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.
Integrating AI into Functional Safety Management
SAFEXPLAIN is developing an AI-Functional Safety Management methodology that guides the development process, maps the traditional lifecycle of safety-critical systems with the AI lifecycle, and addreses their interactions. AI-FSM extends widely adopted FSM methodologies that stem from functional safety standards to the the specific needs of Deep Learning architecture specifications, data, learning, and inference management, as well as appropriate testing steps. The SAFEXPLAIN-developed AI-FSM considers recommendations from IEC 61508 [5], EASA [6], ISO/IEC 5460 [3], AMLAS [7] and ASPICE 4.0 [8], among others.
Certification bodies weigh-in on SAFEXPLAIN functional safety management methodologies integrating AI
SAFEXPLAIN partners from IKERLAN and the Barcelona Supercomputing Center met with TÜV Rheinland experts on 22 January 2024 to share the project´s AI-Functional Safety Management (AI-FSM) methodology. This meeting provided an important opportunity for the project to present its work to an important player in safety certification.
Mixed Critical Systems Workshop at HiPEAC 2024
Irune Agirre, from partner IKERLAN, discusses functional safety approaches for AI-based critical systems at HiPEAC2024 On 19 January 2024, members of the SAFEXPLAIN consortium participated in the 12th Workshop on "MCS: Mixed Critical Systems – Safe and Secure...
MCS: International Workshop on Mixed Critical Systems – Safe and Secure Intelligent CPS and the development cycle
Nowadays society is surrounded by modern embedded systems that typically integrate multitude of functionalities with potentially different criticality (safety-security) levels into a single system. This is what we call Mixed‐Criticality Cyber‐Physical Systems (MCCPS)....
Safexplain Kick-off-Meeting
The eFlows4HPC Kick-off-Meeting takes place on 15-16 March 2021 in a digital format.
Launch Event: Paving the way towards the next generation of R&I excellence in AI, Data and Robotics
The Adra-e and AI4Europe Coordination and Support Actions (CSAs) co-organised the weibinar "Paving the way toward the next generation of R&I excellence in AI, Data and Robotics" to introduce and take stock of the newly funded R&I landscape and to identify...