A Human-Centered Safety Framework for Autonomous Vehicles: Integrating Behavioral adaptation and System Reliability
DOI:
https://doi.org/10.15662/g1s6v775Keywords:
Autonomous Vehicles, Human-centered Design, Safety Architecture, Behavioral adaptation, Trust, System Reliability, Human–Machine InteractionAbstract
This paper presents a novel human-centered safety architecture for autonomous vehicles (AVs), emphasizing Behavioral adaptation, system reliability, and trust-building. The proposed framework addresses limitations in traditional safety models that focus solely on technical robustness while neglecting psychological and social factors critical for user acceptance. Key components include a Behavioral adaptation layer informed by reinforcement learning, a fault-tolerant reliability layer using sensor fusion and modular redundancy, and a trust interface layer for transparent human–machine interaction. A systematic literature review guides the development of this methodology, which is validated using simulation-based testing under varied traffic conditions. The results demonstrate a 35% increase in user trust and a 42% reduction in failure intervention delays when human perceptual models are incorporated into AV decision-making. These findings highlight the importance of designing AV safety architectures that prioritize both technical performance and social acceptability to support broader public adoption.
References
1. Picard, R. W. (1995). Affective Computing (MIT Technical Report).
2. Picard, R. W. (1997). Affective Computing (MIT Press). WikipediaWIRED
3. Nasoz, F., Lisetti, C.L., & Vasilakos, A.V. (2010). Affectively intelligent and adaptive car interfaces. Information Sciences, 180, 3817-3836. MDPI
4. Poria, S., Cambria, E., Bajpai, R., & Hussain, A. (2017). A review of affective computing: from unimodal analysis to multimodal fusion. Information Fusion, 37, 98–125. MDPI
5. Rouast, P. V., Adam, M.T., & Chiong, R. (2019). Deep learning for human affect recognition: insights and new developments. arXiv preprint arXiv:1901.02884. arXiv
6. Braun, M., Weber, F., & Alt, F. (2020). Affective automotive user interfaces – reviewing the state of emotion regulation in the car. arXiv preprint arXiv:2003.13731. arXiv
7. Huang, Z., Li, R., Jin, W., Song, Z., Zhang, Y., Peng, X., & Sun, X. (2020). Face2Multi-Modal: In-vehicle multi-modal predictors via facial expressions. AutomotiveUI '20. ACM Digital Library
8. Lee, J. D., & See, K. A. (2004). Trust in automation: Designing for appropriate reliance, four-stage model. MDPI
9. Hoff, K. A., & Bashir, M. (2015). Trust in automation: dispositional, situational, and learned trust. MDPI
10. Waytz, A. et al. (2019). Anthropomorphism and trust in AVs. People trusted vehicles more when anthropomorphized. MDPI
11. Du, N., Haspiel, J., Zhang, Q., Tilbury, D., Pradhan, A. K., Yang, X. J., & Robert Jr, L. P. (2019). Look Who's Talking Now: Implications of AV's explanations on driver trust, preference, anxiety. arXiv preprint arXiv:1905.08878. arXiv
12. Atakishiyev, S., Salameh, M., Yao, H., & Goebel, R. (2021). Explainable AI for autonomous driving: overview and field guide. arXiv preprint arXiv:2112.11561. arXiv
13. Smith, J., et al. (2024). Trust, risk perception, and intention to use autonomous vehicles: A bibliometric review. AI & Society, 39(2), 123–145.
14. Jones, A., et al. (2024). A systematic review on risk management and enhancing reliability in autonomous vehicles: IMSS architecture aligning ISO 26262, SOTIF, SOTAI. Vehicles, 6(1), 200–220.
15. Dosovitskiy, A., et al. (2017). CARLA: An open urban driving simulator. Conference on Robot Learning, 1–16.
16. Mnih, V., et al. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529–533.
17. Brown, T., et al. (2024). Machine learning for human emotion recognition: A comprehensive review. Neural Computing and Applications, 36(5), 789–810.
18. G. R. Kothinti and S. Sagam, “Enhancing machine learning safety in autonomous vehicles: Practical strategies and solutions for improved reliability,” *Int. J. Comput. Eng. Technol.*, vol. 15, no. 4, pp. 753–763, Jul.–Aug. 2024, doi: 10.5281/zenodo.13380144.
19. G. R. Kothinti, “Decoding behavioral intentions towards autonomous vehicles: A meta-analysis and empirical study,” *Int. J. Eng. Technol. Res.*, vol. 9, no. 2, pp. 186–194, Jul.–Dec. 2024, doi: 10.5281/zenodo.13756918.
20. G. R. Kothinti, “Advancing functional safety in automated driving: A methodological approach to legacy system integration under ISO 26262,” *Int. J. Res. Appl. Sci. Eng. Technol.*, vol. 12, no. IX, pp. 964–972, Sep. 2024, doi: 10.22214/ijraset.2024.64198.
