发表机构
Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences; University of Chinese Academy of Sciences; The Hong Kong Polytechnic University（中国科学院宁波材料技术与工程研究所; 中国科学院大学; 香港理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出阶段关键性引导的动态运动原语（SC-DMPs），利用交互刚度和轨迹一致性构建关键性指标，自适应分配基中心和带宽，提升高关键性阶段的表示密度，在多个任务上实现更优的轨迹再现和泛化性能。
AI 中文摘要
动态运动原语（DMPs）为机器人技能学习中的轨迹表示和泛化提供了一种紧凑且稳定的公式。然而，其预定义的基布局限制了根据阶段相关精度要求分配逼近能力的能力。为解决此问题，本文提出了阶段关键性引导的动态运动原语（SC-DMPs），具有自适应基分配，用于关键精度技能学习。操作者-机器人交互刚度和由跨演示任务空间变异性导出的轨迹一致性线索被整合以构建阶段关键性指标。在该指标引导下，基中心通过逆累积关键性在归一化时间中重新分配，并映射到规范相位域，同时其带宽被细化以调整局部逼近支持。这使得在高关键性阶段能够实现更密集和更灵活的表示，同时在其他地方保持更稀疏的分配。在手写轨迹和三个真实机器人任务上的实验表明，推断出的关键性集中在几何要求高和任务受限的区域。与DMPs、ProMPs、ProDMP、GP-MP和KMP的比较表明，在保持紧凑模型和经典DMPs稳定结构的同时，轨迹再现、端点泛化和任务关键精度均得到改善。
英文摘要
Dynamic Movement Primitives (DMPs) provide a compact and stable formulation for trajectory representation and generalization in robot skill learning. However, their predefined basis layout limits the allocation of approximation capacity according to stage-dependent precision requirements. To address this issue, this article proposes Stage-Criticality-Guided Dynamic Movement Primitives (SC-DMPs) with adaptive basis allocation for precision-critical skill learning. Operator-robot interaction stiffness and a trajectory-consistency cue derived from cross-demonstration task-space variability are integrated to construct a stage-criticality index. Guided by this index, basis centers are redistributed in normalized time through inverse cumulative criticality and mapped to the canonical phase domain, while their bandwidths are refined to adjust local approximation support. This enables denser and more flexible representation at high-criticality stages while retaining sparser allocation elsewhere. Experiments on handwriting trajectories and three real-robot tasks show that the inferred criticality is concentrated in geometrically demanding and task-constrained regions. Comparisons with DMPs, ProMPs, ProDMP, GP-MP, and KMP demonstrate improved trajectory reproduction, endpoint generalization, and task-critical accuracy while retaining a compact model and the stable structure of classical DMPs.
Journal refIEEE Transactions on Industrial Informatics, 2026
