Catalogue of Services

Testing a system in a physical environment requires an environment that has been prepared and set up to support the specific testing activities to be executed. This service supports the customer in the execution of the tests by taking care of such preparation and setup.

The service involves:

agronomic preparation: e.g., providing the required soil conditions, making sure that a given in-field configuration of specific plants at a given growth stage is available at the time of testing, and so on.
technical preparation: e.g., setting up infrastructure elements such as RTK GPS base stations, environmental sensors, power and networking, as well as the computational environment required to interface with the system under test to acquire and possibly pre-process experimental data.

If AgrifoodTEF facilities are involved in the experimental activities, the service also includes configuring the testing facility accordingly.

Environment preparation is done according to an environment design provided by the customer. If needed, such a design can be done by AgrifoodTEF for the customer via Service S00106.

Interested customers can get support from AgrifoodTEF for the entire pipeline involved in experimental testing, from the design of its other elements besides the environment (namely, the testing protocol via service S00107 and the evaluation metrics via service S00108) to test execution (service S00113), data collection (service S00113), and evaluation (S00114).

The output of Service S00110 is the environment ready for the execution of the testing campaign at the time requested by the customer.

National Institute for Research in Digital Science and Technology  (INRIA)

Provision of general-purpose datasets via multisensory ground robot

General-purpose datasets serve two primary objectives: (i) evaluating mobility algorithms and (ii) developing and assessing general-purpose AI applications. In the context of mobility algorithms, this pertains to classical robotics tasks such as mapping, localisation, SLAM (Simultaneous Localisation and Mapping), and navigation. Meanwhile, general-purpose AI applications focus on advancing algorithms and feeding decision support systems (DSS) for tasks such as, but not limited to, weed detection, health monitoring, growth and maturity assessment, and yield estimation in areas like arable farming, horticulture, food processing, forestry, and tree management. A significant challenge in developing AI solutions for agricultural robotics lies in the dynamic nature of agricultural environments, which fluctuate with different seasons and weather conditions. To address this, acquiring consistent and periodic data is essential for monitoring these changes effectively. This real-time data collection, often facilitated by ground robots, is crucial for developing efficient algorithms and AI solutions. Such datasets can support the development of sensor-specific techniques or be leveraged to create multisensory algorithms, enabling more accurate and adaptable systems for agricultural applications.

Data augmentation

National Institute for Research in Digital Science and Technology  (INRIA)

Provision of general-purpose datasets via a multisensory aerial robot.

We provide general-purpose datasets that can be used by customers to evaluate mobility algorithms and to develop and assess general-purpose AI applications. In the context of mobility algorithms, this pertains to classical robotics tasks such as mapping, localisation, and SLAM (Simultaneous Localisation and Mapping). Meanwhile, general-purpose AI applications focus on advancing algorithms and feeding decision support systems (DSS) for tasks including, but not limited to, weed detection, health monitoring, growth and maturity assessment, and yield estimation in areas such as arable farming, horticulture, food processing, forestry, and tree management. A significant challenge in developing AI solutions for agricultural robotics lies in the dynamic nature of agricultural environments, which fluctuate with different seasons and weather conditions. To address this, acquiring consistent and periodic data is essential for effectively monitoring these changes. This real-time data collection, often facilitated by aerial robots, is crucial for developing efficient algorithms and AI solutions. Such datasets can support customers in the development of sensor-specific techniques or be leveraged to create multisensory algorithms, enabling more accurate and adaptable systems for agricultural applications.

Data augmentation

National Institute for Research in Digital Science and Technology  (INRIA)

Provision of general-purpose datasets with user-specified sensor(s)

General-purpose datasets serve two primary objectives: (i) evaluating mobility algorithms and (ii) developing and assessing general-purpose AI applications. In the context of mobility algorithms, this includes classical robotics tasks such as mapping, localisation, SLAM (Simultaneous Localisation and Mapping), and navigation. Meanwhile, general-purpose AI applications focus on advancing algorithms and supporting decision support systems (DSS) for tasks such as, but not limited to, weed detection, health monitoring, growth and maturity assessment, and yield estimation in areas like arable farming, horticulture, food processing, forestry, and tree management. A significant challenge in developing AI solutions for agricultural robotics lies in the dynamic nature of agricultural environments, which fluctuate with different seasons and weather conditions. To address this, acquiring consistent and periodic data is essential for effectively monitoring these changes. This real-time data collection, often facilitated by aerial and/or ground robots equipped with user-specified sensors, is crucial for developing efficient algorithms and AI solutions. Such datasets can support the development of sensor-specific techniques or be leveraged to create multisensory algorithms, enabling more accurate and adaptable systems for agricultural applications.

Data augmentation

Centre d'Estudis Porcins (CEP)

Test and validate intelligent solutions based on sensors to optimise livestock farming

The service validates that the tested solution performs as expected by the vendor or manufacturer. The objective is to detect potential mistakes in the sensor readings, the processing of the signal gathered by the sensor or in the intelligent component deriving the final information to be provided to the user to optimise livestock farming . The test can be performed at sensor or application level. The tests and validation can be performed in a laboratory or in an experimental pig farm equipped with automatic and manual measures of different variables (feed, water, CO2, NH3, temperature, ventilation, liveweight, etc.)

National Institute for Research in Digital Science and Technology  (INRIA)

Testing and evaluating sensor devices

The SOPHIA infrastructure will offer the possibility to test and evaluate the performance of a sensor device in a locally controlled environment. While our indoor facility provides a fully controlled environment (light, volume), all facilities in SOPHIA can be customised to test and evaluate the sensor device. The service consists of three main steps. First, the sensor device will be integrated into the facility. After that, the facility will be customised according to the final application of the sensor device. Then, the performance of the sensor device will be evaluated using quantitative and qualitative metrics. Comparison could be proposed as a complementary option to position the performance of the sensor device in relation to the current state of the technology available in SOPHIA.

People training

National Institute for Research in Digital Science and Technology  (INRIA)

Testing and evaluating the robot’s functionalities

The SOPHIA infrastructure will offer the possibility to test and evaluate the performance of the robot’s functionalities in a locally controlled environment. While our indoor facility will offer a fully controlled environment (light, volume), all facilities at SOPHIA can be customised to test and evaluate the robot’s functionalities. The service consists of three main steps. The robot will be integrated into the facility. After that, the facility will be customised according to the functionality of the robot. Then, the performance of the robot’s functionalities will be tested and evaluated with quantitative and qualitative metrics.

AI model training

People training

National Institute for Research in Digital Science and Technology  (INRIA)

Testing and evaluation of mobility algorithms with ground robots

The SOPHIA infrastructure provides the ability to test and evaluate mobility algorithms embedded on a ground robot. Mobility algorithms concern the classical robotics functionalities of mapping, localisation, SLAM, and navigation. The ground robot is equipped with an array of sensors, including a camera, LiDAR, IMU, and RTK-GPS for ground truth evaluation. The service proceeds in three stages. Firstly, we evaluate the algorithm using representative datasets. After that, the algorithm is integrated into a ROS2 architecture and evaluated with the local agrifoodTEF test infrastructure (various areas are possible). The performance of different attributes of the algorithm is assessed using quantitative and qualitative metrics. Benchmarking could be proposed as a complementary option to position the performance of the proposed algorithm in relation to the current state of the art. The final step involves field testing under real conditions at a specific end-user or customer site using the mobile living lab, which consists of a mobile laboratory deployed in the field and connected to the real robot for monitoring and evaluation purposes.

National Institute for Research in Digital Science and Technology  (INRIA)

Testing and evaluation of mobility algorithms with aerial robots

The SOPHIA infrastructure will offer the possibility to test and evaluate the mobility algorithms embedded on an aerial robot. Mobility algorithms concern the classical robotics functionalities of mapping, localisation, SLAM, and navigation. The aerial robot is equipped with an array of sensors, including a camera, LiDAR, IMU, and RTK-GPS (for ground truth evaluation). The service consists of three main steps. To begin with, the algorithm is evaluated using representative datasets. After that, the algorithm is integrated into a ROS2 architecture and evaluated with the local agrifoodTEF test infrastructure (various areas are possible). The performance of different attributes of the algorithm is evaluated using quantitative and qualitative metrics. Benchmarking could be proposed as a complementary option to position the performance of the proposed algorithm in relation to the current state of the art. The final step involves field testing under real conditions at a specific end-user or customer site using the mobile living lab (which consists of a mobile laboratory deployed in the field and connected to the real robot for monitoring and evaluation purposes).

User Experience (UX) Evaluation

This service is offered by the UsabiliLAB, which specialises in advancing the usability and accessibility of interactive products and services. The service helps companies, particularly SMEs, develop AI and robotics solutions that are not only innovative but also more efficient, effective, and user-friendlier, while considering their accessibility.

The UsabiliLAB offers assessments, including conformity regarding relevant standards, and provides actionable insights to enhance usability and accessibility across various platforms, including:

Web Pages: We evaluate and refine agricultural web platforms to make them more intuitive and accessible.
Mobile Applications: Our detailed assessments help improve the usability of mobile apps, making them more user-friendly and accessible to a wider audience.
Other Interactive Products: from software interfaces to agricultural machinery, we analyse and improve any product with a user interface, ensuring that they are easy to use and meet the needs of your target audience.

Conformity assessment

Validation of Weed Detection Systems

This service evaluates the accuracy and effectiveness of AI-driven weed detection systems, ensuring their accuracy in real agricultural conditions. By combining field trials (both in experimental and real-farm fields), drone-based imaging, and ground truth validation, the service assesses the system’s ability to detect weeds with high precision, minimising false positives (incorrect weed detection) and false negatives (missed weeds). The service also validates the system's adaptability to different environmental conditions, such as varying soil types, weather, and crop growth stages, and it is applicable to herbaceous and arable crops, offering valuable insights for improving targeted weed control and reducing unnecessary herbicide use.

Validation of Yield Estimation based on Computer Vision

Validation of fruit detections, diameter estimation, and yield estimates using artificial intelligence, in particular computer vision techniques.

The service will help the solution provider check its performance using reference datasets or experiments conducted in testing fields. The service might also include the generation of reference datasets and expected detection, diameter measures, or yield values, which can be used both for validation and training of the artificial intelligence solution based on computer vision.

AI model training