学習時アクション条件付けによる効率的なリアルタイムチャンキング
Training-Time Action Conditioning for Efficient Real-Time Chunking
推論時のインペインティングの代わりに、学習時に推論遅延を模擬してアクションプレフィックスで条件付けることで、VLAのリアルタイムチャンキングを計算コストを抑えつつ実現する手法を提案。
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: Kevin Black, Allen Z. Ren, Michael Equi, Sergey Levine
分類: cs.RO, cs.AI
原文アブストラクト
Real-time chunking (RTC) enables vision-language-action models (VLAs) to generate smooth, reactive robot trajectories by asynchronously predicting action chunks and conditioning on previously committed actions via inference-time inpainting. However, this inpainting method introduces computational overhead that increases inference latency. In this work, we propose a simple alternative: simulating inference delay at training time and conditioning on action prefixes directly, eliminating any inference-time overhead. Our method requires no modifications to the model architecture or robot runtime, and can be implemented with only a few additional lines of code. In simulated experiments, we find that training-time RTC outperforms inference-time RTC at higher inference delays. In real-world experiments on box building and espresso making tasks with the $\pi_{0.6}$ VLA, we demonstrate that training-time RTC maintains both task performance and speed parity with inference-time RTC while being computationally cheaper. Our results suggest that training-time action conditioning is a practical drop-in replacement for inference-time inpainting in real-time robot control.
