中文
相关论文

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

200 篇论文

Providing safety guarantees for learning-based controllers is important for real-world applications. One approach to realizing safety for arbitrary control policies is safety filtering. If necessary, the filter modifies control inputs to…

系统与控制 · 电气工程与系统科学 2023-12-18 Lukas Brunke , Siqi Zhou , Mingxuan Che , Angela P. Schoellig

Neural networks are increasingly applied to support decision making in safety-critical applications (like autonomous cars, unmanned aerial vehicles and face recognition based authentication). While many impressive static verification…

机器学习 · 计算机科学 2021-05-07 Guoliang Dong , Jun Sun , Jingyi Wang , Xinyu Wang , Ting Dai

Artificial Neural Networks (ANNs) have demonstrated remarkable utility in various challenging machine learning applications. While formally verified properties of their behaviors are highly desired, they have proven notoriously difficult to…

机器学习 · 计算机科学 2020-10-05 Xuankang Lin , He Zhu , Roopsha Samanta , Suresh Jagannathan

This paper presents a novel approach for the safe control design of systems with parametric uncertainties in both drift terms and control-input matrices. The method combines control barrier functions and adaptive laws to generate a safe…

系统与控制 · 电气工程与系统科学 2024-04-16 Yujie Wang , Xiangru Xu

Verifying the input-output relationships of a neural network so as to achieve some desired performance specification is a difficult, yet important, problem due to the growing ubiquity of neural nets in many engineering applications. We use…

机器学习 · 计算机科学 2022-12-06 Joshua Pilipovsky , Vignesh Sivaramakrishnan , Meeko M. K. Oishi , Panagiotis Tsiotras

Modern data-driven control applications call for flexible nonlinear models that are amenable to principled controller synthesis and realtime feedback. Many nonlinear dynamical systems of interest are control affine. We propose two novel…

机器学习 · 计算机科学 2024-06-12 Kimia Kazemian , Yahya Sattar , Sarah Dean

We consider the problem of designing a machine learning-based model of an unknown dynamical system from a finite number of (state-input)-successor state data points, such that the model obtained is also suitable for optimal control design.…

系统与控制 · 电气工程与系统科学 2024-10-10 Filippo Fabiani , Bartolomeo Stellato , Daniele Masti , Paul J. Goulart

This paper presents conditions for ensuring forward invariance of safe sets under sampled-data system dynamics with piecewise-constant controllers and fixed time-steps. First, we introduce two different metrics to compare the…

最优化与控制 · 数学 2021-06-28 Joseph Breeden , Kunal Garg , Dimitra Panagou

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 for linear time-invariant plant dynamics with NN…

系统与控制 · 电气工程与系统科学 2021-04-08 He Yin , Peter Seiler , Ming Jin , Murat Arcak

This work presents a control-oriented identification scheme for efficient control design and stability analysis of nonlinear systems. Neural networks are used to identify a discrete-time nonlinear state-space model to approximate…

系统与控制 · 电气工程与系统科学 2024-10-04 Maxime Thieffry , Alexandre Hache , Mohamed Yagoubi , Philippe Chevrel

This paper studies the design of neural network (NN)-based controllers for unknown nonlinear systems, using contraction analysis. A Neural Ordinary Differential Equation (NODE) system is constructed by approximating the unknown draft…

系统与控制 · 电气工程与系统科学 2025-05-23 Hao Yin , Claudio De Persis , Bayu Jayawardhana , Santiago Sanchez Escalonilla Plaza

This paper presents a method that learns a regionally stable recurrent neural network model from a set of input-output data generated by an unknown dynamical system. Relying on generalized sector conditions on the deadzone activation…

系统与控制 · 电气工程与系统科学 2026-05-19 Daniel Frank , Fahim Shakib , Steffen Staab

In this paper, we provide a direct data-driven approach to synthesize safety controllers for unknown linear systems affected by unknown-but-bounded disturbances, in which identifying the unknown model is not required. First, we propose a…

系统与控制 · 电气工程与系统科学 2023-01-16 Bingzhuo Zhong , Majid Zamani , Marco Caccamo

Verification of neural networks relies on activation functions being piecewise affine (pwa) -- enabling an encoding of the verification problem for theorem provers. In this paper, we present the first formalization of pwa activation…

机器学习 · 计算机科学 2023-01-31 Andrei Aleksandrov , Kim Völlinger

In this paper, we propose a data-driven approach to derive explicit predictive control laws, without requiring any intermediate identification step. The keystone of the presented strategy is the exploitation of available priors on the…

系统与控制 · 电气工程与系统科学 2022-07-05 Valentina Breschi , Andrea Sassella , Simone Formentin

Neural networks (NNs) are increasingly applied in safety-critical systems such as autonomous vehicles. However, they are fragile and are often ill-behaved. Consequently, their behaviors should undergo rigorous guarantees before deployment…

机器学习 · 计算机科学 2023-06-28 Zhen Liang , Dejin Ren , Bai Xue , Ji Wang , Wenjing Yang , Wanwei Liu

Real-world control applications in complex and uncertain environments require adaptability to handle model uncertainties and robustness against disturbances. This paper presents an online, output-feedback, critic-only, model-based…

系统与控制 · 电气工程与系统科学 2023-04-25 Tochukwu Elijah Ogri , Zachary I. Bell , Rushikesh Kamalapurkar

Autonomous motion planning under unknown nonlinear dynamics requires learning system properties while navigating toward a target. In this work, we develop a hierarchical planning-control framework that enables online motion synthesis with…

机器人学 · 计算机科学 2026-04-02 Zhiquan Zhang , Melkior Ornik

Learning reliably safe autonomous control is one of the core problems in trustworthy autonomy. However, training a controller that can be formally verified to be safe remains a major challenge. We introduce a novel approach for learning…

机器学习 · 计算机科学 2024-11-19 Junlin Wu , Huan Zhang , Yevgeniy Vorobeychik

In this manuscript, we investigate symbolic abstractions that capture the behavior of piecewise-affine systems under input constraints and bounded external noise. This is accomplished by considering local affine feedback controllers that…

最优化与控制 · 数学 2022-11-23 Lucas N. Egidio , Thiago Alves Lima , Raphaël M. Jungers