We are glad to announce that Inglobe Technologies has joined the Human Brain Project to create a new generation of intelligent bio-inspired industrial robots. Together with its partners, the National Research Council of Italy (CNR) and the spinoff AI2Life, Inglobe will contribute to and leverage on the digital EBRAINS infrastructure.
About the Human Brain Project and EBRAINS
The Human Brain Project (HBP) is the largest brain science project in Europe and stands among the biggest research projects ever funded by the European Union. At the intersection of neuroscience and information technology, the HBP investigates the brain with the help of highly advanced methods from computing, neuroinformatics and artificial intelligence, and drives innovation in fields like brain-inspired computing and neurorobotics.
The project is building a research infrastructure to help advance neuroscience, computing and brain-inspired technologies – EBRAINS -to create research platforms and tools that benefit the wider community. It draws on cutting-edge neuroscience and offers an extensive range of brain data sets, a multilevel brain atlas, modelling and simulation tools, easy access to high-performance computing resources and to robotics and neuromorphic platforms.
The GROW Project
Strong of its expertise in the development of Human Machine Interfaces and Perceptual Computing Solutions for the Industry, Inglobe will contribute to the Human Brain Project with its concept of a General-purpose Robot for Object-retrieval in Warehouses (GROW). With the help of innovative bio-inspired algorithms, some of which have already been developed in the context of the GOAL-Robots project by CNR (National Research Council of Italy), we will build a prototype of neuromorphic autonomous Robots to perform industrial tasks that fall outside of those typically performed by more traditional Robots.
The project will show that, by using an “open-ended autonomous learning” approach – i.e. a core research field of machine learning and robotics aiming at building systems able to autonomously acquire knowledge and skills – alongside with bio-inspired learning algorithms, it will be possible to create general-purpose robots for object-retrieval capable of autonomously learning to reach, grasp, and collect a large variety of objects, independently of their shape, rigidity, position, and orientation. Together with its partners, Inglobe will work on new computational architectures based on Reinforcement Learning methods and deep neural network controllers coupled with suitable Industrial Information Systems.
The solution to be built will be demonstrated with applications in both Manufacturing and Logistics. This is a great opportunity for Inglobe Technologies to introduce in the market a new generation of intelligent bio-inspired industrial robots.