改进机器人动作分段控制的平滑性，减少突变与抖动。
Smoother Action Chunking Flow Policy via Prior-Corrected Orthogonal Trust-Region Guidance
- 引入数据先验尺度优化修正权重，增强中间步修正效果。
- 约束垂直于速度方向的扰动，在信任域内保持稳定。
- 在LIBERO数据集上显著提升成功率并降低加速度与抖动。
基于流匹配的机器人策略常采用动作分段推理以实现高效闭环控制，但分段边界易引发动作突变。现有RTC引导方法虽通过去噪过程注入修正信号改善连续性，但其权重调度在中间时间步较弱，且无约束的修正方向可能引入横向扰动。本文提出POTR（Prior-Corrected Orthogonal Trust-Region）方法：首先将数据先验尺度σ_d融入RTC权重，强化中间时间步的修正能力；其次将引导向量分解为沿去噪速度方向与垂直方向的分量，并将垂直分量限制在信任域内。在LIBERO数据集上，当π_{0.5}时，POTR不仅提升成功率，且持续降低分段边界处的不连续性、加速度与急动度。消融实验表明，先验修正权重带来主要性能增益，而正交信任域进一步增强稳定性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。