SYNTHESES

The SYNTHESES project focuses on improving the testing and validation of autonomous systems through the generation of large-scale synthetic datasets. As autonomous vehicles and mobility systems encounter increasingly complex environments, particularly in urban settings, traditional data collection methods struggle to capture rare edge-case scenarios that are critical for ensuring safety and reliability. The project seeks to address this challenge by developing automated tools to generate synthetic data, simulating diverse and difficult-to-replicate real-world conditions. The primary goal of SYNTHESES is to create a scalable framework that automatically generate large pool of edge scenarios and synthetic dataset for validating autonomous systems across multiple operational design domains (ODDs). By leveraging advanced simulation technologies, the project aims to streamline scenario generation, reduce the time and cost of testing, and improve the robustness of autonomous systems. The outcomes will contribute to faster deployment of these systems in industries such as automotive, urban mobility, and robotics, while this project focus on automotive use cases.