Data-Centric Post-Training Framework for Improving Autonomous Driving Performance
Keywords:
autonomous driving; data-centric AI; post-training; machine learning systems; safety validation; data governance; socio-technical infrastructure; model deploymentAbstract
Autonomous driving systems increasingly depend not only on large pre-trained perception and planning models but also on disciplined post-training processes that adapt those models to operational realities. This paper develops a data-centric post-training framework for improving autonomous driving performance while treating data curation, infrastructure, governance, validation, and deployment as coupled system-level concerns. The argument is that post-training should not be understood as a narrow model optimization step but as a socio-technical lifecycle in which fleet telemetry, scenario mining, annotation quality, simulation fidelity, safety validation, and policy constraints continuously reshape model behavior. The framework emphasizes structural trade-offs among coverage, cost, latency, interpretability, fairness, and regulatory accountability. It examines how data-centric adaptation can improve long-tail robustness, reduce silent failure modes, support regional generalization, and enable more transparent safety cases. It also considers risks such as feedback loops, representational bias, overfitting to simulator artifacts, unsustainable data pipelines, and governance fragmentation. By integrating insights from machine learning systems, safety engineering, fairness research, and technology policy, the paper proposes an architecture and institutional logic for post-training that is robust, auditable, and sustainable. The conclusion is that autonomous driving performance gains will depend less on isolated model innovation than on the quality of data institutions that determine what is collected, labeled, validated, deployed, and contested over time.
References
1. Geiger, A., Lenz, P., & Urtasun, R. (2012). Are we ready for autonomous driving? The KITTI vision benchmark suite. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 3354–3361). IEEE. https://doi.org/10.1109/CVPR.2012.6248074
2. Caesar, H., Bankiti, V., Lang, A. H., Vora, S., Liong, V. E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., & Beijbom, O. (2020). nuScenes: A multimodal dataset for autonomous driving. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 11621–11631). IEEE. https://doi.org/10.1109/CVPR42600.2020.01164
3. Sun, P., Kretzschmar, H., Dotiwalla, X., Chouard, A., Patnaik, V., Tsui, P., Guo, J., Zhou, Y., Chai, Y., Caine, B., Vasudevan, V., Han, W., Ngiam, J., Zhao, H., Timofeev, A., Ettinger, S., Krivokon, M., Gao, A., Joshi, A., ... Anguelov, D. (2020). Scalability in perception for autonomous driving: Waymo Open Dataset. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 2446–2454). IEEE. https://doi.org/10.1109/CVPR42600.2020.00252
4. Codevilla, F., Müller, M., López, A., Koltun, V., & Dosovitskiy, A. (2018). End-to-end driving via conditional imitation learning. In 2018 IEEE International Conference on Robotics and Automation (pp. 4693–4700). IEEE. https://doi.org/10.1109/ICRA.2018.8460487
5. Bojarski, M., Del Testa, D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., Jackel, L. D., Monfort, M., Muller, U., Zhang, J., Zhang, X., Zhao, J., & Zieba, K. (2016). End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316.
6. Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., & Koltun, V. (2017). CARLA: An open urban driving simulator. In Proceedings of the 1st Annual Conference on Robot Learning (pp. 1–16). PMLR.
7. Sculley, D., Holt, G., Golovin, D., Davydov, E., Phillips, T., Ebner, D., Chaudhary, V., Young, M., Crespo, J.-F., & Dennison, D. (2015). Hidden technical debt in machine learning systems. In Advances in Neural Information Processing Systems (Vol. 28, pp. 2503–2511). Curran Associates.
8. Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., & Mané, D. (2016). Concrete problems in AI safety. arXiv preprint arXiv:1606.06565.
9. Gebru, T., Morgenstern, J., Vecchione, B., Vaughan, J. W., Wallach, H., Daumé III, H., & Crawford, K. (2021). Datasheets for datasets. Communications of the ACM, 64(12), 86–92. https://doi.org/10.1145/3458723
10. Yang, R., Wang, M., Chen, Y., Guo, T., Xu, Y., Cui, C., ... & Su, L. (2026). Post-Training in End-to-End Autonomous Driving. arXiv preprint arXiv:2607.08072.
11. Mitchell, M., Wu, S., Zaldivar, A., Barnes, P., Vasserman, L., Hutchinson, B., Spitzer, E., Raji, I. D., & Gebru, T. (2019). Model cards for model reporting. In Proceedings of the Conference on Fairness, Accountability, and Transparency (pp. 220–229). ACM. https://doi.org/10.1145/3287560.3287596
12. Breiman, L. (2001). Statistical modeling: The two cultures. Statistical Science, 16(3), 199–231. https://doi.org/10.1214/ss/1009213726
13. Shalev-Shwartz, S., Shammah, S., & Shashua, A. (2017). On a formal model of safe and scalable self-driving cars. arXiv preprint arXiv:1708.06374.
14. Kalra, N., & Paddock, S. M. (2016). Driving to safety: How many miles of driving would it take to demonstrate autonomous vehicle reliability? Transportation Research Part A: Policy and Practice, 94, 182–193. https://doi.org/10.1016/j.tra.2016.09.010
15. Koopman, P., & Wagner, M. (2016). Challenges in autonomous vehicle testing and validation. SAE International Journal of Transportation Safety, 4(1), 15–24. https://doi.org/10.4271/2016-01-0128
16. Russell, S. (2019). Human compatible: Artificial intelligence and the problem of control. Viking.
17. Floridi, L., & Cowls, J. (2019). A unified framework of five principles for AI in society. Harvard Data Science Review, 1(1). https://doi.org/10.1162/99608f92.8cd550d1
18. Hancock, P. A. (2019). Some pitfalls in the promises of automated and autonomous vehicles. Ergonomics, 62(4), 479–495. https://doi.org/10.1080/00140139.2018.1498136
19. Zuboff, S. (2019). The age of surveillance capitalism: The fight for a human future at the new frontier of power. PublicAffairs.
20. National Highway Traffic Safety Administration. (2021). Standing general order on crash reporting for incidents involving vehicles equipped with automated driving systems and Level 2 advanced driver assistance systems. U.S. Department of Transportation.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Data Intelligence and AI Systems
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
