Verifiably Safe Autonomy for Cyber-Physical Systems

Abstract

This thesis demonstrates that autonomous cyber-physical systems that use machine learning for control are amenable to formal verification. Cyber-physical systems, such as autonomous vehicles and medical devices, are increasingly common and increasingly autonomous. Designing safe cyber-physical systems is difficult because of the interaction between the discrete dynamics of control software and the continuous dynamics of the vehicles physical movement. Designing safe autonomous cyber-physical systems is even more difficult because of the interaction between classical controls software and machine learning components.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 2018
Accession Number
AD1173982

Entities

People

  • Nathan Fulton

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Autonomy
  • Cyber
  • Engineered Resilient Systems

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Automata Theory
  • Autonomous Systems
  • Computational Science
  • Computer Languages
  • Computer Programming
  • Computer Science
  • Computers
  • Control Systems
  • Control Systems Engineering
  • Differential Equations
  • Information Systems
  • Machine Learning
  • Mathematical Models
  • Neural Networks
  • Operations Research
  • Reinforcement Learning

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Control Systems Engineering.
  • Software Engineering.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • Autonomy
  • Autonomy - Autonomous System Control
  • Cyber