Reconfigurable

Typically, an evaluation plan is drawn up, including identification of the various influencing factors, evaluation criteria definition, and test scenarios. Using task-appropriate metrics, the overall product performance is assessed, and underperforming scenarios can be identified. It is also necessary to have various data from the product, which must be qualified and annotated in order to evaluate the product as accurately as possible. This facility is based on MATICS software and high-performance computing resources.

This modular platform covers several fields of robotics. In particular, it features a climate chamber to validate the robot's operation at different temperatures and tracking cameras to measure its movements. The modules designed for movement tests (rough terrain, mazes, etc.) and manipulation tests (handles, valves, 6D positioning) are based on NIST (National Institute of Standards and Technology) standards.

Evaluation on this bench consists of placing a device at the heart of a simulation projected onto a 300° screen while a motion capture system and an instrumented conveyor belt measure its movements, if any. These data are integrated into the simulator in real time so that the device's digital twin follows the same movements and the projected environment is updated accordingly. The simulator also incorporates a physics engine and advanced sensor models, enabling a virtual sensor output to be substituted for the robot's sensors in real time.

The bench offers a realistic representation of a physical environment. This includes high-quality graphics with adjustable precision details for textures, lighting, and shadows, as well as advanced physical models to simulate realistic interactions between objects (collision, thermography). The various environments cover a wide range of scenarios to test AI systems in varied and unpredictable situations. The platform also enables new scenarios to be created to meet specific customer requirements.

L-PIT is part of one of Europe’s largest research networks, comprising 22 institutes and 4500 scientists and engineers, which provides a robust infrastructure and multidisciplinary expertise critical for advanced research and development projects.

A test stand with dimensions of 30000x8000 mm, with a centrally mounted, hydraulically lifted platform. The stand is used both in accredited tests based on standardised methods or in-house procedures and in non-accredited activities, including research and development work related to the design and testing of autonomous machinery. The stand is used, among other things, for measuring technical parameters, weights, pressure forces, and stability of machinery and equipment.

As part of PHÉNOME, the French plant phenotyping network, PhénoField® integrates expertise across agronomy, plant physiology, robotics, and bioinformatics. With over 350 plant varieties studied annually, the platform can simulate 17 distinct climates and is equipped with cutting-edge technology: 2 lidars for 3D laser analysis, 6 continuous cameras, 4 spectroradiometers for leaf light reflection measurements, and 36 soil moisture probes across 100 data points.

Bridge sprinkler with a working width of 250 m equipped with a VRI system, e.g., a system of variable irrigation doses. Independent control of each of the 63 sprinklers. The sprinkler can irrigate an area of ​​up to 20 hectares at once. The water dose is controlled manually, but it is possible to retrofit it with an automatic system based on, e.g., satellite data or a weather station system.

There are experimental buildings with an area of 5,430 square meters that can accommodate about two hundred cows. There is a milking parlour with a six-point tandem type. The cows stand one behind the other, are milked, and move forward. The operator's access to the udder is lateral. Milking is much slower, as it allows fewer animals per shift, but the inspection of each cow is more thorough.

The test fields at the RISE Testbed for Digitalised Agriculture consist of five fields, each approximately 1 hectare in size, with a total area of 8 hectares. The fields and their collected data can be used to test products and services under real-world conditions with AI and autonomous vehicles for agriculture. Various crops are cultivated on these fields, and one field is designated as a bare ground area for testing autonomous agricultural machinery.