Smoother Action Chunking Flow Policy via Prior-Corrected Orthogonal Trust-Region Guidance
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_ | 1866918519524818944 |
|---|---|
| author | Fang, Kai Pei, Hailong Chi, Xuemin |
| author_facet | Fang, Kai Pei, Hailong Chi, Xuemin |
| contents | Flow-matching robot policies commonly use action-chunking inference for efficient closed-loop control, but chunk boundaries can introduce discontinuous action transitions. Existing RTC guidance improves continuity by injecting correction signals during denoising, yet its weight schedule is weak at intermediate timesteps and its unconstrained correction direction may introduce transverse perturbations. We propose POTR, a **p**rior-corrected **o**rthogonal **t**rust-**r**egion guidance method. First, we incorporate a data-prior scale $σ_d$ into the RTC guidance weight, yielding stronger intermediate-time correction. Second, we decompose the guidance vector into components parallel and perpendicular to the denoising velocity, and constrain the perpendicular component within a trust region. On LIBERO with $π_{0.5}$, POTR improves success rate and consistently reduces chunk-boundary discontinuity, acceleration, and jerk compared with RTC. Ablations show that the prior-corrected weight provides the main correction gain, while the orthogonal trust region further improves stability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_24433 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Smoother Action Chunking Flow Policy via Prior-Corrected Orthogonal Trust-Region Guidance Fang, Kai Pei, Hailong Chi, Xuemin Robotics Machine Learning Flow-matching robot policies commonly use action-chunking inference for efficient closed-loop control, but chunk boundaries can introduce discontinuous action transitions. Existing RTC guidance improves continuity by injecting correction signals during denoising, yet its weight schedule is weak at intermediate timesteps and its unconstrained correction direction may introduce transverse perturbations. We propose POTR, a **p**rior-corrected **o**rthogonal **t**rust-**r**egion guidance method. First, we incorporate a data-prior scale $σ_d$ into the RTC guidance weight, yielding stronger intermediate-time correction. Second, we decompose the guidance vector into components parallel and perpendicular to the denoising velocity, and constrain the perpendicular component within a trust region. On LIBERO with $π_{0.5}$, POTR improves success rate and consistently reduces chunk-boundary discontinuity, acceleration, and jerk compared with RTC. Ablations show that the prior-corrected weight provides the main correction gain, while the orthogonal trust region further improves stability. |
| title | Smoother Action Chunking Flow Policy via Prior-Corrected Orthogonal Trust-Region Guidance |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2605.24433 |