Search papers, labs, and topics across Lattice.
This paper introduces StyleDrive, a novel world-model-based framework for end-to-end autonomous driving that addresses long-horizon consistency, ego-environment interaction modeling, and adaptability to diverse driving styles. By implementing a temporal consistency regularization with gated cross-attention, an explicit state disentanglement module, and Group Relative Policy Optimization, StyleDrive significantly improves decision-making and reduces reward variance. Evaluated on the Bench2Drive benchmark, StyleDrive achieves a driving score of 88.44 and a success rate of 66.82, marking substantial improvements over previous methods and demonstrating effective sim-to-real transfer on a real automated guided vehicle platform.
StyleDrive achieves a remarkable 17.08-point increase in driving score over existing methods, showcasing its superior long-horizon consistency and adaptability to diverse driving styles.
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 states, and supports multi-style policy optimization within a unified learning paradigm. First, we introduce a temporal consistency regularization that integrates historical latent states through gated cross-attention, stabilizing long-horizon imagined rollouts and mitigating error accumulation. Second, we design an explicit state disentanglement module that separates ego-relevant from ego-irrelevant interactive states, enabling more interpretable and efficient decision-making in complex traffic scenarios. Third, we enable multi-style driving behaviors through Group Relative Policy Optimization, which replaces per-step reward optimization with trajectory-wise relative advantages, reducing reward variance and supporting diverse driving styles without retraining. We evaluate StyleDrive on the Bench2Drive closed-loop driving benchmark, achieving a driving score of 88.44 (+17.08 over the previous best world model-based method) and a success rate of 66.82 (+16.58). Furthermore, we deploy StyleDrive on a real automated guided vehicle platform and demonstrate promising sim-to-real transfer capability in dynamic driving scenarios.
