Artificial intelligence and fuzzy logic for next-generation intelligent transportation systems

Contemporary transportation systems are increasingly complex, requiring the establishment of new traffic management strategies that are intelligent, adaptable, and resilient. This chapter explores the use of a hybrid artificial intelligence (AI) and fuzzy logic paradigm to enhance intelligent transportation systems (ITS). While AI provides strong data-driven analytics and predictive capabilities, it often struggles with uncertainty and explainability. In contrast, fuzzy logic provides valuable reasoning under uncertainty but rarely adapts. The combination of these two paradigms creates one that can learn from dynamic data while using human-like reasoning in uncertain and imprecise scenarios. Important applications are adaptive traffic signal control, multimodal transportation coordination, incident detection, infrastructure planning, and disaster response. Furthermore, the chapter explores architectural components, decision-making strategies, and data fusion methods, as well as possible future research directions, which include the use of blockchain and quantum computing technologies in the AI–fuzzy paradigm. The chapter describes how these methods, illustrated through real-world example case studies, mark AI–fuzzy logic as the foundation for developing next-generation intelligent transportation systems that are efficient, safe, scalable, and human-centric.