Catalogue of Services

Laboratoire National de Métrologie et d’Essais - LNE

Evaluation of AI solutions performance based on testing datasets

By having your AI system tested by the LNE, you ensure it meets the highest standards of safety and performance, boosting your product’s reliability and trustworthiness in the market. Partnering with the LNE for rigorous testing of your AI technologies gives you a competitive edge, as their certification enhances credibility and opens doors to new market opportunities both locally and globally. LNE's AI performance evaluation service uses comprehensive testing datasets to assess the accuracy, robustness, and efficiency of your AI systems by comparing the outputs of the system with a dataset of reference values. By testing real-world scenarios, LNE ensures that your AI models meet industry standards and regulatory requirements, helping you improve performance, reliability, and market readiness. LNE utilises a diverse range of carefully curated datasets that simulate various operating conditions and environments in which the AI may be deployed. These datasets allow for in-depth testing of the system’s ability to process information, make decisions, and produce accurate outputs. The service covers a broad spectrum of AI applications, from machine learning models and deep learning algorithms to computer vision systems, natural language processing (NLP), and autonomous robotics. The evaluation process examines key performance metrics such as accuracy, precision, recall, response time and scalability. It also identifies any potential biases in the system, ensuring that the AI behaves fairly and ethically across different user groups or environmental variables.

Collection of test data

Evaluation of ethical aspects in agrifood technology design and development

Universitat de Lleida

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

Research Institutes of Sweden

Evaluation of readiness for testing

Many actors may need guidance throughout the testing process, requiring support and coaching to become test-ready and purchase a TEF testing service. This service is designed to help customers navigate each step with ease, offering clear and straightforward guidance to ensure readiness. With expert support, customers can confidently move forward, knowing they're well-prepared for testing. The goal is to make the process smooth and easy to understand, allowing customers to focus on their core activities while testing is efficiently handled.

Desk assessment

Evaluation of readiness for testing

Research Institutes of Sweden

Customers are often unaware of the best way to conduct testing and may require support and coaching to reach a state of test-readiness and proceed to purchase a testing service from TEF.
Service S00248 is designed to help customers understand and navigate the various steps involved in testing. The service offers clear and straightforward guidance to ensure customers are fully prepared for testing. By collaborating with RISE experts, customers can be confident that they are receiving the appropriate advice to achieve their goals.
The aim of the service is to make the testing process more accessible and understandable, allowing customers to focus on their core activities.

Desk assessment

Evaluation of results of physical testing

Politecnico di Milano

This service performs the crucial step that follows the execution of physical experimentation, i.e., evaluation of the performance of the system under test. This activity requires the application of suitable performance metrics to specific test data collected during the tests and then interpreting the results in view of the features of the system and the experimental setting. Depending on the specific use case, performance metrics can involve pure computer processing, human expertise by agronomists, or a combination of both. Application of performance metrics may include the development of custom software to extract the necessary information from experimental data and/or to apply suitable processing to the information. If the performance metrics require the data to be subjected to some form of pre-processing, Service S00115 may be leveraged to prepare the data. Besides the object of this service (i.e., evaluation of results), AgrifoodTEF can, on request, support the customer along any other aspect and phase of the physical experimentation pipeline. For instance, for the design of the environment and protocol for the test, the customer can leverage services S00106 and S00107. Preparation of the test environment can be done either by the customer or by AgrifoodTEF via service S00110; in both cases, assistance in interconnecting the system under test with AgrifoodTEF’s test infrastructure is available via service S00111. Finally, data collection during the test can, if needed, be provided by AgrifoodTEF via service S00113.

Data analysis

Evaluation of sprayer boom for spot spraying site-specific applications

University of Cordoba

This service evaluates the efficiency of sprayer booms equipped with sensors that use artificial vision to detect weeds and enable site-specific phytosanitary applications. Through field tests and drone-assisted monitoring, the service examines how accurately the sprayer boom applies treatments, identifying false positives (detecting weeds where none exist) and false negatives (failing to detect actual weeds). The service is essential for improving precision agriculture practices in arable and horticultural crops, as well as in tree crops and viticulture.

Certification

Collection of test data

Evaluation of the energy efficiency of the embedded hardware associated with the AI functionality

Laboratoire National de Métrologie et d’Essais - LNE

By having your AI or robotic system tested by LNE, you ensure it meets the highest standards of safety and performance, boosting your product’s reliability and trustworthiness in the market. Partnering with LNE for rigorous testing of your robotic and AI technologies gives you a competitive edge and trusted third-party assessment that enhances your product credibility and opens doors to new market opportunities both locally and globally. This service provides testing of devices with AI-integrated control systems, focusing on energy efficiency and consumption during the product life cycle. By simulating a wide range of scenarios, we provide detailed insights into the energy performance of these AI systems with regard to their expected operational environment. These tests can be conducted under different conditions, either in a completely simulated way, through a hybrid test bench where the actual physical device is assessed within a simulated environment, or using physical infrastructures based on the device's operational environment to test it in a 'real' setting. Tests are conducted under controlled laboratory conditions, ensuring optimal reproducibility and repeatability, providing reliable insights into the system's efficiency and safety-critical functionalities. Typical assessments may cover the energy efficiency of SLAM, various types of end effectors, and other relevant components such as sensors, motors or AI software. This rigorous testing process helps identify potential areas for improvement, enabling companies to enhance the efficiency and sustainability of their products, ultimately leading to cost savings and reduced environmental impact.

Evaluation of the framework and internal functioning of virtual assistants

University of Cordoba

Technical evaluation of frameworks developed for the creation of virtual assistants, focusing on elements such as the underlying architecture, natural language processing methods, and interactions with databases. Tests will include measuring response times, the ability to handle simultaneous queries, and overall system efficiency. Potential security vulnerabilities will also be identified, with recommendations proposed to strengthen data protection.

Data analysis

Execution of AI testing

The execution AI testing service takes your existing test definitions and handles their execution within our specialized testing infrastructure. We manage the intricate setup process required for each test scenario, ensuring all parameters and conditions are precisely configured to match your requirements. Furthermore, we also offer a test scenario design service that can be executed prior to this service (see related services). Our expert team oversees the complete testing cycle, from initial environment preparation through result collection. After test completion, you receive a detailed report documenting all test outcomes, observations, and relevant measurements. This service is particularly valuable for sophisticated testing needs that demand careful setup and expert knowledge. We understand that certain test scenarios require nuanced configuration and specialised expertise. Our service bridges this gap by providing both the necessary infrastructure and professional oversight to ensure your tests are executed accurately and yield reliable results. The comprehensive reports we deliver enable you to make informed decisions based on thorough test data.

Execution of digital testing

Politecnico di Milano

This service assists customers in executing digital tests using agrifoodTEF’s digital infrastructure. Tests can either be defined by the customer or designed through agrifoodTEF services (e.g., S00176, S00177, S00178). If specific activities are required to properly interface the system under test with the digital infrastructure, these can be handled by either the customer or agrifoodTEF (via Service S00180).

Support provided by this service includes general assistance during the test execution phase, such as monitoring to ensure compliance with the testing protocol or offering immediate help in identifying and resolving issues. Additionally, the service provides technical support during the test execution of the system under test, including ensuring that all necessary processes are correctly configured and running, as well as helping the customer address any unforeseen challenges that may arise when complex digital systems interact.

Finally, through this service, agrifoodTEF manages the technical infrastructure for test execution, ensuring smooth data exchange between the system under test and the agrifoodTEF infrastructure, and verifying that all testing requirements—potentially identified during the desk assessment phase (Service S00179)—are met during the actual test runs.

Experimentation implementing robotics in agricultural processes

This pilot service focuses on the integration of robotic systems into agricultural processes, enabling the automation of key tasks such as planting, harvesting, and crop monitoring. By combining robotics with advanced software, this service improves operational efficiency, reduces labor costs, and enhances the precision of agricultural tasks. The integration ensures that robotic systems work seamlessly within existing workflows and provide consistent, high-quality performance.

Collection of test data