Imitation learning with stability and safety guarantees
A method is presented to learn neural network (NN) controllers with stability and safety
guarantees through imitation learning (IL). Convex stability and safety conditions are derived …
guarantees through imitation learning (IL). Convex stability and safety conditions are derived …
Safe and stable secondary voltage control of microgrids based on explicit neural networks
This paper proposes a novel safety-critical secondary voltage control method based on
explicit neural networks (NNs) for islanded microgrids (MGs) that can guarantee any state …
explicit neural networks (NNs) for islanded microgrids (MGs) that can guarantee any state …
Differentiable predictive control: Deep learning alternative to explicit model predictive control for unknown nonlinear systems
We present differentiable predictive control (DPC) as a deep learning-based alternative to
the explicit model predictive control (MPC) for unknown nonlinear systems. In the DPC …
the explicit model predictive control (MPC) for unknown nonlinear systems. In the DPC …
Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approach
Large-scale cyber-physical systems require that control policies are distributed, that is, that
they only rely on local real-time measurements and communication with neighboring agents …
they only rely on local real-time measurements and communication with neighboring agents …
Event-triggered neural network control using quadratic constraints for perturbed systems
This paper investigates the event-triggered control problem for perturbed systems under
neural network controllers. We propose a novel event-triggering mechanism, based on local …
neural network controllers. We propose a novel event-triggering mechanism, based on local …
Convolutional neural networks as 2-d systems
This paper introduces a novel representation of convolutional Neural Networks (CNNs) in
terms of 2-D dynamical systems. To this end, the usual description of convolutional layers …
terms of 2-D dynamical systems. To this end, the usual description of convolutional layers …
Linear systems with neural network nonlinearities: Improved stability analysis via acausal Zames-Falb multipliers
P Pauli, D Gramlich, J Berberich… - 2021 60th IEEE …, 2021 - ieeexplore.ieee.org
In this paper, we analyze the stability of feedback interconnections of a linear time-invariant
system with a neural network nonlinearity in discrete time. Our analysis is based on …
system with a neural network nonlinearity in discrete time. Our analysis is based on …
Neural network training under semidefinite constraints
P Pauli, N Funcke, D Gramlich… - 2022 IEEE 61st …, 2022 - ieeexplore.ieee.org
This paper is concerned with the training of neural networks (NNs) under semidefinite
constraints, which allows for NN training with robustness and stability guarantees. In …
constraints, which allows for NN training with robustness and stability guarantees. In …
Neural system level synthesis: Learning over all stabilizing policies for nonlinear systems
L Furieri, CL Galimberti… - 2022 IEEE 61st …, 2022 - ieeexplore.ieee.org
We address the problem of designing stabilizing control policies for nonlinear systems in
discrete-time, while minimizing an arbitrary cost function. When the system is linear and the …
discrete-time, while minimizing an arbitrary cost function. When the system is linear and the …
Enhancing deep reinforcement learning with integral action to control tokamak safety factor
Recent advances in the use of Artificial Intelligence to control complex systems make it
suitable for profile plasma control. In this work, we propose an algorithm based on Deep …
suitable for profile plasma control. In this work, we propose an algorithm based on Deep …