Neuromorphic Embedded Processing for Touch

This project is part of the H2020 MSCA-ITN NeuTouch (grant ID: 813713).

When grasping a glass of water, our hand automatically adjusts the force used to stably hold the glass depending on its size, weight, roughness, slippery, softness. This is done by a very efficient system that spares the slightest bit of information, to avoid consuming too much energy for each single action. As such, artificial systems have much to learn from biology, to develop cheap solutions that can run in a very small device and at minimum energy cost. This is especially true in autonomous systems (such as robots) and in medical devices that run on the body of people, to minimize heat produced and maximize battery life.

NeuTouch aims at improving artificial tactile systems, by training a new generation of researchers that study how human and animal’s tactile systems work, develop a new type of technology that is based on the same principles, and use this technology for building robots that can help humans in daily tasks and artificial limbs that can give the user the sensation of real touch.

Within this project the objective is to identify neural network architectures for reproducing biological receptive field responses and to implement them in neuromorphic hardware. This will involve the design, simulation, fabrication and characterization of neuromorphic circuits for spike-based computation of tactile sensory data. The resulting networks will be evaluated with methods used in computational neuroscience based on their performances to infer the information content about the stimulus. Furthermore, the developed fabricated hardware will be integrated with novel sensors developed within this ITN.