HONEST-CAV: Hierarchical Optimization of Network Signals and Trajectories for Connected and Automated Vehicles with Multi-Agent Reinforcement Learning

2026-02-21

AI Summary

This study addresses the inefficiency and high energy consumption arising from mixed traffic environments where human-driven vehicles coexist with connected and automated vehicles (CAVs). To tackle this challenge, the authors propose a hierarchical cooperative control framework that jointly optimizes intersection signal timing and eco-driving trajectories for CAVs. At the upper level, decentralized multi-agent reinforcement learning based on Value Decomposition Networks (VDN) enables cycle-level signal control, while the lower level employs a machine learning–based trajectory planning algorithm (MLTPA) to generate eco-approach and eco-departure strategies. Evaluated on a real-world 4×4 road network with a 60% CAV penetration rate, the proposed method achieves a 7.67% increase in average vehicle speed, a 10.23% reduction in fuel consumption, and a 45.83% decrease in idling time compared to the Webster method, significantly enhancing both traffic efficiency and energy economy.

Technology Category

• Planning, Routing, and Scheduling: Mixed Discrete/Continuous Planning
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

This study presents a hierarchical, network-level traffic flow control framework for mixed traffic consisting of Human-driven Vehicles (HVs), Connected and Automated Vehicles (CAVs). The framework jointly optimizes vehicle-level eco-driving behaviors and intersection-level traffic signal control to enhance overall network efficiency and decrease energy consumption. A decentralized Multi-Agent Reinforcement Learning (MARL) approach by Value Decomposition Network (VDN) manages cycle-based traffic signal control (TSC) at intersections, while an innovative Signal Phase and Timing (SPaT) prediction method integrates a Machine Learning-based Trajectory Planning Algorithm (MLTPA) to guide CAVs in executing Eco-Approach and Departure (EAD) maneuvers. The framework is evaluated across varying CAV proportions and powertrain types to assess its effects on mobility and energy performance. Experimental results conducted in a 4*4 real-world network demonstrate that the MARL-based TSC method outperforms the baseline model (i.e., Webster method) in speed, fuel consumption, and idling time. In addition, with MLTPA, HONEST-CAV benefits the traffic system further in energy consumption and idling time. With a 60% CAV proportion, vehicle average speed, fuel consumption, and idling time can be improved/saved by 7.67%, 10.23%, and 45.83% compared with the baseline. Furthermore, discussions on CAV proportions and powertrain types are conducted to quantify the performance of the proposed method with the impact of automation and electrification.

Problem

• Connected and Automated Vehicles
• Traffic Signal Control
• Eco-Driving
• Mixed Traffic
• Energy Consumption

Innovation

• Multi-Agent Reinforcement Learning
• Eco-Approach and Departure
• Signal Phase and Timing Prediction
• Hierarchical Traffic Control
• Connected and Automated Vehicles