ColaVLA：利用认知潜变量推理实现自动驾驶中的层级并行轨迹规划
ColaVLA: Leveraging Cognitive Latent Reasoning for Hierarchical Parallel Trajectory Planning in Autonomous Driving
把 VLM 的文本思维链推理迁移到统一潜空间，并用层级并行解码器一次前向输出多尺度轨迹，为视觉研究者提供了「潜变量推理 + 并行轨迹头」这一可复用范式，可显著降低 VLM 规划器的自回归延迟。
原文依据 transfers reasoning from text to a unified latent space and couples it with a hierarchical, parallel trajectory decoder
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论自动驾驶需要从复杂的多模态输入中生成安全可靠的轨迹。传统模块化流水线将感知、预测与规划分离，而近期的端到端（E2E）系统则对三者进行联合学习。视觉语言模型（VLM）通过引入跨模态先验与常识推理进一步丰富了这一范式，然而当前基于 VLM 的规划器面临三个关键挑战：（i）离散文本推理与连续控制之间的失配；（ii）自回归思维链解码带来的高延迟；（iii）低效或非因果的规划器限制了实时部署。我们提出 ColaVLA，一个统一的视觉-语言-动作框架，将推理从文本迁移到统一潜空间，并与层级并行轨迹解码器相耦合。认知潜变量推理器通过自我自适应选择与仅两次 VLM 前向传播，将场景理解压缩为紧凑的、面向决策的元动作嵌入。层级并行规划器随后在单次前向传播中生成多尺度、因果一致的轨迹。二者结合，在保持 VLM 泛化性与可解释性的同时，实现了高效、准确且安全的轨迹生成。在 nuScenes 基准上的实验表明，ColaVLA 在开环与闭环设置下均取得最优性能，并具有良好的效率与鲁棒性。
英文原文摘要 1449 字符
Autonomous driving requires generating safe and reliable trajectories from complex multimodal inputs. Traditional modular pipelines separate perception, prediction, and planning, while recent end-to-end (E2E) systems learn them jointly. Vision-language models (VLMs) further enrich this paradigm by introducing cross-modal priors and commonsense reasoning, yet current VLM-based planners face three key challenges: (i) a mismatch between discrete text reasoning and continuous control, (ii) high latency from autoregressive chain-of-thought decoding, and (iii) inefficient or non-causal planners that limit real-time deployment. We propose ColaVLA, a unified vision-language-action framework that transfers reasoning from text to a unified latent space and couples it with a hierarchical, parallel trajectory decoder. The Cognitive Latent Reasoner compresses scene understanding into compact, decision-oriented meta-action embeddings through ego-adaptive selection and only two VLM forward passes. The Hierarchical Parallel Planner then generates multi-scale, causality-consistent trajectories in a single forward pass. Together, these components preserve the generalization and interpretability of VLMs while enabling efficient, accurate and safe trajectory generation. Experiments on the nuScenes benchmark show that ColaVLA achieves state-of-the-art performance in both open-loop and closed-loop settings with favorable efficiency and robustness.