SOURCE-LINKED INTELLIGENCE

Testing Between the Test Cases: Proving End-to-End Steering in Conditions You Never Drove

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

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 disturban

Read original source ↗ Open in workspace

recordType

paper

region

Global