The rapid evolution of autonomous transportation networks and smart mobility solutions has necessitated the integration of adaptive artificial intelligence (AI) models to enhance public engagement, optimize traffic flow, and ensure predictive traffic management. This research proposes a human-centric AI framework that leverages real-time adaptive learning, reinforcement-based decision-making, and scalable AI-driven public engagement models to transform urban mobility. The study introduces privacy-preserving federated AI models, bias-free decision-making algorithms, and cooperative AI traffic control systems to address challenges in mixed-traffic environments. By integrating real-time user feedback, demand-responsive transport systems, and explainable AI (XAI) governance, the proposed approach fosters public trust and ensures inclusive, ethical, and efficient smart transportation ecosystems. Furthermore, this research tackles emerging challenges such as the curse of rarity in autonomous vehicle (AV) decision-making, low-connectivity environments for smart traffic optimization, and scalable generative AI for vehicular networks. The findings highlight the importance of AI-driven public engagement in developing resilient, self-optimizing, and future-proof smart transportation systems, paving the way for next-generation predictive mobility solutions.
Adaptive Artificial Intelligence Enabled Public Engagement Models for Future Autonomous Transportation Networks Smart Mobility and Predictive Traffic Optimization
Advances in Computer Science res
International Conference on Sustainability Innovation in Computing and Engineering ; 2024 ; Chennai, India December 30, 2024 - December 31, 2024
Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 24) ; Kapitel : 4 ; 25-36
24.05.2025
12 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch