神经符号驱动：基于规则忠实推理的驾驶VLA
Neuro-Symbolic Drive: Rule-Grounded Faithful Reasoning for Driving VLAs
AI总结：
提出神经符号驱动框架，利用规则规划器的决策轨迹监督驾驶VLA，实现推理与运动生成的因果耦合，显著降低轨迹误差和碰撞率。
摘要：
融合链式推理的驾驶VLA模型具有吸引力，因为它们利用预训练的VLM表示并以自然语言暴露中间决策，但当前的推理过程往往缺乏逐步决策语义，无法将推理与规划运动保持因果关联。我们提出神经符号驱动，一种神经符号驾驶框架，通过直接从经典规则规划器中提取基于规则的推理轨迹来监督驾驶VLA。我们的关键观察是，规则规划器作为符号AI系统，本身即可作为可执行的推理引擎：它们推理主动安全约束，搜索候选机动，并选择最终轨迹。我们在仿真中装备这些规划器，以捕获执行轨迹和每个规则评估步骤的内部决策轨迹。每条轨迹被序列化为结构化的规则基础推理，并与轨迹配对，用于微调Qwen3.5-4B作为驾驶VLA。由于这些轨迹直接来源于决定动作的规划器状态，它们确保推理在结构上与运动生成耦合，而非通过事后对齐。在我们仿真生成的基准上，详细的规则基础推理在三摄像头感知下将ADE@3s从0.47降至0.26，丢失率从8.30%降至6.40%；在八摄像头感知下从0.54降至0.26，丢失率从10.13%降至5.99%。因此，神经符号驱动将神经符号规划逻辑转化为结构化监督。代码库：此https URL。
英文摘要：
Driving VLA models incorporating Chain-of-Thought (CoT) reasoning are attractive because they leverage pretrained VLM representations and expose intermediate decisions in natural language, yet current rationales often lack the step-by-step decision semantics needed to keep the rationale causally connected to the planned motion. We introduce Neuro-Symbolic Drive, a neuro-symbolic driving framework that supervises a driving VLA with rule-grounded reasoning traces extracted directly from classical rule-based planners. Our key observation is that rule-based planners are symbolic AI systems that already function as executable reasoning engines: they reason about active safety constraints, search over candidate maneuvers, and select a final trajectory. We instrument these planners in simulation to capture both the executed trajectory and the internal decision trace at each rule-evaluation step. Each trace is serialized into structured rule-grounded reasoning and paired with the trajectory to fine-tune Qwen3.5-4B as a driving VLA. Because these traces are derived directly from the planner states that determine the action, they ensure reasoning is structurally coupled to motion generation by construction, rather than by post-hoc alignment. On our simulator-generated benchmark, detailed rule-grounded reasoning reduces ADE@3s from 0.47 to 0.26 and miss rate from 8.30% to 6.40% under three-camera perception, and from 0.54 to 0.26 and 10.13% to 5.99% under eight-camera perception. Neuro-Symbolic Drive thus converts neuro-symbolic planning logic into structured supervision. Code base: https://github.com/XiangboGaoBarry/Neural-Symbolic-Drive.
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。
