ROSA-RL: Uncertainty-Aware Roundabout Optimized Speed Advisory with Reinforcement Learning
2026-06-15 • Artificial Intelligence
Artificial IntelligenceRobotics
AI summaryⓘ
The authors developed a system called ROSA-RL that helps self-driving and human-driven cars navigate roundabouts safely and smoothly. It uses a special AI model to predict if the roundabout will be busy or free in the next five seconds, considering how different drivers behave. This prediction includes uncertainty, helping the AI decide the best speed to enter without crashing or causing delays. In tests based on real traffic data, their method worked better than older models and nearly matched perfect knowledge scenarios. They also shared their code publicly for others to use.
RoundaboutAutomated drivingReinforcement LearningTransformer modelConflict zone occupancyUncertainty estimationMixed trafficProbabilistic forecastingTraffic efficiencyHuman driving behavior
Authors
Anna-Lena Schlamp, Jeremias Gerner, Klaus Bogenberger, Werner Huber, Stefanie Schmidtner
Abstract
Roundabouts challenge automated driving in mixed traffic, as heterogeneous and non-deterministic human behavior, unknown driving intentions, and high interaction complexity create uncertainty about whether the conflict zone will be blocked or available at the moment of entry. We present ROSA-RL -- uncertainty-aware Roundabout Optimized Speed Advisory with Reinforcement Learning. It enables safe and efficient roundabout entry for automated and human-driven vehicles in mixed traffic through probabilistic conflict forecasting. A Transformer-based model predicts conflict zone occupancy over a five-second horizon, capturing multi-agent interactions to anticipate upcoming conflicts and available gaps. The prediction outputs encode uncertainty in future motion and intent, and augment the state of a classical RL framework, enabling uncertainty-aware speed coordination. Evaluated in simulations grounded in real-world data, ROSA-RL can effectively handle uncertainty and outperform a comparable model-based baseline, closing the gap to an ideal setting assuming fully known occupancy while improving traffic efficiency and safety. The source code of this work is available under: github.com/urbanAIthi/ROSA-RL.