# Neural Identification for Control

arXiv: https://arxiv.org/abs/2009.11782 · HTML: https://mlsanity.com/paper/2009.11782/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2020.

## Built on by (most cited first, 3 of 3)

- [Neural Lyapunov Differentiable Predictive Control](https://mlsanity.com/paper/2205.10728/) (2022)
- [Bridging Autoencoders and Dynamic Mode Decomposition for Reduced-order Modeling and Control of PDEs](https://mlsanity.com/paper/2409.06101/) (2024)
- [Learn Proportional Derivative Controllable Latent Space from Pixels](https://mlsanity.com/paper/2110.08239/) (2021)

## Abstract (arXiv)

We present a new method for learning control law that stabilizes an unknown nonlinear dynamical system at an equilibrium point. We formulate a system identification task in a self-supervised learning setting that jointly learns a controller and corresponding stable closed-loop dynamics hypothesis. The input-output behavior of the unknown dynamical system under random control inputs is used as the supervising signal to train the neural network-based system model and the controller. The proposed method relies on the Lyapunov stability theory to generate a stable closed-loop dynamics hypothesis and corresponding control law. We demonstrate our method on various nonlinear control problems such as n-link pendulum balancing and trajectory tracking, pendulum on cart balancing, and wheeled vehicle path following.