AI RESEARCH
CausalVAD: De-confounding End-to-End Autonomous Driving via Causal Intervention
arXiv CS.LG
•
ArXi:2603.18561v1 Announce Type: cross Planning-oriented end-to-end driving models show great promise, yet they fundamentally learn statistical correlations instead of true causal relationships. This vulnerability leads to causal confusion, where models exploit dataset biases as shortcuts, critically harming their reliability and safety in complex scenarios. To address this, we