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 …
Applying neural networks as controllers in dynamical systems has shown great promises. However, it is critical yet challenging to verify the safety of such control systems with neural …
We present an approach to construct reachable set overapproximations for continuous-time dynamical systems controlled using neural network feedback systems. Feedforward deep …
We present POLAR (The source code can be found at https://github. com/ChaoHuang2018/ POLAR_Tool. The full version of this paper can be found at https://arxiv …
L Zhang, X Chen, F Kong… - 2020 IEEE Real-Time …, 2020 - ieeexplore.ieee.org
Attack detection and recovery are fundamental elements for the operation of safe and resilient cyber-physical systems. Most of the literature focuses on attack-detection, while …
W Xiang, TT Johnson - arXiv preprint arXiv:1805.09944, 2018 - arxiv.org
Autonomous cyber-physical systems (CPS) rely on the correct operation of numerous components, with state-of-the-art methods relying on machine learning (ML) and artificial …
Neural networks (NNs) playing the role of controllers have demonstrated impressive empirical performance on challenging control problems. However, the potential adoption of …
Approximating the set of reachable states of a dynamical system is an algorithmic yet mathematically rigorous way to reason about its safety. Although progress has been made in …
Y Chou, H Yoon… - 2020 IEEE/RSJ …, 2020 - ieeexplore.ieee.org
We present a predictive runtime monitoring technique for estimating future vehicle positions and the probability of collisions with obstacles. Vehicle dynamics model how the position …