Update on Machine-Learned Correctness Properties

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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 31, 2023
Accession Number
AD1193452

Entities

People

  • Doron Drusinsky
  • James B Michael
  • Matthew Litton

Organizations

  • Naval Postgraduate School

Tags

Communities of Interest

  • Autonomy
  • C4I
  • Cyber
  • Energy and Power Technologies
  • Ground and Sea Platforms
  • Materials and Manufacturing Processes
  • Weapons Technologies

DTIC Thesaurus Topics

  • Air Force
  • Artificial Intelligence
  • Computational Science
  • Computer Languages
  • Computer Programming
  • Computers
  • Control Systems
  • Human-Machine Systems
  • Machine Learning
  • Military Research
  • Network Science
  • Neural Networks
  • Software Testing
  • Supervised Machine Learning
  • Test And Evaluation
  • Unmanned Systems
  • Unmanned Vehicles

Fields of Study

  • Computer science

Readers

  • Database Systems and Applications
  • Neural Network Machine Learning.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - Neural Networks
  • Autonomy
  • Autonomy - Autonomous System Control