Inverse design of artificial skins

TL;DR

This paper introduces a novel inverse design method for artificial skins using small dataset machine learning, enabling rapid prediction of diverse solutions and overcoming traditional trial-and-error limitations.

Contribution

It presents the first property-to-structure inverse design approach for artificial skins leveraging small datasets, significantly improving efficiency and solution diversity.

Findings

Achieved at least four orders of magnitude higher efficiency than conventional methods.

Predicted hundreds of solutions within hours, addressing signal saturation issues.

Solutions are applicable across various materials.

Abstract

Mimicking the perceptual functions of human cutaneous mechanoreceptors, artificial skins or flexible pressure sensors can transduce tactile stimuli to quantitative electrical signals. Conventional methods to design such devices follow a forward structure-to-property routine based on trial-and-error experiments/simulations, which take months or longer to determine one solution valid for one specific material. Target-oriented inverse design that shows far higher output efficiency has proven effective in other fields, but is still absent for artificial skins because of the difficulties in acquiring big data. Here, we report a property-to-structure inverse design of artificial skins based on small dataset machine learning, exhibiting a comprehensive efficiency at least four orders of magnitude higher than the conventional routine. The inverse routine can predict hundreds of solutions that overcome the intrinsic signal saturation problem for linear response in hours, and the solutions are valid to a variety of materials. Our results demonstrate that the inverse design allowed by small dataset is an efficient and powerful tool to target multifarious applications of artificial skins, which can potentially advance the fields of intelligent robots, advanced healthcare, and human-machine interfaces.