As part of the four-year B-CRATOS “Wireless Brain-Connect inteRfAce TO machineS” project, researchers will be developing wireless body area networks (WBANs) with the aim of connecting the nervous system with signalling systems to stimulate various functions, primarily in prostheses.
However, in the long-term, the goal will be to do the same even in muscles and internal organs. This will be achieved through the use of chip implants in parts of the body that need to communicate.
B-CRATOS has a budget of approximately EUR 4.5 million and brings together seven partners from higher education institutions, businesses and institutes across Europe. HPC and embedded AI models will play an essential role in the system since the complex deep learning models needed to translate neural signals into meaningful commands for the robotic hand will be trained by LINKS on high-performance, GPU-equipped nodes provided by IT4Innovations supercomputing centre in Czech Republic.
These models will also require a continual learning approach to compensate for the time variability of the neural signals, also supported by an HPC-as-a-service infrastructure. Finally, these models will be distilled and deployed on the very low-power devices used to control the prothesis. B-CRATOS project has received funding from the European Union’s Horizon 2020 research and innovation programme under Grant Agreement No. 965044.
Partners: Uppsala University; SINANO Institute; Scuola Superiore Sant’Anna; Blackrock Microsystems Europe GmbH; Deutsches Primatenzentrum GmbH; Norwegian University of Science and Technology