用高斯混合模型学习机器人运动几何力学，提升预测精度与适用范围。
Learning the Geometric Mechanics of Robot Motion Using Gaussian Mixtures
- 用高斯混合模型学习运动的几何力学流形结构。
- 相比旧方法预测精度显著提升，且可处理非周期运动数据。
- 适用于任意运动数据集，尤其适合线性区域外推场景。
基于几何力学原理构建的数据驱动机器人运动模型已在多种机器人中展现出良好预测能力。对于自由度较多的机器人，这类模型通常只能在步态附近建立。本文提出使用高斯混合模型（GMM）作为流形学习工具，自动学习几何力学中的“运动能力图”结构。实验表明：[i] 相较于已有方法，预测质量明显提升；[ii] 方法可应用于任意运动数据集，不限于周期性步态；[iii] 提出一种数据预处理方式，可在已知为线性的区域实现更优外推。本方法可广泛应用于各类需数据驱动几何运动建模的场景。
原文摘要 · Abstract (English)
Data-driven models of robot motion constructed using principles from Geometric Mechanics have been shown to produce useful predictions of robot motion for a variety of robots. For robots with a useful number of DoF, these geometric mechanics models can only be constructed in the neighborhood of a gait. Here we show how Gaussian Mixture Models (GMM) can be used as a form of manifold learning that learns the structure of the Geometric Mechanics "motility map" and demonstrate: [i] a sizable improvement in prediction quality when compared to the previously published methods; [ii] a method that can be applied to any motion dataset and not only periodic gait data; [iii] a way to pre-process the data-set to facilitate extrapolation in places where the motility map is known to be linear. Our results can be applied anywhere a data-driven geometric motion model might be useful.
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。