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.

EV community at Innovex 24 welcomes presentation by SAFEXPLAIN

EV community at Innovex 24 welcomes presentation by SAFEXPLAIN

SAFEXPLAIN partner, Carlo Donzella from exida development, opens EV session with key note on "Enabling the Future of EV with TrustworthyAI" June 6, 2024 marked an important opportunity for the SAFEXPLAIN project to share project results with key audiences from the...

SAFEXPLAIN presents at 22º Automotive SPIN Italia WS

SAFEXPLAIN presents at 22º Automotive SPIN Italia WS

Announcement from the Automotive SPIN ITALIA website The SAFEXPLAIN project will mark its presence at the Automotive SPIN Italia 22º Workshop on Automotive Software & System. Carlo Donzella from partner exida development will share insights into "A Tale of Machine...

Challenges and approaches for the development of Artificial Intelligence (AI)-based Safety-Critical Systems

Challenges and approaches for the development of Artificial Intelligence (AI)-based Safety-Critical Systems

Jon Perez Cerrolaza from SAFEXPLAIN was invited to give a presentation on the “Challenges and approaches for the development of Artificial Intelligence (AI)-based Safety-Critical Systems” at the Instituto Tecnológico de Informática (ITI). The talk was well received by around 25 researchs from the ITI and the Polytechnic University of Valencia who were interested in the SAFEXPLAIN perspective on AI, Safety & Explainability and Trustworthiness.

SAFEXPLAIN at ERTS 2024

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...