Services

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 (Protocol 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.

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.

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. 

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.

The Evaluation of AI Camera Perception Systems service offers a holistic approach to test AI-based monocular RGB camera perception systems. It provides the following tasks:Record and annotate RGB images by the operational domain (vineyard, orchard, or other crop); create relevant (for your application) datasets covering a large number of scenarios (variation in parameters concerning the vegetation, the meteorological conditions, and humans' position and posture in the scene); evaluate the systems (hardware or software/algorithm) to datasets and analyse responses. This service provides a complete solution for developing, refining, and evaluating perception systems based on cameras using AI algorithms in agricultural and other operational environments.

Ensuring that agricultural robots operate safely and comply with regulations is crucial for gaining market acceptance and managing risks. This service provides a design folder evaluation of robotic systems according to selected standards (ISO 18497 - ISO 25119 - ISO 13849...), emphasising: ✔Risk assessment: Check and advise on the consistency of the manufacturer's risk assessment concerning the use of the autonomous machine in relation to its field and operating environment. ✔ Evaluation of functions and technical choices to cover risks ✔ Verification of the validation plan, including physical tests, and of the entire safety file This service provides an external, third-party assessment to identify potential gaps, anticipate certification issues, and enhance the overall safety concept, giving the manufacturer the confidence to self-certify or obtain approval for the autonomous vehicle in accordance with the applicable regulations, such as the Machinery Regulation 2023/1230.

Before initiating testing, a structured evaluation is conducted to define both the system and the test objectives clearly. This service includes the following components:- Expert review of the AI or robotic solution’s scope and intended use. - Identification of technical requirements in alignment with TEF service capabilities. - Structured documentation outlining what to test, why, and how. Through collaborative working sessions and technical document analysis, the team identifies any gaps or ambiguities in the testing scope, facilitating efficient and appropriate test design. This service is crucial for enhancing the relevance and quality of subsequent validation campaigns.

The AgroTechnoPôle, under the leadership of INRAE-TSCF, has pioneered a groundbreaking testing facility designed to assess alternative weeding technologies. This innovative test bench accurately simulates various crop and weed scenarios—including maize, wheat, beans, mustard, and chamomile—allowing for realistic evaluations. By replicating real-world conditions, we can effectively analyse the performance of weeding systems in a controlled and reproducible environment, ensuring the development of more efficient agricultural practices. With this innovative test bench, we can critically assess the spatial precision of perception and decision-making systems. It comprehensively analyses the effectiveness of diverse solutions that integrate perception, decision-making, and action, whether through mechanical, laser, electrical, or targeted spraying weeding methods. The tests occur at AgroTechnoPôle (INRAE—Montoldre, France) and last 2 to 4 weeks, depending on the technology to be tested.

ARPA PC2 thoroughly evaluates how well agricultural robots can follow established paths in indoor and outdoor environments. This service helps ensure that robots can successfully navigate various settings typical of a farm, including any obstacles and transitions between spaces they might face. ARPA PC2 provides essential information about the robot's accuracy and behaviour while moving by testing in real-life conditions. This assessment enhances operational reliability and safety and supports manufacturers in optimising their robots for improved performance in diverse agricultural scenarios.

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.