DriveZero: End-to-End Driving Beyond Human Demonstrations
DriveZero pairs a frozen vision-foundation-model perception stack with a PPO-trained closed-loop RL teacher to beat replay experts on nuPlan.
DriveZero is an end-to-end camera-only autonomous-driving planner that separates perception and action. Its DriveVFM perception backbone consolidates frozen vision foundation models (DINOv3, SigLIP2, SAM, Depth Anything V2) from raw images without task annotations, while DriveRL trains a privileged PPO teacher policy through closed-loop rollouts in interactive worlds built from real driving logs. The planner distills this teacher, achieving a 93.57 mean nuPlan score across Val14, Test14-hard and Test14-random splits and beating the Log-Replay expert on all three. It also sets state of the art on NAVSIMv1, NAVSIMv2 and closed-loop HUGSIM without human trajectory supervision.
- DriveRL trains a PPO privileged teacher in closed-loop simulated worlds
- DriveVFM merges DINOv3, SigLIP2, SAM and Depth Anything V2, no annotations
- 93.57 mean nuPlan score, above Log-Replay expert on all splits
- SOTA on NAVSIMv1, NAVSIMv2 and HUGSIM with no human trajectory data
- Tags
- autonomous-drivingdrivezeroend-to-end-planningnavsimnuplanreinforcement-learningvision-foundation-models
- Products
- DriveZero
From the original article
1 min read at huggingface.co
Most end-to-end autonomous-driving systems learn by imitating human driving logs, leaving their learned behavior constrained by the quality and behavioral coverage of the recorded trajectories. This report presents DriveZero, an end-to-end system that learns driving behavior beyond human demonstrations.
By Hao He, Chengcheng Hu, Zirun Su · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.