汎用ロボットデータフライホイールに向けて:高次元因子分解と構成
Towards Generalizable Robotic Data Flywheel: High-Dimensional Factorization and Composition
ロボットデータの多様性不足と効率性の課題に対し、データ分布を因子空間に分解し、因子ごとの収集と反復学習で構成的一般化を促すF-ACILフレームワークを提案。実世界実験で少ないデモ数で大幅な性能向上を実証した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Yuyang Xiao, Yifei Zhou, Haoran Wang, Wenxuan Ou, Yuxiao Liu
分類: cs.RO
原文アブストラクト
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/
