Search Results for author: Joseph A. Vincent

Found 2 papers, 2 papers with code

Reachable Polyhedral Marching (RPM): An Exact Analysis Tool for Deep-Learned Control Systems

1 code implementation15 Oct 2022 Joseph A. Vincent, Mac Schwager

We then develop algorithms using this tool to compute invariant sets and regions of attraction (ROAs) for control systems with neural networks in the feedback loop.

Reachable Polyhedral Marching (RPM): A Safety Verification Algorithm for Robotic Systems with Deep Neural Network Components

1 code implementation23 Nov 2020 Joseph A. Vincent, Mac Schwager

We present a method for computing exact reachable sets for deep neural networks with rectified linear unit (ReLU) activation.

Cannot find the paper you are looking for? You can Submit a new open access paper.