no code implementations • 10 Mar 2022 • Guangyi Liu, Arash Amini, Martin Takac, Nader Motee
For a given stable recurrent neural network (RNN) that is trained to perform a classification task using sequential inputs, we quantify explicit robustness bounds as a function of trainable weight matrices.
no code implementations • 29 Dec 2021 • Guangyi Liu, Christoforos Somarakis, Nader Motee
We develop a framework to assess the risk of cascading collisions in a platoon of vehicles in the presence of exogenous noise and communication time-delay.
no code implementations • 29 Dec 2021 • Christoforos Somarakis, Guangyi Liu, Nader Motee
We develop a framework to quantify systemic risk measures in a class of Wide-Area-Control (WAC) laws in power networks in the presence of noisy and time-delayed sensory data.
no code implementations • 5 Sep 2021 • Guangyi Liu, Christoforos Somarakis, Nader Motee
We develop a systemic risk framework to explore cascading systemic failures in networked control systems.
no code implementations • 3 May 2021 • Arash Amini, Guangyi Liu, Nader Motee
However, artificial neural networks are known to exhibit poor robustness in presence of input noise, where the sequential architecture of RNNs exacerbates the problem.
no code implementations • 18 Dec 2020 • Guangyi Liu, Arash Amini, Martin Takáč, Héctor Muñoz-Avila, Nader Motee
We consider the problem of classifying a map using a team of communicating robots.
no code implementations • 20 Sep 2019 • Hossein K. Mousavi, Guangyi Liu, Weihang Yuan, Martin Takáč, Héctor Muñoz-Avila, Nader Motee
We propose a planning and perception mechanism for a robot (agent), that can only observe the underlying environment partially, in order to solve an image classification problem.
1 code implementation • 13 May 2019 • Hossein K. Mousavi, MohammadReza Nazari, Martin Takáč, Nader Motee
We investigate a classification problem using multiple mobile agents capable of collecting (partial) pose-dependent observations of an unknown environment.