Secure-by-construction synthesis of cyber-physical systems

S Liu, A Trivedi, X Yin, M Zamani - Annual Reviews in Control, 2022 - Elsevier
Correct-by-construction synthesis is a cornerstone of the confluence of formal methods and
control theory towards designing safety-critical systems. Instead of following the time-tested …

Safe control with learned certificates: A survey of neural lyapunov, barrier, and contraction methods for robotics and control

C Dawson, S Gao, C Fan - IEEE Transactions on Robotics, 2023 - ieeexplore.ieee.org
Learning-enabled control systems have demonstrated impressive empirical performance on
challenging control problems in robotics, but this performance comes at the cost of reduced …

Learning safe control for multi-robot systems: Methods, verification, and open challenges

K Garg, S Zhang, O So, C Dawson, C Fan - Annual Reviews in Control, 2024 - Elsevier
In this survey, we review the recent advances in control design methods for robotic multi-
agent systems (MAS), focusing on learning-based methods with safety considerations. We …

Safe control with learned certificates: A survey of neural lyapunov, barrier, and contraction methods

C Dawson, S Gao, C Fan - arXiv preprint arXiv:2202.11762, 2022 - arxiv.org
Learning-enabled control systems have demonstrated impressive empirical performance on
challenging control problems in robotics, but this performance comes at the cost of reduced …

How to train your neural control barrier function: Learning safety filters for complex input-constrained systems

O So, Z Serlin, M Mann, J Gonzales… - … on Robotics and …, 2024 - ieeexplore.ieee.org
Control barrier functions (CBFs) have become popular as a safety filter to guarantee the
safety of nonlinear dynamical systems for arbitrary inputs. However, it is difficult to construct …

FOSSIL: a software tool for the formal synthesis of lyapunov functions and barrier certificates using neural networks

A Abate, D Ahmed, A Edwards, M Giacobbe… - Proceedings of the 24th …, 2021 - dl.acm.org
This paper accompanies FOSSIL: a software tool for the synthesis of Lyapunov functions
and of barrier certificates (or functions) for dynamical systems modelled as differential …

Learning safe, generalizable perception-based hybrid control with certificates

C Dawson, B Lowenkamp, D Goff… - IEEE Robotics and …, 2022 - ieeexplore.ieee.org
Many robotic tasks require high-dimensional sensors such as cameras and Lidar to navigate
complex environments, but developing certifiably safe feedback controllers around these …

Learning safe neural network controllers with barrier certificates

H Zhao, X Zeng, T Chen, Z Liu, J Woodcock - Formal Aspects of Computing, 2021 - Springer
We provide a new approach to synthesize controllers for nonlinear continuous dynamical
systems with control against safety properties. The controllers are based on neural networks …

Unifying qualitative and quantitative safety verification of DNN-controlled systems

D Zhi, P Wang, S Liu, CHL Ong, M Zhang - International Conference on …, 2024 - Springer
The rapid advance of deep reinforcement learning techniques enables the oversight of
safety-critical systems through the utilization of Deep Neural Networks (DNNs). This …

Formally Verifying Deep Reinforcement Learning Controllers with Lyapunov Barrier Certificates

U Mandal, G Amir, H Wu, I Daukantas… - arXiv preprint arXiv …, 2024 - arxiv.org
Deep reinforcement learning (DRL) is a powerful machine learning paradigm for generating
agents that control autonomous systems. However, the" black box" nature of DRL agents …