Episode
DriveZero: End-to-End Driving Beyond Human Demonstrations
- Podcast
- Daily Paper Cast
- Published
- Sep 9, 2026
- Duration seconds
- 1333
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/b7ae44fe
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/drivezero-end-to-end-driving-beyond-human-demonstrations/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/drivezero-end-to-end-driving-beyond-human-demonstrations.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 43 | cs.CV Authors: Hao He, Chengcheng Hu, Zirun Su, Heng Zhang, Haisong Liu, Jinke Li, Haochen Tian, Zhenwei Shen, Hongyang Li, Zhichao Li, Yunchen Yang, Bochao Huang, Siyu Zhang, Kuangye Chen, Xiongjie Zhang, Wentao Dai, Hengchen Dai, Siyuan Liu, Zehao Huang, Naiyan Wang Title: DriveZero: End-to-End Driving Beyond Human Demonstrations Arxiv: http://arxiv.org/abs/2609.06055v1 Abstract: 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. It decomposes driving into a perception model and an action model, pretrains each in the regime best suited to it, and combines them into one end-to-end planner. The two models call for different learning recipes: perception must understand the world, and benefits from massive and diverse visual data; action must interact with it, and requires closed-loop feedback. On the action side, we introduce DriveRL, a mixed-agent closed-loop reinforcement-learning framework. It converts real driving logs into interactive worlds, where a privileged teacher policy is trained with PPO through closed-loop rollouts. For the perception model, DriveVFM consolidates multiple frozen vision foundation models, including DINOv3, SigLIP2, SAM and Depth Anything V2, into a single backbone from raw images alone, requiring no task-specific annotations. DriveZero then unifies the two: a camera-only planner that distills the frozen DriveRL teacher through its rolled-out trajectories. The goal-conditioned teacher can moreover be queried under augmented driving intents, yielding diverse, goal-consistent su…