The navigation of an autonomous system (robot or vehicle) in an unstructured environment remains an open problem despite the significant progress made in recent years in the field of autonomous vehicles. Recent innovations in the field of perception using Deep-Learning methods suggest solutions that have yet to be put into practice on real applications in complex environments. In the ASTRA (Autonomous System for Terrain Recognition & Adaptation) project, ESIGELEC and SITIA are proposing the development of a system for environmental perception, semantic mapping and navigation adapted to the constraints of difficult real environments: natural, forest or agricultural terrain; unstructured and/or disturbed environments... This system is based on a complete set of sensors (colour and NIR cameras, neuromorphic cameras, LIDAR, RADAR, GNSS-RTK and inertial unit) allowing the acquisition of reliable and rich measurements of the environment. The perceptions from these sensors are then merged by specific algorithms to improve the reliability of the data collected and to compensate for sensor failures or transient defects (occlusions, dust, rain). Finally, a set of higher-level algorithms is based on these merged data to achieve an understanding of the environment (detection of visible or hidden obstacles, qualification of the quality and geometry of the ground); precise localisation that is robust to GNSS failures; and finally, the fully or semi-autonomous navigation of a mobile robot. Man-machine collaboration is not forgotten: several alternative piloting modes are developed, each with a different level of decision-making by the machine, with the objective of a simple and intuitive handover between the human operator and the onboard intelligence. During all phases of the project, the methods and algorithms are developed in a generic and reusable way, so that they can be easily transposed to other types of mobile systems (vehicles, robots of different sizes and with different crossing capacities). This result is guaranteed by the use of 3 robots of different sizes on which the algorithms are tested and validated at each stage of the challenge. The new methods developed during this project will be valorised by a technological transfer to the field of autonomous agricultural robotics, of which SITIA is one of the leaders.

agROBOfood is dedicated to accelerate the digital transformation of the European agri-food sector through the adoption of robotic technologies. It will consolidate, extend and strengthen the current ecosystem by establishing a sustainable network of DIHs. This will boost the uptake of robotic solutions by the agri-food sector: a huge challenge requiring an inclusive approach involving all relevant European players. The agROBOfood consortium has 39 partners, led by Wageningen University & Research and other core partners of previous key projects such as IoF2020, ROBOTT-NET, PicknPack and I4MS, to leverage the ecosystem that was established in those projects. The heart of the project is formed by Innovation Experiments (IEs), organized and monitored by the DIHs. In each of the 7 Regional Clusters, an initial IE will demonstrate the robotics innovations in agri-food in a manner that ensures replicability across Europe, wide adoption and sustainability of the DIHs network. agROBOfood will work in lockstep with the European robotics community, ensuring synergetic effects with initiatives such as EU-Robotics. This will maximize the return of European, including private capital, investments in the digital transformation of agri-food. A key instrument to achieve this objective is the Industrial Advisory Board. They will provide strategic guidance and also define priorities for the selection of solutions to be funded. Open Calls of 8MEUR will attract additional Innovation Experiments (12) and Industrial Challenges (8). These will expand the network and ensure that vast technological developments and emerging challenges of the agri-food sector are incorporated in the service portfolio of DIHs. Through its inclusive structure and ambitious targets, agROBOfood aims to bring the entire European ecosystem together; connecting the dots in a way that ensures effective adoption of robotics technologies in the European agri-food sector.

The HortiQD project aims to develop an affordable and easy-to-use machine vision system for precision farming. The objective is to build a hyperspectral Short-Wave Infra Red camera working in the wavelength range of 1 - 2 µm with integrated point detection at smaller wavelengths, specifically suitable for orchard monitoring. To reach this goal we propose a novel detector type based on QD technology, based on lead- and mercury-free QDs in compliance with EU regulations and reducing the component cost by approximately 99%. The optical filter will allow for high spectral and spatial resolution, tunable to specific application requirements by design. The hyperspectral images, recorded in-vivo, will be analyzed by deep-learning algorithms in order to identify diseases in an early state and assess the plant health, starting with apples. A data management and correlation system will be set up and present the derived diagnoses and measures directly to the farmer in real-time. The system will be mounted on an already existing autonomous tractor, customized for horticulture, in order to verify the feasibility and targeted TRLs under realistic conditions in several orchard types. HortiQD will help to reduce or avoid the usage of pesticides in European orchards, paving the way towards sustainable farming and increasing food quality. It will scale up the intensity of monitoring by automation, hence, ensure the reliability of European food production. It will help analyze and address the impacts of climate change. The project aims for a fully integrated solution, consisting of several innovative sub components. Each of the developments brings benefit to the industry it addresses and opens up new markets, beyond agriculture and food.