Car-following Behavior Model Learning Using Timed Automata

Car-following Behavior Model Learning Using Timed Automata

Learning driving behavior is fundamental for autonomous vehicles to “understand” traffic situations. This paper proposes a novel method for learning a behavioral model of carfollowing using automata learning algorithms. The model is interpretable for car-following behavior analysis. Frequent common state sequences are extracted from the model and clustered as driving patterns. The Next Generati...

Model Predictive Control System Design using ARMAX Identification Method for Car-following Behavior

The control of car following is essential due to its safety and its operational efficiency. For this purpose, this paper builds a model of car following behavior based on ARMAX structure from a real traffic dataset and design a Model Predictive Control (MPC) system. Based on the relative distance and relative acceleration of each instant, the MPC predicts the future behavior of the leader vehic...

Understanding Driver Car-Following Behavior Using a Fuzzy Logic Car-Following Model

Model Checking Timed Automata

The theory of timed automata provides a formal framework to model and to verify the correct functioning of real-time systems. Among the di erent veri cation problems that have been investigated within this theory, the so-called reachability problem has been the most throughly studied. This problem is stated as follows. Given two states of the system, is there an execution starting at one of the...

Model Checking Timed Automata

Different time scales do often occur in real-time systems, e.g., a polling real-time system samples the environment many times per second, whereas the environmentmay only change a few times per second. When these systems are modeled as (networksof) timed automata, the verification using symbolic model checking techniques can signif-icantly be slowed down by unnecessary fragmenta...