Sep 2026
ForeDrive: Foresight-Guided End-to-End Autonomous Driving with a Planning-Relevant Latent World Model
ForeDrive is proposed, which learns a planning-relevant latent representation and couples it asymmetrically to a Diffusion Transformer (DiT) planner and attains 89.9 PDMS on NAVSIM v1 and 90.0 one-stage EPDMS on NAVSIM v2, without reinforcement learning or an external trajectory scorer.
Si-Nuo Wang, Zi-Chong Gu, Yu-Han Huang et al.
· arXiv.org · 0 citations