Catalogue of Services

Support clients in defining metrics and testing their AI solutions in real life, in the field, or virtually. Within normal and "stressed" operating conditions, including AI-generated test cases, we assess the readiness of agriculture-related AI algorithms for classification (weeds, chromatic analysis of crops), surround understanding and perception capabilities (for safety, for navigation), yield measurement (quantity of produce, quality), and robotics (anomaly detection, etc.). Besides accuracy metrics, we have experience evaluating memory and computing power footprints, and by doing so, understanding bottlenecks and improving the energy efficiency of proposed solutions.

Assessment of AI performance and software optimisation on edge computing devices

The tests in this service are aimed at products that run complex apps (based on a multitude of microservices, including heavy AI algorithms) in the fields, with limited to no connectivity to the cloud. In these cases, we propose a benchmarking designed to understand what the bottlenecks are in the implemented solution architecture to help TEF customers improve the efficiency and reliability of such products/solutions. The service may also encompass virtual facility elements (enriched datasets, virtual machines hosting containerised modules) blended with physical sensors and infrastructure in our test field or directly installed at the client's premises if need be for the duration of the experimentation.

Collection of test data

Desk assessment of the proposed solution

Universitat de Lleida (UdL)

This service consists of a detailed analysis of the customer's system, software, or AI solution. It is a preliminary step for testing and validation services, providing important information on the solution and leading the following activities. As a consequence, the detailed mapping of the solution can help the customer understand bottlenecks and better prepare the solution for testing and validation activities.

Desk assessment

Evaluation of ethical aspects in agrifood technology design and development

We offer a specialised service to companies, particularly small and medium-sized enterprises (SMEs), that develop AI- and robotics-based products and services for the agri-food sector. Our service supports these companies in integrating ethical considerations throughout the design and development process of their AI- or robotics-based products and services. By utilising Value Sensitive Design (VSD) methods, we ensure that human values such as sustainability, fairness, transparency, and privacy are incorporated into technological solutions from the outset. Through stakeholder analysis, participatory design, value scenarios, and ethical reflection, we guide companies in creating responsible, innovative technologies that align with societal needs and ethical standards.

Desk assessment

ELSA assessment

Setup for AI solution testing

Digital testing of an AI solution often requires action to obtain the proper configuration. This service contains all the required actions necessary to configure, integrate and execute the client AI solution with FBK test environment. Carrying out these preliminary activities, FBK will be able to have a working setup that will be the entry point for subsequent testing and validation services.

Testing of edge intelligence and IoT architectures

Testing of AI and robotics solutions leveraging edge computing and communication protocols in the IoT cloud-edge continuum. Can be a digital test (run on virtualised machines) or a physical test deployed either at the customer's premises or using the wide coverage wireless network installed in Trento valleys (Val d'Adige and Val di Non) for fruit crops (including but not limited to apples and grapes). FBK can support test design, proposing a benchmarking architecture to stress and monitor key components, helping to understand bottlenecks, allowing for better performance, lower bandwidth use, more reliability, and lower operating costs of tested solutions.

Testing of translation solutions for multilingual applications

Agriculture is a local and specific business, where localisation of solutions is required, especially when it comes to language and interfacing with users. Albeit the diffusion of multilingual generative AI technologies (or large language models, e.g., GPT), these models are not optimised for a specific industry. We can test the performance of multilingual AI solutions in agriculture, highlighting bottlenecks that limit them. This allows for optimised localisation of solutions and quicker achievement of scalability at the European level.

Testing the integration and performance of advanced weather forecasting

Solutions in the agricultural sector that use weather forecasts can suffer from inaccuracies of standard weather service APIs, such as lack of granularity, no usage of in-field sensors, and low precision of generic models. Using FBK's expertise in advanced weather forecasting, we are capable of testing weather-related functionalities in solutions and proposing ways forward to take it to the next level: nowcasting, higher resolution, model optimisation for specific regions, etc.

AI model training