SYNTRA – NovelSense becomes part of EUHubs4Data Project

We are excited to share that the SYNTRA project, which targets synthetic traffic data generation, was selected among 18 other experiments into the EU Hubs 4 Data – 3rd Open Call. EUHubs4Data is programme under the umbrella of the European Union’s Horizon 2020 research and innovation programme to forster the increase the data-driven innovation in SMEs in the EU. SYNTRA is a 10 month project led by NovelSense together with Fraunhofer IOSB, PERCIPIO, SDIL, and KNOWCENTER. With SYNTRA, NovelSense aims to develop a Software-as-a-Service which generates customizable training and benchmarking datasets for traffic AI model benchmarking, training and optimization. The SaaS will soon be available at

About synthetic data and AI: Synthetic data plays a crucial role in the development and testing of artificial intelligence (AI) systems. Creating a large, diverse, and realistic dataset is often challenging, especially in fields where obtaining such data can be costly, time-consuming, or difficult. Synthetic data can be generated with specific characteristics and properties to simulate real-world scenarios, allowing developers to train and test AI algorithms more efficiently and accurately. Furthermore, synthetic data enables developers to create controlled experiments, making it easier to evaluate and compare different AI models. Ultimately, the use of synthetic data can accelerate the development of AI, leading to more advanced and reliable systems.

In the mobility domain, synthetic traffic data is particularly valuable for training and testing AI algorithms. Obtaining real-world traffic data can be difficult due to factors such as privacy concerns, data availability, and safety issues. Synthetic data can be used to generate large and diverse datasets that simulate various traffic scenarios, including different road layouts, weather conditions, and driving behaviors. This synthetic data can be used to train AI models to detect and predict traffic patterns and improve safety systems such as collision avoidance. Additionally, synthetic data can be used to test the robustness of these systems under various scenarios, ensuring that they are reliable and effective in real-world situations. Overall, synthetic traffic data can significantly enhance the development and deployment of AI systems in the mobility domain.