Stretchable e-skin and transformer enable high-resolution morphological reconstruction for soft robots

Dataset

Abstract

The zip file includes data and code for replicate the results of 'Stretchable e-skin and transformer enable ultra-high proprioceptive geometry resolution morphological reconstruction for soft robots'. Manuscript abstract: Many robotic tasks require knowledge of the exact 3D robot geometry. However, this remains extremely challenging in soft robotics because of the infinite degrees of freedom of soft bodies deriving from their continuum characteristics. Previous studies have only been able to achieve low proprioceptive geometry resolution (PGR), making it suffer from loss of geometric details (e.g. local deformation and surface information) and limited applicability. Here, we report an intelligent stretchable capacitive e-skin to endow soft robots with ultra-high PGR (=3,900) bodily awareness. We demonstrate that our e-skin can finely capture a wide range of complex 3D deformations across the entire soft body through multi-position capacitance measurements. The e-skin signals can be directly translated to high-density point clouds portraying the complete geometry via a deep architecture based on transformer. This ultra-high PGR proprioception system providing millimeter-scale (2.322 ± 0.687 mm error on a 20 x 20 x 200 mm soft robot), local and global geometry reconstruction has the potential to assist in solving fundamental problems in soft robotics, such as precise closed-loop control and accurate digital twin modelling.
Date made available18 Oct 2022
PublisherEdinburgh DataShare

Cite this