Neuromorphic metamaterials for mechanosensing and perceptual associative learning

TL;DR

This paper introduces neuromorphic metamaterials that combine bioinspired mechanosensing, memory, and learning functionalities, enabling autonomous tactile sensing and pattern recognition through mechanical instabilities and memristive materials.

Contribution

It presents a novel physical system that physically encodes a Hopfield network into metamaterials, allowing for learning and memory of mechanical input patterns without supervised training.

Findings

The system can physically encode and retrieve spatially distributed mechanical patterns.

It demonstrates learning and memory capabilities in a neuromorphic metamaterial platform.

The metamaterials operate over large areas for touch sensing and pattern recognition.

Abstract

Physical systems exhibiting neuromechanical functions promise to enable structures with directly encoded autonomy and intelligence. We report on a class of neuromorphic metamaterials embodying bioinspired mechanosensing, memory, and learning functionalities obtained by leveraging mechanical instabilities and flexible memristive materials. Our prototype system comprises a multistable metamaterial whose bistable units filter, amplify, and transduce external mechanical inputs over large areas into simple electrical signals using piezoresistivity. We record these mechanically transduced signals using non-volatile flexible memristors that remember sequences of mechanical inputs, providing a means to store spatially distributed mechanical signals in measurable material states. The accumulated memristance changes resulting from the sequential mechanical inputs allow us to physically encode a Hopfield network into our neuromorphic metamaterials. This physical network learns a series of external spatially distributed input patterns. Crucially, the learned patterns input into our neuromorphic metamaterials can be retrieved from the final accumulated state of our memristors. Therefore, our system exhibits the ability to learn without supervised training and retain spatially distributed inputs with minimal external overhead. Our system's embodied mechanosensing, memory, and learning capabilities establish an avenue for synthetic neuromorphic metamaterials enabling the learning of touch-like sensations covering large areas for robotics, autonomous systems, wearables, and morphing structures.