Runtime Safety Monitoring of Neural-Network-Enabled Dynamical Systems

Research output: Contribution to journalArticlepeer-review


Complex dynamical systems rely on the correct deployment and operation of numerous components, with state-of-the-art methods relying on learning-enabled components in various stages of modeling, sensing, and control at both offline and online levels. This article addresses the runtime safety monitoring problem of dynamical systems embedded with neural-network components. A runtime safety state estimator in the form of an interval observer is developed to construct the lower bound and upper bound of system state trajectories in runtime. The developed runtime safety state estimator consists of two auxiliary neural networks derived from the neural network embedded in dynamical systems, and observer gains to ensure the positivity, namely, the ability of the estimator to bound the system state in runtime, and the convergence of the corresponding error dynamics. The design procedure is formulated in terms of a family of linear programming feasibility problems. The developed method is illustrated by a numerical example and is validated with evaluations on an adaptive cruise control system.

Original languageEnglish (US)
Pages (from-to)9587-9596
Number of pages10
JournalIEEE Transactions on Cybernetics
Issue number9
StatePublished - Sep 1 2022


  • Dynamical systems
  • interval observer
  • neural networks
  • runtime monitoring

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Information Systems
  • Human-Computer Interaction
  • Computer Science Applications
  • Electrical and Electronic Engineering


Dive into the research topics of 'Runtime Safety Monitoring of Neural-Network-Enabled Dynamical Systems'. Together they form a unique fingerprint.

Cite this