Search Results for author:
Found 5 papers, 3 papers with code
Synthesis of Stabilizing Recurrent Equilibrium Network Controllers
We propose a parameterization of a nonlinear dynamic controller based on the recurrent equilibrium network, a generalization of the recurrent neural network.
Learning Neural Networks under Input-Output Specifications
In this paper, we examine an important problem of learning neural networks that certifiably meet certain specifications on input-output behaviors.
Safe-by-Design Planner-Tracker Synthesis
We present a safe-by-design trajectory planning and tracking framework for nonlinear dynamical systems using a hierarchy of system models.
Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systems
Neural network controllers have become popular in control tasks thanks to their flexibility and expressivity.
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).
