Our team specialises in developing reliable software for intelligent systems that run on heterogeneous platforms and integrate complex functions such as AI, artificial perception, and advanced control systems. We have extensive experience in state-of-the-art methodologies and technologies for the development of autonomous systems, with a focus on software development for highly autonomous vehicles, such as railway GoA2-4 and automotive SAE2-4. Our focus is on enhancing the software's automation and robustness while maintaining its modularity and scalability.
We work in cutting-edge fields such as intelligent mobility, Industry 4.0, and the edge-cloud continuum. Our expertise lies in adapting platforms, frameworks and reference communication systems to ensure real-time execution and/or reliability in (hyper) distributed software. Additionally, we develop partitioned architectures for critical applications using hypervisors and encapsulation platforms like Docker.
We create automated test environments for software with complex functionality. These environments enable developers to test their applications efficiently and effectively, ensuring that the software performs as expected under various conditions. Our work is essential to maintaining the high quality and dependability of the software we develop. Additionally, we integrate generative AI models for software development and automation.
We implement dependability assurance mechanisms in software that implements AI algorithms or artificial perception functions, providing an additional layer of security with diagnostics, fault tolerance, redundancy and hybridisation mechanisms. We complement this with the study and integration of ML/IA algorithms that consider dependability aspects (e.g. Safe RL) and are designed to guarantee the security, integrity and availability of AI systems.
Our pioneering and high-level facilities offer the essential tools to carry out tests and validations of different technologies and thus address challenges such as sustainability, energy efficiency and cybersecurity.
We tackle projects in sectors with the highest levels of functional safety integrity (SIL-4). In other words, we develop control applications that must minimise the probability of failure to exceptionally low levels, because they can put people's lives at risk or the condition of expensive infrastructure or equipment.