用大模型+记忆系统实现自动驾驶长期自适应规划，应对罕见场景。
LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios
- 结合大模型与记忆增强的规划系统，支持持续学习新场景。
- 在nuPlan基准上优于静态规则与学习型规划器，罕见场景表现更优。
- 适合关注自动驾驶长尾问题与可进化系统的研究人员。
近期自动驾驶研究聚焦于鲁棒、安全且自适应的运动规划器。然而，现有基于规则和数据驱动的规划器难以适应长尾场景，而知识驱动方法虽具强推理能力，却面临表征、控制与真实世界评估的挑战。为此，我们提出LiloDriver，一种面向长尾自动驾驶场景的闭环运动规划终身学习框架。通过将大语言模型（LLMs）与记忆增强的规划生成系统融合，LiloDriver可在不重新训练的情况下持续适应新场景。其四阶段架构包括感知、场景编码、基于记忆的策略优化以及大模型引导的推理。在nuPlan基准上的评估显示，该框架在常见与罕见驾驶场景中均表现优异，显著超越静态规则与学习型规划器。结果表明，结构化记忆与大模型推理结合，能实现可扩展的人类级运动规划，适用于真实自动驾驶。代码已开源：https://github.com/Hyan-Yao/LiloDriver。
原文摘要 · Abstract (English)
Recent advances in autonomous driving research towards motion planners that are robust, safe, and adaptive. However, existing rule-based and data-driven planners lack adaptability to long-tail scenarios, while knowledge-driven methods offer strong reasoning but face challenges in representation, control, and real-world evaluation. To address these challenges, we present LiloDriver, a lifelong learning framework for closed-loop motion planning in long-tail autonomous driving scenarios. By integrating large language models (LLMs) with a memory-augmented planner generation system, LiloDriver continuously adapts to new scenarios without retraining. It features a four-stage architecture including perception, scene encoding, memory-based strategy refinement, and LLM-guided reasoning. Evaluated on the nuPlan benchmark, LiloDriver achieves superior performance in both common and rare driving scenarios, outperforming static rule-based and learning-based planners. Our results highlight the effectiveness of combining structured memory and LLM reasoning to enable scalable, human-like motion planning in real-world autonomous driving. Our code is available at https://github.com/Hyan-Yao/LiloDriver.
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。