A Biomimetic Learning Control Scheme for control of Modular Robots

Información del proyecto

BIOMODULAR

Identificador del acuerdo de subvención: 705100

DOI

10.3030/705100

Proyecto cerrado

Fecha de la firma de la CE 22 Febrero 2016

Fecha de inicio 1 Febrero 2017

Fecha de finalización 31 Enero 2019

Financiado con arreglo a

• EXCELLENT SCIENCE - Marie Skłodowska-Curie Actions

Coste total

€ 212 194,80

Aportación de la UE

€ 212 194,80

Coordinado por

DANMARKS TEKNISKE UNIVERSITET
Denmark

Objetivo

Motor control is a very important feature in the human brain for the performance of a motor skill. The biological basis of this feature can be better understood by emulating the cerebellar mechanisms of learning. The cerebellum plays a key role in implementing fine motor control, since it extracts the information from sensory-motor signals and uses it to respond to the environment. The purpose of this project is to benefit from the interplay between a body agent and an embodied artificial brain to understand the role of the first in the behavior of the latter and vice versa. The project aims to build a novel bio-inspired computational learning model for modular robots, and to incorporate it into a biologically plausible control scheme. The aforementioned model will merge machine learning techniques and a spiking modular cerebellum to develop a process that leads to the formation of long-term motor memories. Novel modular robots, such as Fable, will benefit from this adaptive predictive control system to perform desired, task-fulfilling behaviors. Exploiting this approach, the project pursues the discovery of important insights into the modular structure of the cerebellum, and its involvement in processing the sensory input for motor control tasks. The project will be developed at DTU with a run time of two years and will benefit from collaborations with other research groups (UGR and TUM). Their long expertise in neuromorphic computing and spiking networks will ensure that the candidate receives scientific training related to these fields (e.g. about cerebellar topology and cellular properties, and implementation of spiking networks in hardware). By providing multiple relevant contributions across the spectrum of the H2020 objectives in terms of its potential to advance robotic manufacturing, brain processing understanding, and novel computing paradigms, this project will enable the candidate to enhance her position at the forefront of advances in this fields.

Ámbito científico (EuroSciVoc)

• ciencias naturales › ciencias biológicas › neurobiología
• ingeniería y tecnología › ingeniería eléctrica, ingeniería electrónica, ingeniería de la información › ingeniería electrónica › sistemas de automatización y control
• ciencias naturales › matemáticas › matemáticas puras › topología
• ciencias naturales › informática y ciencias de la información › inteligencia artificial › aprendizaje automático
• ciencias naturales › informática y ciencias de la información › inteligencia artificial › inteligencia computacional

Programa(s)

• H2020-EU.1.3. - EXCELLENT SCIENCE - Marie Skłodowska-Curie Actions PROGRAMA PRINCIPAL
  
• H2020-EU.1.3.2. - Nurturing excellence by means of cross-border and cross-sector mobility
  

Tema(s)

• MSCA-IF-2015-EF - Marie Skłodowska-Curie Individual Fellowships (IF-EF)
  

Régimen de financiación

MSCA-IF-EF-ST - Standard EF

Convocatoria de propuestas

H2020-MSCA-IF-2015

Coordinador

DANMARKS TEKNISKE UNIVERSITET

• Aportación neta de la UEn: € 212 194,80
• Dirección: ANKER ENGELUNDS VEJ 101 ; 2800 Kongens Lyngby ; Dinamarca
• Región: Danmark › Hovedstaden › Københavns omegn
• Tipo de actividad: Higher or Secondary Education Establishments
• Coste total: € 212 194,80