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.
Safety patterns for AI-based systems
Through the SAFEXPLAIN project, Ikerlan has analyzed strategies and developed specific solutions to implement safety patterns in systems that incorporate AI components. Learn more about the 4 key safety mechanisms used in the reference safety architurecture pattern.
Coming Soon! SAFEXPLAIN technologies converge in an open demo
As the project enters into its 27th month, releases for most technologies are already available and undergoing the last steps towards completing their integration.To demonstrate the SAFEXPLAIN approach, project partners are working towards creating an open source demo...
Developing Scenario Catalogues for SAFEXPLAIN Case Studies: the Railway Case
Part of Exida developnet SRL’s work in the SAFEXPLAIN project includes developing a Catalogue of Scenarios and Test Cases for each case study. These scenarios are performed in either a real or simulated testing environment.
SE keynote & WS as part of Gate4SPICE Event “Optimal Performance of Modern Development: Automotive SPICE® Fusion with Intelligent Systems and Agile Frameworks”
SAFEXPLAIN will present a keynote at the INTACS event "Optimal Performance of Modern Development: Automotive SPICE® Fusion with Intelligent Systems and Agile Frameworks" hosted by SEITech Solutions GmbH as part of the Gate4SPICE. The keynote, "A Tale of Machine...
Keynote at 36th Euromicro Conference on Real-Time Systems
SAFEXPLAIN research and results will have high visibility in the 2024 36th Euromicro Conference on Real-Time Systems. Francisco Cazorla, co-leader of the BSC’s Critical and AutOnomous Systems (CAOS) group delivered the keynote at this major international conference...
Webinar: AI-FSM- Towards Functional Safety Management for Artificial Intelligence-based Critical Systems
Javier Fernandez from partner IKERLAN will share the SAFEXPLAIN project approach to integrating AI into Functional Safety Management in a safe, trustworthy and transparent way. In this 1.5 hour webinar hosted by HiPEAC, Javier will introduce a AI-FSM lifecycle that...