Neuroprosthetics & Robotics

👁️ NeuraViPeR - Neural Active Visual Prosthetics for Restoring Function (H2020, 2020-2024)

Institution: Universidad Miguel Hernández de Elche | Funding: €4M Horizon 2020 European Commission

Development of next-generation active visual neuroprosthetics based on thousands of microelectrodes controlled by Deep Learning algorithms to restore vision in blind individuals. The project creates lightweight, portable systems stimulating large portions of visual cortex with flexible implants, minimising tissue damage whilst ensuring long-term durability.

• Duration: 4 years (September 2020 - 2024)
• Innovation: Flexible cortical implants with thousands of microelectrodes, Deep Learning-driven stimulation pattern optimization, lightweight and portable neuroprosthetic system design
• Contribution: Algorithm development for image processing, phosphene prediction, real-time phase estimation for closed-loop stimulation, electrophysiological record cleaning using machine learning and knowledge graphs
• Technologies: Deep Learning (object detection, monocular depth estimation, edge detection), UMAP embedding, Louvain-Communities graph analysis, intracortical microelectrode arrays (Utah arrays), real-time EEG/ECoG signal processing
• Clinical Application: Visual cortex stimulation for restoring functional vision in acquired blindness, Activities of Daily Living assessment in blind volunteers with cortical implants
• Publications:
  • "Horizon cyber-vision: A cybernetic approach for a cortical visual prosthesis" (2022)
  • "The Assessment of Activities of Daily Living Skills Using Visual Prosthesis" (2022)
  • "A new environment for assessing orientation and mobility in persons with severe visual impairments"
  • "Performance evaluation of a real-time phase estimation algorithm applied to intracortical signals from human visual cortex"
  • "Neuronal Waveform Classification in Multielectrode Recordings Using Machine Learning Techniques and Multidimensional Analysis"
  • "Recruiting native visual representations in visual cortex for electrode array based vision restoration" (Contributed Talk)
  • "Advantages of Bidirectional Cortical Visual Prostheses"
  • "Recruiting native representations for electrically induced perception in blind humans"
  • "Automating Electrophysiological Record Cleaning in Visual Cortical Neuroprostheses using Machine Learning Techniques applied to knowledge graphs"

🤖 Emotional Human-Robot Interaction with Physiological Signals

Development of HRI systems utilising EEG and GSR signals for real-time emotional recognition and adaptive robotic behaviour. Aplicaciones en robótica narrativa afectiva y terapia.

• Platform: Robots sociales (NAO, otros), Python, ROS
• Signals: EEG en tiempo real con eliminación de artefactos optimizada, GSR para arousal
• IA: Algoritmos de estimación emocional, robótica afectiva adaptativa
• Publications:
  • "Optimization of Real-Time EEG Artifact Removal and Emotion Estimation for Human-Robot Interaction Applications" (2019)
  • "Affective Robot Story-telling Human-Robot Interaction: Exploratory Real-time Emotion Estimation Analysis using Facial Expressions and Physiological Signals"
  • "Real-time Facial Expression Recognition Using Smoothed Deep Neural Network Ensemble"
  • "Real-Time Multi-Modal Estimation of Dynamically Evoked Emotions Using EEG, Heart Rate and Galvanic Skin Response"
  • "On the Use of Lateralization for Lightweight and Accurate Methodology for EEG Real Time Emotion Estimation Using Gaussian-Process Classifier"
  • "Setting the Parameters for an Accurate EEG (Electroencephalography)-Based Emotion Recognition System"
  • "A New Model for the Implementation of Positive and Negative Emotion Recognition"
  • "Exploring the Physiological Basis of Emotional HRI Using a BCI Interface"
  • "Real-time Emotional Recognition for Sociable Robotics Based on Deep Neural Networks Ensemble"
• Thesis: "Emotional Human-Robot Interaction Using Physiological Signals"

🧬 Robotic Control via Functional Connectivity Graphs in Neuronal Cultures

Pioneering computational neuroscience research utilising tetanic stimulation of hippocampal cultures to generate functional connectivity graphs applied to real-time robotic control.

• Approach: Interfaz cultivo neuronal-robot, estimulación tetánica, análisis de conectividad
• Techniques: Micro-electrodes for recording and stimulation, functional connectivity graph analysis
• Application: Bio-inspired robotic control based on biological neuronal activity patterns
• Publications:
  • "Functional Connectivity Graphs in Hippocampal Cultures Using Tetanic Stimulation for Real Time Robotic Control" (2016)
  • "Toward an Improvement of the Analysis of Neural Coding"
  • "Frequency Variation Analysis in Neuronal Cultures for Stimulus Response Characterization"