VERtical Innovation in the Domain of Robotics Enabled by Artificial intelligence Methods

Informazioni relative al progetto

VeriDream

ID dell’accordo di sovvenzione: 951992

DOI

10.3030/951992

Progetto chiuso

Data della firma CE 26 Giugno 2020

Data di avvio 1 Ottobre 2020

Data di completamento 31 Marzo 2023

Finanziato da

• EXCELLENT SCIENCE - Future and Emerging Technologies (FET)

Costo totale

€ 1 988 670,00

Contributo UE

€ 1 988 670,00

Coordinato da

DEUTSCHES ZENTRUM FUR LUFT - UND RAUMFAHRT EV
Germany

Periodic Reporting for period 2 - VeriDream (VERtical Innovation in the Domain of Robotics Enabled by Artificial intelligence Methods)

Periodo di rendicontazione: 2021-10-01 al 2023-03-31

Sintesi del contesto e degli obiettivi generali del progetto

Robots act in the real world. When deploying AI methods on robots, the continuous and dynamic nature of the physical world raises many challenges which are not encountered in purely digital domains such as Internet search and social networks. To address these challenges, VeriDream builds on the DREAM [https://cordis.europa.eu/project/id/640891] and RobDream [https://cordis.europa.eu/project/id/645403] research projects to pursue a two-fold innovation strategy for AI in robotics. Its deep innovation strategy will strive to achieve high technological readiness in a set of use cases at a warehouse logistics start-up. Its broad innovation strategy will promote a wider uptake of effective innovation methods in SMEs, thus enhancing the innovation potential of SMEs in AI for robotics, and thus the creation of novel high-quality jobs in Europe.

Lavoro eseguito dall’inizio del progetto fino alla fine del periodo coperto dalla relazione e principali risultati finora ottenuti

The main results in the first year have been the detailed definition of ten industrial use cases in which machine learning algorithms will be applied, along with their requirements and key performance indicators. The pragmatic guidelines for the use of the machine learning algorithms have been documented, and four open-source software packages have been published on the European AI On Demand Platform and Ecosystem (AI4EU). Although the pandemic has severely limited the ability of partners to visit each other, first successes have been achieved by applying machine learning to the industrial use cases.

Progressi oltre lo stato dell’arte e potenziale impatto previsto (incluso l’impatto socioeconomico e le implicazioni sociali più ampie del progetto fino ad ora)

The added value of VeriDream goes beyond the progress in the individual industrial use cases. The use cases themselves are in fact data points for further analysis within VeriDream. Which of the use cases will be success stories? Which of them will lead to only marginal improvement in KPIs, or not at all? Documenting our experiences and lessons learned on the pathway to answering these questions, and sharing them with the broader research and industrial communities is the overarching objective in VeriDream. This will allow other SMEs to understand the advantages and pitfalls of machine learning, thus improving their ability to judge and apply machine learning algorithms for their own use cases. In the long-term, making such knowledge available will make SMEs more competitive, thus ensuring growth and securing jobs.

Overview of the VeriDream project, including the main research and innovation activities