学习原生延续以实现动作分块流策略
Learning Native Continuation for Action Chunking Flow Policies
AI总结：
本文提出Legato方法，通过训练时的延续技术改进动作分块流基于VLA策略，减少动作边界不连续性和伪多模态切换，提升轨迹平滑度和任务完成效率。
摘要：
动作分块使Vision Language Action (VLA)模型能够实时运行，但朴素的分块执行常在分块边界处出现不连续性。实时分块（RTC）缓解了这一问题，但其作为外部策略导致伪多模态切换和非内在平滑的轨迹。我们提出Legato，一种针对动作分块流基于VLA策略的训练时延续方法。具体而言，Legato从具有调度形状的已知动作和噪声混合物初始化去噪，使模型接触部分动作信息。此外，Legato重塑学习的流动力学，确保在每步指导下去噪过程在训练和推理之间保持一致。Legato进一步在训练中使用随机调度条件以支持变化的推理延迟并实现可控的平滑度。实证结果表明，Legato产生更平滑的轨迹并减少执行中的伪多模态切换，导致较少的犹豫和更短的任务完成时间。广泛的现实世界实验表明，Legato在五个操作任务中始终优于RTC，实现了轨迹平滑度和任务完成时间的约10%的改进。
英文摘要：
Action chunking enables Vision Language Action (VLA) models to run in real time, but naive chunked execution often exhibits discontinuities at chunk boundaries. Real-Time Chunking (RTC) alleviates this issue but is external to the policy, leading to spurious multimodal switching and trajectories that are not intrinsically smooth. We propose Legato, a training-time continuation method for action-chunked flow-based VLA policies. Specifically, Legato initializes denoising from a schedule-shaped mixture of known actions and noise, exposing the model to partial action information. Moreover, Legato reshapes the learned flow dynamics to ensure that the denoising process remains consistent between training and inference under per-step guidance. Legato further uses randomized schedule condition during training to support varying inference delays and achieve controllable smoothness. Empirically, Legato produces smoother trajectories and reduces spurious multimodal switching during execution, leading to less hesitation and shorter task completion time. Extensive real-world experiments show that Legato consistently outperforms RTC across five manipulation tasks, achieving approximately 10% improvements in both trajectory smoothness and task completion time.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
