发表机构
Harvard; MIT; UT Austin（哈佛大学; 麻省理工学院; 德克萨斯大学奥斯汀分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究提出B样条策略，将动作参数化为连续B样条曲线，可集成到标准策略学习管道，通过直接预测参数实现。实验表明该策略能显著减少任务完成时间，在模拟和现实任务中优于基线方法且成功率高。
AI 中文摘要
在这项工作中，我们提出了B样条策略（BSP），一种为加速机器人操纵策略而设计的动作表示。BSP不是预测离散时间动作块，而是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。这种表示产生平滑、时间连续的轨迹，可在时间上缩放并由低级控制器以更高频率和速度执行。我们表明，通过直接预测B样条参数，B样条参数化动作可无缝集成到标准策略学习管道中。在模拟和现实世界任务上的实验表明，BSP显著减少任务完成时间，在保持高成功率的同时比基线方法有大幅改进。
英文摘要
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
