Two-timescale Mechanism-and-Data-Driven Control for Aggressive Driving of Autonomous Cars
This work addresses control problems for autonomous cars in aggressive driving scenarios, representing an incremental advance by combining existing method types.
The paper tackled the challenge of controlling autonomous cars under aggressive driving conditions by fusing mechanism-based and data-driven methods, resulting in improved data efficiency, transfer ability, and performance as verified on TORCS.
The control for aggressive driving of autonomous cars is challenging due to the presence of significant tyre slip. Data-driven and mechanism-based methods for the modeling and control of autonomous cars under aggressive driving conditions are limited in data efficiency and adaptability respectively. This paper is an attempt toward the fusion of the two classes of methods. By means of a modular design that is consisted of mechanism-based and data-driven components, and aware of the two-timescale phenomenon in the car model, our approach effectively improves over previous methods in terms of data efficiency, ability of transfer and final performance. The hybrid mechanism-and-data-driven approach is verified on TORCS (The Open Racing Car Simulator). Experiment results demonstrate the benefit of our approach over purely mechanism-based and purely data-driven methods.