An Exploration-Exploitation Approach to Anti-lock Brake Systems

TL;DR

This paper introduces a Dual Control for Exploration-Exploitation (DCEE) method for anti-lock brake systems that improves vehicle state estimation and braking performance across various conditions, outperforming existing extremum seeking techniques.

Contribution

The paper presents a novel DCEE approach that integrates state and environment estimation with braking control, enhancing performance over traditional methods.

Findings

Up to 15% improvement in stopping time.

Up to 8.5% reduction in stopping distance.

Effective across diverse driving scenarios and road conditions.

Abstract

Anti-lock Brake System (ABS) is a mandatory active safety feature on road vehicles with analogous systems for aircraft and locomotives. This feature aims to prevent locking of the wheels when braking and to improve the handling performance, as well as reduce stopping distance of the vehicle. Estimation uncertainties in the vehicle state and environment (road surface) are often neglected or handled separately from the ABS controller, leading to sub-optimal braking. In this paper, a Dual Control for Exploration-Exploitation (DCEE) approach is taken toward the ABS problem which achieves both accurate state (and environment) estimation and superior braking performance. Compared with popular Extremum Seeking methods, improvements of up to $15\%$ and $8.5\%$ are shown in stopping time and stopping distance, respectively. A Regularized Particle Filter with Markov Chain Monte Carlo step is used to estimate vehicle states and parameters of the Magic Formula tyre model that includes the peak friction coefficient for the environment. The effectiveness of the DCEE approach is demonstrated across a range of driving scenarios such as low and high speeds; snow, wet and dry roads and changing road surfaces.