SafeDriveVLA：面向冲突感知端到端自动驾驶的导航条件世界模型梦境生成
SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving
AI总结：
针对现有视觉-语言-动作（VLA）自动驾驶模型无法应对冲突指令的问题，提出SafeDriveVLA模型，通过导航合规模式与导航条件世界模型梦境生成，提升了导航跟随性能与对抗鲁棒性。
摘要：
视觉-语言-动作（VLA）模型在自动驾驶领域受到关注，它们继承了大型语言模型（LLM）的常识先验，并将导航接口从固定命令集扩展为自由形式的自然语言指令。然而，这种开放式接口暴露出新的漏洞：注意力不集中的驾驶员可能会发出与当前场景不符的不安全指令，恶意用户则可能故意发出危险指令。我们提出了首个同时评估导航跟随能力、冲突感知能力以及对抗鲁棒性的基准套件。现有VLA模型在这两方面均表现不足：SimLingo在闭环场景中无法完成任何语言指令的变道操作，且所有模型在冲突信号下性能急剧下降。我们提出SafeDriveVLA，这是首个驾驶VLA模型，具备两项核心特性：（1）显式预测三级导航合规模式，将冲突推理与动作生成解耦；（2）采用导航条件世界模型梦境生成来辅助该预测。与此前生成专家或规划动作的世界模型不同，我们的模型梦境生成时严格遵循导航信号，以此判断何时跟随是安全的。SafeDriveVLA在Bench2Drive上达到88.16的驾驶评分（DS）和68.64%的成功率（SR），相比最优的SimLingo变体，将闭环语言跟随性能提升49.3%，并在不安全指令下的碰撞次数从60次降至38次。视频演示可在我们的项目页面查看。
英文摘要：
Vision-Language-Action (VLA) models are gaining attention in autonomous driving, inheriting commonsense priors from large language models (LLMs) and widening the navigation interface from a fixed command set to free-form natural-language instructions. However, this open-ended interface exposes a new vulnerability surface: an inattentive driver may issue instructions that are unsafe given the current scene, and a malicious user may issue dangerous ones on purpose. We present the first benchmark suite that evaluates navigation following and conflict awareness together, along with adversarial robustness. Existing VLAs fall short on both: SimLingo completes no language-instructed lane change in closed loop, and all models degrade sharply under conflicting signals. We propose SafeDriveVLA, the first driving VLA that (1) explicitly predicts a three-level navigation-compliance mode to decouple conflict reasoning from action generation, and (2) uses navigation-conditioned world model dreaming to inform this prediction. Unlike prior world models that roll out expert or planned actions, ours dreams of strictly following the navigation signal, showing when following is safe. SafeDriveVLA reaches 88.16 Driving Score (DS) and 68.64% Success Rate (SR) on Bench2Drive, lifts closed-loop language following by 49.3% and reduces collisions under unsafe instructions from 60 to 38 compared to the best SimLingo variant. Video demonstrations are available on our project page.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
