研究人员引入了一个名为滚动检索终身策略学习 (R$^2$LPL) 的新框架，旨在使自动驾驶策略能够通过从自身错误中学习来持续改进。该方法解决了闭环场景中的失败会突出策略弱点，但不会明确定义纠正措施的挑战。R$^2$LPL 过滤可恢复的与错误相关的状态并检索可行的纠正目标，将稀疏的失败证据转化为监督知识，以实现稳定高效的策略增强。在 nuPlan 基准测试上的评估表明，R$^2$LPL 在仅几个学习周期后，显著提升了初始策略的性能至最先进水平，尤其是在困难的长尾场景下。 AI
影响 该框架通过从真实驾驶数据中持续改进，有望带来更强大、更具适应性的自动驾驶系统。
排序理由 该集群包含一篇详细介绍自动驾驶策略学习新框架的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.30537v1 Announce Type: cross Abstract: Autonomous driving policies should be able to improve continually as deployment exposes them to increasingly diverse and long-tail traffic situations. However, most learning-based policies are trained or fine-tuned on expert demon…
Autonomous driving policies should be able to improve continually as deployment exposes them to increasingly diverse and long-tail traffic situations. However, most learning-based policies are trained or fine-tuned on expert demonstrations and then rely largely on generalization …