From August 2020 to October 2020, the Human Brain Project (HBP) launched 4 Calls for Expression of Interest inviting researchers to submit projects to add new expertise to the HBP community and to its research infrastructure EBRAINS, with the aim to contributing to the further development of the EBRAINS’ platform and increase the scope of its applications in terms of innovation, neuroscience and clinical research.
From a total of 33 admissible and eligible proposals, seven successful projects were selected: among these, the GROW project (General-purpose Robot for Object retrieval in Warehouses) is coordinated by the National Research Council of Italy (Istituto di scienze e tecnologie della cognizione, Cnr-Istc, Laboratory of Computational Embodied Neuroscience).
The overall goal of GROW is to develop the scene understanding technology of the HBP to achieve a Technology Readiness Level 5 (TRL5) by integrating it into a system developed by CNR for autonomous ‘open-ended learning’ (OEL) robot technology. This system will be used to address the market need for a robot-based autonomous retrieval of sets of small objects from shelves in weakly-engineered warehouses. Scene understanding is critical inthe addressed scenarios as these present highly cluttered conditions that require disentangling the identity and features of a large number of objects that are highly variable in terms of visibility, shape, position, and orientation.
The project will deliver:
(a) the industrialisation of the HBP scene-understanding technology,
(b) the assessment and dissemination of the technology
(c) pre-market analyses.
Laboratory of Computational Embodied Neuroscience, Cnr - Istc