Making critical autonomous AI-based systems safe

Making critical autonomous AI-based systems safe

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 deliverables now available!

SAFEXPLAIN deliverables now available!

Twelve deliverables reporting on the work undertaken by the project have been published in the results section of the website. The SAFEXPLAIN deliverables provide key details about the project and how it is progressing. The following deliverables have been created for...

Webinar: XAI for systems with functional safety requirements

Webinar: XAI for systems with functional safety requirements

Robert Lowe, Senior Researcher in AI and Driver Monitoring Systems from partner RISE, will introduce new complexities to XAI in relation to functional safety, transparency and compliance with safety standards. In this 1.5 hour webinar, hosted by HiPEAC, Robert will...

Keynote at 36th Euromicro Conference on Real-Time Systems

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...