HiFlow: トークン化不要のスケール単位自己回帰ポリシー学習をフローマッチングで実現
HiFlow: Tokenization-Free Scale-Wise Autoregressive Policy Learning via Flow Matching
ロボットの行動は低次元連続ベクトルであるため、離散トークン化を不要とし、時間プーリングで多スケールの連続行動目標を構築する自己回帰ポリシーHiFlowを提案。単一ステージでエンドツーエンドに学習し、既存手法を上回る性能を示した。
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: Daichi Yashima, Koki Seno, Shuhei Kurita, Yusuke Oda, Komei Sugiura
分類: cs.RO
原文アブストラクト
Coarse-to-fine autoregressive modeling has recently shown strong promise for visuomotor policy learning, combining the inference efficiency of autoregressive methods with the global trajectory coherence of diffusion-based policies. However, existing approaches rely on discrete action tokenizers that map continuous action sequences to codebook indices, a design inherited from image generation where learned compression is necessary for high-dimensional pixel data. We observe that robot actions are inherently low-dimensional continuous vectors, for which such tokenization introduces unnecessary quantization error and a multi-stage training pipeline. In this work, we propose Hierarchical Flow Policy (HiFlow), a tokenization-free coarse-to-fine autoregressive policy that operates directly on raw continuous actions. HiFlow constructs multi-scale continuous action targets from each action chunk via simple temporal pooling. Specifically, it averages contiguous action windows to produce coarse summaries that are refined at finer temporal resolutions. The entire model is trained end-to-end in a single stage, eliminating the need for a separate tokenizer. Experiments on MimicGen, RoboTwin 2.0, and real-world environments demonstrate that HiFlow consistently outperforms existing methods including diffusion-based and tokenization-based autoregressive policies.
