Hyper-DP3: 視覚運動制御のための3D拡散ポリシーの周波数認識型最適化
Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control
ロボットの動作軌跡が低周波成分に集中する性質を利用し、3D拡散ポリシーの復元モデルを大幅に簡素化して2ステップ推論を可能にする軽量モデルHyper-DP3を提案した。
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: Jinhao Zhang, Zhexuan Zhou, Huizhe Li, Yichen Lai, Wenlong Xia, Haoming Song, Youmin Gong, Jie Mei
分類: cs.RO
原文アブストラクト
Diffusion-based visuomotor policies perform well in robotic manipulation, yet current methods still inherit image-generation-style decoders and multi-step sampling. We revisit this design from a frequency-domain perspective. Robot action trajectories are highly smooth, with most energy concentrated in a few low-frequency discrete cosine transform modes. Under this structure, we show that the error of the optimal denoiser is bounded by the low-frequency subspace dimension and residual high-frequency energy, implying that denoising error saturates after very few reverse steps. This also suggests that action denoising requires a much simpler denoising model than image generation. Motivated by this insight, we propose Hyper-DP3 (HDP3), a pocket-scale 3D diffusion policy with a lightweight Diffusion Mixer decoder that supports two-step DDIM inference. Our synthetic experiments validate the theory and support the sufficiency of two-step denoising. Futhermore, across RoboTwin2.0, Adroit, MetaWorld, and real-world tasks, HDP3 achieves state-of-the-art performance with fewer than 1% of the parameters of prior 3D diffusion-based policies and substantially lower inference latency.
