Traffic State Estimation Using Basic Safety Messages Based on Kalman Filter Technique

Basic safety messages (BSMs) serve as one of the main information types transmitted with vehicle-to-everything (V2X) communications to primarily improve traffic safety. However, BSMs also offer potential as a resource for traffic state estimation, which helps in optimizing traffic control measures. This study presents an approach based on the Kalman filter to estimate traffic conditions using BSM data. To evaluate the performance of the proposed model, test dataset are prepared using BSM data generated from microscopic simulation. Results show that while speed estimations show high precision, flow and density predictions present challenges, particularly at low BSM penetration rates. Nonetheless, the data may provide more detailed insights than existing traffic sensors.