Skip to content

论文arXiv 2611.177206 天前

Ego2Flow发布:基于真实地图蒸馏的自动驾驶交通系统级闭环评测基准 ​

本文由 AI 根据公开内容整理,可能有误,请以原文为准:Ego2Flow: Benchmarking the Traffic-System Impact of Autonomous Driving on Maps Distilled from Real-World Roads(arXiv 2611.17720)

核心内容 ​

针对端到端自动驾驶在城市交通中集体交互效应评估不足的问题,研究团队推出Ego2Flow闭环评测基准。该工作突破了仅关注单车安全的局限,聚焦自动驾驶策略对整体交通系统的效率、稳定性及能耗影响。基于Argoverse 2数据集,团队构建并开源了6张高保真CARLA地图,支持真实世界与仿真环境下的驾驶行为配对比较,为系统级影响分析提供了标准化数据基础。

技术上采用Agent引导的地图蒸馏框架,融合真实地图、观测数据与地理信息生成3D城市场景。通过迭代反馈机制与交通信息图联合指导,在保留车道拓扑、关键几何及决策相关视觉条件的同时简化非必要细节并补全未观测区域。实验表明,该方法在配对真实与仿真观测的规划输出平均位移误差上优于现有构建方法,有效支撑了代表性驾驶策略在复杂路网下的系统级性能表征。

关键看点 ​

  • 地图蒸馏框架:集成真实地图与GIS数据,利用迭代反馈与交通信息图保留车道拓扑及决策视觉条件,补全未观测区域以支撑闭环仿真。
  • 开源数据集:发布6张源自Argoverse 2的CARLA地图,覆盖真实城市区域,支持真实与仿真观测下的驾驶行为配对对比验证。
  • 系统级评测维度:超越单车安全指标,量化评估自动驾驶策略在不同道路结构下对交通效率、安全性、稳定性及能源消耗的综合影响。
  • 规划一致性验证:相比现有方法,该框架生成的场景在配对真实与仿真观测下的规划输出平均位移误差最低,确保仿真置信度。

工程与产业观察 ​

该工作填补了具身智能从单车智能迈向交通系统级评估的空白。其地图蒸馏方法论可直接迁移至机器人城市导航仿真,解决Sim-to-Real中语义与几何不一致难题。开源的高保真配对地图资产,为验证端到端模型在复杂交互场景下的泛化能力提供了关键基础设施,推动算法评价从任务完成率向系统兼容性演进。

英文摘要 (Abstract) ​

End-to-end autonomous driving is predominantly evaluated through ego-vehicle safety and task completion. Its deployment in urban traffic, however, creates sustained interactions among vehicles whose collective effects remain insufficiently evaluated. We introduce Ego2Flow, a closed-loop benchmark for assessing the traffic-system impact of autonomous driving on maps distilled from real-world cities. To construct realistic 3D urban environments for sustained closed-loop traffic simulation, we develop an agent-guided map distillation framework that integrates real-world maps and observations with complementary geographic information. Through an iterative feedback mechanism and a traffic information graph that jointly guide scene generation, the framework preserves lane topology, critical road geometry and decision-relevant visual conditions while simplifying nonessential details and completing unobserved regions. Using our proposed framework, we generate and publicly release six CARLA maps from the Argoverse 2 dataset, covering the corresponding real-world regions and enabling paired comparisons of driving behavior under real and simulated observations. On these maps, Ego2Flow evaluates how autonomous driving policies affect traffic efficiency, safety, stability and energy consumption across diverse road structures. Compared with existing construction methods, our framework achieves the lowest average displacement error between planning outputs from paired real and simulated observations. We further benchmark representative driving policies to characterize their system-level impact on urban traffic. Project Page: https://github.com/Fisher-007/Ego2Flow.

作者:Yu Dong, Weiying Shen, Hangyu Li, Shu Han, Hong Li, Xiangbo Gao, Keshu Wu, Zhengzhong Tu, Soyoung Ahn, Zhiyuan Liu, Xiaopeng Li

基于本页技术方向关联的整机参数、核心零部件、实测报告与同赛道选型横评。

外部来源

本页事实对应的公开页面,以原文为准。(点击将离开本站)

  1. arXiv 2611.17720:Ego2Flow: Benchmarking the Traffic-System Impact of Autonomous Driving on Maps Distilled from Real-World Roads ↗访问 2026-11-16