Safety and Stability in Learning-Enabled Control

Robust-control and optimization tools for certifying neural control systems.

This research direction connects modern learning methods with formal control guarantees.

Focus areas:

  • Stability analysis of neural-network-based controllers using quadratic constraints.
  • Safety-aware imitation learning with formal stability/safety guarantees.
  • Robust nonlinear control methods for systems with uncertainty and partial observability.

Representative outputs include publications in IEEE Transactions on Automatic Control, IEEE Control Systems Letters, and AAAI.