A behavior driven approach for sampling rare event situations for autonomous vehicles
This addresses the challenge of costly and limited data for rare event evaluation in autonomous vehicles, though it appears incremental as it builds on existing bounded rationality theory.
The paper tackled the problem of evaluating autonomous vehicles in rare traffic events by developing a bounded rationality-based model of traffic behavior, showing it can estimate rare event probabilities and generate new traffic situations from naturalistic driving data.
Performance evaluation of urban autonomous vehicles requires a realistic model of the behavior of other road users in the environment. Learning such models from data involves collecting naturalistic data of real-world human behavior. In many cases, acquisition of this data can be prohibitively expensive or intrusive. Additionally, the available data often contain only typical behaviors and exclude behaviors that are classified as rare events. To evaluate the performance of AV in such situations, we develop a model of traffic behavior based on the theory of bounded rationality. Based on the experiments performed on a large naturalistic driving data, we show that the developed model can be applied to estimate probability of rare events, as well as to generate new traffic situations.