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: Based on Automatic Train Operation (ATO), this case study seeks to check the viability of a safety architectural pattern composed of: DL artificial vision software elements that serve as “sensors” to provide information to safety-related software elements

Space: This case study envisions the use of state-of-the-art mission autonomy and artificial intelligence technologies to enable fully autonomous operations during space missions

Automotive: This case study will consider Apollo deployed on a variety of prototype vehicles. It supports state-of the-art hardware such as latest LIDARs and cameras as well as GPU acceleration
SAFEXPLAIN to present in COMPSAC Autonomous Systems Symposium
The paper "Efficient Diverse Redundant DNNs for Autonomous Driving", coauthored by BSC authors Martí Caro, Jordi Fornt and Jaume Abella, has been accepted for publication in the 47th IEEE International Conference on Computers, Software & Applications (COMPSAC)....
SAFEXPLAIN Presentation on Safe and Explainable Critical Embedded Systems Based on AI at DATE Conference in Antwerp
SAFEXPLAIN presented its latest research on Safe and Explainable Critical Embedded Systems Based on AI at the upcoming Design, Automation and Test in Europe Conference (DATE) in Antwerp, Belgium. The DATE conference is a leading event for electronic system design and...
SAFEXPLAIN’s Presentation “Efficient Diverse Redundant DNNs for Autonomous Driving” Accepted for COMPSAC 2023
Join us at COMPSAC 2023 to explore innovative research in resilient computing and computing for resilience in a sustainable cyber-physical world! We are excited to announce that the "Efficient Diverse Redundant DNNs for Autonomous Driving" presentation from the...
Standardizing the Probabilistic Sources of Uncertainty for the sake of Safety Deep Learning
The Safexplain team from the CAOS research group of the Barcelona Supercomputing Center (BSC-CNS) presented their latest research at the AAAI's Workshop on Artificial Intelligence Safety of the AAAI 2023, held on February 14, 2023, in Washington D.C. The team's...
Tweets
on #functional saftety, #safexplainproject partner @exidadev presented on
👉 "User Cases and Scenario Catalogue for ML/DL-based solutions testing in Vehicles"
👥to 180+ participants.
More info https://t.co/ekDlUGYLbB https://t.co/3bnG76mbDL
@exidadev presents in the Functional Safety session "User Cases and Scenario Catalogue for ML/DL-based solutions testing in Vehicles"
Registration 👇
https://t.co/IXIN94E2o9
Read what our partner @RISEsweden has to say about this challenge👇
https://t.co/lDsGB5jYwl https://t.co/qoKGUNwQnr
