用大模型自动修复自动驾驶失败案例，实现系统自我进化
From Failures to Fixes: LLM-Driven Scenario Repair for Self-Evolving Autonomous Driving
- 通过分析运行日志识别失败模式，用大模型推荐语义相关场景
- 在多个基准上提升关键指标，少样本微调即见效
- 适合需要安全迭代的自动驾驶研发团队
确保自动驾驶系统的鲁棒性和泛化能力，不仅需要广泛的情境覆盖，还需高效修复失败案例，尤其是复杂且安全关键的情境。然而，现有情景生成与选择方法常缺乏自适应性与语义相关性，限制了性能提升效果。本文提出SERA框架，一种基于大模型的方案，使自动驾驶系统可通过针对性情景推荐实现自我演化。通过分析性能日志，SERA识别失败模式，并从结构化情境库中动态检索语义对齐的情景；基于大模型的反思机制进一步优化推荐，以最大化相关性与多样性。所选情景用于少样本微调，实现最小数据下的精准适配。实验表明，SERA在多个基准测试中持续提升关键指标，在安全关键条件下展现出有效性与泛化能力。
原文摘要 · Abstract (English)
Ensuring robust and generalizable autonomous driving requires not only broad scenario coverage but also efficient repair of failure cases, particularly those related to challenging and safety-critical scenarios. However, existing scenario generation and selection methods often lack adaptivity and semantic relevance, limiting their impact on performance improvement. In this paper, we propose \textbf{SERA}, an LLM-powered framework that enables autonomous driving systems to self-evolve by repairing failure cases through targeted scenario recommendation. By analyzing performance logs, SERA identifies failure patterns and dynamically retrieves semantically aligned scenarios from a structured bank. An LLM-based reflection mechanism further refines these recommendations to maximize relevance and diversity. The selected scenarios are used for few-shot fine-tuning, enabling targeted adaptation with minimal data. Experiments on the benchmark show that SERA consistently improves key metrics across multiple autonomous driving baselines, demonstrating its effectiveness and generalizability under safety-critical conditions.
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。