Multi-Step Deep Koopman Network (MDK-Net) for Vehicle Control in Frenet Frame
This work addresses vehicle control for autonomous driving applications, presenting an incremental improvement by applying a novel method to a known bottleneck in nonlinear dynamics.
The paper tackled the challenge of controlling highly nonlinear vehicle dynamics for path planning and following by introducing a deep learning-based Koopman modeling approach, which achieved superior accuracy compared to linear models and enabled an MPC controller to provide significantly improved performance with comparable computational efficiency.
The highly nonlinear dynamics of vehicles present a major challenge for the practical implementation of optimal and Model Predictive Control (MPC) approaches in path planning and following. Koopman operator theory offers a global linear representation of nonlinear dynamical systems, making it a promising framework for optimization-based vehicle control. This paper introduces a novel deep learning-based Koopman modeling approach that employs deep neural networks to capture the full vehicle dynamics-from pedal and steering inputs to chassis states-within a curvilinear Frenet frame. The superior accuracy of the Koopman model compared to identified linear models is shown for a double lane change maneuver. Furthermore, it is shown that an MPC controller deploying the Koopman model provides significantly improved performance while maintaining computational efficiency comparable to a linear MPC.