STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Advancements in Robotics Original Research

Swarm-Enabled AI for Smart Mobility and Sustainable Transport

  1. Maitri Mohanty Department of Computer Science and Engineering, Gandhi Institute of Excellent Technocrats, Ghangapatana, Bhubaneswar
  2. Rajlaxmi Biswal Department of Computer Science and Engineering, Gandhi Institute of Excellent Technocrats, Ghangapatana, Bhubaneswar
  3. Madal Sameeksha Department of Computer Science and Engineering, Gandhi Institute of Excellent Technocrats, Ghangapatana, Bhubaneswar
  4. Tanushree Patra Department of Computer Science and Engineering, Gandhi Institute of Excellent Technocrats, Ghangapatana, Bhubaneswar
  5. Subham Bisoi Department of Computer Science and Engineering, Gandhi Institute of Excellent Technocrats, Ghangapatana, Bhubaneswar

Abstract

The significant issues facing the modern urban infrastructure are the management of road traffic problems, such as severe traffic congestion, the detection of unsafe driving behavior, and road safety. The traditional ground-based surveillance systems will be helpful, but they will reach their limits in large and dynamic environments. It is because of predetermined perspectives, blindness, and the inability to scale. To designate these problems, the present study proposes a traffic monitoring swarm system utilizing a UAV (unmanned aerial vehicle). This system provides continuous aerial multi-angle surveillance, real-time behavior monitoring, and early identification of anomalies. The swarm applies a decentralized spread-control to maintain an optimal spacing between the swarm members and to avoid overlapping observation space. It identifies and monitors traffic objects such as cars, pedestrians, and two-wheelers on a frame-by-frame basis. They are analyzed based on their movements to do behavioral modeling. This system can detect abnormal driving like sudden braking, driving in the reverse direction, near crashes, and improper lane changes. Verified exceptions are reported to a central traffic control platform, which launches dynamic control actions like timing the signal, regulating localized congestion, and operator alerting. The suggested framework is checked through field experiments and simulations that are carried out in a heterogeneous urban environment. The effectiveness of the suggested method can be observed in the positive outcomes, which present the correct detection, multi-entity tracking, and anomaly classification with significant increases in flow parameters, even in the presence of communication delays, occlusion, and data association difficulties.

Keywords

References (18)

  1. Sai S, Garg A, Jhawar K, Chamola V, Sikdar B. A Comprehensive Survey on Artificial Intelligence for Unmanned Aerial Vehicles. IEEE Open Journal of Vehicular Technology. 2023;4:713-738. doi:10.1109/ojvt.2023.3316181
  2. Arshi O, Khan IU, Kaushik K, Iqbal N, Ullah I, Slimani K, editors. Unmanned Aerial Vehicles Swarm for Protecting Smart Cities: Future Trends and Challenges. Berkeley (CA): Apress; 2025.
  3. Taj S, Ma X, Liu Y, Khan R, Cheng X, Hassan H, et al. Introduction to Unmanned Aerial Vehicles Swarm and Smart Cities. Unmanned Aerial Vehicles Swarm for Protecting Smart Cities. 2025:1-43. doi:10.1007/979-8-8688-1047-3_1
  4. Beg A, Qureshi AR, Sheltami T, Yasar A. UAV-enabled intelligent traffic policing and emergency response handling system for the smart city. Personal and Ubiquitous Computing. 2020;25(1):33-50. doi:10.1007/s00779-019-01297-y
  5. Trinh M, Nguyen D, Dinh L, Nguyen M, Setiadi D, Nguyen M. Unmanned Aerial Vehicles (UAV) Networking Algorithms: Communication, Control, and AI-Based Approaches. Algorithms. 2025;18(5):244. doi:10.3390/a18050244
  6. Vardhan SS, Rupa C, Rakesh K. YOLOv5-enhanced ornithopter UAV simulator for multi-object detection. In: Shrivastava V, Bansal JC, Panigrahi BK, editors. Power Engineering and Intelligent Systems: Proceedings of PEIS 2024, volume 2. Lecture Notes in Electrical Engineering. Cham: Springer Nature; 2024. p. 309–326.
  7. Pal OK, Shovon MS, Mridha MF, Shin J. A comprehensive review of AI-enabled unmanned aerial vehicle: trends, vision, and challenges. [Preprint]. 2023. arXiv:2310.16360. doi:10.48550/arXiv.2310.16360.
  8. Ali Shah SA, Fernando X, Kashef R. A Survey on Artificial-Intelligence-Based Internet of Vehicles Utilizing Unmanned Aerial Vehicles. Drones. 2024;8(8):353. doi:10.3390/drones8080353
  9. Alam A, Jaffery ZA, Sharma H. A cost-effective computer vision-based vehicle detection system. Concurrent Engineering. 2022;30(2):148-158. doi:10.1177/1063293x211069193
  10. Mustafa FM, Jasim MA, Mejbel BG, Abdullah SB, Gati KH, Noga H, et al. Using Emergency Drones to Speed Up Hospital Alerts and Ambulance Dispatch. 2024 36th Conference of Open Innovations Association (FRUCT). 2024:409-422. doi:10.23919/fruct64283.2024.10749864
  11. Zhu Y, Wang Y, An Y, Yang H, Pan Y. Real-time vehicle detection and urban traffic behavior analysis based on UAV traffic videos on mobile devices. [Preprint]. 2024. arXiv:2402.16246. doi:10.48550/arXiv.2402.16246.
  12. Cao H, Wu Z, Yu W. Drone for Intelligent Traffic Monitoring: Current Status and Future Trends. Mechanisms and Machine Science. 2024:1133-1150. doi:10.1007/978-3-031-44947-5_88
  13. Alahvirdi D, Tuci E. Autonomous Traffic Monitoring and Management by a Simulated Swarm of UAVs. 2023 11th RSI International Conference on Robotics and Mechatronics (ICRoM). 2023:91-96. doi:10.1109/icrom60803.2023.10412448
  14. Bouassida S, Nouveliere L, Neji N, Neji J. Enhancing Road Safety: A Comparative Study Between UAV-Assisted and Autonomous Vehicles. 2024 18th International Conference on Control, Automation, Robotics and Vision (ICARCV). 2024:1118-1123. doi:10.1109/icarcv63323.2024.10821584
  15. Ahmed A, Farhan M, Eesaar H, Chong KT, Tayara H. From Detection to Action: A Multimodal AI Framework for Traffic Incident Response. Drones. 2024;8(12):741. doi:10.3390/drones8120741
  16. Sarkar DR, Rao KR, Chatterjee N. Automatic Traffic Safety Analysis using Unmanned Aerial Vehicle Technology at Unsignalized Intersections in Heterogeneous Traffic. Transportation Research Record: Journal of the Transportation Research Board. 2024;2679(2):1274-1290. doi:10.1177/03611981241266838
  17. Ma W, Chu Z, Chen H, Li M. Spatio-temporal envolutional graph neural network for traffic flow prediction in UAV-based urban traffic monitoring system. Scientific Reports. 2024;14(1). doi:10.1038/s41598-024-78335-0
  18. Liu S, Bai Y. Multiple UAVs collaborative traffic monitoring with intention-based communication. Computer Communications. 2023;210:116-129. doi:10.1016/j.comcom.2023.08.005
Support