Enhancing Integral Vehicle Safety: Weighted Crash Probability Prediction Using Naturalistic Driving Data

Crash probability predictions play a crucial role in integral vehicle safety. This paper presents an integrated approach for enhancing crash probability prediction in critical driving situations by combining synthetic data generation, machine learning techniques, and naturalistic driving studies. The study bridges the gap between active and passive vehicle safety and involves two main parts: Collision Calculation and Trajectory Weighting. The first part focuses on simulating driving maneuvers to predict vehicle trajectories and assess collision risks using a machine learning model, specifically a neural network. The second part utilizes data from naturalistic driving studies to compute realistic weightings for different trajectories based on historical driving data. By integrating these parts, the approach provides a detailed and accurate estimation of crash probabilities, considering context-specific driving behaviors. The results indicate that the individual weighting model offers a more realistic and practical estimation of crash probabilities compared to an equal weighting scheme. The proposed algorithm's runtime averages 5 ms for 185 trajectories (37 steering wheel angles and 5 brake pedal positions), making it suitable for real-time applications. This enhanced crash probability calculation can be used to preemptively activate passive safety systems when the collision risk is high or an accident is unavoidable.