AI-Driven Trajectory optimization for precise targeting in Anti- Terrorism operation
Mr. Chetan Ghatge (Author),RNSIT Email : chetanghatage@rnsit.ac.in
Supreeth S Athreyas (Author), RNSIT Email : 1rn21ei043.supreethsathreyas@rnsit.ac.in
Srilakshmi K P Hebbar (Author), RNSIT Email : 1rn21ei039.srilakshmikphebbar@rnsit.ac.in
Abstract
The growing complexity of security threats, especially in counter-terrorism operations, demands advanced technological solutions that integrate artificial intelligence (AI), unmanned aerial vehicles (UAVs), and real-time trajectory optimization. This study introduces an AI-powered UAV trajectory optimization system aimed at enhancing precision targeting and surveillance in anti-terrorism applications. By incorporating deep learning-based object detection, fractional-order PID (FOPID) control, and adaptive flight path optimization, the proposed system achieves superior tracking accuracy, manoeuvrability, and operational efficiency in dynamic environments.
The UAV leverages YOLOv8 with Contextual Transformer Modules to improve object detection accuracy, even in challenging scenarios involving low visibility, occlusions, and high-speed target movement. Additionally, the implementation of a FOPID controller enhances flight stability and response precision, resulting in a 30 percent reduction in settling time and improved trajectory control compared to conventional PID controllers. The Hardware-in-the-Loop (HIL) simulation methodology is employed to replicate real-world conditions, ensuring the system's reliability and performance optimization.
Experimental validation highlights the UAV’s effectiveness in border security, counter-infiltration surveillance, and large-scale monitoring, with successful detection and tracking of unauthorized movements at distances of up to 300 meters. Furthermore, the integration of heat-seeking sensors and thermal imaging technology enhances target recognition in low-visibility conditions. The system also features secure Wi-Fi communication and real-time data transmission, enabling seamless coordination with security forces.
The AI-driven trajectory optimization framework significantly enhances UAV-based threat detection, energy efficiency, and autonomous adaptability, making it a scalable and dependable solution for national security applications. Future work will focus on advancing multi-agent UAV collaboration, ethical AI integration, and strengthening cybersecurity measures to further improve autonomous surveillance and threat mitigation capabilities.
