arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.24949cs.ROcs.AIcs.CVcs.LG
收藏

SCOUT:一种用于自动驾驶场景覆盖度评估的轻量级框架

SCOUT: A Lightweight Framework for Scenario Coverage Assessment in Autonomous Driving

Department of Aeronautics and Astronautics, Stanford University(航空航天工程系,斯坦福大学);Nuro Inc.(Nuro公司)

Anil Yildiz, Sarah M. Thornton, Carl Hildebrandt, Sreeja Roy-Singh, Mykel J. Kochenderfer

AI总结:

针对自动驾驶场景覆盖度评估现有方法成本高、效率低的问题,提出轻量级框架SCOUT,通过蒸馏学习逼近LVLM生成的标签,利用预计算感知特征实现快速可扩展的评估,在真实场景数据集上验证了其高精度与低成本优势。

摘要:

评估场景覆盖度对于衡量自动驾驶智能体的鲁棒性至关重要,但现有方法依赖成本高昂的人工标注或计算密集型的大视觉语言模型(LVLM)。受成本和效率限制,这些方法难以大规模部署。为解决这些不足,我们提出SCOUT(场景覆盖度监督与理解工具),这是一种轻量级代理模型,可直接根据智能体的传感器潜在表征预测场景覆盖度标签。SCOUT通过蒸馏过程训练,学习逼近LVLM生成的覆盖度标签,无需持续调用LVLM推理,也无需人工标注。通过利用预计算的感知特征,SCOUT避免了冗余计算,可实现快速、可扩展的场景覆盖度估算。我们在包含大量真实自动驾驶导航场景的数据集上评估了该方法,结果表明其在保持高精度的同时显著降低了计算成本。研究结果显示,SCOUT为大规模覆盖度分析提供了有效且实用的替代方案。尽管其性能依赖于LVLM生成的训练标签的质量,但SCOUT仍是迈向自动驾驶系统高效场景覆盖度监督的重要一步。

英文摘要:

Assessing scenario coverage is crucial for evaluating the robustness of autonomous agents, yet existing methods rely on expensive human annotations or computationally intensive Large Vision-Language Models (LVLMs). These approaches are impractical for large-scale deployment due to cost and efficiency constraints. To address these shortcomings, we propose SCOUT (Scenario Coverage Oversight and Understanding Tool), a lightweight surrogate model designed to predict scenario coverage labels directly from an agent's latent sensor representations. SCOUT is trained through a distillation process, learning to approximate LVLM-generated coverage labels while eliminating the need for continuous LVLM inference or human annotation. By leveraging precomputed perception features, SCOUT avoids redundant computations and enables fast, scalable scenario coverage estimation. We evaluate our method across a large dataset of real-life autonomous navigation scenarios, demonstrating that it maintains high accuracy while significantly reducing computational cost. Our results show that SCOUT provides an effective and practical alternative for large-scale coverage analysis. While its performance depends on the quality of LVLM-generated training labels, SCOUT represents a major step toward efficient scenario coverage oversight in autonomous systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑