PHASOR: Phase-Anchored Universal Action Representations for Humanoid Embodiments
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913178197164032 |
|---|---|
| author | Kim, Kihyun Kim, Chaeyun Shin, Jongho Kwon, Taeyoun Kim, Junghyun Koo, Mijin Park, Haon |
| author_facet | Kim, Kihyun Kim, Chaeyun Shin, Jongho Kwon, Taeyoun Kim, Junghyun Koo, Mijin Park, Haon |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01851 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PHASOR: Phase-Anchored Universal Action Representations for Humanoid Embodiments Kim, Kihyun Kim, Chaeyun Shin, Jongho Kwon, Taeyoun Kim, Junghyun Koo, Mijin Park, Haon Robotics 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. |
| title | PHASOR: Phase-Anchored Universal Action Representations for Humanoid Embodiments |
| topic | Robotics |
| url | https://arxiv.org/abs/2606.01851 |