Heterogeneous Mixed Traffic Control and Coordination

2024-09-18

arXiv.org

AI Summary

Heterogeneous mixed traffic—ranging from passenger cars to large semi-trailers—exhibits low intersection throughput and high environmental impact at complex urban intersections under non-signalized control, especially during signal failures (e.g., power outages). Method: This paper proposes a multi-agent reinforcement learning (MARL)-based cooperative control framework for robot vehicles (RVs), supporting dynamic RV penetration rates of 10%–90%. Contribution/Results: We first identify and exploit the “rarity advantage” phenomenon: under RV coordination, large vehicles at low penetration rates experience up to 87% reduction in waiting time. Experiments show that our method reduces average waiting time by 86% and 91% compared to signalized and uncontrolled baselines, respectively; significantly decreases headway, improves road spatial utilization, and concurrently lowers CO₂ emissions and fuel consumption. The system demonstrates strong robustness under emergency scenarios, including complete signal failure.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Multiagent Systems: Multiagent Learning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Urban intersections, filled with a diverse mix of vehicles from small cars to large semi-trailers, present a persistent challenge for traffic control and management. This reality drives our investigation into how robot vehicles (RVs) can transform such heterogeneous traffic flow, particularly at unsignalized intersections where traditional control methods often falter during power failures and emergencies. Using reinforcement learning (RL) and real-world traffic data, we study heterogeneous mixed traffic across complex intersections under gradual automation by varying RV penetration from 10% to 90%. The results are compelling: average waiting times decrease by up to 86% and 91% compared to signalized and unsignalized intersections, respectively. Additionally, we uncover a"rarity advantage,"where less frequent vehicles, such as trucks, benefit the most from RV coordination (by up to 87%). RVs' presence also leads to lower CO2 emissions and fuel consumption compared to managing traffic via traffic lights. Moreover, space headways decrease across all vehicle types as RV rate increases, indicating better road space utilization.

Problem

• Enhancing traffic flow at unsignalized intersections with robot vehicles
• Reducing waiting times in mixed traffic using reinforcement learning
• Balancing traffic efficiency and environmental impact with diverse vehicles

Innovation

• Uses reinforcement learning for traffic control
• Simulates mixed traffic with robot vehicles
• Reduces waiting times significantly