An Approach for Optimizing Acceleration in Connected and Automated Vehicles

TL;DR

This paper presents a neural network-based method to optimize the acceleration of connected and automated vehicles by tuning controller gains, improving performance in merging scenarios.

Contribution

It introduces an optimization framework for gain tuning in CAVs and trains a neural network to quickly identify optimal gains based on initial conditions.

Findings

Neural network accurately predicts optimal gains for various initial conditions.

Optimized gains improve vehicle acceleration performance in merging scenarios.

The approach enables real-time gain tuning for CAVs.

Abstract

Vehicle automation technology has made significant progress, laying the groundwork for a future of fully automated vehicles. This paper delves into the operation of connected and automated vehicles (CAVs). In prior work, we developed a controller that includes a tunable gain whose value significantly influences CAV performance and, in particular, its acceleration. By varying this gain, CAV acceleration is associated with different values depending on some initial conditions. Thus, our goal in this paper is to identify the optimal value of this gain in terms of acceleration for any group of initial conditions. To this end, we formulate an optimization problem where the decision variable is the gain value, and the objective function includes the acceleration of the vehicles. The complexity of this problem prohibits real-time solutions. To address this challenge, we train a neural network to map different initial conditions to the optimal gain values efficiently. We showcase the proposed approach to deriving the optimal gains in a merging scenario with an on-ramp.