提出并行解码框架PD-VLA，让视觉语言动作模型在保持性能的同时提速2.5倍。
PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding
- 将自回归解码重构为并行固定点迭代，突破串行生成瓶颈。
- 在7自由度机械臂上实现2.52倍执行频率提升，成功率不下降。
- 无需修改模型结构，可无缝集成现有加速技术，适合工业部署。
视觉-语言-动作（VLA）模型在通用机器人操作中展现出巨大潜力。通过引入动作分块（action chunking）可显著提升控制效果，但其线性增加动作维度，导致推理效率下降。为此，我们提出首个集成动作分块的并行解码框架PD-VLA。该框架将自回归解码重构为非线性系统，通过并行固定点迭代求解，数学上保证性能不变的同时大幅提升推理速度。该方法无需训练且不改变模型架构，可与现有加速技术无缝协同。大量仿真验证表明，PD-VLA在7自由度机械臂上相较基础VLA模型实现2.52倍执行频率提升，同时保持竞争力的成功率。实机实验进一步证明其在多种任务中的高适用性。
原文摘要 · Abstract (English)
Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation. The performance of VLA models can be improved by integrating with action chunking, a critical technique for effective control. However, action chunking linearly scales up action dimensions in VLA models with increased chunking sizes. This reduces the inference efficiency. To tackle this problem, we propose PD-VLA, the first parallel decoding framework for VLA models integrated with action chunking. Our framework reformulates autoregressive decoding as a nonlinear system solved by parallel fixed-point iterations. This approach preserves model performance with mathematical guarantees while significantly improving decoding speed. In addition, it enables training-free acceleration without architectural changes, as well as seamless synergy with existing acceleration techniques. Extensive simulations validate that our PD-VLA maintains competitive success rates while achieving 2.52 times execution frequency on manipulators (with 7 degrees of freedom) compared with the fundamental VLA model. Furthermore, we experimentally identify the most effective settings for acceleration. Finally, real-world experiments validate its high applicability across different tasks.
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。