are part of the design to ensure that the system is accountable and ethical. Simulation results project a mean average precision (mAP@50) greater than 92%, real-time interference greater than 30 FPS on edge-class hardware and patrol area coverage greater than 95% across simulated 15-minute urban missions. The hardware implementation of this framework using physical components of UAV’s is considered as future work. This study makes a replicable and open architecture blueprint for next-generation intelligent aerial patrol systems in the Indian public safety scenarios.

Keywords: ROS2, autonomous UAV, YOLO object detection, multi-sensor fusion, SLAM navigation, law enforcement surveillance, simulation framework, edge AI, human-in-the-loop, India drone policy

[This article belongs to International Journal of Robotics and Automation in Mechanics ]

How to cite this article: Shivam Kumar, Bhoomi Roy, Mohammad Shahrookh Husain, Abhijeet Das, Rahul Verma, Digant Mondal. A ROS2-Based Autonomous UAV Software Framework with YOLO-Driven Multi-Sensor Surveillance for Law Enforcement: A Simulation Study. International Journal of Robotics and Automation in Mechanics. 2026; 04(02):1-10.
How to cite this URL: Shivam Kumar, Bhoomi Roy, Mohammad Shahrookh Husain, Abhijeet Das, Rahul Verma, Digant Mondal. A ROS2-Based Autonomous UAV Software Framework with YOLO-Driven Multi-Sensor Surveillance for Law Enforcement: A Simulation Study. International Journal of Robotics and Automation in Mechanics. 2026; 04(02):1-10. Available from: https://journals.stmjournals.com/ijram/article=2026/view=259692

References

  1. MarketsandMarkets, “India Drone (UAV) Market – Forecast to 2030,” MarketsandMarkets Research, 2025. [Online]. Available: https://www.marketsandmarkets.com/Market-Reports/india-drone-market-136782206.html
  2. Bureau of Police Research and Development (BPRD), “Drone: A New Age Policing Tool,” Ministry of Home Affairs, Government of India, Project Report No. 13/MM:03. [Online]. Available: https://bprd.nic.in/uploads/pdf/Drone%20A%20New%20Age%20Polcing%20Tool.pdf
  3. Macenski, T. Foote, B. Gerkey, C. Lalancette, and W. Woodall, “Robot Operating System 2: Design, architecture, and uses in the wild,” Science Robotics, vol. 7, no. 66, p. eabm6074, 2022. doi: 10.1126/scirobotics. abm6074
  4. Zhang et al., “RTUAV-YOLO: A Family of Efficient and Lightweight Models for Real-Time Object Detection in UAV Aerial Imagery,” Sensors, vol. 25, no. 21, p. 6573, 2025. doi: 10.3390/s25216573
  5. Thermal-RGB Fusion with Lightweight CNNs for Night-Time Drone Surveillance and Real-Time Adaptive Sensor Selection, Problems of Information Technology, vol. 16, no. 2, pp. 45–55, 2025. [Online]. Available: https://jpit.az/uploads/article/en/2025_2/
  6. Munguia, A. Grau, Y. Bolea, and G. Obregón-Pulido, “A Simultaneous Control, Localization, and Mapping System for UAVs in GPS-Denied Environments,” Drones, vol. 9, no. 1, p. 69, 2025. doi: 10.3390/drones9010069
  7. Bhaskar, K. Dolaskar, H. Jadhav, M. Shirke, and K. Kulkarni, “Autonomous Navigation and Object Detection Using ROS 2 and YOLOv8,” International Journal of Scientific Research in Engineering and Management (IJSREM), 2024. [Online]. Available: https://ijsrem.com/download/autonomous-navigation-and-object-detection-using-ros-2-and-yolov8/
  8. Yallamraju et al., “Dynamic Object Detection and Tracking System on Unmanned Aerial Vehicles for Surveillance Applications Using RegionViT-Based Adaptive Multi-Scale YOLOv8,” Computational Intelligence, Wiley, July 2025. doi: 10.1111/coin.70101
  9. Munguia, A. Grau, Y. Bolea, and G. Obregón-Pulido, “A Simultaneous Control, Localization, and Mapping System for UAVs in GPS-Denied Environments,” Drones, vol. 9, no. 1, p. 69, Jan. 2025. doi: 10.3390/drones9010069
  10. Zhang et al., “RTUAV-YOLO: A Family of Efficient and Lightweight Models for Real-Time Object Detection in UAV Aerial Imagery,” Sensors, vol. 25, no. 21, p. 6573, 2025. doi: 10.3390/s25216573
  11. Fan, Y. Li, M. Deveci, K. Zhong, and S. Kadry, “LUD-YOLO: A Novel Lightweight Object Detection Network for Unmanned Aerial Vehicle,” Information Sciences, vol. 686, p. 121366, Jan. 2025. doi: 10.1016/j.ins.2024.121366
  12. S. Mahdi, K. R. Kumar, and K. J. D. Christopher, “Real-Time Drone Communication System Using ROS 2 and GStreamer with YOLOv8Seg for Face Segmentation,” International Journal of Computational and Experimental Science and Engineering, vol. 11, no. 2, 2025. [Online]. Available: https://ijcesen.com/index.php/ijcesen/article/view/2123
  13. “Thermal-RGB Fusion with Lightweight CNNs for Night-Time Drone Surveillance and Real-Time Adaptive Sensor Selection,” Problems of Information Technology, vol. 16, no. 2, pp. 45–55, 2025.
  14. Wu et al., “RMF-ED: Real-Time Multimodal Fusion for Enhanced Target Detection in Low-Light Environments,” IET Cyber-Systems and Robotics, Apr. 2025. doi: 10.1049/csy2.70011
  15. “Enhancing Low-Light RGB-D Pedestrian Detection Through Dual-Stage Modality-Guided Fusion,” The Visual Computer, Springer, Dec. 2025. doi: 10.1007/s00371-025-04237-5
  16. Jiang et al., “GPS-Denied LiDAR-Based SLAM — A Survey,” IET Cyber-Systems and Robotics, Nov. 2025. doi: 10.1049/csy2.70031
  17. Wang et al., “UAV-Based Simultaneous Localization and Mapping in Outdoor Environments: A Systematic Scoping Review,” Journal of Field Robotics, Wiley, Apr. 2024. doi: 10.1002/rob.22325
  18. “RGB-D Camera and Graph Neural Network-Based SLAM for Dynamic and Low-Texture Environments,” Scientific Reports, Nature, Aug. 2025. doi: 10.1038/s41598-025-12978-5
  19. Alsadie, “Cybersecurity and Artificial Intelligence in Unmanned Aerial Vehicles: Emerging Challenges and Advanced Countermeasures,” IET Information Security, Wiley, Oct. 2025. doi: 10.1049/ise2/2046868
  20. “Cyber Threat in Drone Systems: Bridging Real-Time Security, Legal Admissibility, and Digital Forensic Solution Readiness,” Frontiers in Communications and Networks, Aug. 2025. doi: 10.3389/frcmn.2025.1661928
  21. “Securing UAV Communication: Authentication and Integrity,” arXiv:2410.09085, Oct. 2024. [Online]. Available: https://arxiv.org/html/2410.09085v1
  22. Khaledi, “px4_sim_ros2: Drone Simulation with ROS2, PX4, NAV2 and GZ,” GitHub Repository, 2024. [Online]. Available: https://github.com/ParsaKhaledi/px4_sim_ros2
  23. Monemati, “PX4-ROS2-Gazebo-YOLOv8: Aerial Object Detection using a Drone with PX4 Autopilot and ROS 2,” GitHub Repository, 2024. [Online]. Available: https://github.com/monemati/PX4-ROS2-Gazebo-YOLOv8
  24. “ASFN: An RGB-T Adaptive Selection Fusion Network for Nighttime Tracking,” in Proceedings of the 2024 International Conference on Intelligent Perception and Pattern Recognition (IPPR), ACM, 2024. doi: 10.1145/3700035.3700054
Regular Issue Subscription Review Article
Volume 04
Issue 02
Received 27/06/2026
Accepted 11/07/2026
Published 09/10/2026
Publication Time 104 Days

Login

My IP

PlumX Metrics

Support