Two-timescale Mechanism-and-Data-Driven Control for Aggressive Driving of Autonomous Cars

TL;DR

This paper presents a hybrid two-timescale control method for autonomous cars that combines mechanism-based and data-driven approaches, improving data efficiency, transferability, and performance in aggressive driving scenarios.

Contribution

It introduces a modular fusion of mechanism and data-driven models leveraging two-timescale dynamics, enhancing control effectiveness under aggressive driving conditions.

Findings

Outperforms purely mechanism-based methods in experiments.

Demonstrates improved data efficiency and transferability.

Validated on TORCS simulator with positive results.

Abstract

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.