中文
相关论文

相关论文: Safety verification of Neural-Network-based contro…

200 篇论文

This paper presents an approach to deal with safety of dynamical systems in presence of multiple non-convex unsafe sets. While optimal control and model predictive control strategies can be employed in these scenarios, they suffer from high…

系统与控制 · 电气工程与系统科学 2021-06-14 Gennaro Notomista , Matteo Saveriano

Even though neural networks are being increasingly deployed in safety-critical control applications, it remains difficult to enforce constraints on their output, meaning that it is hard to guarantee safety in such settings. While many…

机器学习 · 计算机科学 2025-08-27 Long Kiu Chung , Shreyas Kousik

Online model predictive control (MPC) for piecewise affine (PWA) systems requires the online solution to an optimization problem that implicitly optimizes over the switching sequence of PWA regions, for which the computational burden can be…

系统与控制 · 电气工程与系统科学 2025-03-27 Samuel Mallick , Azita Dabiri , Bart De Schutter

Neural networks have recently become popular for a wide variety of uses, but have seen limited application in safety-critical domains such as robotics near and around humans. This is because it remains an open challenge to train a neural…

机器学习 · 计算机科学 2021-07-19 Long Kiu Chung , Adam Dai , Derek Knowles , Shreyas Kousik , Grace X. Gao

Infinite-horizon optimal control of constrained piecewise affine (PWA) systems has been approximately addressed by hybrid model predictive control (MPC), which, however, has computational limitations, both in offline design and online…

系统与控制 · 电气工程与系统科学 2024-12-16 Kanghui He , Shengling Shi , Ton van den Boom , Bart De Schutter

A novel control method is proposed to ensure compatibility of safe, stabilizing control laws, i.e., simultaneous satisfaction of asymptotic stability and constraint satisfaction for nonlinear affine systems. The results are dependent on an…

系统与控制 · 电气工程与系统科学 2022-04-22 Wenceslao Shaw Cortez , Dimos V. Dimarogonas

Neural network controllers have become popular in control tasks thanks to their flexibility and expressivity. Stability is a crucial property for safety-critical dynamical systems, while stabilization of partially observed systems, in many…

系统与控制 · 电气工程与系统科学 2021-12-08 Fangda Gu , He Yin , Laurent El Ghaoui , Murat Arcak , Peter Seiler , Ming Jin

This work presents several improvements to the closed-loop stability verification framework using semialgebraic sets and convex semidefinite programming to examine neural-network-based control systems regulating nonlinear dynamical systems.…

系统与控制 · 电气工程与系统科学 2025-07-15 Alvaro Detailleur , Guillaume Ducard , Christopher Onder

In this paper, a novel online, output-feedback, critic-only, model-based reinforcement learning framework is developed for safety-critical control systems operating in complex environments. The developed framework ensures system stability…

系统与控制 · 电气工程与系统科学 2024-06-28 Tochukwu Elijah Ogri , Muzaffar Qureshi , Zachary I. Bell , Rushikesh Kamalapurkar

The action governor is an add-on scheme to a nominal control loop that monitors and adjusts the control actions to enforce safety specifications expressed as pointwise-in-time state and control constraints. In this paper, we introduce the…

系统与控制 · 电气工程与系统科学 2022-07-19 Yutong Li , Nan Li , H. Eric Tseng , Anouck Girard , Dimitar Filev , Ilya Kolmanovsky

This paper focuses on finding reinforcement learning policies for control systems with hard state and action constraints. Despite its success in many domains, reinforcement learning is challenging to apply to problems with hard constraints,…

机器学习 · 计算机科学 2020-03-24 Liyuan Zheng , Yuanyuan Shi , Lillian J. Ratliff , Baosen Zhang

Neural network controllers are currently being proposed for use in many safety-critical tasks. Most analysis methods for neural network control systems assume a fixed control period. In control theory, higher frequency usually improves…

系统与控制 · 电气工程与系统科学 2024-07-29 Ali ArjomandBigdeli , Andrew Mata , Stanley Bak

Modern nonlinear control theory seeks to endow systems with properties such as stability and safety, and has been deployed successfully across various domains. Despite this success, model uncertainty remains a significant challenge in…

系统与控制 · 电气工程与系统科学 2021-04-02 Andrew J. Taylor , Victor D. Dorobantu , Sarah Dean , Benjamin Recht , Yisong Yue , Aaron D. Ames

Control Barrier Functions (CBFs) provide a powerful framework for ensuring safety in dynamical systems. However, their application typically relies on full state information, which is often violated in real-world due to the availability of…

系统与控制 · 电气工程与系统科学 2026-05-19 Vaishnavi Jagabathula , Ahan Basu , Pushpak Jagtap

Despite the empirical success of DNN, their internal training dynamics remain difficult to characterize. In ReLU-based models, the activation pattern induced by a given input determines the piecewise-linear region in which the network…

Neural certificates have emerged as a powerful tool in cyber-physical systems control, providing witnesses of correctness. These certificates, such as barrier functions, often learned alongside control policies, once verified, serve as…

符号计算 · 计算机科学 2025-07-17 Thomas A. Henzinger , Konstantin Kueffner , Emily Yu

In this paper, a systematic framework is presented for determining piecewise affine PWA barrier functions and their corresponding invariant sets for dynamical systems identified via Rectified Linear Unit (ReLU) neural networks or their…

系统与控制 · 电气工程与系统科学 2025-04-22 Pouya Samanipour , Hasan Poonawala

In this work, we address the problem of formal safety verification for stochastic cyber-physical systems (CPS) equipped with ReLU neural network (NN) controllers. Our goal is to find the set of initial states from where, with a…

系统与控制 · 电气工程与系统科学 2021-03-10 Shiqi Sun , Yan Zhang , Xusheng Luo , Panagiotis Vlantis , Miroslav Pajic , Michael M. Zavlanos

Neural Networks (NNs) have been successfully employed to represent the state evolution of complex dynamical systems. Such models, referred to as NN dynamic models (NNDMs), use iterative noisy predictions of NN to estimate a distribution of…

系统与控制 · 电气工程与系统科学 2025-05-27 Rayan Mazouz , Karan Muvvala , Akash Ratheesh , Luca Laurenti , Morteza Lahijanian

The transfer of reinforcement learning (RL) techniques into real-world applications is challenged by safety requirements in the presence of physical limitations. Most RL methods, in particular the most popular algorithms, do not support…

系统与控制 · 计算机科学 2021-05-18 Kim P. Wabersich , Melanie N. Zeilinger