Analyzing Cyber-Physical Systems from the Perspective of Artificial Intelligence

TL;DR

This paper compares traditional analytical methods for cyber-physical systems with AI-based approaches, emphasizing the role of reinforcement learning in managing uncertainty and complexity in CPS analysis.

Contribution

It provides a comparative analysis of classical and AI-driven methods for CPS modeling, highlighting the potential of reinforcement learning to handle uncertainties.

Findings

AI approaches address uncertainties better than traditional methods

Reinforcement learning offers promising results in complex CPS analysis

Traditional methods may lack adaptability in unpredictable scenarios

Abstract

Principles of modern cyber-physical system (CPS) analysis are based on analytical methods that depend on whether safety or liveness requirements are considered. Complexity is abstracted through different techniques, ranging from stochastic modelling to contracts. However, both distributed heuristics and Artificial Intelligence (AI)-based approaches as well as the user perspective or unpredictable effects, such as accidents or the weather, introduce enough uncertainty to warrant reinforcement-learning-based approaches. This paper compares traditional approaches in the domain of CPS modelling and analysis with the AI researcher perspective to exploring unknown complex systems.