将机器人操作分解为可复用动作单元，提升学习效率与泛化能力
PrimitiveVLA: Learning Reusable Motion Primitives for Efficient and Generalizable Robotic Manipulation
- 通过多模态表征拆解示范视频，提取通用动作基元
- 在未见过的长序列任务上实现零样本泛化，数据效率提升显著
- 适合需要快速适配新任务的机器人应用场景
视觉-语言-动作（VLA）模型为通用机器人策略提供了前景，但其适应受限于数据效率低和泛化能力差。我们指出，这些瓶颈源于当前直接指令到控制的映射范式，迫使模型记忆完整轨迹而非可复用的动作模式（即基元）。为此，我们提出PrimitiveVLA框架，转向以基元为中心的“拆解-组装”范式。基于共享的多模态共同表示（MCR），该框架包含两个阶段：(1) 微调阶段的拆解，利用自动化流程将示范分解为可复用基元；(2) 推理阶段的组装，采用基于VLM的规划器与LLM生成的切换模块实现鲁棒闭环执行。通过将任务分解为可复用基元，PrimitiveVLA使VLA模型学习不变的动作模式而非特定任务轨迹。大量实验表明，该框架提升了数据效率，并在未见过的长时序任务上实现了优越的零样本泛化能力。
原文摘要 · Abstract (English)
Vision-Language-Action (VLA) models offer a promising paradigm for generalist robotic policies, yet their adaptation is hindered by data inefficiency and poor generalization. We argue that these bottlenecks stem from the prevailing Direct Instruction-to-Control Mapping, which forces models to memorize monolithic trajectories rather than reusable motion patterns, i.e., primitives. We propose PrimitiveVLA, a framework that shifts this paradigm toward a Primitive-Centric Disassemble & Assemble paradigm. Supported by a shared Multimodal Canonical Representation (MCR), PrimitiveVLA unifies two phases: (1) Fine-tuning-phase Disassembly, which uses an automated pipeline to disassemble demonstrations into reusable primitives; and (2) Inference-phase Assembly, which employs a VLM-based planner and an LLM-generated switch module for robust closed-loop execution. By disassembling tasks into reusable primitives, PrimitiveVLA enables VLA models to learn invariant motion patterns instead of task-specific trajectories. Extensive experiments show that our framework improves data efficiency and achieves superior zero-shot generalization across unseen and long-horizon 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。