Corpus ID: 202765392

Neural Lyapunov Control

@article{Chang2019NeuralLC,
  title={Neural Lyapunov Control},
  author={Ya-Chien Chang and N. Roohi and Sicun Gao},
  journal={ArXiv},
  year={2019},
  volume={abs/2005.00611}
}
  • Ya-Chien Chang, N. Roohi, Sicun Gao
  • Published 2019
  • Computer Science, Mathematics, Engineering
  • ArXiv
  • We propose new methods for learning control policies and neural network Lyapunov functions for nonlinear control problems, with provable guarantee of stability. The framework consists of a learner that attempts to find the control and Lyapunov functions, and a falsifier that finds counterexamples to quickly guide the learner towards solutions. The procedure terminates when no counterexample is found by the falsifier, in which case the controlled nonlinear system is provably stable. The approach… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    Neural Lyapunov Model Predictive Control
    • 2
    • PDF
    Formal Synthesis of Lyapunov Neural Networks
    • 1
    • Highly Influenced
    • PDF
    Automated Formal Synthesis of Lyapunov Neural Networks
    • 1
    • Highly Influenced
    Neural Contraction Metrics for Robust Estimation and Control: A Convex Optimization Approach
    • 1
    • PDF
    Learning Dynamical Systems with Side Information (short version)
    • 1
    • PDF
    Neural Certificates for Safe Control Policies
    Learning Safe Neural Network Controllers with Barrier Certificates

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 32 REFERENCES
    Linear Optimal Control Systems
    • 4,074
    • PDF
    Safe Model-based Reinforcement Learning with Stability Guarantees
    • 254
    • PDF
    Nonlinear Dynamical Systems and Control: A Lyapunov-Based Approach
    • 931
    • PDF
    Concrete Problems in AI Safety
    • 690
    • PDF
    Positive Polynomials in Control
    • 254
    Simulation-guided lyapunov analysis for hybrid dynamical systems
    • 100
    • PDF
    A Lyapunov-based Approach to Safe Reinforcement Learning
    • 92
    • PDF
    Funnel libraries for real-time robust feedback motion planning
    • 142
    • PDF
    The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamic Systems
    • 41
    • PDF