just better DATA
Efficient and highly accurate data generation for AI applications in autonomous driving
Start: 07/2023
End: 06/2026
The primary objective of jbDATA is to develop and implement AI-based methods and tools to collect data with high accuracy and efficiency. A novel aspect is that jbDATA shifts data evaluation to the Edge, i.e., in the capturing vehicle.
Instead of uploading all data to the Cloud as before, recorded data will be pre-processed, evaluated, and sorted for further processing and storage using the Smart Data Loop, which will also be developed as part of the project. Data will be anonymized, analyzed for data gaps, and, where necessary, enriched with synthetic data using methods to be developed in the project.
Test vehicles, including one from the FZI, are used to exemplarily record a data set intended to serve as the foundation for a comprehensive, industrially usable data set. Additionally, jbDATA plans to make the data set collected in the project widely accessible for research beyond the consortium.
The FZI’s initial focus is on determining requirements and designing databases and data sets. Based on this, methods are developed to automatically detect unusual cases (‘corner cases’) and intelligently and efficiently capture data directly at the Edge. To expand the data sets, synthetic data is subsequently added to them. Active learning, domain adaptation, and data augmentation methods are used for this purpose.
In this research focus, the FZI concentrates on practical research into the key technology of Artificial Intelligence (AI). Innovative AI solutions are developed and transferred to application areas such as mobility, robotics, healthcare technology, logistics, production, and supply and disposal on behalf of our partners and customers.
Smart solutions for the transportation of people and goods are a focus of FZI research to shape mobility in the future. To this end, the FZI develops integrated mobility systems – from vehicle automation and the application of AI in traffic systems to urban mobility and logistics.
Project partners:
Efficient and highly accurate data generation for AI applications in autonomous driving
Generative AI in Software Development with a focus on smart home applications.
Standardized interfaces for greater speed, safety, and sovereignty in vehicle development
New approaches for interconnected hospital logistics
The modular toolbox for flexible robotics, tailored to the needs of small and medium-sized automotive suppliers
An AI Dashboard helping young people uncover online disinformation
Automated modeling and analysis using intelligent network algorithms and graph methods
The FZI develops ROS driver for Universal Robots
German-Israeli Research Initiative on Digital Democracy
Artificial Intelligence in Traffic Systems