| 1. |
- Abella, Jaume, et al.
(författare)
-
SAFEXPLAIN : Safe and Explainable Critical Embedded Systems Based on AI
- 2023
-
Ingår i: DATE 23: Design, Automation And Test In Europe. - 9783981926378 ; , s. 1-6
-
Konferensbidrag (refereegranskat)abstract
- Deep Learning (DL) techniques are at the heart of most future advanced software functions in Critical Autonomous AI-based Systems (CAIS), where they also represent a major competitive factor. Hence, the economic success of CAIS industries (e.g., automotive, space, railway) depends on their ability to design, implement, qualify, and certify DL-based software products under bounded effort/cost. However, there is a fundamental gap between Functional Safety (FUSA) requirements on CAIS and the nature of DL solutions. This gap stems from the development process of DL libraries and affects high-level safety concepts such as (1) explainability and traceability, (2) suitability for varying safety requirements, (3) FUSA-compliant implementations, and (4) real-time constraints. As a matter of fact, the data-dependent and stochastic nature of DL algorithms clashes with current FUSA practice, which instead builds on deterministic, verifiable, and pass/fail test-based software. The SAFEXPLAIN project tackles these challenges and targets by providing a flexible approach to allow the certification - hence adoption - of DL-based solutions in CAIS building on: (1) DL solutions that provide end-to-end traceability, with specific approaches to explain whether predictions can be trusted and strategies to reach (and prove) correct operation, in accordance to certification standards; (2) alternative and increasingly sophisticated design safety patterns for DL with varying criticality and fault tolerance requirements; (3) DL library implementations that adhere to safety requirements; and (4) computing platform configurations, to regain determinism, and probabilistic timing analyses, to handle the remaining non-determinism. © 2023 EDAA.
|
|
| 2. |
- Perez-Cerrolaza, Jon, et al.
(författare)
-
Artificial Intelligence for Safety-Critical Systems in Industrial and Transportation Domains: A Survey
- 2024
-
Ingår i: ACM Computing Surveys. - New York : Association for Computing Machinery. - 0360-0300 .- 1557-7341. ; 56:7
-
Tidskriftsartikel (refereegranskat)abstract
- Artificial Intelligence (AI) can enable the development of next-generation autonomous safety-critical systems in which Machine Learning (ML) algorithms learn optimized and safe solutions. AI can also support and assist human safety engineers in developing safety-critical systems. However, reconciling both cutting-edge and state-of-the-art AI technology with safety engineering processes and safety standards is an open challenge that must be addressed before AI can be fully embraced in safety-critical systems. Many works already address this challenge, resulting in a vast and fragmented literature. Focusing on the industrial and transportation domains, this survey structures and analyzes challenges, techniques, and methods for developing AI-based safety-critical systems, from traditional functional safety systems to autonomous systems. AI trustworthiness spans several dimensions, such as engineering, ethics and legal, and this survey focuses on the safety engineering dimension.
|
|
