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

Ahmet Onur Akman (Jagiellonian University) · Anastasia Psarou (Jagiellonian University in Krakow) · Michał Hoffmann (Jagiellonian University in Krakow) · Łukasz Gorczyca (Jagiellonian University in Krakow) · Lukasz Kowalski (Institute of Urban and Regional Development) · Paweł Gora (Jagiellonian University in Krakow) · Grzegorz Jamróz (Jagiellonian University in Krakow) · Rafal Kucharski (Jagiellonian University Krakow, Poland)

baseline methodsbenchmarking environmentcollective data-driven policiesconnected autonomous vehiclesdemand patternsleaderboardmachine learning algorithmsmodular configurationmulti-agent reinforcement learning performance metricspredefined tasksreinforcement learningrouting optimizationscalability challenges state-of-the-art algorithmsurban traffic networks

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 $\texttt{URB}$: Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles. $\texttt{URB}$ is a comprehensive benchmarking environment that unifies evaluation across 29 real-world traffic networks paired with realistic demand patterns. $\texttt{URB}$ 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.