Agricultural Robotics and Augmented Reality for Workplace Enhancement and Labor Linkage

The agricultural sector is known for its demanding and hazardous working environments, leading to high rates of accidents and health issues among workers. Furthermore, drudgery due to physical work and repetitive tasks diminishes the attractiveness of the sector for youth.

Emerging challenges such as digitalisation, technological intensification, structural change, environmental targets, and new risks due to climate change, coupled with global economic implications demand more and more from farmers and farm workers, exacerbate the need for timely information, and have new implications for occupational safety and health (OSH).AGRO-WELL follows a highly interdisciplinary approach to enhance knowledge for technological transitions towards an environmentally, economically, and socially sustainable agricultural sector.

It brings together leading scientists from a multitude of OSH-related disciplines, various regions across Europe, key technology providers and farmer representatives.The project will assess farmer needs and explore ways to increase awareness with respect to smart farming.

AGRO-WELL builds on five technologies to leverage the potential of robotics, augmented reality, and artificial intelligence to enhance working conditions and farm safety, enable faster and better-informed farm management decisions, and reduce the environmental impact of four different farming systems.

Potential effects of the technologies will be multidimensionally assessed.

To support market uptake, AGRO-WELL will design and explore the viability of business models based on novel technologies that are predominantly focused on improving OSH.

To support other promising technologies, AGRO-WELL will incorporate an open technology competition enabled by cascade funding.

All project results will be synthesized in effective dissemination strategies and meaningful policy recommendations to foster promising technological solutions and sustainable business models.