.png){kind=icon}
Return
Gaussian process movement primitive
.png){kind=icon}
PRE
AI
DOI：10.1016/j.automatica.2023.111120.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Using probabilistic movement primitives (ProMPs) has been shown as an effective way to encode basic robot movements. However, ProMPs are learned based on parametric approaches, which increases the demands for human efforts, and also limits the reproduction accuracy. In this technical communique, we present a novel non-parametric movement primitive, named Gaussian process movement primitive (GP-MP), which is totally data-driven and more accurate. Moreover, different from existing ProMP or its variants, we propose a sufficient condition for GP-MP to ensure that the generated trajectory can pass desired via-points with 100% probability. We also show that different GP-MPs can be analytically blended like ProMPs. Comparative simulations on the LASA data set are conducted to show the advantages of the presented GP-MP. & COPY; 2023 Elsevier Ltd. All rights reserved.
Keywords:
Movement primitives
Gaussian process
Imitation learning
Motion planing
Journal
IF:
5.9
Papers:
1.2W
Citations:
5.2W
Organization
Cited Papers
ShareSave
ShareSaveShareSaveShareSaveDecomposition of human motion into dynamics-based primitives with application to drawing tasks.png)
AUTOMATICA
OAAI
AUTOMATICAIF5.9
OAAIShareSave no more
no more