Safety and Artificial Intelligence in Cyberphysical Systems
Abstract
Safe artificial intelligence/machine learning (AI/ML)-enabled systems require design methodologies that accommodate for failures in AI/ML decisions. Certification of AI/ML systems and components will increase trust and accelerate adoption, deployment, and use in critical domains.
References
[1]
“EU AI Act: First regulation on artificial intelligence,” European Parliament, Brussels, Belgium, Dec. 2023. [Online]. Available: Dec. 27, 2023. https://www.europarl.europa.eu/news/en/headlines/society/20230601STO93804/eu-ai-act-first-regulation-on-artificial-intelligence
[2]
“Blueprint for an AI bill of rights,” The White House, Washington, DC, USA, 2023. [Online]. Available: Dec. 27, 2023. https://www.whitehouse.gov/ostp/ai-bill-of-rights/
[3]
P. Kooman, How Safe is Safe Enough?: Measuring and Predicting Autonomous Vehicle Safety. Independently Published, Pittsburgh, PA, USA, Sep. 2, 2022.
[4]
K. Samal, T. Walton, D. H. Tran, and M. Wolf, “A Markovian error model for false negatives in DNN-based perception-driven control systems,” Procedia Comput. Sci., vol. 222, pp. 549–560, Aug. 2023.
[5]
W. Widen and P. Koopman, “Winning the imitation game: Setting safety expectations for automated vehicles,” Minnesota J. Law, Sci. Technol., vol. 25, no. 1, pp. 1–35, Apr. 25, 2023.
Index Terms
- Safety and Artificial Intelligence in Cyberphysical Systems
Index terms have been assigned to the content through auto-classification.
Recommendations
Toward Responsible Artificial Intelligence Systems: Safety and Trustworthiness
Engineering of Computer-Based SystemsAbstractThis short paper associated to the invited lectures introduces two key concepts essential to artificial intelligence (AI), the area of trustworthy AI and the concept of responsible AI systems, fundamental to understand the technological, ethical ...
Artificial intelligence
AbstractArtificial intelligence (AI) is the Science and Engineering domain concerned with the theory and practice of developing systems that exhibit the characteristics we associate with intelligence in human behavior. Starting with a brief history of ...
Comments
Information & Contributors
Information
Published In
0018-9162 © 2024 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.
Publisher
IEEE Computer Society Press
Washington, DC, United States
Publication History
Published: 06 March 2024
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 21 Sep 2024
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in