SOURCE-LINKED INTELLIGENCE

Long-Horizon Consistent and Interaction-Aware World Models for Multi-Style End-to-End Driving

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

End-to-end autonomous driving has increasingly adopted world model-based reinforcement learning frameworks to improve learning efficiency through \textit{imagined rollouts}. However, existing world models suffer from three key limitations: temporal inconsistency in long-horizon imagined rollouts, inadequate modeling of ego-environment interactions, and limited adaptability to diverse driving styles. To address these challenges, we propose \textit{StyleDrive}, a world-model-based learning framework that jointly enforces long-horizon consistency, explicitly disentangles interactive traffic state

Read original source ↗ Open in workspace

recordType

paper

region

Global