A new integrated collision risk assessment methodology for autonomous vehicles

Real-time risk assessment of autonomous driving at tactical and operational levels is extremely challenging since both contextual and circumferential factors should concurrently be considered. Recent methods have started to simultaneously treat the context of the traffic environment along with vehicle dynamics. In particular, interaction-aware motion models that take inter-vehicle dependencies into account by utilizing the Bayesian interference are employed to mutually control multiple factors. However, communications between vehicles are often assumed and the developed models are required many parameters to be tuned. Consequently, they are computationally very demanding. Even in the cases where these desiderata are fulfilled, current approaches cannot cope with a large volume of sequential data from organically changing traffic scenarios, especially in highly complex operational environments such as dense urban areas with heterogeneous road users. To overcome these limitations, this paper develops a new risk assessment methodology that integrates a network-level collision estimate with a vehicle-based risk estimate in real-time under the joint framework of interaction-aware motion models and Dynamic Bayesian Networks (DBN). Following the formulation and explanation of the required functions, machine learning classifiers were utilized for the real-time network-level collision prediction and the results were then incorporated into the integrated DBN model for predicting collision probabilities in real-time. Results indicated an enhancement of the interaction-aware model by up to 10%, when traffic conditions are deemed as collision-prone. Hence, it was concluded that a well-calibrated collision prediction classifier provides a crucial hint for better risk perception by autonomous vehicles.