The lack of sufficiently diverse data, coupled with limited data efficiency, remains a major bottleneck for generalist robotic models, yet systematic strategies for collecting and curating such data are not fully explored. Task diversity arises from implicit factors that are sparsely distributed across multiple dimensions and are difficult to define explicitly. To address this challenge, we propose F-ACIL, a heuristic factor-aware compositional iterative learning framework that enables structured data factorization and promotes compositional generalization. F-ACIL decomposes the data distribution into structured factor spaces such as object, action, and environment. Based on the factorized formulation, we develop a factor-wise data collection and an iterative training paradigm that promotes compositional generalization over the high-dimensional factor space, leading to more effective utilization of real-world robotic demonstrations. With extensive real-world experiments, we show that F-ACIL can achieve more than 45% performance gains with 5-10$\times$ fewer demonstrations comparing to that of which without the strategy. The results suggest that structured factorization offers a practical pathway toward efficient compositional generalization in real-world robotic learning. We believe F-ACIL can inspire more systematic research on building generalizable robotic data flywheel strategies. More demonstrations can be found at: https://f-acil.github.io/

翻译：缺乏足够多样化的数据，加之数据效率有限，仍是通用机器人模型的主要瓶颈，然而针对此类数据的系统化采集与整理策略尚未被充分探索。任务多样性源于隐式因素，这些因素在多维度上稀疏分布且难以明确定义。为应对这一挑战，我们提出F-ACIL——一种启发式的因子感知组合迭代学习框架，它能实现结构化数据分解并促进组合泛化。F-ACIL将数据分布分解为对象、动作和环境等结构化因子空间。基于分解后的表示，我们开发了因子级数据采集与迭代训练范式，从而在高维因子空间上促进组合泛化，更有效地利用真实世界的机器人示教数据。通过大量真实世界实验，我们证明与未采用该策略的方法相比，F-ACIL能在减少5至10倍示教次数的条件下实现超过45%的性能提升。结果表明，结构化分解为真实世界机器人学习中实现高效组合泛化提供了一条可行路径。我们相信F-ACIL能启发更多关于构建通用化机器人数据飞轮策略的系统性研究。更多演示请访问：https://f-acil.github.io/