Set-Based Threat Assessment in Lane Guidance Applications

We present a model based threat assessment method for semi-autonomous vehicles. Based on the assumption that information about the surrounding environment is available over a future finite time horizon, we first introduce a set of constraints on the vehicle states, which are satisfied under “safe” driving conditions. Then, we use vehicle and driver mathematical models in order to predict future constraints violation, indicating the possibility of accident or loss of vehicle control.The proposed method is demonstrated in a roadway departure application and validated through experimental data.