Catalogue of Services

Raumberg Gumpenstein Research & Development (RGRD)

Our service is designed to assist clients in identifying and evaluating potential agricultural applications for AI or robotics technologies originally developed for other sectors. Clients can provide detailed information about their technology, including its current applications and technical specifications. Our expert team will conduct extensive research to identify possible use cases related to the agricultural and food production sector, analysing factors such as feasibility, potential benefits, and relevance to current agricultural challenges. The tools used for this work will depend on the use case and may include, for example, online research as well as expert interviews. The customer will receive the results as a comprehensive report outlining the identified potential applications, adoptions needed and an assessment of their relevance and impact within the agricultural sector. This service enables clients to explore new markets and adapt their technologies to meet the evolving needs of modern agriculture.

Desk assessment

Market research

Benchmarking & Testing Suite for Edge Hardware Systems

Lukasiewicz Poznanski Instytut Technologiczny (L-PIT)

The Benchmarking & Testing Suite for Edge Hardware Systems delivers a set of tests designed to evaluate the performance, reliability, and functionality of edge hardware and its components under various operational conditions.

The tests can be compared to specific industry standards or the performance of other solutions available on the market. Examples of tests offered as part of the service:

- Environmental tests: Assessing devices' resistance to extreme conditions, such as temperature, humidity, and vibrations.

- Signal tests: Evaluating devices using GNSS signal generators, testing their resilience to interference or false signals.

- Network tests: Evaluate device performance within a prototype 5G network infrastructure.

- Functional tests: Assessing the capability of devices, such as remote PTZ (pan, tilt, zoom) cameras, to perform operational tasks in field conditions.

- Integration tests: Examining the cooperation of edge devices with sensors, AI systems, and their responses to data input failures. - Accuracy tests: Measuring the precision of sensors and control systems. Test results can be compared to specified standards or the performance of competitive solutions, enabling customers to better understand their devices' capabilities.

Desk assessment

Lukasiewicz Poznanski Instytut Technologiczny (L-PIT)

Test design

Test execution

Test setup

Curation and provision of annotated datasets

The service provides access to annotated data collected from devices tested as part of other project services. It includes both data annotation services (manual and automatic) and the provision of annotated databases or data packages. In addition, we offer disc space for temporary archiving of the collected data along with its annotation in cases where this is not possible at the client's site. As a result of the service, procedures for both manual and automatic annotation will be identified that are appropriate to the type of measurement data and the way it is collected and assembled. The methods of labelling and assigning specific data classes collected by the agriFoodTEF technical infrastructure will be proposed. Possibilities for documenting and storing data in datasets will be indicated. In addition, procedures for extracting selected features from stored research data can be offered.

Data analysis to optimise AI model training

Our service enhances your dataset's quality using descriptive statistics to gain insights and ensure robustness. We use measures like mean, median, standard deviation, etc., to identify central tendencies and variability. We perform plausibility filtering to check for logical consistency and outlier filtering to remove data points that could skew predictions. This careful data preparation refines your dataset, boosting the accuracy and reliability of your model training. Tailored to your needs, these methods optimise your dataset for better model performance.

Data augmentation to optimise AI model training and prevent the model from overfitting

Lukasiewicz Poznanski Instytut Technologiczny (L-PIT)

In preparing image or sensor data, pre-processing is crucial. We apply techniques like normalisation for data uniformity and correlation analysis to uncover patterns, enhancing interpretability. Dimension reduction optimises computational efficiency, while adding randomised noise and artificial expansion improves model generalisation. We implement anonymisation to protect data privacy and ensure precise data labelling for supervised learning. These methods, tailored to your needs, enhance your data's quality and usability.

Data augmentation

Experimentation with synthetic data generation and data augmentation techniques

This service involves expanding training datasets using synthetic data and data augmentation techniques. This will use algorithms capable of generating synthetic data simulating certain aspects of existing datasets. Such an approach will lead to the enrichment of the existing training material. The service includes the creation of synthetic replicas based on real data, the combining of real and synthetic data, and also, for example, the creation of digital terrain maps based on ground data, which can be further enriched with synthetically generated details. As a result, we offer a comprehensive solution for more reliable development of datasets.

Data augmentation

Lukasiewicz Poznanski Instytut Technologiczny (L-PIT)

Generation and provision of labelled datasets for benchmarking purposes

The service provides the ability to deliver to the client model training data sets with labels and metadata, which will later be used to conduct comparative analyses of AI algorithms by the target groups using the technologies under study. The datasets delivered to the client will be configured or customised in advance, as appropriate, according to the requirements and needs of the client of the service. Customisation processes will include configuring and adjusting the data and labelling according to the scopes of field operations, technological processes or communications to which the transferred data assets relate. These data sets include, but are not limited to, satellite and spatial data for remote sensing, phenological data for different crops, or synthetic data to expand training opportunities.

Performance evaluation of an AI model

Our service provides a thorough evaluation of AI models by utilising a wide range of benchmark datasets—from images and sensor data to remote sensing and multimodal data. This comprehensive testing assesses the model's performance across standard metrics, specifically chosen based on the model’s intended tasks. The results offer insights into the model’s effectiveness and accuracy, guiding developers in refining their AI solutions to achieve optimal performance in real-world applications.

Lukasiewicz Poznanski Instytut Technologiczny (L-PIT)

Providing demonstration testing on the test field of robotic or AI-driven solutions

As part of the service, a testbed will be provided for product demonstration of robotic machines along with AI systems. The polygon will be configured and prepared to meet the customer's individual needs in terms of field operations, technological processes, and communication. The service provider will provide polygons with a variety of surfaces according to the customer's specifications, e.g., meadow, ploughed field. The service will include soil moisture control, continuous monitoring of the field, and all activities carried out on it. The service providers will provide the necessary assistance and infrastructure needed to support the fieldwork carried out by the surveyed sites. The service may also involve demonstration of AI systems used in apiaries.

Desk assessment

People training

Lukasiewicz Poznanski Instytut Technologiczny (L-PIT)

Test design

Test execution

Test setup

Provision of cloud-based data storage

Within the service we provide: - remote access to the disc space, allowing for safe storage of data (e.g., from sensors, photos from specialised cameras, weather data, satellite data, archive historical crop yields, etc.). - Depending on the needs, the available disc space can range from several gigabytes to tens, if not hundreds, of terabytes. - The stored data may be used directly by the customer or may be used in other services (this refers to using data for AI/ML model training, testing and validation for applications such as precision farming, yield prediction and pest detection). - The ability to store both structured (e.g., CSV, SQL) and unstructured data (e.g., images, videos)

Provision of datasets

Our service offers a comprehensive dataset tailored for training or testing your solutions in the technology and agricultural sectors. Whether you're looking to enhance existing models or build new ones, our versatile data can be adapted to fit your specific needs. For those requiring an even more robust solution, our service seamlessly integrates with our data augmentation and labelling service (S00172), ensuring that you have access to well-organized and precisely labelled data. This flexibility allows us to support a variety of sensors and use cases, utilizing both existing data records and capturing new data in your application area. Optimize your agricultural technology solutions with our data services, designed to propel your projects forward efficiently and effectively.

Data augmentation

Testing of AI-based sensor performance

Our service thoroughly evaluates AI-based sensors by measuring key metrics like accuracy, mean squared error, and other tailored parameters. Testing is conducted in real-world environments where the sensor will be used, with reference data recorded or labelled for analysis. For certain sensors, we also utilise benchmark datasets to validate performance. We assess consistency under identical conditions, adaptability to environmental changes (e.g., light, temperature, or weather), and improvements in accuracy over time. Additionally, we measure power consumption, processing efficiency, and memory usage to ensure optimal resource utilisation. Response time between detection and action is evaluated for real-time applications, while extreme condition testing (e.g., bright light, rainy conditions, compacted soil) ensures robustness in challenging environments. We also verify data security and resilience against adversarial attacks. This comprehensive testing is essential, ensuring sensors meet high standards of precision, reliability, and efficiency. Benchmark datasets, standardised data collections used for validation, provide a reliable baseline for performance comparison. By addressing these aspects, our service ensures your sensor technology is ready for real-world deployment, delivering the performance and adaptability your application demands.