给自动驾驶模型加个安全守卫，实时纠正违规指令。
Herding End-to-End Autonomous Driving via Neuro-Symbolic Safety Guards
- 用符号规则+神经网络结合的轻量模块，实时审查驾驶指令
- 在两个长尾数据集上使成功率提升15%，致命碰撞减少53%
- 无需重训模型，可解释性强，适合已部署的端到端系统
现代端到端驾驶代理虽平均表现优异，但仍会违反人类司机不会犯的基本交通规则。根源在于其学习的是统计模式而非保障安全的物理条件，导致决策过程不透明且安全约束未被强制执行。本文提出一种神经符号安全守卫，作为轻量模块接入已训练好的代理最终命令接口。在指令传至车辆前，该守卫依据明确的安全规则进行检查，仅在必要时用最近的安全替代指令替换原指令。每次干预均直接可执行且可追溯至触发规则，守卫本身无需重新训练，也不引入任何学习组件。以最先进的TransFuser v6（TFv6）为案例，在长尾基准测试Fail2Drive和Bench2Drive上评估，该守卫使成功率提升15%，安全关键碰撞减少最多53%，同时保持原始驾驶得分不变。
原文摘要 · Abstract (English)
Modern end-to-end driving agents can achieve high average performance yet still violate basic traffic rules that a human driver would never miss. The reason is structural: they learn statistical patterns rather than the physical conditions that guarantee safe driving, leaving their decision-making process opaque and safety constraints unenforced. We introduce a neuro-symbolic safety guard, a lightweight module that attaches to the final command interface of an already-trained agent. Immediately before a command reaches the vehicle, it checks the command against explicit safety rules and, only when necessary, replaces it with the nearest safe alternative. Each intervention is directly executable and traceable to the rule that triggered it, while the guard itself requires no retraining and adds no learned component. Evaluated on the long-tail benchmarks Fail2Drive and Bench2Drive using the state-of-the-art TransFuser v6 (TFv6) as a case study, the guard improves Success Rate by 15% and reduces safety-critical collisions by up to 53%, while preserving the original Driving Score.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。