Hybrid Autonomous Unmanned Aerial Vehicle with Adaptive Task Allocation and Peer-to-Peer Communication for Surveillance Monitoring System | IJCSE Volume 9 – Issue 6 | IJCSE-V9I6P1

In the context of rapidly advancing smart city infrastructure and disaster management systems, autonomous aerial platforms have emerged as pivotal tools for real-time monitoring, anomaly detection, and adaptive decision-making. This study presents a Hybrid Autonomous Unmanned Aerial Vehicle (UAV) Framework that incorporates decentralized multi-UAV coordination, dynamic task allocation, and peer-to-peer communication to achieve resilient and intelligent surveillance operations. Unlike conventional centralized control mechanisms, the proposed system adopts a distributed intelligence model, enhancing fault tolerance, scalability, and energy efficiency under varying environmental conditions. Each UAV in the network is equipped with multimodal sensing units, integrating YOLO-based visual object detection for identifying vehicles, humans, animals, and abnormal events, along with acoustic anomaly recognition to improve environmental perception. The drones collaboratively perform surveillance tasks through an adaptive task allocation mechanism, redistributing workloads according to energy constraints, detection relevance, and spatial coverage requirements. Peer-to-peer communication facilitates real-time information sharing and cooperative path optimization without the need for a central processing node. For navigation and swarm control, the framework combines an Improved Artificial Potential Field (APF) for obstacle avoidance, Bidirectional RRT* for path optimization, and reinforcement learning algorithms to refine coordination strategies through experience-based adaptation. The proposed design would be implemented and validated in simulation environments thereby, it addresses the key challenges in urban surveillance, including coverage gaps, energy-aware coordination, and distributed decision-making. It offers a scalable and modular foundation for traffic monitoring, crowd analysis, and emergency management, contributing to the advancement of intelligent UAV-based surveillance architectures

This paper presents a conceptual framework for a hybrid autonomous UAV system designed for intelligent surveillance monitoring. The proposed architecture integrates adaptive task allocation, peer-to-peer communication, and multimodal anomaly detection to enable decentralized, scalable, and energy-aware aerial monitoring. The system design leverages YOLO-based visual recognition and audio anomaly classification, coordinated through MQTT-based communication and hybrid path planning strategies including Improved APF, Bidirectional RRT*, and adaptive reinforcement learning. The design emphasizes modularity, transparency, and real-world applicability, targeting use cases in smart-city surveillance, disaster response, and security monitoring. This conceptual model lays the groundwork for future simulation, validation, and deployment. The proposed Hybrid Autonomous UAV System currently represents a conceptual framework aimed at addressing the key challenges of decentralized aerial surveillance and adaptive mission control. Future research would focus on transforming this design into a fully functional simulation environment where the mechanisms for multi-drone coordination, adaptive task allocation, and peer-to-peer communication would be systematically validated under dynamic and controlled conditions. Also, planned field trials would focus on evaluating the system’s operational performance in traffic surveillance, crowd monitoring, and emergency response applications, thereby bridging the gap between simulation and practical implementation in intelligent aerial monitoring systems

[1]Pu Jin et al., “Anomaly Detection in Aerial Videos with Transformers,” IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–13, 2023. doi: 10.1109/TGRS.2022.3198130. [2]M. Alshammari et al., “Crowd Behaviour Detection: Leveraging Video Swin Transformer for Crowd Size and Violence Level Analysis,” Applied Intelligence, vol. 54, pp. 10709–10730, 2024. https://doi.org/10.1007/s10489-024-05775-6. [3]M.H. Habeb, M. Salama, and L.A. Elrefaei, “Enhancing Video Anomaly Detection Using a Transformer Spatiotemporal Attention Unsupervised Framework for Large Datasets,” Algorithms, vol. 17, p. 286, 2024. [4]H. Khalil et al., “A UAV-Swarm-Communication Model Using a Machine-Learning Approach for Search-and-Rescue Applications,” Drones, vol. 6, pp. 372, 2022. [5]A. Alotaibi et al., “A Secure Communication Framework for Drone Swarms in Autonomous Surveillance Operations,” Journal of Computer and Communications, vol. 12, pp. 1-25, 2024. [6]S. Kumaran et al., “IoT-Based Autonomous Search and Rescue Drone for Precision Firefighting,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 11, 2023. [7]M. Eşer and A.E. Yılmaz, “Distributed Task Allocation for UAV Swarms with Limited Communication,” Sakarya University Journal of Computer and Information Sciences, vol. 7, 2024. [8]E. Nebe et al., “Chaos Detection and Mitigation in Swarm of Drones,” International Journal of Advanced Computer Science and Applications, vol. 13, no. 6, 2022. [9]A. Arsalan et al., “Next-Gen Internet of Drones: Federated Learning and Digital Twin Synergy for Energy-Efficient Task Allocation and Seamless Service Migration,” in IEEE Access, vol. 13, pp. 64459-64472, 2025, doi: 10.1109/ACCESS.2025.3558439. [10]M. Yahuza et al., “Internet of Drones Security and Privacy Issues: Taxonomy and Open Challenges,” in IEEE Access, vol. 9, pp. 57243-57270, 2021, doi: 10.1109/ACCESS.2021.3072030. [11]R. Arranz et al., “Application of Deep Reinforcement Learning to UAV Swarming for Ground Surveillance,” Sensors, vol. 23, no. 21, p. 8766, 2023. [12]S. Kümmritz, “The Sound of Surveillance: Enhancing ML via Acoustic Signatures,” Drones, vol. 8, p. 105, 2024. [13]B. Niu et al., “Path planning for unmanned aerial vehicles in complex environment based on an improved continuous ant colony optimisation,” Computers & Electrical Engineering, vol. 123, p. 110034, 2024, https://doi.org/10.1016/j.compeleceng.2024.110034. [14]A. Kamil and B. Mahmood, “Integrating Path Planning and Task Scheduling in Autonomous Drone Operations,” Applied Computer Science, vol. 21, pp. 1–17, 2025, https://doi.org/10.35784/acs_6872. [15]Y. Huang et al., “A 3D Path Planning Algorithm for UAVs Based on an Improved Artificial Potential Field and Bidirectional RRT*”, Drones, vol. 8, no. 12, p. 760, 2024. [16]C. Zammit, “Real-time 3D UAV Path Planning in Dynamic Environments with Uncertainty,” International Journal of Intelligent Unmanned Systems, vol. 13, pp. 1-18, 2022, https://doi.org/10.1142/S2301385023500073. [17]T. Zhang et al., “UAV 3D Path Planning Using Improved Artificial Fish Swarm Algorithm,” Drones, vol. 7, pp. 636, 2023. [18]Z. Zhang, J. Jiang, H. Xu, and W.-A. Zhang, “Distributed dynamic task allocation for unmanned aerial vehicle swarm systems: A networked evolutionary game-theoretic approach,” Chinese Journal of Aeronautics, vol. 37, pp. 182–204, 2024, https://doi.org/10.1016/j.cja.2023.12.027. [19]R. Nasir et al., “An Enhanced Framework for Real-Time Dense Crowd Abnormal Behaviour Detection Using YOLOv8,” Artificial Intelligence Review, vol. 58, 2025, https://doi.org/10.1007/s10462-025-11206-w. [20]N.S. Albalawi, “High-Precision Multi-Class Object Detection Using YOLOv11,” International Journal of Advanced Computer Science and Applications, vol. 16, 2025. [21]Pavithra S., “Panoramic Video Surveillance: Burglary Detection via YOLO,” Journal of Computer Science, vol. 19, pp. 1345–1358, 2023. [22]Ivan Tan et al., “Runtime Anomaly Detection for Drones: An Integrated Rule-Mining and Unsupervised-Learning Approach,” arXiv, 2025. [23]R.J.A.A. Nathan et al., “An Autonomous Drone Swarm for Detecting and Tracking Anomalies Among Dense Vegetation,” arXiv, 2024. [24]Y. Alqudsi and M. Makaraci, “UAV Swarms: Research, Challenges, and Future Directions,” Journal of Engineering and Applied Science, vol. 72, no. 1, pp. 1–22, Jan. 2025. https://doi.org/10.1186/s44147-025-00582-3. A. Sharma et al., “The Rise of UAV-Based Smart Surveillance: A Systematic Review of Trends and Technologies,” IEEE Access, vol. 13, pp. 11203961–11203978, 2025. doi: 10.1109/ACCESS.2025.3621736.

Call for Paper (Hub) Fast Paper Publication IJCSE Indexing & Databases Submit Manuscript Call for Paper: Sep–Oct 2025 Call for Paper: Publish Research