提出新方法提升自动驾驶模型在分布外场景下的适应能力
LoRD: Adapting Differentiable Driving Policies to Distribution Shifts
- 采用低秩残差解码器与多任务微调，优化端到端自动驾驶系统
- 相比标准微调，减少23.33%灾难性遗忘，闭环泛化性能提升9.93%
- 首次在闭环环境下验证方法有效性，适用于真实驾驶场景迁移
自动驾驶车辆在不同运行域间存在分布偏移，严重影响学习模型性能。以往研究多聚焦于运动预测任务的简单微调，忽视了规划与控制等模块的协同适应。本文针对包含预测、规划、控制的可微分自主系统，提出两种高效策略：低秩残差解码器（LoRD）和多任务微调，并在nuPlan、exiD两个真实数据集上进行闭环评估。实验表明，所提方法显著优于传统微调，在闭环分布外场景下驾驶得分提升9.93%，同时减少23.33%的灾难性遗忘。结果揭示了开环与闭环评估间的巨大性能差距，强调闭环测试对真实场景迁移的重要性。
原文摘要 · Abstract (English)
Distribution shifts between operational domains can severely affect the performance of learned models in self-driving vehicles (SDVs). While this is a well-established problem, prior work has mostly explored naive solutions such as fine-tuning, focusing on the motion prediction task. In this work, we explore novel adaptation strategies for differentiable autonomy stacks consisting of prediction, planning, and control, perform evaluation in closed-loop, and investigate the often-overlooked issue of catastrophic forgetting. Specifically, we introduce two simple yet effective techniques: a low-rank residual decoder (LoRD) and multi-task fine-tuning. Through experiments across three models conducted on two real-world autonomous driving datasets (nuPlan, exiD), we demonstrate the effectiveness of our methods and highlight a significant performance gap between open-loop and closed-loop evaluation in prior approaches. Our approach improves forgetting by up to 23.33% and the closed-loop OOD driving score by 9.93% in comparison to standard fine-tuning.
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。