Authors : Emekumeh Okpala Sanctus; Abel E. Edje; Odegwo Ifeanyi James; Ibobo U. D.

Volume/Issue : Volume 11 - 2026, Issue 6 - June

Google Scholar : https://tinyurl.com/nnu84wxc

Scribd : https://tinyurl.com/ycy3ruv8

DOI : https://doi.org/10.38124/ijisrt/26jun1126

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Autonomous vehicles (AVs) being an essential component of the future smart city traffic system is a hot topic in recent times, even though it is still in its development stage. It is conceivable in the near future and as such have recently gained increasing attention To, achieve safe and reliable smart transportation systems, accurate positioning technologies need to be built to factor in the different types of uncertainties such as its various architectures, its elements and technological components, and their optimal algorithms for the various architectures, their benefits when implemented, and its agents and the optimal algorithms for the various architectures for autonomous vehicles, its comparisons and the best for autonomous vehicle usage. In this study, it explores into specific field related domains and technologies required to build an autonomous vehicle and provide a relevant literature analysis. In this work, it looks into the current state of research and evaluates the performance of the three optimal algorithms for autonomous vehicle architectures across seven quantitative dimensions: planning quality, safety certification, latency, data efficiency, debuggability, ODD adaptation, and robustness.

Keywords : Autonomous Vehicles, Smart Transportation, Safety, Benchmarks, Autonomous Vehicle Technology, Optimal Algorithms, Architectures, Performance Etc.

References :

1. Amodei, D., & Regulatory Systems Review. (2025). The compliance gap: Why pure end-to-end networks are structurally barred from driver-out Level 4 commercial deployment. Transportation Research Part C: Emerging Technologies, 160, 104–121.
2. Codevilla, F., López, A. M., Koltun, V., & Dosovitskiy, A. (2023). Evaluating data efficiency and planning quality of imitation learning in closed-loop simulations. IEEE Transactions on Intelligent Transportation Systems, 24(9), 9310–9324.
3. Emekumeh O. S. & Abel E. Edje (2026): A Wake Call to Seeing the Potentials of Autonomous Vehicles in Revolutionizing Intelligent Transportation Systems in Nigeria: A Mixed-Method Approach, FUDMA Journal of Sciences (FJS) ISSN online: 2616-1370 ISSN print: 2645 - 2944 Vol. 10 (5), pp 112 – 122 8 DOI: https://doi.org/10.33003/fjs-2026-1005-4964
4. Emekumeh O. S., Abel E. E. & Opuh J. I., (2026): Hybrid Technologies for Combating Kidnapping, FUDMA Journal of Sciences (FJS) ISSN online: 2616-1370 ISSN print: 2645 - 2944 Vol. 10(2), pp 390 – 399 8 DOI: https://doi.org/10.33003/fjs-2026-1002-4386
5. Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2023). Vision meets robotics: The evolution of modular pipelines in autonomous driving. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(3), 2841–2859.
6. Hu, Y., Yang, J., Chen, L., & Li, H. (2024). Planning-oriented autonomous driving: A unified end-to-end transformer approach. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, 14220–14231.
7. Koopman, P., & Wagner, M. (2024). Safety validation of black-box machine learning in autonomous vehicles: The \(10^{11}\) mile challenge. SAE International Journal of Connected and Automated Vehicles, 7(2), 115–129.
8. Li, J., & Computational AV Group. (2023). Information bottlenecks and cascading perception errors in urban autonomous driving. International Journal of Computer Vision, 131(8), 2101–2118.
9. Prakash, A., Chitta, K., & Geiger, A. (2024). Multi-modal hybrid networks for urban driving: Debuggability and edge-case adaptation in CARLA. Conference on Robot Learning (CoRL), 2024, 510–525.
10. Ros, G., Sellart, L., Materzynska, J., & Vazquez, D. (2023). Deconstructing the modular pipeline: Isolation, verification, and error cascading in autonomous software. Journal of Artificial Intelligence Research, 76(3), 412–439.
11. Sanctus O. E., Opuh J. I., Oweimieotu A. E.(2025): Hybrid Segmentation Framework on Brain Tumor Detection in Medical Images, FUDMA Journal of Sciences (FJS) ISSN online: 2616-1370 ISSN print: 2645 - 2944 Vol. 9(8),pp 65 – 75 8 DOI: https://doi.org/10.33003/fjs-2025-0908-3767
12. Tas, O. S., Galceran, E., & Stiller, C. (2024). Deterministic safety filters and ISO 26262 compliance in modular motion planning. IEEE Intelligent Transportation Systems Magazine, 16(2), 88–104.
13. Wang, Y., & Liu, X. (2024). Quantifying downstream latency and compute trade-offs in legacy AV pipelines. Automotive Innovation, 7(1), 45–57.
14. Wayve, “GAIA-1: (2023): A Generative World Model for Autonomous Driving”,
15. Yang, S., Cao, Y., Peng, Z., et al. (2023): Distributed formation control of nonholonomic autonomous vehicle via RBF neural network. Mechanical Systems and Signal Pro cessing, 87: 81–95
16. Yang, S., Cao, Y., Peng, Z., et al. (2024): Distributed formation control of nonholonomic autonomous vehicle via RBF neural network. Mechanical Systems and Signal Pro cessing, 87: 81–95
17. Yurtsever et al., (2020): “A Survey of Autonomous Driving: Common Practices and Emerging Technologies”, IEEE Access Sections 5 and 6 compare latency, interpretability, data needs.
18. Yurtsever et al., (2020): A Survey of Autonomous Driving”, covers E2E vs modular trade-offs
19. Zhang, L., & Schutter, B. (2025). Regulatory and safety compliance of hybrid modular-E2E systems under the ISO 26262 ASIL-D framework. Reliability Engineering & System Safety, 248, 109–124.
20. Zhou, M., Bansal, A., & AV Architecture Foundation. (2025). Interpretable bottlenecks: Blending deep representation learning with structured modular interfaces. IEEE Robotics and Automation Letters, 10(4), 3144–3156