Trainable soft electronics with memory in liquid crystal polymers
Open Access
- 10 July 2026
- journal article
- research article
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 12 (28) , eaee8616
Abstract
State-of-the-art soft materials can be engineered as sensors and actuators, yet, methods for learning from external information remain a subject of current research. Inspired by the use of large datasets to train artificial intelligence, tuning physical responsiveness to relayed data would introduce learning behavior in soft materials. In this work, we develop a trainable liquid crystal oligomer network (LCON) that stores digital information directly into its molecular configuration. By functionalizing the anisotropic LCON with photo-switchable azobenzene, we simultaneously integrate basic logic and memory in a material through a binary-state system; we coin this design the trainable self-propelled gate (T-SPG). We can tune the memory of our T-SPG with photonic stimuli, allowing the system to be trained by a conventional digital controller. We demonstrate the trainability of the T-SPG through two hierarchical tasks: a lower-level binary classification task where the decision boundary is stored as material memory, and a higher-level motion task that uses the stored memory to trigger actuation.Keywords
Funding Information
- HORIZON EUROPE Framework Programme (956150)
- Nederlandse Organisatie voor Wetenschappelijk Onderzoek (10854)
- Nederlandse Organisatie voor Wetenschappelijk Onderzoek (START-UP 8872)
- ICMS-CRT STA Neural Networks Project
This publication has 52 references indexed in Scilit:
- The Persistence and Transience of MemoryNeuron, 2017
- Photocontrol of fluid slugs in liquid crystal polymer microactuatorsNature, 2016
- Programmable and adaptive mechanics with liquid crystal polymer networks and elastomersNature Materials, 2015
- Smart Muscle‐Driven Self‐Cleaning of Biomimetic Microstructures from Liquid Crystal ElastomersAdvanced Materials, 2015
- Human-level control through deep reinforcement learningNature, 2015
- Synthetic homeostatic materials with chemo-mechano-chemical self-regulationNature, 2012
- Shape selection of twist-nematic-elastomer ribbonsProceedings of the National Academy of Sciences, 2011
- Error Correction, Sensory Prediction, and Adaptation in Motor ControlAnnual Review of Neuroscience, 2010
- CORTICAL PLASTICITY: From Synapses to MapsAnnual Review of Neuroscience, 1998
- How Neural Networks Learn from ExperienceScientific American, 1992