paper-with-me

Papers

Provably-Stable Neural Network-Based Control of Nonlinear Systems

2025-02-01 · Anran Li, John P. Swensen, Mehdi Hosseinzadeh

In recent years, Neural Networks (NNs) have been employed to control nonlinear systems due to their potential capability in dealing with situations that might be difficult for conventional nonlinear control schemes. However, to the best of our knowledge, the current literature on NN-based control lacks theoretical guarantees for stability and tracking performance. This precludes the application of NN-based control schemes to systems where stringent stability and performance guarantees are required. To address this gap, this paper proposes a systematic and comprehensive methodology to design provably-stable NN-based control schemes for affine nonlinear systems. Rigorous analysis is provided to show that the proposed approach guarantees stability of the closed-loop system with the NN in the loop. Also, it is shown that the resulting NN-based control scheme ensures that system states asymptotically converge to a neighborhood around the desired equilibrium point, with a tunable proximity threshold. The proposed methodology is validated and evaluated via simulation studies on an inverted pendulum and experimental studies on a Parrot Bebop 2 drone.

📄 PDF Abstract BibTeX arXiv:2502.00248

Code (1)

anran-github/provably-stable-neural-network-based-control-of-nonlinear-systems 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Tanh Activation 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Sigmoid Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Parrot 설명 없음

Similar Papers 제목 키워드 기반

Neural Lyapunov Control for Discrete-Time Systems

2023-05-11 · NeurIPS 2023 11 · Junlin Wu, Andrew Clark, Yiannis Kantaros, Yevgeniy Vorobeychik

While ensuring stability for linear systems is well understood, it remains a major challenge for nonlinear systems. A general approach in such cases is to compute a combination of a Lyapunov function and an associated co…

An exact active sensing strategy for a class of bio-inspired systems

2024-11-10 · Debojyoti Biswas, Eduardo D. Sontag, Noah J. Cowan

We consider a general class of translation-invariant systems with a specific category of output nonlinearities motivated by biological sensing. We show that no dynamic output feedback can stabilize this class of systems …

Neural Stochastic Contraction Metrics for Learning-based Control and Estimation

2020-11-06 · Hiroyasu Tsukamoto, Soon-Jo Chung, Jean-Jacques E. Slotine

We present Neural Stochastic Contraction Metrics (NSCM), a new design framework for provably-stable robust control and estimation for a class of stochastic nonlinear systems. It uses a spectrally-normalized deep neural n…

Co-Design of Lipschitz Nonlinear Systems

2022-01-11 · Prasad Vilas Chanekar, Nikhil Chopra

Empirical experiences have shown that simultaneous (rather than conventional sequential) plant and controller design procedure leads to an improvement in performance and saving of plant resources. Such a simultaneous syn…

Synthesizing Stable Reduced-Order Visuomotor Policies for Nonlinear Systems via Sums-of-Squares Optimization

2023-04-24 · Glen Chou, Russ Tedrake

We present a method for synthesizing dynamic, reduced-order output-feedback polynomial control policies for control-affine nonlinear systems which guarantees runtime stability to a goal state, when using visual observati…