A Systems Engineering Framework for Safe and Secure LiDAR Perception in Autonomous Vehicles
This paper addresses the critical need for a revised systems engineering framework to ensure the safety and security of LiDAR perception software in autonomous vehicles. Traditional approaches, often rooted in waterfall methodologies, prove inadequate in addressing the complexity, stringent safety requirements (ISO 26262), and evolving cybersecurity threats inherent in this rapidly advancing field. We propose a novel framework that integrates best practices from Model-Based Systems Engineering (MBSE), agile development, formal methods, and security-by-design principles, creating a holistic approach to development and validation. This framework directly tackles the limitations of traditional methods by incorporating iterative development cycles, rigorous verification and validation processes, and proactive security measures throughout the entire lifecycle. The framework’s practical application is demonstrated through a comparative case study analyzing DBSCAN and Euclidean clustering algorithms for object detection within a safety-critical Autonomous Emergency Braking (AEB) system. This case study highlights the importance of algorithm selection, parameter optimization, and the crucial role of testing methodologies in achieving both high performance and compliance with ISO 26262 safety standards. Our analysis reveals significant performance differences between the algorithms, underscoring the necessity of a rigorous and data-driven approach to algorithm selection and validation within a comprehensive systems engineering framework. The research concludes by outlining key areas for future investigation, including advancements in algorithmic efficiency, robust sensor fusion strategies, enhanced cybersecurity measures (addressing both known and emerging threats), and the development of standardized testing and validation procedures to ensure the continued improvement and widespread adoption of safe and reliable autonomous driving systems. This holistic framework offers a significant contribution to the ongoing effort of building more robust and trustworthy autonomous vehicles, directly addressing the challenges of safety, security, and reliability in this rapidly evolving technology.
J. D'Ambrosio and G. Soremekun, "Systems engineering challenges and MBSE opportunities for automotive system design," 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Banff, AB, Canada, 2017, pp. 2075-2080, doi: 10.1109/SMC.2017.8122925. https://ieeexplore.ieee.org/document/8122925
H. Sandgren and V. Antinyan, "Software Safety Analysis to Support ISO 26262-6 Compliance in Agile Development," in IEEE Software, vol. 38, no. 3, pp. 52-60, May-June 2021, doi: 10.1109/MS.2020.3026145.https://ieeexplore.ieee.org/document/9203866
H. An and K. Zhang, "Functional Safety Design of Lidar System for Autonomous Vehicles," 2022 IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA), Dalian, China, 2022, pp. 1219-1225, doi: 10.1109/AEECA55500.2022.9919087.
https://ieeexplore.ieee.org/document/9919087
M. K. Khan and A. Quadri, "Augmenting Cybersecurity in Autonomous Vehicles: Innovative Recommendations for Aspiring Entrepreneurs," in IEEE Consumer Electronics Magazine, vol. 10, no. 3, pp. 111-116, 1 May 2021, doi: 10.1109/MCE.2020.3024513.
C. -S. Lee, Y. -H. Huang and I. -W. Lan, "Hardware-in-the-Loop Test Case Specification for Verification of Software Safety Requirements in the Context of ISO 26262," 2018 International Conference of Electrical and Electronic Technologies for Automotive, Milan, Italy, 2018, pp. 1-6, doi: 10.23919/EETA.2018.8493208.
K. Fatseas, M. J. G. Bekooij and W. P. Sanberg, "Optimizing PointNet++ and DBSCAN for Object Detection in Automotive Radar Point Clouds," 2024 21st European Radar Conference (EuRAD), Paris, France, 2024, pp. 39-42, doi: 10.23919/EuRAD61604.2024.10734887.
Yeong, D. J., Velasco-Hernandez, G., Barry, J., & Walsh, J. (2021). Sensor and Sensor Fusion Technology in Autonomous Vehicles: A Review. Sensors, 21(6), 2140. https://doi.org/10.3390/s21062140
G. H. Fisher, "Model-based systems engineering of automotive systems," 17th DASC. AIAA/IEEE/SAE. Digital Avionics Systems Conference. Proceedings (Cat. No.98CH36267), Bellevue, WA, USA, 1998, pp. B15/1-B15/7 vol.1, doi: 10.1109/DASC.1998.741455.
S. Bansal, F. Alimardani and J. S. Baras, "Model-Based Systems Engineering Applied to the Trajectory Planning for Autonomous Vehicles," 2018 IEEE International Systems Engineering Symposium (ISSE), Rome, Italy, 2018, pp. 1-8, doi: 10.1109/SysEng.2018.8544452.
Hobbs, C. (2019). Embedded Software Development for Safety-Critical Systems, Second Edition (2nd ed.). CRC Press. https://doi.org/10.1201/9780429323010
R. Alur, C. Courcoubetis and D. Dill, "Model-checking for real-time systems," [1990] Proceedings. Fifth Annual IEEE Symposium on Logic in Computer Science, Philadelphia, PA, USA, 1990, pp. 414-425, doi: 10.1109/LICS.1990.113766.
L. J. Moukahal, M. Zulkernine and M. Soukup, "Towards a Secure Software Lifecycle for Autonomous Vehicles," 2021 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW), Wuhan, China, 2021, pp. 371-377, doi: 10.1109/ISSREW53611.2021.00104.
D. Jain, M. Singh and A. K. Sharma, "Performance enhancement of DBSCAN density based clustering algorithm in data mining," 2017 International Conference on Energy, Communication, Data Analytics and Soft Computing (ICECDS), Chennai, India, 2017, pp. 1559-1564, doi: 10.1109/ICECDS.2017.8389708.
Wang, Y., Su, J., Murakami, H. et al. PointNet + + Based Concealed Object Classification Utilizing an FMCW Millimeter-Wave Radar. J Infrared Milli Terahz Waves 45, 1040–1057 (2024). https://doi.org/10.1007/s10762-024-01017-5
Farag W. Kalman-filter-based sensor fusion applied to road-objects detection and tracking for autonomous vehicles. Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering. 2021;235(7):1125-1138. doi:10.1177/0959651820975523
K. -L. Lu and Y. -Y. Chen, "ISO 26262 ASIL-Oriented Hardware Design Framework for Safety-Critical Automotive Systems," 2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE), Graz, Austria, 2019, pp. 1-6, doi: 10.1109/ICCVE45908.2019.8965235.
P. Koopman and M. Wagner, "Autonomous Vehicle Safety: An Interdisciplinary Challenge," in IEEE Intelligent Transportation Systems Magazine, vol. 9, no. 1, pp. 90-96, Spring 2017, doi: 10.1109/MITS.2016.2583491.
Swaroop Reddy Gayam. (2022). Deep Learning for Autonomous Driving: Techniques for Object Detection, Path Planning, and Safety Assurance in Self-Driving Cars. Journal of AI in Healthcare and Medicine, 2(1), 170-200. https://healthsciencepub.com/index.php/jaihm/article/view/99
D. Kim, R. R. L. Mendoza, K. F. R. Chua, M. A. A. Chavez, R. S. Concepcion and R. R. P. Vicerra, "A Systematic Analysis on the Trends and Challenges in Autonomous Vehicles and the Proposed Solutions for Level 5 Automation," 2021 IEEE 13th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), Manila, Philippines, 2021, pp. 1-6, doi: 10.1109/HNICEM54116.2021.9731982.
Copyright (c) 2025 International Journal of Engineering and Computer Science
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.