提出并行推理方法，让自动驾驶决策更快更实时。
Accelerating Structured Chain-of-Thought in Autonomous Vehicles
- 将思维链分解为可并行的子任务，减少串行计算
- 实测推理速度提升3-4倍，端到端延迟显著降低
- 适合对响应速度要求高的自动驾驶系统
思维链（CoT）推理能增强视觉-语言-动作模型在自动驾驶中的决策能力，但其自回归特性导致推理延迟高，难以满足实时应用需求。为此，我们提出FastDriveCoT，一种新型并行解码方法，用于加速模板结构化的思维链。该方法将推理过程分解为独立子任务的依赖图，如关键物体识别和交通规则总结，其中部分任务可并行生成。通过在单次前向传播中同时生成多个独立推理步骤，显著减少了串行计算量。实验表明，该方法在多种模型架构下实现3-4倍的思维链生成速度提升，并大幅降低端到端延迟，同时保持引入思维链后带来的下游任务性能优势。
原文摘要 · Abstract (English)
Chain-of-Thought (CoT) reasoning enhances the decision-making capabilities of vision-language-action models in autonomous driving, but its autoregressive nature introduces significant inference latency, making it impractical for real-time applications. To address this, we introduce FastDriveCoT, a novel parallel decoding method that accelerates template-structured CoT. Our approach decomposes the reasoning process into a dependency graph of distinct sub-tasks, such as identifying critical objects and summarizing traffic rules, some of which can be generated in parallel. By generating multiple independent reasoning steps concurrently within a single forward pass, we significantly reduce the number of sequential computations. Experiments demonstrate a 3-4$\times$ speedup in CoT generation and a substantial reduction in end-to-end latency across various model architectures, all while preserving the original downstream task improvements brought by incorporating CoT reasoning.
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。