Autonomous Vehicles (AVs) are advancing rapidly, with Level-4 AVs already operating in real-world conditions. Current AVs, however, still lag behind human drivers in adaptability and performance, often exhibiting overly conservative behaviours and occasionally violating traffic laws. Existing solutions, such as runtime enforcement, mitigate this by automatically repairing the AV's planned trajectory at runtime, but such approaches lack transparency and should be a measure of last resort. It would be preferable for AV repairs to generalise beyond specific incidents and to be interpretable for users. In this work, we propose FixDrive, a framework that analyses driving records from near-misses or law violations to generate AV driving strategy repairs that reduce the chance of such incidents occurring again. These repairs are captured in {\mu}Drive, a high-level domain-specific language for specifying driving behaviours in response to event-based triggers. Implemented for the state-of-the-art autonomous driving system Apollo, FixDrive identifies and visualises critical moments from driving records, then uses a Multimodal Large Language Model (MLLM) with zero-shot learning to generate {\mu}Drive programs. We tested FixDrive on various benchmark scenarios, and found that the generated repairs improved the AV's performance with respect to following traffic laws, avoiding collisions, and successfully reaching destinations. Furthermore, the direct costs of repairing an AV -- 15 minutes of offline analysis and $0.08 per violation -- are reasonable in practice.

翻译：自动驾驶车辆（AVs）正快速发展，L4级自动驾驶车辆已在现实条件下运行。然而，当前自动驾驶车辆在适应性和性能方面仍落后于人类驾驶员，常表现出过于保守的行为，并偶尔违反交通法规。现有解决方案（如运行时强制执行）通过在运行时自动修复自动驾驶车辆的规划轨迹来缓解此问题，但此类方法缺乏透明度，应作为最后手段。更理想的方式是使自动驾驶车辆的修复能够泛化至特定事件之外，并对用户具有可解释性。本文提出FixDrive框架，该框架通过分析来自险情或违规事件的驾驶记录，生成自动驾驶车辆驾驶策略修复方案，以降低此类事件再次发生的概率。这些修复方案由{\mu}Drive捕获——这是一种用于描述基于事件触发的驾驶行为的高级领域特定语言。FixDrive针对前沿自动驾驶系统Apollo实现，能够从驾驶记录中识别并可视化关键时刻，随后利用具备零样本学习能力的多模态大语言模型（MLLM）生成{\mu}Drive程序。我们在多种基准场景中对FixDrive进行测试，发现生成的修复方案在遵守交通法规、避免碰撞及成功抵达目的地方面有效提升了自动驾驶车辆性能。此外，修复自动驾驶车辆的直接成本——15分钟离线分析及每次违规0.08美元——在实践中处于合理范围。