ROSA-RL: Uncertainty-Aware Roundabout Optimized Speed Advisory with Reinforcement Learning

2026-06-15

AI Summary

This study addresses the challenge of occupancy uncertainty in roundabout conflict zones under mixed traffic conditions, arising from the unpredictability of human driving behavior and high interaction complexity. To tackle this issue, the authors propose an uncertainty-aware speed guidance framework that uniquely integrates Transformer-based multi-agent trajectory prediction with reinforcement learning. The method probabilistically models the five-second-ahead occupancy state of the conflict zone and explicitly incorporates prediction uncertainty into the decision-making process. Evaluated in a realistic data-driven simulation environment, the proposed system significantly outperforms baseline approaches and achieves performance approaching that of an idealized scenario with perfect occupancy knowledge, thereby enhancing traffic throughput while maintaining safety.

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.

Problem

• roundabouts
• uncertainty
• mixed traffic
• conflict zone
• automated driving

Innovation

• Uncertainty-aware
• Reinforcement Learning
• Transformer-based prediction
• Roundabout navigation
• Mixed traffic