PHASOR: ヒューマノイド身体のための位相固定型汎用行動表現
PHASOR: Phase-Anchored Universal Action Representations for Humanoid Embodiments
行動埋め込み空間を第一級の設計対象とし、動作の周期性を位相多様体と姿勢分岐に分解して、複数のヒューマノイドロボットに共有可能な解釈可能で身体非依存の行動表現を構築した。
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: Kihyun Kim, Chaeyun Kim, Jongho Shin, Taeyoun Kwon, Junghyun Kim, Mijin Koo, Haon Park
分類: cs.RO
原文アブストラクト
Learning a good action embedding space is fundamental to scalable robot policy learning, yet existing methods treat action latents as task-specific intermediates rather than first-class representations. The resulting latents are unstructured, embodiment-specific, and weakly tied to motion semantics, limiting interpretability, controllability, and transferability across robots. We position the action embedding space itself as a first-class design target, with downstream policy quality emerging from representation quality. Exploiting motion's intrinsic periodicity, we factorize it into a phase manifold that captures cyclic structure via FFT-parametric coefficients, together with a pose branch that conditions the manifold on non-periodic configuration detail. Combined with motion-semantic distillation, this factorized structure yields a cross-embodiment motion manifold that is interpretable and embodiment-agnostic by design. Anchoring multiple humanoid robots to a shared human-pretrained manifold then produces a unified action embedding space across diverse platforms, achieving strong cross-embodiment retrieval and consistent gains on downstream robot tasks.
