eess.SYNov 16, 2026

Learning and Verifying Stabilizing Controllers with Structured Neural Control Lyapunov Functions

Authors: Jose Luis Ledesma Martin, Patricia Pauli

Organizations: Department of Mechanical Engineering, Delft University of Technology, Delft, 2628 CD Delft, The Netherlands · Department of Mechanical Engineering, Eindhoven University of Technology, 5612 AZ Eindhoven, The Netherlands

Abstract

This work investigates the joint learning of neural controllers and control Lyapunov functions (CLFs) for nonlinear discrete-time systems. We exploit the structural properties of Input Convex Neural Networks and Polyak-Łojasiewicz Networks to guarantee positive definiteness of CLF candidates by construction, reducing the conditions requiring formal verification. We develop a mixed-integer programming framework to formally verify the remaining stability conditions and introduce an iterative region of attraction (ROA) expansion procedure to enlarge the certified ROA without retraining. Experiments on an inverted pendulum and a path-tracking system demonstrate the advantages of structured neural CLFs, particularly PLNets, and illustrate how their structural bounds influence the geometry of the certified regions. Our code is available at: https://github.com/JLedesMart/Structured-Neural-Control-Lyapunov-Functions.

Figures & tables

Explore similar work

CardsList
  1. Joint Learning of Control Lyapunov Functions and Controllers via Stable-by-Design Surrogates

    Nov 16, 2026Patricia Pauli, Matthieu BarreauLyapunov-Based ControlControl Lyapunov Functions

  2. Certified Robust Invariant Polytope Training in Neural Controlled ODEs

    Aug 2, 2024Akash Harapanahalli, Samuel CooganNeural Controlled Differential EquationsRobust Control

  3. Hyperlyve: Parallelized Enumeration and Exact Lyapunov Stability Certification for Deep ReLU Networks

    Nov 16, 2026Brian Yarbrough, Jesse Wayment, Jingbo Wang +2Neural Network StabilityLyapunov Stability