An Improved Probabilistic Threat Assessment Method for Intelligent Vehicles in Critical Rear-End Situations

Threat assessment (TA) method is vital in the decision-making process of intelligent vehicles (IVs), especially for ADAS systems. In the research of TA, the probabilistic threat assessment (PTA) method is acting an increasing role, which can reduce the uncertainties of driver’s maneuvers. However, the driver behavior model (DBM) used in present PTA methods was mainly constructed by limited data or simple functions, which is not entirely reasonable and may affect the performance of the TA process. This work aims to utilize crash data extracted from Event Data Recorder (EDR) to establish more accurate DBM and improve the current PTA method in rear-end situations. EDR data with responsive maneuvers were firstly collected, which were then employed to construct the initial DBM (I-DBM) model by using the multivariate Gaussian distribution (MGD) framework. Besides, the model was further subdivided into six parts by two important risk indicators, Time-to-collision (TTC) and velocity. To accurately represent the driver’s maneuvers in critical situations, unresponsive samples were introduced and the I-DBMs were upgraded by the Gaussian mixture model (GMM). The obtained DBMs were employed to sample driver’s evasive behaviors by Monte Carlo Markov Chain (MCMC) method, which generated multiple collision-avoidance trajectories. Finally, we chose the real-world crash case in the SHRP2 dataset to verify the proposed method. Results show that the upgraded DBMs reasonably represented the driver’s evasive maneuvers, and the MCMC method could capture the main features of given GMM distributions. The proposed PTA method can accurately depict the changing trend of dangerous degree and derive the crash probability (CP) at critical point of time. Its effectiveness and real-time performance were verified in the chosen rear-end case. The improved PTA method can be used for real-time TA application and contribute to the development of the decision-making process for ADAS and IVs.