Neuromorphic Learning in Organic Adaptive Biohybrid Systems

Descripción del proyecto

Construcción de interfaces bioelectrónicas inteligentes

Los dispositivos sanitarios modernos recurren cada vez más a la inteligencia artificial para mejorar el diagnóstico y el tratamiento. Sin embargo, la mayoría de los sistemas de inteligencia artificial dependen de grandes superordenadores de alto consumo energético situados lejos del punto de atención. Al mismo tiempo, gran parte de la información necesaria para estas aplicaciones se encuentra localmente, dentro del organismo. Esta brecha dificulta la creación de soluciones inteligentes y personalizadas que puedan adaptarse y aprender con el tiempo. En este contexto, el equipo del proyecto NEURO-LABS, financiado por el Consejo Europeo de Investigación, combinará la ingeniería neuromórfica orgánica y la bioelectrónica. En concreto, creará una plataforma flexible capaz de vigilar y controlar bioseñales al instante. Utilizando materiales avanzados y sinapsis biohíbridas, la investigación pretende demostrar el control adaptativo del aprendizaje en una pinza robótica blanda, lo que abrirá la puerta a biointerfaces innovadoras.

Objetivo

Artificial intelligence has demonstrated unprecedented advances in pattern and image recognition and is widely expected to significantly increase progress in smart healthcare devices, but continues to rely on inefficient supercomputers, operating remotely. On the other hand, relevant information for these applications mostly exists locally at the physiological level. Smart personalised bioelectronic applications can be tailored to a specific and unique case – or person – with the ability to be adapted, trained and optimised over time.

In this ERC project, organic neuromorphic engineering is combined with bioelectronics to achieve a tuneable neuromorphic platform, locally monitoring and modulating biosignals for the dynamic and adaptive learning control of a proof-of-principle soft robotic actuator.
Due to their compliant and non-linear characteristics soft actuators are difficult to model and thus present an ideal opportunity to demonstrate neuromorphic learning control. Organic electronic materials have been successfully implemented as building blocks in neuromorphic computing and bioelectronic applications. Particularly, mixed ionic-electronic conductors possess exceptional characteristics for use in biological environments.

At the interface between mechanical engineering, materials science, neuromorphic engineering and bioelectronics, neuro-labs will develop an organic neuromorphic platform, by optimisation of organic materials and circuits, and integration of sensors, neuromorphic devices, and microfluidics. We will develop a closed-loop adaptive biocircuit and demonstrate local tuning and neuromorphic learning control of a soft gripper. Finally, we will show optimised biocontrol of the gripper using biohybrid synapses modulated by the neurotransmitter environment, directly tuning the feedforward parameters in hardware. This will open a completely new field of adaptive neuromorphic biointerfaces and inspire a novel conceptual approach for learning control.