https://doi.org/10.46793/TIL2025.240C DOI ikonica

EXPLAINABLE ARTIFICIAL INTELLIGENCE FOR TRUSTWORTHY EDGE-BASED ROAD INTERSECTION MANAGEMENT

Authors:

Žarko Ćojbašić https://orcid.org/0000-0002-4581-1048
Faculty of Mechanical Engineering, University of Niš, Serbia
Goran Petrović https://orcid.org/0000-0002-3562-9576
Faculty of Mechanical Engineering, University of Niš, Serbia
Dejan Rančić https://orcid.org/0000-0002-9445-7700
Faculty of Electronic Engineering, University of Niš, Serbia
Emilija Ćojbašić https://orcid.org/0009-0008-3843-6703
Faculty of Electronic Engineering, University of Niš, Serbia
Nemanja Marković
Faculty of Mechanical Engineering, University of Niš, Serbia
Bratislav Lukić https://orcid.org/0009-0004-1397-8195
Faculty of Mechanical Engineering, University of Niš, Serbia

Abstract: Artificial Intelligence (AI) is increasingly applied to road intersection management to optimize traffic flow, reduce congestion, and improve safety. However, the opaque nature of AI-based decisions can undermine trust and limit adoption in intelligent transportation systems. This paper extends research on AI-driven intersection management by integrating Explainable Artificial Intelligence (XAI) methods ensuring the decisions of AI are interpretable and trustworthy for real-world deployment by traffic management authorities. A YOLO-based model is used for vehicle detection and traffic state recognition, while XAI techniques are applied to provide interpretable insights into system decisions. Implementation on the NVIDIA Edge AI device is considered and tested on a large dataset of real-world road scenes with multiple traffic objects, including various vehicle types and pedestrians. Results from experiments show that XAI integration enhances system comprehensibility without significantly reducing performance. These findings underline the importance of explainability for deploying trustworthy, accountable, and safe AI solutions in road intersection management.

Keywords: Explainable Artificial Intelligence (XAI); Edge AI; Deep Learning; YOLO; Intersection Management

Pages: 240-243

The paper is available at the following link: Pregled rada...

REFERENCES:

1. Saadi, A., Abghour, N., Chiba, Z., Moussaid, K. and Ali, S., 2025. A survey of reinforcement and deep reinforcement learning for coordination in intelligent traffic light control. Journal of Big Data, 12(1), pp.1-20.
2. Khan, S., Ghazal, T.M., Alyas, T., Waqas, M., Raza, M.A., Ali, O., Khan, M.A. and Abbas, S., 2025. Towards Transparent Traffic Solutions: Reinforcement Learning and Explainable AI for Traffic Congestion. International Journal of Advanced Computer Science and Applications (IJACSA), 16(1), pp.503-511.
3. Liu, X. et al, (2025). From Black Box to Glass Box: A Practical Review of Explainable Artificial Intelligence (XAI). AI, 6(11), 285.
4. Liu, G., Shi, H., Kiani, A., Khreishah, A., Lee, J., Ansari, N., Liu, C. and Yousef, M.M., 2022. Smart Traffic Monitoring System Using Computer Vision and Edge Computing, IEEE Transactions on Intelligent Transportation Systems, 23(8), pp.12027–12038.
5. Agrahari, A., Dhabu, M.M., Deshpande, P.S., Tiwari, A., Baig, M.A. and Sawarkar, A.D., 2024. Artificial intelligence-based adaptive traffic signal control system: A comprehensive review, Electronics, 13(19), p.3875.
6. Prajapati, M., Upadhyay, A. K., Patil, H. & Dongradive, J. , 2024, A Review of Deep Reinforcement Learning for Traffic Signal Control, International Journal for Multidisciplinary Research (IJFMR), 6(1), pp. 1-13.
7. Singh, R. and Gill, S.S., 2023, Edge AI: A survey, Internet of Things and Cyber-Physical Systems, 3, pp. 71–92.
8. Gong, T., Zhu, L. and Tang, T., 2023, Edge Intelligence in Intelligent Transportation Systems: A Survey, IEEE Transactions on Intelligent Transportation Systems, 24(9), pp. 8919-8944.
9. Wei, J. et al., 2025, A Review of YOLO Algorithm and Its Applications in Autonomous Driving Object Detection, IEEE Access, early access, DOI: 10.1109/ACCESS.2025.3573376.
10. Wang, J. and Shang, P., 2024, Edge Computing Application of Expressway Intelligent Transportation System Based on IoT Technology, Computing and Informatics, 43(4), pp. 974–992.
11. Milić, P., Marinković, D., Klinge, S. and Ćojbašić, Ž., 2023. Reissner-Mindlin based isogeometric finite element formulation for piezoelectric active laminated shells, Tehnički vjesnik, 30(2), pp.416-425.
12. Abusitta, A., Li, M.Q. and Fung, B.C., 2024, Survey on Explainable AI: Techniques, challenges and open issues. Expert Systems with Applications, 255, p.124710.
13. Sarıdoğan, Y.B. (2023) Traffic Detection Project [dataset]. Kaggle. Available at: https://www.kaggle.com/datasets/
yusufberksardoan/traffic-detection-project, (Accessed 15th November 2025).
14. A. Kuznietsov et. Al, 2024, Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review," IEEE Transactions on Intelligent Transportation Systems, vol. 25, no. 12, pp. 19342-19364.