Catalogue of Services

In order to train, test, and validate AI applications, annotated datasets are needed. Wageningen Research - Field Crops can provide FAIR datasets consisting of high-quality raw images, annotations, and metadata on crops, weeds, diseases, and pests. At the moment a dataset on volunteer potato in sugar beet and onion is available. Let us know in which other datasets you are interested.

AI model training

Data augmentation

ARPA 1 - Qualification of safety systems providing obstacle detection and robot safety functions (ISO 18497:2024 reference obstacle)

We offer a comprehensive testing service to validate the safety functions of autonomous mobile robots and robotic systems. Our tests use a high-precision laser tracker for accuracy to assess your robot's ability to detect and stop when encountering an obstacle, as defined in ISO 18497:2024 (Protoco included in part IV Annex D.2).

These tests, conducted at our Montoldre site in France, will help ensure your robot's compliance with industry safety standards. A representative from your team must be present to assist in configuring and monitoring the system during testing.

ARPA 1 - Qualification of safety systems providing obstacle detection and robot safety functions (ISO 18497 reference obstacle)

INRAE offers a comprehensive testing service to validate robot's safety functions in line with ISO 18497:2018.

Our tests assess robot's ability to detect and stop when encountering obstacles using a high-precision laser tracker for accuracy. These tests, conducted at our Montoldre site in France, will help ensure robot's compliance with industry safety standards.

A representative from the team must be present to assist in configuring and monitoring the system during testing.

ARPA 2 - Qualification of perception systems in harsh environmental conditions (rain, fog, night)

This service tests the performance of on-board detection systems in agricultural robots, focusing on their safety functions under challenging environmental conditions like fog and rain. Conducted at the PAVIN platform in Clermont-Ferrand, France, the tests evaluate sensor accuracy and response, identifying any false negatives or positives. A manufacturer's representative must be present to configure the system and ensure proper operation during testing.

ARPA 3 - Qualification of safety functions ensuring robots keep within their working area (physical or virtual barriers)

This service evaluates the effectiveness of onboard geofencing safety systems in agricultural robots, ensuring they stay within designated work areas as required by ISO 18497:2024. The test involves the robot following various trajectories that challenge boundary limits. High-precision monitoring ensures compliance, with the robot required to enter a safe state if it breaches the boundary. A manufacturer's representative must be present to oversee the process.

ARPA 4 - Qualification of safety systems for human detection and collision avoidance (diverse working environments)

The ARPA 4 test thoroughly evaluates the safety systems of agricultural robots, focusing on their ability to detect human-like obstacles and automatically stop to prevent accidents. It simulates real-world scenarios by positioning mannequins in front of the robot as it moves through artificial crop rows. Using a high-precision laser tracking system, the test measures the robot’s trajectory and speed at our Montoldre site in France. This ensures the robot can safely operate in environments like vineyards or orchards, providing valuable insights into its emergency stop functions and compliance with safety standards. A manufacturer’s representative must oversee the process.

Assessment of interoperability for AI-driven solutions

Data interoperability in the agrifood sector hinders innovation and development due to the need for many custom solutions to share data. This service helps agricultural organisations improve how they handle and share data across the entire food value chain. By implementing standardised reference data models like rmAgro (https://rmagro.org), we help to optimise your data flows and make your information systems work better together. Our team at Wageningen Research provides expert guidance in data modelling and implements reference models that align with industry standards and tests the reference models against various use cases. This promotes more efficient data sharing between different systems and organisations, reducing data integration challenges and improving operational efficiency. The service is particularly valuable for organisations looking to modernise their data infrastructure or needing to share data more effectively with partners in the agri-food sector. This service provides an assessment of interoperability for AI-driven solutions within the agri-food sector. The service facilitates conformance testing and verification of whether the related IT systems comply with relevant standards, guidelines, data space regulations, and other interoperability requirements. By evaluating the IT systems against established reference data models and frameworks like rmAgro (https://rmagro.org), the service ensures that it meets the necessary criteria for effective data sharing and integration. Wageningen Research leverages its expertise to evaluate the overall AI solution on its quality, performance, and how well it aligns with industry standards, offering insights and recommendations for improvement. This service supports organisations in ensuring their solutions are interoperable, compliant, and ready for seamless integration within the agri-food value chain.

Conformity assessment

Evaluation for Ethical, Legal, and Social Aspects (ELSA Scan) for responsible AI development

Laboratoire National de Métrologie et d’Essais - LNE

What are the ethical, legal, and social aspects (ELSA) of AI-driven technology in agri-food? Mitigation of potential risks and finding opportunities are easier by identifying ELSA aspects in early development stages, when the technology is still in the making. Examples of ELSA aspects are autonomy, transparency, and bias, but also data privacy and other legal aspects. How does your AI technology deal with ELSA aspects? A combined survey and interview help AI developers to identify opportunities and issues with ELSA in the agri-food context from the perspective of end users and more broadly, for society. For example, to better align with the sustainability objectives of the AI-driven technology. The outcomes of the ELSA scan are a list of identified key ELSA aspects and high-level recommendations to further improve the AI technology.

ELSA assessment

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

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.

Instituut voor Landbouw-, Visserij- en Voedingsonderzoek

Field Spectrometer Measurements

This service utilises field spectrometers to measure the spectral properties of physical environments, such as barns, greenhouses, or outdoor fields. By capturing detailed spectral data, we help you develop, improve, or validate your agri-food solutions, whether for monitoring plant health, optimising lighting conditions, or enhancing environmental control systems. The measurements provide insights into how different wavelengths of light interact with the environment, enabling fine-tuned adjustments for better crop growth, energy efficiency, or precision farming applications. Additionally, this service can serve as a follow-up to lab-scale measurements where hyperspectral technology is used to conduct pilot tests to determine which wavelengths provide valuable information. In this service, we then perform field tests on these specific wavelengths.

Conformity assessment

Desk assessment

Laboratoire National de Métrologie et d’Essais - LNE

Performance evaluation of AI and robotics based on physical testing environments

Provision of a phenotyping greenhouse with extensive sensor set - NPEC

NPEC will enable you to make accurate, high-throughput studies of plant performance possible in relation to relevant biotic (diseases, bacteria) and abiotic (light quantity and quality, nutrients, temperature, moisture, soil pH and atmospheric CO2 level) factors across a range of scales.

The experiments can be performed in a greenhouse compartment with an extensive set of sensors to measure the plant and it’s environment. In growth rooms smaller scale experiments can be performed, with a special chamber for studying the roots of plants using transparent growth media. In the open field crop measurements can be performed using the Traitseeker for RGB, spectral and 3D measurements.

AI model training

Data analysis