分離型アクションエキスパート:タスク知識を条件付け経路に閉じ込める
Decoupled Action Expert: Confining Task Knowledge to the Conditioning Pathway
拡散ポリシーの行動生成バックボーンはタスク非依存にできることを示し、条件付け経路のみを学習させる分離型学習法を提案。244MのU-Netを5MのMLPに置き換えても同等以上の性能を達成した。
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: Jian Zhou, Sihao Lin, Shuai Fu, Zerui Li, Gengze Zhou, Qi WU
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
Many recent Vision-Language-Action models employ diffusion or flow-matching backbones with hundreds of millions of parameters for action generation. However, unlike image synthesis where the output spans millions of diverse pixels, a manipulation policy generates only short sequences of low-dimensional, physically correlated action values, a far simpler target that should not demand such capacity. We confirm this intuition and show that task-specific knowledge in these policies can be fully confined to the conditioning pathway, leaving the action backbone task-agnostic. To establish this, we introduce a decoupled training recipe: a general-purpose action head is first pretrained on observation-free forward-kinematics data, then frozen while only the conditioning pathway is trained for downstream tasks. Using Diffusion Policy as a testbed, we show that on both MimicGen and LIBERO, a single frozen backbone shared across all tasks matches normally trained counterparts. This confirms that the action expert encodes little task-specific knowledge. Ablations show that the specific pretraining signal (joint positions, end-effector poses, or no conditioning at all) has no effect on downstream performance, indicating that the backbone learns only general trajectory structure. Pushing this finding further, we replace the 244M U-Net in Diffusion Policy with a 5M-parameter MLP backbone that matches or exceeds its performance, calling into question the large capacity budgets allocated to action generation in current VLA designs.
