将机器人操作分为移动与接触两阶段，提升精准抓取成功率。
Move-Then-Operate: Behavioral Phasing for Human-Like Robotic Manipulation
- 分阶段控制：先粗略移动，再精细操作，结构更清晰。
- 成功率68.9%，比单一策略高24%，训练更快更省数据。
- 适合需要高精度动作的工业机器人场景。
我们提出一种视觉语言动作框架Move-Then-Operate，将机器人操作显式分解为粗略重定位（move）和接触关键交互（operate）两个阶段。不同于将两种行为混为一体的单体策略，该方法采用双专家政策，由可学习的阶段选择器路由，引入结构归纳偏置以分离各阶段动态。阶段标签通过基于多模态大模型的管道自动生成，依赖末端执行器速度等轻量上下文线索，确保与人类运动模式对齐。在RoboTwin2基准上，该方法平均成功率达68.9%，较单体基线π₀提升24%。其性能媲美甚至超过在10倍更多数据上训练的模型，且仅需40%的训练步数达到峰值表现，证明显式解耦移动与操作阶段是掌握高精度操作的有效高效策略。
原文摘要 · Abstract (English)
We present Move-Then-Operate, a Vision language action framework that explicitly decouples robotic manipulation into two distinct behavioral phases: coarse relocation (move) and contact-critical interaction (operate). Unlike monolithic policies that conflate these heterogeneous regimes, our architecture employs a dual-expert policy routed by a learnable phase selector, introducing a structural inductive bias that isolates phase-specific dynamics. Phase labels are automatically generated via an MLLM-based pipeline conditioned on lightweight contextual cues such as end-effector velocity and subtask decomposition to ensure alignment with human motor patterns. Evaluated on the RoboTwin2 benchmark, our method achieves an average success rate of $68.9\%$, outperforming the monolithic $π_0$ baseline by $24\%$. It matches or exceeds models trained on $10\times$ more data and reaches peak performance in $40\%$ fewer training steps, demonstrating that architectural disentanglement of move and operate phases is a highly effective and efficient strategy for mastering high-precision manipulation.
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。