Catalogue of Services

Provision of datasets

Qualification of trajectory execution accuracy of crop production robots (outdoor mobility)

The test assesses the accuracy of crop production robots in following precise paths across different terrains, simulating typical agricultural tasks. The test uses advanced laser tracking to measure how well the robot follows a set trajectory, including straight and curved paths, on slopes and amidst obstacles. This enables manufacturers to ensure that their robots meet performance standards for real-world field operations. A detailed report is provided, helping optimise robot performance for outdoor mobility in agricultural settings. A manufacturer’s representative must oversee the process. This test is part of a series known as ARPA: Agricultural Robot Performance Assessment. It is identified as ARPA n (where n is 1, 2, 3, etc.) for tests that focus on safety functions and as ARPA XXn for other performance evaluations.

Collection of test data

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 for safety in alignment with relevant legislation

The purpose of this service is to provide advanced testing for AI and navigation software in the agrifood sector. By leveraging AI-powered test case generation, the service aims to create enriched and realistic testing scenarios that address safety and performance challenges in the control systems of complex agricultural systems. It seeks to support companies in identifying performance issues, allowing them to optimise system efficiency and reliability, with the objective of reducing costs and improving overall system performance.

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

Valorisation of data and assessment of data space integration