<p>Vehicular emissions continue to be a primary contributor to urban air pollution, releasing harmful pollutants such as NO_x, SO₂, CO₂, CO, and PM, which pose grave risks to environmental quality and public health. This review critically examines recent advances in functional nanomaterials, including carbon-based adsorbents, metal oxide photocatalysts (e.g., TiO₂, Fe₃O₄, ZnO), nanofilters, and nanosensors, which are employed for the capture, degradation, and real-time monitoring of vehicular air pollutants. The emphasis of this study is on the physicochemical properties, hybrid nanoarchitectures, and surface modifications that enhance adsorption, photocatalytic activity, and stability. Literature findings reveal superior performance metrics, such as &gt; 90% pollutant removal in real effluents via defect-engineered adsorbents, 59% NO oxidation efficiency under visible light with N-doped TiO₂, &gt; 500 mg g^− 1 VOC adsorption capacities in graphene-based hybrids, and up to 85% predictive accuracy in ML-optimized designs. The integration of machine learning (ML) into nanotechnology-based platforms for air quality management is also explored, particularly with regard to predictive modeling and performance optimization. Key barriers to implementation, such as cost, environmental risks, and regulatory challenges, are critically assessed. The review’s conclusions offer a series of recommendations for advancing sustainable development, encompassing green synthesis approaches, life cycle assessment, and policy-oriented strategies. This work provides a comprehensive and interdisciplinary perspective that aligns with sustainable development goals (SDG 11, 12, 13), contributing to global efforts in mitigating urban air pollution.</p>