Introducing SAFEXPLAIN:
Safe and Explainable Critical Embedded Systems based on AI
Objectives
To improve the explainability and traceability of DL components
To provide clear safety patterns for the incremental adoption of DL software in Critical Autonomous AI-based Systems (CAIS)
To integrate the SAFEXPLAIN libraries with an industrial system-testing toolset
To create architectures of DL components with quantifiable and controllable confidence, and that have the ability to identify when predictions should not be released based on applicability’s scope or security concerns
To design, implement, or update selected representative DL software libraries according to safety patterns and safety lifecycle considerations, meeting specific performance requirements on relevant platforms
Deep Learning (DL) techniques are key for most future advanced
software functions in Critical Autonomous AI-based Systems (CAIS) in
cars, trains and satellites. Hence, those CAIS industries depend on their
ability to design, implement, qualify, and certify DL-based software
products under bounded effort/cost
Case studies
Railway: This case studies the viability of a safety architectural pattern for the completely autonomous operation of trains (Automatic Train Operation, ATO) using intelligent Deep Learning (DL)-based solutions.
Space: This case employs state-of-the-art mission autonomy and artificial intelligence technologies to enable fully autonomous operations during space missions. These technologies are developed through high safety-critical scenarios.
Automotive: This case develops advanced methods and procedures that enable self-driving cars to accurately detect road users, estimate their distance from the vehicle, and predict their trajectories while adhering to both safety and explainability requirements.
SAFEXPLAIN Update: Building Trustworthy AI for Safer Roads
For enhanced safety in AI-based systems in the railway domain, the SAFEXPLAIN project has been working to integrate cutting-edge simulation technologies with robust communication frameworks. Learn more about how we’re integrating Unreal Engine (UE) 5 with Robot Operating System 2 (ROS 2) to generate dynamic, interactive simulations that accurately replicate real-world railway scenarios.
Enhancing Railway Safety: Implementing Closed-Loop Validation with Unreal Engine 5 and ROS 2 Integration
For enhanced safety in AI-based systems in the railway domain, the SAFEXPLAIN project has been working to integrate cutting-edge simulation technologies with robust communication frameworks. Learn more about how we’re integrating Unreal Engine (UE) 5 with Robot Operating System 2 (ROS 2) to generate dynamic, interactive simulations that accurately replicate real-world railway scenarios.
Case Studies Update: Integrating XAI, Safety Patterns and Platform Development
The SAFEXPLAIN project has reached an exciting point in its lifetime: the integration of the outcomes of the different partners.
The work related to the case studies began with the preparation of AI algorithms, as well as the datasets required for the trainings and for the simulation of the operational scenarios. Simultaneously, the case studies have counted on support from the partners focused on explainable AI (XAI), safety patterns and platform development.
40th ACM/SIGAPP symposium on Applied Computing
On 4 April 2025, Sergi Vilardell from the Barcelona Supercomputing Center will present "Probabilistic Timing Estimates in Scenarios Under Testing Constraints " as part of the Conference track on System Software and Security EMBS, Embedded Systems Track. The 40th...
Future-Ready On-Demand Solutions with AI, Data, and Robotics
SAFEXPLAIN project coordinator, Jaume Abella, represented the project as part of the first day of the “Future-Ready: On-Demand Solutions with AI, Data, and Robotics” event. The TrustworthyAI Cluster held a Birds of a Feather workshop on main innovations and future challenges on 18 Feb 2025 at 10:30.
Webinar- Putting it together: The SAFEXPLAIN platform and toolsets
The third webinar in the SAFEXPLAIN webinar series will share the novative infrastructure behind the AI-FSM and XAI methodologies. Participants will gain insights into the integration of the proposed solutions and how they are designed to enhance the safety, portability and adaptability of AI systems.