Statistical Analysis and Runtime Monitoring for an AI-based Autonomous Centerline Tracking System

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Sep 4, 2023
Yuning He Johann Schumann

Abstract

Autonomous Centerline Tracking (ACT) enables an unmanned aircraft to be guided down the center of the runway, using a camera-based Deep Neural Network (DNN). ACT is safety-critical. The EASA Guidelines for machine-learning based systems list numerous assurance objectives that must be met toward certification and V&V. We extend our analysis framework SYSAI to provide feedback on performance of system and AI component to the designer and describe a combination with a runtime monitoring architecture that also supports advanced risk mitigation to support safety assurance of a complex AI-based aerospace system.

Abstract 657 | PDF Downloads 159

##plugins.themes.bootstrap3.article.details##

Keywords

runtime monitoring, assurance and certification, Deep Neural Network, autonomous systems

References
EASA, & Daedalean. (2021). Concepts of Design Assurance for Neural Networks II (Tech. Rep.).

EASA Concept Paper: First usable guidance for Level 1 machine learning applications (Tech. Rep.). (2021). European Aviation Safety Agency.

AA. (2021). Neural Network based Runway Landing Guidance for General Aviation Autoland (Tech. Rep. No. DOT/FAA/TC-21/48). Gramacy, R., & Polson, N. (2011). Particle learning of Gaussian process models for sequential design and optimization. Journal of Computational and Graphical Statistics, 20(1), 467–478.

He, Y., & Schumann, J. (2020). A Framework for the Analysis of Deep Neural Networks in Aerospace Applications using Bayesian Statistics. In Proc. Int. Joint Conf. for Neural Networks (IJCNN), WCCI .

He, Y., Schumann, J., & Yu, H. (2022). Toward runtime assurance of complex systems with ai components. In Proc. PHME 2022.

Nagarajan, P., Kannan, S. K., Torens, C., Vukas, M. E., & Wilber, G. F. (2021). ASTM F3269 An Industry Standard on Run Time Assurance for Aircraft Systems. In AIAA Scitech 2021 Forum. Retrieved from https://arc.aiaa.org/doi/ abs/10.2514/6.2021-0525 doi: 10.2514/6 .2021-0525

Pike, L., Goodloe, A., Morisset, R., & Niller, S. (2010, November). Copilot: A Hard Real-Time Runtime Monitor. In Proceedings of the 1st intl. Conference on Runtime Verification. Springer.

Reinbacher, T., Rozier, K. Y., & Schumann, J. (2014). Temporal-Logic Based Runtime Observer Pairs for System Health Management of Real-Time Systems. In Tools and Algorithms for the Construction and Analysis of Systems 20th International Conference, TACAS (Vol. 8413, pp. 357–372). Springer.

Taddy, M. A., Gramacy, R. B., & Polson, N. G. (2011). Dynamic trees for learning and design. Journal of the American Statistical Association, 106(493), 109-123.

Yu, T., & Zhu, H. (2020). Hyper-parameter Optimization: A review of Algorithms and Applications. Retrieved from https://arxiv.org/abs/2003.05689
Section
Regular Session Papers