DeeP-LCC: Data-EnablEd Predictive Leading Cruise Control in Mixed Traffic Flow

TL;DR

DeeP-LCC is a data-driven predictive control method for mixed traffic flow that does not require explicit car-following models, improving safety, efficiency, and fuel economy of autonomous vehicles in traffic.

Contribution

The paper introduces DeeP-LCC, a novel non-parametric, data-driven predictive control approach for CAVs in mixed traffic, bypassing the need for explicit car-following models.

Findings

DeeP-LCC outperforms standard predictive controllers in simulations.

It ensures collision-free control with input/output constraints.

Numerical experiments show improved traffic efficiency and safety.

Abstract

For the control of connected and autonomous vehicles (CAVs), most existing methods focus on model-based strategies. They require explicit knowledge of car-following dynamics of human-driven vehicles that are non-trivial to identify accurately. In this paper, instead of relying on a parametric car-following model, we introduce a data-driven non-parametric strategy, called DeeP-LCC (Data-EnablEd Predictive Leading Cruise Control), to achieve safe and optimal control of CAVs in mixed traffic. We first utilize Willems' fundamental lemma to obtain a data-centric representation of mixed traffic behavior. This is justified by rigorous analysis on controllability and observability properties of mixed traffic. We then employ a receding horizon strategy to solve a finite-horizon optimal control problem at each time step, in which input/output constraints are incorporated for collision-free guarantees. Numerical experiments validate the performance of DeeP-LCC compared to a standard predictive controller that requires an accurate model. Multiple nonlinear traffic simulations further confirm its great potential on improving traffic efficiency, driving safety, and fuel economy.