Driving Dynamic

Driving dynamics research focuses on modeling and controlling vehicle behavior, aiming to improve safety, efficiency, and comfort in both autonomous and human-driven vehicles. Current research emphasizes developing accurate yet computationally efficient models, often employing machine learning techniques like Long Short-Term Memory networks (LSTMs) and Gaussian Processes, alongside classical control methods such as Model Predictive Control (MPC) and Control Barrier Functions (CBFs). These advancements are crucial for enhancing autonomous driving systems, improving advanced driver-assistance systems (ADAS), and enabling safer and more efficient traffic flow in mixed-autonomy environments.