在测试用例之间进行测试：在从未驾驶过的条件下证明端到端转向
Testing Between the Test Cases: Proving End-to-End Steering in Conditions You Never Drove
- Western Michigan University（西密歇根大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出用边界传播形式化验证方法，在未驾驶条件下证明端到端转向策略的可靠性，并发现测试用例间的潜在失败，表明其可作为模拟测试的有效补充。
AI中文摘要：
基于AI的自动驾驶车辆测试具有挑战性，因为通过所有测试条件的模型在现实世界中仍可能失败。形式化验证提供了一种直接解决这一差距的方法。在模拟高速公路和主干道上，我们在CARLA中分别训练了两个小型端到端转向网络，一个仅在晴朗条件下训练，另一个在晴朗、雾天、夜晚和低日照条件下训练。所有四个模型均在2.19英尺的车道偏离预算下进行驾驶测试。在不重新驾驶的情况下，我们使用边界传播（一种读取训练权重的形式化方法）来计算在两张捕获图像之间每个扰动强度下转向可能漂移的程度。一次计算覆盖的范围超过了一场测试活动所能驾驶的范围：在主干道上，它涵盖133个姿态，若每个姿态有10种强度，则组合数可达10^133，而计算仅在单块GPU上花费几分钟。形式化验证不仅发现了未经模拟测试即可破坏晴朗训练策略的条件，还为测试用例之间可能存在的失败提供了一些初步证据。我们的总体结论是，形式化验证是模拟的有效补充，可作为自动驾驶验证与确认的一部分被采用。
英文摘要：
AI-based automated vehicle testing is challenging because a model that passes every test condition can still fail in the real world. Formal verification offers a way to directly address this gap. On a simulated highway and an arterial road we trained two small end-to-end steering networks each in CARLA, one on clear conditions alone and one on clear, fog, night and low sun. All four models were driven against a 2.19 ft lane-departure budget. Without driving again, we used bound propagation, a formal method that reads the trained weights, to compute how far steering can drift at every disturbance strength between two captured images. One calculation covers more than a campaign could drive: on the arterial it spans 133 poses, where ten intensities each would be 10^133 combinations, in minutes on one GPU. Not only did formal verification find conditions that broke the clear-trained policy without simulation testing, it provided some preliminary evidence for potential failures between the test cases. Our overall conclusion is that formal verification is a viable complement to simulation, and could be adopted as a part of verification and validation for automated driving.
