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
Recognizing the Contributions of Women in Science
Women have made huge contributions to the scientific community. Raising their visibility and representation of women in science is key for ensuring that the next generation of scientists have positive role models and learn to value diversity and equity in...
Safexplain at HiPEAC conference 2023
Safexplain gives a talk and presents a poster during the HiPEAC conference 2023, that took place from 16 – 18 January 2023 in Toulouse, France.
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.
Tweets
We're Basqu-ing in her success (sorry...!) Go @IruneAgirre! https://twitter.com/SafexplainAI/status/1623993559077486593
#Womeninscience inspire the next generation of scientists!
Meet @IruneAgirre . She's helping to ensure critical autonomous #ai -based systems are safe. Read about her work
🔗http://ow.ly/iNIy50MP37p
#11F @IKERLANofficial