用B样条曲线表示动作，让机械臂更平滑高效地完成操作。
B-spline Policy: Accelerating Manipulation Policies via B-spline Action Representations
- 用控制点和节点定义连续动作曲线，替代离散动作块。
- 在模拟和真实任务中，完成时间显著缩短，成功率仍很高。
- 适合对动作流畅性和执行速度有要求的机器人操控场景。
本文提出B样条策略（B-spline Policy, BSP），一种用于加速机器人操纵策略的动作表示方法。与直接预测离散时间动作片段不同，BSP将动作参数化为由一组节点和控制点定义的连续B样条曲线。该表示生成平滑、时间连续的轨迹，可被底层控制器以更高频率和速度执行。我们证明，通过直接预测B样条参数，该方法可无缝集成到标准策略学习流程中。在模拟和真实任务上的实验表明，BSP显著减少任务完成时间，在保持高成功率的同时实现明显性能提升。
原文摘要 · Abstract (English)
In this work, we present B-spline Policy (BSP), an action representation designed for accelerating robot manipulation policies. Rather than predicting discrete-time action chunks, BSP parameterizes actions as continuous B-spline curves defined by a set of knots and control points. This representation yields smooth, time-continuous trajectories that can be temporally scaled and executed by low-level controllers at higher frequencies and speeds. We show that B-spline-parameterized actions can be seamlessly integrated into standard policy learning pipelines by directly predicting B-spline parameters. Experiments on simulated and real-world tasks demonstrate that BSP significantly reduces task completion time, achieving substantial improvements over baseline methods while maintaining strong success rates. More results: https://b-spline-policy.github.io
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。