从真实轨迹数据中学习自动驾驶多目标最优权衡边界
Learning the Pareto Space of Multi-Objective Autonomous Driving: A Modular, Data-Driven Approach
- 用安全、效率、交互复合得分构建统一目标空间
- 仅0.23%驾驶实例达帕累托最优，交互改进潜力最大
- 仅需运动数据即可模块化应用，适合多场景评估
平衡安全性、效率与交互是设计自动驾驶代理和理解车辆实际行为的核心。本文提出一种基于自然轨迹数据的实证学习框架，通过复合得分表征每个时间步的自动驾驶状态，利用帕累托支配识别非劣解，构建可实现的性能前沿。在Foggy Bottom和I-395的第三代仿真数据集（TGSIM）上验证，仅有0.23%的驾驶实例达到帕累托最优，表明多目标同时优化极为罕见。帕累托最优状态在安全、效率与交互上均显著优于非最优案例，其中交互指标提升空间最大。该框架无需额外标注，仅依赖运动与位置数据，具有高度模块化和非侵入性，可直接推广至其他场景以生成和可视化多目标学习曲面。
原文摘要 · Abstract (English)
Balancing safety, efficiency, and interaction is fundamental to designing autonomous driving agents and to understanding autonomous vehicle (AV) behavior in real-world operation. This study introduces an empirical learning framework that derives these trade-offs directly from naturalistic trajectory data. A unified objective space represents each AV timestep through composite scores of safety, efficiency, and interaction. Pareto dominance is applied to identify non-dominated states, forming an empirical frontier that defines the attainable region of balanced performance. The proposed framework was demonstrated using the Third Generation Simulation (TGSIM) datasets from Foggy Bottom and I-395. Results showed that only 0.23\% of AV driving instances were Pareto-optimal, underscoring the rarity of simultaneous optimization across objectives. Pareto-optimal states showed notably higher mean scores for safety, efficiency, and interaction compared to non-optimal cases, with interaction showing the greatest potential for improvement. This minimally invasive and modular framework, which requires only kinematic and positional data, can be directly applied beyond the scope of this study to derive and visualize multi-objective learning surfaces
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。