
Overview
Through this service, we offer customers a complete feasibility study of their digital systems and/or data, evaluating their suitability for the test use cases identified by the customer. The study involves both technical and agronomic aspects. The goal of this service is to provide the customer with a comparison between the features of the system or data submitted for review and the requirements of the use cases chosen for (possible) subsequent testing. Examples of systems and data requiring digital testing include (but are not limited to) software modules for data processing (e.g., machine vision modules), AI models, software architectures (e.g., control systems of robots), simulations, datasets collected in the field, synthetic datasets, designs of software systems, and so on. This assessment is crucial to provide customers with key information on elements of their system that need to be further developed to become “fit for testing.” It can also identify changes to apply to either the system or AgrifoodTEF’s testing facilities to meet the requirements for experimentation.
More about the service
For these reasons, it is often beneficial for a company to discuss with AgrifoodTEF the features of the systems or subsystems and the chosen use cases before any experimentation takes place, as well as the features and suitability of any dataset that the company already possesses or plans to generate.
This service allows the customer to examine such issues in detail together with personnel specialised in AI, robotics, advanced agricultural machinery, and agronomic research.This service is very flexible in order to meet each customer's specific needs.
The second stage is an analysis of system/subsystem features to be tested and/or an analysis of the datasets that the customer already has or plans to generate. In the case of data, custom software may be developed and employed to process the data in order to highlight relevant features.
During this second stage, the customer can decide to share technical details about their solution and/or the results of preliminary testing, under NDA if needed.
Finally, we evaluate how the features of the current systems/subsystems and/or data align with the desired outcomes and test requirements and provide guidelines and advice about how this alignment can be improved. If required, this service can be tied to other AgrifoodTEF services aimed at designing the elements of experimental testing campaigns (services S00176, S00177, S00178).
The following is an example of a service instance (please note that the service is available for many agricultural sectors, not only the one considered by the example).
Example service: The customer is a company that is developing a weeding robot equipped with cameras and a computer vision module, used to discriminate weeds from crops to select zones that require weeding. While the hardware of the machine is already at an advanced state of development, the software is at an earlier stage of development. The company has the design of the software system and a preliminary implementation of it, along with a few preliminary datasets collected with their robot.
They would like to further develop their software module and generate high-quality datasets to build a prototype software and to test it experimentally in a digital environment.Before starting the construction of software and datasets, the customer asks AgrifoodTEF for feedback about the design of the software and for an evaluation of the features of the datasets that they plan to collect and use for testing; for these reasons, the company decides to use this AgrifoodTEF service. A series of meetings of company personnel with AgrifoodTEF engineers and agronomists follows. During the meetings, system and data features and the intended applications of the system are discussed; additionally, technical details are exchanged under the cover of a suitable NDA.In the end, AgrifoodTEF provides the customer with feedback about the suitability of system design and data features with respect to the chosen use cases, with clear pointers at the areas that can be improved to enable good performance in the testing of the resulting prototype.