URB -- Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles

TL;DR

This paper introduces URB, a comprehensive benchmark environment for evaluating reinforcement learning algorithms in urban routing for connected autonomous vehicles, highlighting current challenges and establishing a leaderboard.

Contribution

The paper presents URB, a standardized, realistic benchmarking environment with multiple networks, tasks, algorithms, and metrics for RL-based urban routing of autonomous vehicles.

Findings

State-of-the-art MARL algorithms rarely outperform humans.

Training RL models in this domain is lengthy and costly.

Current approaches struggle to scale effectively.

Abstract

Connected Autonomous Vehicles (CAVs) promise to reduce congestion in future urban networks, potentially by optimizing their routing decisions. Unlike for human drivers, these decisions can be made with collective, data-driven policies, developed using machine learning algorithms. Reinforcement learning (RL) can facilitate the development of such collective routing strategies, yet standardized and realistic benchmarks are missing. To that end, we present URB: Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles. URB is a comprehensive benchmarking environment that unifies evaluation across 29 real-world traffic networks paired with realistic demand patterns. URB comes with a catalog of predefined tasks, multi-agent RL (MARL) algorithm implementations, three baseline methods, domain-specific performance metrics, and a modular configuration scheme. Our results show that, despite the lengthy and costly training, state-of-the-art MARL algorithms rarely outperformed humans. The experimental results reported in this paper initiate the first leaderboard for MARL in large-scale urban routing optimization. They reveal that current approaches struggle to scale, emphasizing the urgent need for advancements in this domain.