发表机构
Universidad Carlos III de Madrid; Idiap Research Institute; Ecole Polytechnique Fédérale de Lausanne (EPFL)（马德里卡洛斯三世大学; Idiap研究所; 洛桑联邦理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有子运动分解方法扩展性差且缺乏可辨识性准则的问题，提出基于时空核相关性的Sub-ID方法，通过自适应岭正则化实现低相关分解，在合成和真实三维长时程数据上验证了有效性。
AI 中文摘要
长期以来，人们假设自主运动由称为子运动的离散基本单元组成，作为人类运动行为的描述性模型。然而，现有方法扩展性差，且缺乏原则性方法来判断分解是否具有信息量。我们提出将基本单元对之间的时空核相关性作为可辨识性准则。子运动可辨识分解（Sub-ID）将该准则嵌入其自适应岭正则化中，促使优化器偏向低相关性的解。当基本单元共线时，可辨识性丧失；当它们在空间上发散时，可辨识性恢复。在合成数据上，Sub-ID 能恢复现有方法无法恢复的真实参数分布；此外，当基本单元重叠过于严重而无法区分时，该方法明确检测到这种模糊性，而不是输出误导性结果。Sub-ID 从真实的三维、长时程运动中提取子运动，这是先前方法无法处理的场景。该方法有望为运动控制研究和模仿学习识别出生理基础的基本单元。
英文摘要
Voluntary movements have long been hypothesised to be comprised of discrete primitives called submovements, as a descriptive model of human motor behaviour. However, existing methods scale poorly, and no principled method exists to determine whether a decomposition is informative. We propose a spatiotemporal kernel correlation between primitive pairs as an identifiability criterion. Submovement-Identifiable Decomposition (Sub-ID) embeds this criterion in its adaptive-ridge regularisation, biasing the optimiser toward low-correlation solutions. Identifiability is lost when primitives become collinear and recovered when they diverge spatially. On synthetic data, Sub-ID recovers ground-truth parameter distributions where existing methods fail; furthermore, when primitives overlap too heavily to be distinguished, the method explicitly detects this ambiguity rather than outputting misleading results. Sub-ID extracts submovements from real three-dimensional, long-horizon movements, a regime no prior method addresses. This method has the potential to identify physiologically grounded primitives for motor control research and imitation learning.
