SAFEXPLAIN Presentation on Safe and Explainable Critical Embedded Systems Based on AI at DATE Conference in Antwerp

Date: April 18, 2023

SAFEXPLAIN presented its latest research on Safe and Explainable Critical Embedded Systems Based on AI at the Design, Automation and Test in Europe Conference (DATE) in Antwerp, Belgium.

The DATE conference is a leading event for electronic system design and test, attracting experts and professionals from around the world. Safexplain’s participation in the conference highlights the project’s commitment to advancing safety in embedded AI and shaping the future of AI-based safety measures in critical systems.

Francisco J Cazorla during the presentation

SAFEXPLAIN’s paper will provide insights into how AI can be used to improve safety in critical embedded systems, particularly in industries such as automotive, railway, and space. The research will also propose the concept of safety patterns, which allows for an incremental safety approach that adapts to the needs of every AI usage level of AI software until reaching autonomous operation.

Deep Learning techniques are increasingly being used in critical autonomous AI-based systems. However, there is a significant gap between Functional Safety (FUSA) requirements on CAIS and the nature of DL solutions, particularly in areas such as explainability, traceability, FUSA-compliant implementations, and real-time constraints. With AI-based safety measures becoming increasingly crucial in critical systems, SAFEXPLAIN’s participation in the DATE conference is expected to generate significant interest from attendees interested in the latest developments in AI and embedded systems. The presentation of SAFEXPLAIN’s paper brings added value to the ongoing discussion around safety in embedded AI.

By presenting their latest research on the topic at the DATE conference, Safexplain is playing an active role in shaping the future of AI-based safety measures in critical systems. SAFEXPLAIN’s presentation at the DATE conference will provide insights into these innovative solutions and their potential impact on the future of AI-based safety measures in critical systems. If you’re interested in learning more about this topic and attending the presentation, be sure to check out the event link and the slides from the presentation below.