AI-Driven ADAS in Software-Defined Vehicles: Architectures, Safety Assurance, and Lifecycle Challenges
DOI:
https://doi.org/10.63282/3050-922X.ICAILLMBA-116Keywords:
Advanced Driver Assistance Systems, Software-Defined Vehicles, Deep Learning, Sensor Fusion, Bird’s-Eye View, SOTIF, Automotive CybersecurityAbstract
Advanced Driver Assistance Systems (ADAS) Advanced Driver Assistance Systems (ADAS) are rapidly evolving toward AI-driven, software-defined vehicle (SDV) architectures. Despite significant advances, ensuring robust safety, validation, cybersecurity, and driver trust remains a critical challenge. This paper presents a structured review of recent developments in ADAS, focusing on deep-learning-based perception, multimodal sensor fusion, centralized and zonal computing, and lifecycle-oriented safety governance. A qualitative review methodology is adopted, analyzing peer-reviewed literature, international standards, and industry reports published between 2018 and 2025. The results indicate a clear shift from rule-based systems to data-driven architectures using Bird’s-Eye View representations, transformer-based models, and over-the-air software updates. The study concludes that a holistic lifecycle approach integrating AI performance monitoring, SOTIF, cybersecurity, and human-centered design is essential for the safe and trustworthy deployment of ADAS in software-defined vehicles.
References
[1] World Health Organization, Global Status Report on Road Safety, Geneva, Switzerland, 2018. [Online]. Available: https://www.who.int/publications/i/item/9789241565684
[2] European Commission, Road Safety in the EU, Brussels, Belgium, 2023. [Online]. Available: https://road-safety.transport.ec.europa.eu/index_en
[3] P. S. Chib and P. Singh, “Recent advancements in end-to-end autonomous driving using deep learning: A survey,” IEEE Trans. Intell. Vehicles, vol. 9, no. 1, pp. 103–118, 2024, doi: 10.1109/TIV.2023.3318070.
[4] SAE International, J3016: Taxonomy and Definitions for Terms Related to Driving Automation Systems, Warrendale, PA, USA, 2021. [Online]. Available: https://www.sae.org/standards/content/j3016_202104/
[5] S. Favelli, M. Xie, and A. Tonoli, “Sensor fusion method for object detection and distance estimation in assisted driving applications,” Sensors, vol. 24, no. 24, Art. no. 7895, 2024, doi: 10.3390/s24247895.
[6] H. Winner, S. Hakuli, and F. Lotz, Eds., Handbook of Driver Assistance Systems. Cham, Switzerland: Springer, 2016, doi: 10.1007/978-3-319-12352-3.
[7] R. Isnardi and S. White, “Centralized automotive compute platforms,” SAE Tech. Paper 2020-01-0123, 2020, doi: 10.4271/2020-01-0123.
[8] J. Janai, F. Güney, and A. Behl, “Computer vision for autonomous vehicles,” Foundations Trends Comput. Graph. Vis., 2020, doi: 10.1561/0600000079.
[9] A. Vaswani et al., “Attention is all you need,” in Advances in Neural Information Processing Systems (NeurIPS), 2017. [Online]. Available: https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf
[10] Y. Ma et al., “Vision-centric BEV perception: A survey,” IEEE Trans. Pattern Anal. Mach. Intell., 2024, doi: 10.1109/TPAMI.2024.3449912.
[11] Bosch, Software-Defined Vehicle Architecture, 2024. [Online]. Available: https://www.bosch-mobility.com/en/solutions/software-defined-vehicle/
[12] NVIDIA, DRIVE Hyperion Architecture, 2025. [Online]. Available: https://www.nvidia.com/en-us/self-driving-cars/hyperion/
[13] G. Elinoff, “Zonal architecture: The next phase for software-defined vehicles,” 2025. [Online]. Available: https://www.electropages.com/blog/2025/05/zonal-architecture-next-phase-software-designed-vehicles
[14] Tesla, Full Self-Driving (Supervised) Safety. [Online]. Available: https://www.tesla.com/fsd/safety
[15] K. Jain and S. Gupta, Cybersecurity in Connected Vehicles. Amsterdam, Netherlands: Elsevier, 2023.
[16] M. Bojarski et al., “End-to-end learning for self-driving cars,” arXiv preprint arXiv:1604.07316, 2016.
[17] UNECE, UN Regulation No. 155: Cybersecurity, Geneva, Switzerland, 2021. [Online]. Available: https://unece.org/transport/vehicle-regulations
[18] S. Halder, A. Ghosal, and M. Conti, “Secure OTA software updates,” Comput. Netw., 2020, doi: 10.1016/j.comnet.2020.107343.
[19] B. Li et al., “Over-the-air upgrading for intelligent connected vehicle security,” Artif. Intell. Rev., 2024, doi: 10.1007/s10462-024-10968-z.
[20] S. Ren et al., “Faster R-CNN: Towards real-time object detection with region proposal networks,” IEEE Trans. Pattern Anal. Mach. Intell., 2017, doi: 10.1109/TPAMI.2016.2577031.
[21] F. You et al., “AR cognitive interface in human-vehicle safety,” Int. J. Human-Computer Interaction, 2024, doi: 10.1080/10447318.2023.2295695.
[22] T. Tampuu et al., “Survey of end-to-end driving,” IEEE Trans. Neural Netw. Learn. Syst., 2022, doi: 10.1109/TNNLS.2020.3043505.
[23] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, pp. 436–444, 2015, doi: 10.1038/nature14539.
[24] J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” arXiv preprint arXiv:1804.02767, 2018.
[25] A. Geiger et al., “Are we ready for autonomous driving? The KITTI benchmark suite,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2012, doi: 10.1109/CVPR.2012.6248074.
[26] R. Rasshofer and K. Gresser, Automotive Radar and Sensor Fusion. Norwood, MA, USA: Artech House, 2017.
[27] J. Long et al., “Fully convolutional networks for semantic segmentation,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2015, doi: 10.1109/CVPR.2015.7298965.
[28] Z. Liu et al., “Swin transformer: Hierarchical vision transformer using shifted windows,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), 2021, doi: 10.1109/ICCV48922.2021.00986.
[29] Z. Li et al., “BEVFormer: Learning bird’s-eye-view representation from multi-camera images via spatiotemporal transformers,” in Proc. Eur. Conf. Comput. Vis. (ECCV), Cham, Switzerland: Springer, 2022.
[30] J. D. Lee and K. A. See, “Trust in automation: Designing for appropriate reliance,” Human Factors, vol. 46, no. 1, pp. 50–80, 2004, doi: 10.1518/hfes.46.1.50_30392.
[31] A. Kamel, T. Sayed, and M. Kamel, “Real-time combined safety-mobility assessment using self-driving vehicle data,” Accident Anal. Prev., vol. 199, Art. no. 107513, May 2024, doi: 10.1016/j.aap.2024.107513.
[32] J. R. Clark et al., Human-Automation Interaction in Driving Automation. London, U.K.: Routledge, 2024.
[33] SAE International, SOTIF and ISO 21448 Guide. [Online]. Available: https://www.sae.org/publications/books/content/r-514/
[34] H. Wang et al., “SOTIF safety challenges,” Engineering, 2024, doi: 10.1016/j.eng.2023.10.011.
[35] ISO, ISO 26262: Functional Safety, Geneva, Switzerland, 2018. [Online]. Available: https://www.iso.org/standard/68383.html
[36] C. Miller and C. Valasek, “Automotive security research,” in Proc. USENIX Security Symp., 2024.
[37] Netwalk, Automotive Cybersecurity. [Online]. Available: https://netwalk.co.in/automotive-cybersecurity/
[38] Model Engineers, “Functional safety vs. SOTIF: Differences and overlaps.” [Online]. Available: https://model-engineers.com/en/blog/functional-safety-vs-sotif-differences-overlaps/
[39] Automotive IQ, “Navigating SOTIF and ISO 21448.” [Online]. Available: https://www.automotive-iq.com/functional-safety/articles/navigating-sotif-iso-21448-and-ensuring-safety-in-autonomous-driving
[40] R. Bielawski, “Secure OTA updates for software-defined vehicles.” [Online]. Available: https://blog.guardknox.com/software-defined-vehicles-ota-automotive-updates
[41] Z. Li et al., “BEVFormer: Learning bird’s-eye-view representation from multi-camera images via spatiotemporal transformers,” arXiv preprint arXiv:2203.17270, 2022.
[42] Rambus, OTA Updates Explained. [Online]. Available: https://www.rambus.com/blogs/ota-updates-explained/
[43] Hitachi, OTA Software Updates (Lumada). [Online]. Available: https://www.hitachi.com/products/it/lumada/global/en/spcon/uc_00866s/index.html
[44] J. M. Scanlon and K. D. Kusano, “Scenario-based testing for ADAS,” SAE J., 2024, doi: 10.4271/12-07-02-0009.
[45] S. Riedmaier and J. Nesensohn, “Validation of automated driving systems,” IEEE Access, 2024, doi: 10.1109/ACCESS.2024.3356790.
[46] S. Checkoway and D. McCoy, “Automotive attack surfaces,” in Proc. USENIX Security Symp., 2024.
[47] M. S. Young and N. A. Stanton, Driving Automation: A Human Factors Perspective. London, U.K.: Routledge, 2023.
[48] E. A. Lee and S. A. Seshia, Introduction to Embedded Systems. Berkeley, CA, USA. [Online]. Available: https://ptolemy.berkeley.edu/books/leeseshia/
[49] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.
[50] R. Rajamani, Vehicle Dynamics and Control. New York, NY, USA: Springer, 2012, doi: 10.1007/978-1-4614-1433-9.
[51] N. Mehrabi et al., “Bias and fairness in machine learning,” ACM Comput. Surveys, 2021, doi: 10.1145/3457607.
