activity
20162022
most citedEnforcing robust control guarantees within neural network policies

12 citations · 19 across the 9 of their papers we have counts for

collaborators

16 papers

eess.SY2022

One-Shot Reachability Analysis of Neural Network Dynamical Systems

Shaoru Chen, Victor M. Preciado, Mahyar Fazlyab

The arising application of neural networks (NN) in robotic systems has driven the development of safety verification methods for neural network dynamical systems (NNDS). Recursive…

eess.SY2021

Learning Region of Attraction for Nonlinear Systems

Shaoru Chen, Mahyar Fazlyab, Manfred Morari +2

Estimating the region of attraction (ROA) of general nonlinear autonomous systems remains a challenging problem and requires a case-by-case analysis. Leveraging the universal appro…

cs.LG2021

Performance Bounds for Neural Network Estimators: Applications in Fault Detection

Navid Hashemi, Mahyar Fazlyab, Justin Ruths

We exploit recent results in quantifying the robustness of neural networks to input variations to construct and tune a model-based anomaly detector, where the data-driven estimator…

math.OC2020

Learning Lyapunov Functions for Hybrid Systems

Shaoru Chen, Mahyar Fazlyab, Manfred Morari +2

We propose a sampling-based approach to learn Lyapunov functions for a class of discrete-time autonomous hybrid systems that admit a mixed-integer representation. Such systems incl…

cs.LG2020

Certifying Incremental Quadratic Constraints for Neural Networks via Convex Optimization

Navid Hashemi, Justin Ruths, Mahyar Fazlyab

Abstracting neural networks with constraints they impose on their inputs and outputs can be very useful in the analysis of neural network classifiers and to derive optimization-bas…

eess.SY2020

Stability Analysis of Complementarity Systems with Neural Network Controllers

Alp Aydinoglu, Mahyar Fazlyab, Manfred Morari +1

Complementarity problems, a class of mathematical optimization problems with orthogonality constraints, are widely used in many robotics tasks, such as locomotion and manipulation,…