Search Results for author: Sydney M. Katz

Found 8 papers, 4 papers with code

Efficient Determination of Safety Requirements for Perception Systems

no code implementations3 Jul 2023 Sydney M. Katz, Anthony L. Corso, Esen Yel, Mykel J. Kochenderfer

Perception systems operate as a subcomponent of the general autonomy stack, and perception system designers often need to optimize performance characteristics while maintaining safety with respect to the overall closed-loop system.

Gaussian Processes

AVOIDDS: Aircraft Vision-based Intruder Detection Dataset and Simulator

1 code implementation19 Jun 2023 Elysia Q. Smyers, Sydney M. Katz, Anthony L. Corso, Mykel J. Kochenderfer

We also provide an interface that evaluates trained models on slices of this dataset to identify changes in performance with respect to changing environmental conditions.

object-detection Object Detection

Backward Reachability Analysis of Neural Feedback Loops: Techniques for Linear and Nonlinear Systems

no code implementations28 Sep 2022 Nicholas Rober, Sydney M. Katz, Chelsea Sidrane, Esen Yel, Michael Everett, Mykel J. Kochenderfer, Jonathan P. How

As neural networks (NNs) become more prevalent in safety-critical applications such as control of vehicles, there is a growing need to certify that systems with NN components are safe.

Risk-Driven Design of Perception Systems

1 code implementation21 May 2022 Anthony L. Corso, Sydney M. Katz, Craig Innes, Xin Du, Subramanian Ramamoorthy, Mykel J. Kochenderfer

We formulate a risk function to quantify the effect of a given perceptual error on overall safety, and show how we can use it to design safer perception systems by including a risk-dependent term in the loss function and generating training data in risk-sensitive regions.

ZoPE: A Fast Optimizer for ReLU Networks with Low-Dimensional Inputs

no code implementations9 Jun 2021 Christopher A. Strong, Sydney M. Katz, Anthony L. Corso, Mykel J. Kochenderfer

We demonstrate how to formulate and solve three types of optimization problems: (i) minimization of any convex function over the output space, (ii) minimization of a convex function over the output of two networks in series with an adversarial perturbation in the layer between them, and (iii) maximization of the difference in output between two networks.

Verification of Image-based Neural Network Controllers Using Generative Models

no code implementations14 May 2021 Sydney M. Katz, Anthony L. Corso, Christopher A. Strong, Mykel J. Kochenderfer

For this reason, recent work has focused on combining techniques in formal methods and reachability analysis to obtain guarantees on the closed-loop performance of neural network controllers.

Generating Probabilistic Safety Guarantees for Neural Network Controllers

1 code implementation1 Mar 2021 Sydney M. Katz, Kyle D. Julian, Christopher A. Strong, Mykel J. Kochenderfer

In this work, we develop a method to use the results from neural network verification tools to provide probabilistic safety guarantees on a neural network controller.

Learning an Urban Air Mobility Encounter Model from Expert Preferences

1 code implementation12 Jul 2019 Sydney M. Katz, Anne-Claire Le Bihan, Mykel J. Kochenderfer

Airspace models have played an important role in the development and evaluation of aircraft collision avoidance systems for both manned and unmanned aircraft.

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