A Comparative Study for Postural Synergy Synthesis Using Linear and Nonlinear Methods

Abstract

Human controls dozens of muscles for different hand postures in a coordinated manner. Such coordination is referred to as a postural synergy. Postural synergy has enabled an anthropomorphic robotic hand with many actuators to be applied as a prosthetic hand and controlled by two to three channels of biological signals. Principle component analysis (PCA) of the hand postures has become a popular way to extract the postural synergies. However, relatively big errors are often produced while the hand postures are reconstructed using these PCA-synthesized synergies due to the linearity nature of this method. This paper presents a comparative study in which the postural synergies are synthesized using both linear and nonlinear methods. Specifically, the Gaussian process latent variable model (GPLVM), as a nonlinear dimension reduction method, is implemented to produce nonlinear postural synergies and the hand postures can then be reconstructed from the two-dimensional synergy plane. Computational and experimental verifications show that the posture reconstruction errors are greatly reduced using this nonlinear method. The results suggest that the use of nonlinear postural synergies should be considered while applying a dexterous robotic hand as prosthesis. Versatile hand postures could be formed via only two channels of bio-signals.

Robotic hand synergies for in-hand regrasping driven by object information

“…The methods presented until now in this section were deterministic. In Romero et al (2013); Xu et al (2016), the Gaussian Process Latent Variable Model (GPLVM) (Lawrence, 2003), which is a non linear probabilistic model, was used to learn a grasp manifold from a dataset of recorded grasp postures. They showed that this model has lower reconstruction error when compared with the PCA.…”

“…Following works (Romero et al, 2013;Xu et al, 2016), have improved the reconstruction error of the grasp postures, when compared with PCA, by using a non-linear latent variable model based on Gaussian processes (GPLVM). Auto-Encoder (AE) models, which is a non-linear, deterministic dimensionality reduction method, based on neural networks, have also been shown to improve the performance in terms of reconstruction and are able to encode additional information such as the object size (Starke et al, 2018(Starke et al, , 2020.…”

“…the synergistic components, and θ are the parameters of the model. The GPLVM approach uses Gaussian Processes to model the probability distribution p. In Xu et al (2016); Romero et al (2013), a variant of the GPLVM with back constraints (BCG-PLVM) (Lawrence et al, 2006) is used for synergy extraction. This model enforces a constraint on the latent variables that ensures that points that are close in the original space remain close in the latent space.…”

A Brief Survey on the Role of Dimensionality Reduction in Manipulation Learning and Control

“…In [53] a Gaussian Process Latent Variable Model (GPLVM) is used to model the subspace of human hand motions, demonstrating better performance in reconstructing spatial and temporal grasping actions with respect to PCA and Isomap. A comparison between linear and nonlinear synergies can be found in [54].…”