CausalDrive splits "where to go" from "how to drive" in end-to-end driving, reaching 91.2 PDMS on NAVSIM v1
End-to-end driving policies usually imitate an expert trajectory as one target, yet similar trajectories can arise from different intentions and execution styles, leaving their contributions entangled. CausalDrive splits supervision in two: a deterministic nominal intention planner trained on style-free counterfactual trajectories built from the navigation command, map topology and ego state, and a diffusion-based style policy that models multimodal residuals between nominal and expert trajectories. It reaches 91.2 PDMS on NAVSIM v1 and 89.5 EPDMS on NAVSIM v2, matching or surpassing the best of the compared methods.