GenAI-Powered Smart Traffic Assistant: A Multimodal AI Framework for Real-Time Traffic Prediction, Route Recommendation, and Explainable Urban Mobility

Urban traffic management increasingly requires systems that can reason over heterogeneous, time-varying information rather than rely only on static maps or historical averages. This paper presents the GenAI-Powered Smart Traffic Assistant, a prototype intelligent transportation platform that combines real-time location, traffic and weather inputs, historical traffic data, machine-learning-based congestion prediction, computer-vision vehicle detection, route recommendation, alerts, explainable AI (XAI), and role-aware dashboards in a unified workflow. The system is derived from a semester project report and its associated prototype deployment. The design follows a layered client-server architecture with a web/mobile oriented interface, application services, machine-learning components, and persistent traffic data. A structured development methodology is used to integrate data collection, preprocessing, prediction, recommendation, visualization, security, and maintenance. Rather than claiming benchmark accuracy that is not reported in the source project, the paper evaluates the prototype through functional coverage, architecture consistency, safety constraints, and explicit non-functional targets. The resulting framework provides a practical foundation for multimodal traffic assistance and a pathway toward live CCTV integration, IoT sensing, adaptive signal control, continuous model learning, and smart-city interoperability.