开源自动驾驶系统在236公里测试中每公里0.127次中断，暴露感知与规划短板。
Disengagement Analysis and Field Tests of a Prototypical Open-Source Level 4 Autonomous Driving System
- 基于Autoware的开源系统在混合交通中运行，用五级危急度分类分析中断事件。
- 总中断30次，空间中断率0.127次/km，40%因感知丢失，26.7%因路径规划死锁。
- 适合关注开源自动驾驶鲁棒性与安全评估的研究者和开发者参考。
专有自动驾驶系统通常通过“中断”（即人为干预）来评估，这是加州机动车管理局年度报告中的标准做法。然而，原型开源级4级车辆在长距离真实路况下的表现仍不明确。本研究评估了一辆搭载基于Autoware软件栈的自动驾驶车辆，在236公里混合交通环境中的表现。通过对26次行程中的30次中断事件，采用新型五级危急度框架进行分类分析，得出空间中断率为0.127次/km。干预主要发生在低速靠近静态物体和红绿灯处。感知与规划失败分别占40%和26.7%，主因是目标跟踪丢失及停靠车辆引发的运行死锁。频繁且不必要的干预反映出安全驾驶员信任不足。结果表明，尽管开源软件支持大规模部署，但中断分析对发现标准指标忽略的鲁棒性问题至关重要。
原文摘要 · Abstract (English)
Proprietary Autonomous Driving Systems are typically evaluated through disengagements, unplanned manual interventions to alter vehicle behavior, as annually reported by the California Department of Motor Vehicles. However, the real-world capabilities of prototypical open-source Level 4 vehicles over substantial distances remain largely unexplored. This study evaluates a research vehicle running an Autoware-based software stack across 236 km of mixed traffic. By classifying 30 disengagements across 26 rides with a novel five-level criticality framework, we observed a spatial disengagement rate of 0.127 1/km. Interventions predominantly occurred at lower speeds near static objects and traffic lights. Perception and Planning failures accounted for 40% and 26.7% of disengagements, respectively, largely due to object-tracking losses and operational deadlocks caused by parked vehicles. Frequent, unnecessary interventions highlighted a lack of trust on the part of the safety driver. These results show that while open-source software enables extensive operations, disengagement analysis is vital for uncovering robustness issues missed by standard metrics.
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。