Data-Driven Cooperative Adaptive Cruise Control for Unknown Nonlinear Vehicle Platoons

TL;DR

This paper introduces a data-driven cooperative adaptive cruise control method for vehicle platoons with unknown nonlinear dynamics, using online data and semidefinite programming to improve control performance in mixed and pure vehicle platoons.

Contribution

It proposes a novel data-driven CACC design that accounts for unknown nonlinear vehicle dynamics and can be efficiently solved via SDP, applicable to mixed and pure vehicle platoons.

Findings

The proposed CACC outperforms classic ACC in simulations.

The method effectively handles unknown nonlinear dynamics.

It is applicable to both pure AV and mixed platoons.

Abstract

This paper studies cooperative adaptive cruise control (CACC) for vehicle platoons with consideration of the unknown nonlinear vehicle dynamics that are normally ignored in the literature. A unified data-driven CACC design is proposed for platoons of pure automated vehicles (AVs) or of mixed AVs and human-driven vehicles (HVs). The CACC leverages online-collected sufficient data samples of vehicle accelerations, spacing and relative velocities. The data-driven control design is formulated as a semidefinite program (SDP) that can be solved efficiently using off-the-shelf solvers. The efficacy and advantage of the proposed CACC are demonstrated through a comparison with the classic adaptive cruise control (ACC) method on a platoon of pure AVs and a mixed platoon under a representative aggressive driving profile.