H2020Индивидуална стипендия2017–2019

BIOMODULAR · A Biomimetic Learning Control Scheme for control of Modular Robots

„Хоризонт 2020“ — Действия „Мария Склодовска-Кюри“

Период: 2017-02-01 → 2019-01-31
Финансиране от ЕС: 212 195 €
Участници: 1
Схема: MSCA-IF-EF-ST

Линиите свързват координатора с партньорите.

Накратко на български

Модулните роботи се използват за изучаване на невронната система чрез създаване на модели, които се учат и адаптират към различни задачи. Това помага за разработването на автономни машини, които да работят безопасно в реална среда до хора.

Този кратък обзор е генериран от изкуствен интелект

Кратко обяснение, генерирано от езиков модел по текста на CORDIS. Оригиналът е по-долу.

Резултати накратко

A Biomimetic Learning Control Scheme for control of Modular Robots

• What is the problem/issue being addressed? The problem is to build biologically plausible models (yet functional) to study working hypothesis behind certain characteristics of the neurobiological substrate. Thus, we use robotics to study how the neural system works in the framework of perception action closed-loops. As an example, we aim not to build high performance robotics directly, but rather systems that are able to adapt and learn from actual training towards improving their performance. In this way, we make them very flexible for a wide variety of tasks and scenarios. Furthermore, this allows the control engine to adapt to a robot and optimizing its performance at each stage. • Why is it important for society? BioModular has promoted the development of artificial adaptive learning systems embedding spiking neural network and machine learning mechanisms. These learning systems could have wide applicability in robotics. At the same time, understanding the brain will aid the design of biological plausible control schemes to be generalized to any robot, to any conditions. As a matter of fact, mimicking the biological functionality of the central nervous system will lead to create autonomous intelligent robot agents as the next generation of robots. Robots of the future will perform in real environments, maybe partially unknown and/or changing, as living systems do, under control paradigms that go beyond the scope of conventional control algorithms in terms of self-adaptation, self-learning, and self-recognition. Robots that will operate safely in proximity with people and in different fields away from the tightly controlled environment of the factory floor. This will enhance the future generation of self-learning and compliant robots operating in a safely human environment. • What are the overall objectives? Objective 1. To design and model an optimized cerebellar-machine learning (CML) network. Objective 2. To design and implement an efficient framework for online model-based learning control embedded in bio-inspired closed-loop architectures. Objective 3. To design and develop a novel bio-inspired composite architecture for online model-based learning control. Objective 4. To validate the composite architecture applicability in modular robotic systems.

Текст от CORDIS, на английски · Данни: CORDIS, © Европейски съюз

Цел на проекта

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.

Оригинален текст от CORDIS (на английски).

Участници

DANMARKS TEKNISKE UNIVERSITET · Kongens LyngbyКоординаторДания