Update on Machine-Learned Correctness Properties

Loading...
Thumbnail Image
Authors
Michael, James
Drusinsky, Doron
Litton, Matthew
Subjects
assurance
machine learning
runtime verification
formal methods
cross entropy
autonomous systems
Advisors
Date of Issue
2023-01
Date
January 2023
Publisher
Monterey, California. Naval Postgraduate School
Language
Abstract
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.
Type
Technical Report
Description
Prepared for: Naval Information Warfare Systems Command (NAVWAR)
Series/Report No
Department
Computer Science (CS)
Organization
Naval Postgraduate School
Identifiers
NPS Report Number
NPS-CS-23-001
Sponsors
Naval Information Warfare Systems Command (NAVWAR) 4301 Pacific Hwy., Bldg. OT7 San Diego, CA 92110-3127
Funder
Naval Information Warfare Systems Command (NAVWAR)
Format
77 p.
Citation
Distribution Statement
Approved for public release; distribution is unlimited.
Rights
This 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.
Collections