Foggy weather is one of the main causes of road traffic accidents. The existing driving assistant systems (DAS) are based on cloud computing environment. In today’s world, where Internet of Thing (IoT) and smart cities are commonplace, the need to process and make decisions in real-time has never been more important. To solve this problem, this research proposes a fog computing-powered DAS under fog weather. The proposed solution utilizes fog computing, a local and real-time information processing model. Kalman filter algorithm is used to predict the position of vehicles in a traffic scenario. The system processes data locally, avoiding the need to send large amounts of data to remote cloud servers that consume a lot of energy and contribute to environmental degradation. An einxperiment was conducted to generate dataset and simulate the proposed DAS. Simulation results showed a promising performance in terms of prediction accuracy, with Root Mean Square Error (RSME) value of 0.45 and average of computational time of 53.71%.