F6S EU TECH INNOVATION NETWORK DAC

AgRimate focuses on transforming pruning tasks for small-scale farmers by using Augmented Reality (AR) and Robotics technologies, enriched with Artificial Intelligence (AI). Tackling the significant challenges and labour-intensive aspects of pruning in high-value crops like olive groves and vineyards, AgRimate introduces an innovative and scalable solution. This solution relies on an artificial intelligence module capable of learning from expert human knowledge to address tree pruning challenges. This module extends its functionality to the solution through various tools, from a learning tool that adapts to the user's knowledge to an Augmented Reality solution providing real-time guidance during the pruning process with the human at the centre. It seamlessly integrates with two different robotic solutions, either assisting the user with exoskeletons or autonomously performing tasks with a highly advanced robot. Additionally, AgRimate incorporates a comprehensive assessment tool designed to evaluate the solution's impact, not only on farmers but also on rural communities. This holistic approach aims not only to enhance productivity and resource efficiency but also to improve social inclusiveness and working conditions within the agricultural sector. By forging a consortium of leading research institutions, SMEs, and agricultural stakeholders from across Europe, AgRimate is at the forefront of cultivating sustainable, technologically advanced, and socially responsible farming practices. Ultimately, AgRimate stands as a beacon of innovation in agricultural technology, keenly aligned with the EU's broader goals of digital transformation, environmental sustainability, and socio-economic equity, showcasing a path forward for future farming that prioritizes both yield and community wellbeing.

EC contribution:

EUR 1M

Start:

2025-02-01

End:

2030-01-31

Status:

SIGNED

Scheme:

HORIZON-RIA

Call:

HORIZON-CL6-2024-GOVERNANCE-01

View on CORDIS (DOI 10.3030/101182739)

Modern industrial companies aim to extend their products with services as fundamental value-added activities. The key potential of the concept of Product Service System (PSS), besides radical improvements in the use of products, is a reduction of environmental footprint of products and services. The overall footprint of PSS is still insufficiently investigated. The services within PSS are an important, insufficiently used source of (digitalized) data on the product and its use. It is likely that digital means facilitating provision of consistent “track and trace” information on the origin, composition and entire life cycle not only of a product but of all services offered and used around the product, will offer important contribution towards achievement of full circularity for manufacturing. The key idea of PSS-Pass is to investigate how extension of DPP to Digital Product Service System Passport (DPSSP) can be effectively achieved and how it will allow for improved circularity of the manufacturing industry. The overarching hypothesis is that LCA underpinned by Machine Learning (ML) methods and informed by dynamic data paves the way to more accurate LCA while supporting PSS life cycle decision making. The collected and sharable data from DPSSP will allow to effectively apply ML as well as Digital Twin (DT) for more reliable decision-making processes concerning circularity of PSS. The project will provide Methodological Framework for definition, development and update of DPSSP, Digital Environment for DPSSP built on existing interoperability architectures, set of ontologies for improved interoperability at DPSSP Environment, novel DT-based Simulation Framework, for modelling standardized and interoperable DTs for PSS lifecycle analysis, and AI based method/tool to forecasts the environmental impact of PSS. The PSS-Pass solutions will be tested and evaluated within 3 pilots in diverse sectors: home appliances, complex equipment, and textile industry.

EC contribution:

EUR 198k

Start:

2024-10-01

End:

2027-09-30

Status:

SIGNED

Scheme:

HORIZON-RIA

Call:

HORIZON-CL4-2024-TWIN-TRANSITION-01

View on CORDIS (DOI 10.3030/101177594)