EUVIMEDEUVIMED entdecken
Crossref

Anunnaki: A Modular Framework for Developing Trusted Artificial Intelligence

Michael Austin Langford, Sol Zilberman, Betty Cheng

ACM Transactions on Autonomous and Adaptive Systems · 30.09.2024 · 19 (3) · 1-34

DOI: 10.1145/3649453 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Autonomous and Adaptive Systems, online erschienen am 13.09.2024. Verfasst von Michael Austin Langford und 2 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 96 Literaturangaben. Gefördert von: National Science Foundation, Air Force Research Laboratory.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Trustworthy artificial intelligence (Trusted AI) is of utmost importance when learning-enabled components (LECs) are used in autonomous, safety-critical systems. When reliant on deep learning, these systems need to address the reliability, robustness, and interpretability of learning models. In addition to developing strategies to address these concerns, appropriate software architectures are needed to coordinate LECs and ensure they deliver acceptable behavior even under uncertain conditions. This work describes Anunnaki, a model-driven framework comprising loosely-coupled modular services designed to monitor and manage LECs with respect to Trusted AI assurance concerns when faced with different sources of uncertainty. More specifically, the Anunnaki framework supports the composition of independent, modular services to assess and improve the resilience and robustness of AI systems. The design of Annunaki was guided by several key software engineering principles (e.g., modularity, composability, and reusability) in order to facilitate its use and maintenance to support different aggregate monitoring and assurance analysis tools for LESs and their respective data sets. We demonstrate Anunnaki on two autonomous platforms, a terrestrial rover, and an unmanned aerial vehicle. Our studies show how Anunnaki can be used to manage the operations of different autonomous learning-enabled systems with vision-based LECs while exposed to uncertain environmental conditions.

Förderung

  • National Science Foundation
  • Air Force Research Laboratory

Zitieren

APA

Langford, M. A., Zilberman, S., & Cheng, B. (2024). Anunnaki: A Modular Framework for Developing Trusted Artificial Intelligence. ACM Transactions on Autonomous and Adaptive Systems, 19(3), 1-34. https://doi.org/10.1145/3649453

Vancouver

Langford MA, Zilberman S, Cheng B. Anunnaki: A Modular Framework for Developing Trusted Artificial Intelligence. ACM Transactions on Autonomous and Adaptive Systems. 2024;19(3):1-34. doi:10.1145/3649453

BibTeX
@article{Langford2024,
  author = {Langford, Michael Austin and Zilberman, Sol and Cheng, Betty},
  title = {Anunnaki: A Modular Framework for Developing Trusted Artificial Intelligence},
  journal = {ACM Transactions on Autonomous and Adaptive Systems},
  year = {2024},
  volume = {19},
  number = {3},
  pages = {1--34},
  doi = {10.1145/3649453}
}
Kostenlos starten →