将复杂操作分解为原子动作，提升通用视觉语言动作模型的泛化能力。
Atomic Action Slicing: Planner-Aligned Options for Generalist VLA Agents
- 将长程示范拆分为短时序、带类型标签的原子动作，适配规划器使用。
- 在LIBERO数据集上，任务成功率提升至95.3%（原94.2%）和88.8%（原83.8%）。
- 适合需要强泛化与组合新技能的机器人控制研究者使用。
当前视觉-语言-动作（VLA）模型泛化能力差，尤其在需要新技能或物体组合的任务中表现不佳。本文提出原子动作切分（AAS），一种与规划器对齐的方法，将长程示范分解为短时序、带类型标签的原子动作，更易被规划器使用且利于策略学习。基于LIBERO示范数据，AAS构建了包含2,124个原子片段的标注数据集，每个片段标注动作类型、时间跨度与置信度。更强的分割器（Gemini 2.5 Pro）能紧密匹配规划定义的计划，并在关键帧抖动下保持鲁棒性；而小型模型在多物体任务中表现较差。在原子数据集上微调CLIP-RT+后，LIBERO-Goal任务成功率从94.2%提升至95.3%，LIBERO-Long任务从83.8%提升至88.8%。数据集已公开发布于HuggingFace（https://huggingface.co/datasets/gate-institute/GATE-VLAP-datasets）。
原文摘要 · Abstract (English)
Current vision-language-action (VLA) models generalize poorly, particularly when tasks require new compositions of skills or objects. We introduce Atomic Action Slicing (AAS), a planner-aligned approach that decomposes long-horizon demonstrations into short, typed atomic actions that are easier for planners to use and policies to learn. Using LIBERO demonstrations, AAS produces a validated dataset of 2,124 atomic segments labeled with action type, temporal span, and confidence. A stronger segmenter (Gemini 2.5 Pro) closely matches planner-defined plans and remains robust under keyframe jitter, while smaller models perform worse on multi-object tasks. Fine-tuning CLIP-RT+ on our atomic dataset improves task success from 94.2% to 95.3% on LIBERO-Goal and 83.8% to 88.8% on LIBERO-Long. We publicly release the GATE-VLAP dataset on HuggingFace(https://huggingface.co/datasets/gate-institute/GATE-VLAP-datasets)
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。