Energy Efficient Automated Driving as a GNEP: Vehicle-in-the-loop Experiments

TL;DR

This paper presents a multi-agent motion planning approach for connected automated vehicles that minimizes energy consumption during lane changes by modeling interactions as a generalized Nash equilibrium problem, validated through simulations and vehicle-in-the-loop experiments.

Contribution

It introduces a novel GNEP-based control framework for energy-efficient vehicle coordination, implemented with MPC and validated in real-time vehicle-in-the-loop tests.

Findings

Energy savings demonstrated in experiments

Reduced travel time during lane changes

Effective multi-agent coordination achieved

Abstract

In this paper, a multi-agent motion planning problem is studied aiming to minimize energy consumption of connected automated vehicles (CAVs) in lane change scenarios. We model this interactive motion planning as a generalized Nash equilibrium problem and formalize how vehicle-to-vehicle intention sharing enables solution of the game between multiple CAVs as an optimal control problem for each agent, to arrive at a generalized Nash equilibrium. The method is implemented via model predictive control (MPC) and compared with an advanced baseline MPC which utilizes unilateral predictions of other agents' future states. A ROS-based in-the-loop testbed is developed: the method is first evaluated in software-in-the-loop and then vehicle-in-the-loop experiments are conducted. Experimental results demonstrate energy and travel time benefits of the presented method in interactive lane change maneuvers.