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.
RISE explains XAI for systems with Functional Safety Requirements
The SAFEXPLAIN project is analysing how DL can be made dependable, i.e., functionally assured in critical systems like cars, trains and satellites. Together with other consortium members, RISE has been working on establishing principles for ensuring that DL components, together with required explainable AI supports, comply with the guidelines set forth by AI-FSM and the safety pattern(s).
High interest in SAFEXPLAIN tech @ Gate4SPICE INTACS event
The SAFEXPLAIN 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 was extremely well-received by attendees. The...
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...
SAFEXPLAIN at ERTS 2024
SAFEXPLAIN presented at the 2024 Embedded Real Time System Congress, to be held in Toulouse, France from 11-12 June 2024. Barcelona Supercomputing Center researcher Martí Caro presented “Software-Only Semantic Diverse Redundancy for High-Integrity AI-Based...
BSC talks Functional Safety at UPC Automotive Embedded Systems course
First slide of training course module given by SAFEXPLAIN coordinator, Jaume Abella and co-presenter Roger Marsal The Technical Unversity of Catalunya hosted a course on "Automotive Embedded Systems" directed at Master´s students coming from the disciplines of...
Exida Development SRL Invited to Speak at InnoVEX 2024
SAFEXPLAIN partner, Carlo Donzella, from Exida Development SRL, has been invited to deliver the first keynote speech of the EV Era Forum session, as part of the 2024 InnoVEX Startup Exhibition, the Innovation Hub of Asia. The event will take place from 4-7 June 2024....