Y Wang, MP Chapman - Artificial Intelligence, 2022 - Elsevier
We present an historical overview about the connections between the analysis of risk and the control of autonomous systems. We offer two main contributions. Our first contribution is …
Reachability analysis is a fundamental problem in verification that checks for a given model and set of initial states if the system will reach a given set of unsafe states. Its importance lies …
Abstract Convolutional Neural Networks (CNN) have redefined state-of-the-art in many real- world applications, such as facial recognition, image classification, human pose estimation …
H Yin, P Seiler, M Arcak - IEEE Transactions on Automatic …, 2021 - ieeexplore.ieee.org
A method is presented to analyze the stability of feedback systems with neural network controllers. Two stability theorems are given to prove asymptotic stability and to compute an …
It is quite challenging to ensure the safety of reinforcement learning (RL) agents in an unknown and stochastic environment under hard constraints that require the system state …
There has been an increasing interest in using neural networks in closed-loop control systems to improve performance and reduce computational costs for on-line implementation …
Abstract This paper presents Verisig 2.0, a verification tool for closed-loop systems with neural network (NN) controllers. We focus on NNs with tanh/sigmoid activations and develop …
Deep learning methods can be used to produce control policies, but certifying their safety is challenging. The resulting networks are nonlinear and often very large. In response to this …
This article addresses the problem of verifying the safety of autonomous systems with neural network (NN) controllers. We focus on NNs with sigmoid/tanh activations and use the fact …