用压缩令牌实现高效端到端自动驾驶，性能超越主流模型。
Driving on Registers
- 引入相机感知的注册令牌，压缩多摄像头特征
- 在多个基准上达到或超越现有模型表现
- 支持可解释的驾驶行为条件控制，适合实车部署
我们提出 DrivoR，一种基于 Transformer 的简洁高效端到端自动驾驶架构。该方法基于预训练视觉变换器（ViTs），引入相机感知的注册令牌，将多摄像头特征压缩为紧凑场景表示，显著降低下游计算量而不牺牲精度。这些令牌驱动两个轻量级 Transformer 解码器，分别生成并评分候选轨迹。评分解码器学习模仿理想决策者，预测安全、舒适、效率等可解释子得分，实现推理时的行为条件化驾驶。尽管设计极简，DrivoR 在 NAVSIM-v1、NAVSIM-v2 和拟真闭环 HUGSIM 基准上均优于或匹配当前强基线。结果表明，纯 Transformer 架构结合针对性令牌压缩，足以实现准确、高效且可适应的端到端驾驶。代码与模型检查点将通过项目页面公开。
原文摘要 · Abstract (English)
We present DrivoR, a simple and efficient transformer-based architecture for end-to-end autonomous driving. Our approach builds on pretrained Vision Transformers (ViTs) and introduces camera-aware register tokens that compress multi-camera features into a compact scene representation, significantly reducing downstream computation without sacrificing accuracy. These tokens drive two lightweight transformer decoders that generate and then score candidate trajectories. The scoring decoder learns to mimic an oracle and predicts interpretable sub-scores representing aspects such as safety, comfort, and efficiency, enabling behavior-conditioned driving at inference. Despite its minimal design, DrivoR outperforms or matches strong contemporary baselines across NAVSIM-v1, NAVSIM-v2, and the photorealistic closed-loop HUGSIM benchmark. Our results show that a pure-transformer architecture, combined with targeted token compression, is sufficient for accurate, efficient, and adaptive end-to-end driving. Code and checkpoints will be made available via the project page.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。