Application of Collision Probability Estimation to Calibration of Advanced Driver Assistance Systems

Advanced Driver Assistance Systems (ADAS) are designed and calibrated rigorously to provide them with the robustness against highly uncertain environments that they usually operate in. Typical calibration procedures for such systems rely extensively on track (controlled environment) testing, which is time-consuming, expensive, and sometimes cannot cover all the critical test scenarios that could be encountered by ADAS in the real world. Therefore, virtual (simulation-based) testing and validation has been gaining more prominence and emphasis for ensuring high coverage along with easier scalability and usage. This paper attempts to provide an alternative approach for calibrating ADAS in the controller validation phase by the aid of simulated test case scenarios. The study executes characterization of the uncertainty in the position and heading of the ego and the obstacle vehicles. This exercise captures the uncertainties in the states detection of vehicles in the environment and localization errors of the states of the ego vehicle. Following it, the approach estimates the probability of collision between the two vehicles for a given trajectory through a Monte Carlo approach. For illustration purposes, the method is then applied on tuning a Lane Change Assistance System for a four-wheel sedan equipped with Short-Range and Long-Range Radar Sensors.