提出高效实时自动驾驶仿真模型，解决长期滚动中精度与速度问题。
VectorWorld: Efficient Streaming World Model via Diffusion Flow on Vector Graphs
- 用向量图增量生成64×64米地图块，支持实时交互仿真。
- 单步完成图像补全，实现毫秒级响应，满足实时性要求。
- 引入物理对齐的非我方车辆策略，保障长时仿真的稳定性。
自动驾驶策略的闭环评估需要超越日志回放的交互式仿真。然而，现有生成式世界模型在闭环中常因（1）无历史依赖的初始化与策略输入不匹配、（2）多步采样延迟超出实时预算、（3）长时程运动不一致性累积而退化。我们提出VectorWorld，一种流式世界模型，在滚动过程中增量生成以自车为中心的64m×64m车道-智能体向量图块。通过运动感知门控变分自编码器（VAE），VectorWorld实现与历史条件策略兼容的初始状态生成。利用无求解器的一步掩码补全，结合边门控关系扩散变换器（DiT），在区间条件均值流与基于JVP的大步监督下实现实时外推。为稳定长时滚动，提出ΔSim——一种具有混合离散-连续动作的物理对齐非我方车辆策略，并引入可微分运动学逻辑重塑机制。在Waymo开放运动与nuPlan数据集上，VectorWorld提升地图结构保真度与初始状态有效性，支持稳定、实时的1公里以上闭环滚动（代码见：https://github.com/jiangchaokang/VectorWorld）。
原文摘要 · Abstract (English)
Closed-loop evaluation of autonomous-driving policies requires interactive simulation beyond log replay. However, existing generative world models often degrade in closed loop due to (i) history-free initialization that mismatches policy inputs, (ii) multi-step sampling latency that violates real-time budgets, and (iii) compounding kinematic infeasibility over long horizons. We propose VectorWorld, a streaming world model that incrementally generates ego-centric $64 \mathrm{m}\times 64\mathrm{m}$ lane--agent vector-graph tiles during rollout. VectorWorld aligns initialization with history-conditioned policies by producing a policy-compatible interaction state via a motion-aware gated VAE. It enables real-time outpainting via solver-free one-step masked completion with an edge-gated relational DiT trained with interval-conditioned MeanFlow and JVP-based large-step supervision. To stabilize long-horizon rollouts, we introduce $Δ$Sim, a physics-aligned non-ego (NPC) policy with hybrid discrete--continuous actions and differentiable kinematic logit shaping. On Waymo open motion and nuPlan, VectorWorld improves map-structure fidelity and initialization validity, and supports stable, real-time $1\mathrm{km}+$ closed-loop rollouts (\href{https://github.com/jiangchaokang/VectorWorld}{code}).
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。