Reachable polyhedral marching (rpm): A safety verification algorithm for robotic systems with deep neural network components

JA Vincent, M Schwager - 2021 IEEE International Conference …, 2021 - ieeexplore.ieee.org
We present a method for computing exact reachable sets for deep neural networks with
rectified linear unit (ReLU) activation. Our method is well-suited for use in rigorous safety …
被引用次数：52 相关文章

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

JA Vincent, M Schwager - arXiv e-prints, 2020 - ui.adsabs.harvard.edu
We present a method for computing exact reachable sets for deep neural networks with
rectified linear unit (ReLU) activation. Our method is well-suited for use in rigorous safety …
[PDF] stanford.edu

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

JA Vincent, M Schwager - msl.stanford.edu
We present a method for computing exact reachable sets for deep neural networks with
rectified linear unit (ReLU) activation. Our method is well-suited for use in rigorous safety …

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

JA Vincent, M Schwager - 2021 IEEE International Conference on …, 2021 - dl.acm.org
We present a method for computing exact reachable sets for deep neural networks with
rectified linear unit (ReLU) activation. Our method is well-suited for use in rigorous safety …
[PDF] nsf.gov

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

JA Vincent, M Schwager - 2021 IEEE International Conference on …, 2021 - par.nsf.gov
We present a method for computing exact reachable sets for deep neural networks with
rectified linear unit (ReLU) activation. Our method is well-suited for use in rigorous safety …

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

JA Vincent, M Schwager - arXiv preprint arXiv:2011.11609, 2020 - arxiv.org
We present a method for computing exact reachable sets for deep neural networks with
rectified linear unit (ReLU) activation. Our method is well-suited for use in rigorous safety …
[PDF] stanford.edu

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

JA Vincent, M Schwager - msl.stanford.edu
We present a method for computing exact reachable sets for deep neural networks with
rectified linear unit (ReLU) activation. Our method is well-suited for use in rigorous safety …