Update on Machine-Learned Correctness Properties
MetadataShow full item record
This report details a novel method which has the potential for improving the U.S. Navy’s ability to perform continuous assurance on autonomous and other cyberphysical systems. Specifically, this report presents a novel technique for simulation-driven data generation of explainable machine-learned correctness properties, called ML-assertions, for the purpose of subsequent runtime verification. The method brings the task of providing formal guarantees about the dependability of autonomous systems from the realm of doctoral-level experts into the domain of system developers and engineers. Preliminary experimentation demonstrates that ML-assertions can be utilized for behavior prediction in complex multi-agent systems, serving as a state-of-the-art method for conducting verification and validation on autonomous cyberphysical systems.
Prepared for: Naval Information Warfare Systems Command (NAVWAR)
RightsThis publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.
NPS Report NumberNPS-CS-23-001
Showing items related by title, author, creator and subject.
Galdorisi, George (2017-04-12);One of the operational and technical challenges of fielding unmanned systems with even more autonomy is the rising cost of military manpower—one of the fastest growing military accounts—and the biggest cost driver in the ...
Consortium for Robotics and Unmanned Systems Education and Research (CRUSER) (Monterey, California: Naval Postgraduate School, 2015-03);Abstract: Dramatic progress in the science and engineering of robotics, alongside the perceived success of the US’s predator and Reaper drones in Iraq and Afghanistan, has led many commentators to conclude that the wars ...
Morsy, Khaled Ahmed (Monterey, California. Naval Postgraduate School, 1997-09);The problem discussed in this dissertation is the development of an efficient method for visual navigation of autonomous vehicles. The approach is to significantly reduce the expensive computational time of landmark detection ...