paper-with-me

홈 › Papers

Learning Safe Neural Network Controllers with Barrier Certificates

2020-09-18 · Hengjun Zhao, Xia Zeng, Taolue Chen, Zhiming Liu, Jim Woodcock

We provide a novel approach to synthesize controllers for nonlinear continuous dynamical systems with control against safety properties. The controllers are based on neural networks (NNs). To certify the safety property we utilize barrier functions, which are represented by NNs as well. We train the controller-NN and barrier-NN simultaneously, achieving a verification-in-the-loop synthesis. We provide a prototype tool nncontroller with a number of case studies. The experiment results confirm the feasibility and efficacy of our approach.

📄 PDF Abstract BibTeX arXiv:2009.09826

Code (1)

zhaohj2017/FAoC-tool 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Compositional Controller Synthesis for Interconnected Stochastic Systems with Markovian Switching

2022-08-06 · Abolfazl Lavaei, Emilio Frazzoli

In this work, we propose a compositional scheme for the safety controller synthesis of interconnected discrete-time stochastic systems with Markovian switching signals. Our proposed approach is based on a notion of so-ca…

Compositional Design of Safety Controllers for Large-scale Stochastic Hybrid Systems

2024-09-16 · Mahdieh Zaker, Omid Akbarzadeh, Behrad Samari, Abolfazl Lavaei

In this work, we propose a compositional scheme based on small-gain reasoning for the safety controller synthesis of interconnected stochastic hybrid systems with both continuous evolutions and instantaneous jumps. In ou…

From Small-Gain Theory to Compositional Construction of Barrier Certificates for Large-Scale Stochastic Systems

2021-01-18 · Mahathi Anand, Abolfazl Lavaei, Majid Zamani

This paper is concerned with a compositional approach for the construction of control barrier certificates for large-scale interconnected stochastic systems while synthesizing hybrid controllers against high-level logic …

Formal Synthesis of Certifiably Robust Neural Lyapunov-Barrier Certificates

2026-02-05 · Chengxiao Wang, Haoze Wu, Gagandeep Singh arxiv

Neural Lyapunov and barrier certificates have recently been used as powerful tools for verifying the safety and stability properties of deep reinforcement learning (RL) controllers. However, existing methods offer guaran…

Reinforcement Learning

Safety Barrier Certificates for Stochastic Control Systems with Wireless Communication Networks

2023-09-11 · Omid Akbarzadeh, Sadegh Soudjani, Abolfazl Lavaei

This work is concerned with a formal approach for safety controller synthesis of stochastic control systems with both process and measurement noises while considering wireless communication networks between sensors, cont…