论文/arXiv 2606.07464·2 个月前

面向长上下文自动驾驶的规划对齐 Token 压缩

针对长时上下文使视觉-动作模型超出实时预算的问题，COMPACT-VA用规划对齐条件VQ-VAE压缩记忆，并在动态驾驶场景验证。

AI 整理

• 本体 SDK 与控制
• 具身模型
• 端侧部署

原文链接：Planning-Aligned Token Compression for Long-Context Autonomous Driving（arXiv 2606.07464 · 发布日期：2026-08-28）

Planning-Aligned Token Compression for Long-Context Autonomous Driving

针对长时上下文使视觉-动作模型超出实时预算的问题，COMPACT-VA用规划对齐条件VQ-VAE压缩记忆，并在动态驾驶场景验证。

核心要点

• 长时上下文会让单体视觉-动作模型的token序列超出实时计算预算。
• COMPACT-VA以条件VQ-VAE构建规划对齐工作记忆，压缩为有界表示。
• 压缩同时依赖历史轨迹和由未来轨迹蒸馏出的规划意图，并端到端优化策略。
• 同等token预算下成功率提升超过6%，闭环评估获3.3倍加速和2.7倍内存降低。

验证范围与局限：验证范围为高信号动态驾驶场景及闭环评估，摘要未说明真机或具体平台。

英文摘要 (Abstract)

Monolithic vision-action models represent an emerging paradigm in autonomous driving. However, this architecture produces token sequences that quickly exceed real-time computational budgets when encoding extended temporal context for complex interactions. While approaches like linear transformers and external memory try to make the context lightweight, token compression is most compatible with the architecture as it requires no backbone modifications. Yet existing compression adopts rule-based heuristics like temporal decay, decoupled from planning, risking loss of decision-critical information. We propose COMPACT-VA, a planning-aligned working memory framework built on conditional VQ-VAE, compressing extended context into bounded representations. Compression is conditioned on both historical trajectory and a learned planning intent that the posterior encoder distills from future trajectories during training, while the prior encoder learns to predict it from compressed observations. The compressed memory, concatenated with the predicted latent, feeds the policy for end-to-end optimization, planning with retained decision-critical information. We evaluate on high-signal dynamic scenarios where historical context is most critical for behavior correctness (e.g., stop, yield, or proceed), and accordingly design behavioral metrics. Under comparable token budgets, we achieve $>$6% improvement (68.3%) on success rates with consistent gains across metrics. Ablations validate planning-aligned coupling effectiveness. Closed-loop evaluation confirms that COMPACT-VA maintained general driving performance with 3.3* speedup and 2.7* memory reduction over uncompressed processing.

作者：Zhixuan Liang, Yuxiao Chen, Yurong You, Péter Karkus, Wenhao Ding, Boyi Li, Alexander Popov, Yan Wang, Maximilian Igl, Yiming Li

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2606.07464：Planning-Aligned Token Compression for Long-Context Autonomous Driving访问 2026-10-21