9 citations · 15 across the 17 of their papers we have counts for
18 papers
The FABRIC Strategy for Verifying Neural Feedback Systems
Samuel I. Akinwande, Sydney M. Katz, Mykel J. Kochenderfer +1
Forward reachability analysis is a dominant approach for verifying reach-avoid specifications in neural feedback systems, i.e., dynamical systems controlled by neural networks, and…
A New Strategy for Verifying Reach-Avoid Specifications in Neural Feedback Systems
Samuel I. Akinwande, Sydney M. Katz, Mykel J. Kochenderfer +1
Forward reachability analysis is the predominant approach for verifying reach-avoid properties in neural feedback systems (dynamical systems controlled by neural networks). This do…
Aircraft Collision Avoidance Systems: Technological Challenges and Solutions on the Path to Regulatory Acceptance
Sydney M. Katz, Robert J. Moss, Dylan M. Asmar +3
Aircraft collision avoidance systems is critical to modern aviation. These systems are designed to predict potential collisions between aircraft and recommend appropriate avoidance…
Predictive Uncertainty for Runtime Assurance of a Real-Time Computer Vision-Based Landing System
Romeo Valentin, Sydney M. Katz, Artur B. Carneiro +2
Recent advances in data-driven computer vision have enabled robust autonomous navigation capabilities for civil aviation, including automated landing and runway detection. However,…
DB-KSVD: Scalable Alternating Optimization for Disentangling High-Dimensional Embedding Spaces
Romeo Valentin, Sydney M. Katz, Vincent Vanhoucke +1
Dictionary learning has recently emerged as a promising approach for mechanistic interpretability of large transformer models. Disentangling high-dimensional transformer embeddings…
Failure Probability Estimation for Black-Box Autonomous Systems using State-Dependent Importance Sampling Proposals
Harrison Delecki, Sydney M. Katz, Mykel J. Kochenderfer
Estimating the probability of failure is a critical step in developing safety-critical autonomous systems. Direct estimation methods such as Monte Carlo sampling are often impracti…
Probabilistic Parameter Estimators and Calibration Metrics for Pose Estimation from Image Features
Romeo Valentin, Sydney M. Katz, Joonghyun Lee +3
This paper addresses the challenge of probabilistic parameter estimation given measurement uncertainty in real-time. We provide a general formulation and apply this to pose estimat…
Efficient Determination of Safety Requirements for Perception Systems
Sydney M. Katz, Anthony L. Corso, Esen Yel +1
Perception systems operate as a subcomponent of the general autonomy stack, and perception system designers often need to optimize performance characteristics while maintaining saf…
AVOIDDS: Aircraft Vision-based Intruder Detection Dataset and Simulator
Elysia Q. Smyers, Sydney M. Katz, Anthony L. Corso +1
Designing robust machine learning systems remains an open problem, and there is a need for benchmark problems that cover both environmental changes and evaluation on a downstream t…
Backward Reachability Analysis of Neural Feedback Loops: Techniques for Linear and Nonlinear Systems
Nicholas Rober, Sydney M. Katz, Chelsea Sidrane +4
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 s…
Risk-Driven Design of Perception Systems
Anthony L. Corso, Sydney M. Katz, Craig Innes +3
Modern autonomous systems rely on perception modules to process complex sensor measurements into state estimates. These estimates are then passed to a controller, which uses them t…
Collision Risk and Operational Impact of Speed Change Advisories as Aircraft Collision Avoidance Maneuvers
Sydney M. Katz, Luis E. Alvarez, Michael Owen +4
Aircraft collision avoidance systems have long been a key factor in keeping our airspace safe. Over the past decade, the FAA has supported the development of a new family of collis…
Verifying Inverse Model Neural Networks
Chelsea Sidrane, Sydney Katz, Anthony Corso +1
Inverse problems exist in a wide variety of physical domains from aerospace engineering to medical imaging. The goal is to infer the underlying state from a set of observations. Wh…
ZoPE: A Fast Optimizer for ReLU Networks with Low-Dimensional Inputs
Christopher A. Strong, Sydney M. Katz, Anthony L. Corso +1
Deep neural networks often lack the safety and robustness guarantees needed to be deployed in safety critical systems. Formal verification techniques can be used to prove input-out…
Verification of Image-based Neural Network Controllers Using Generative Models
Sydney M. Katz, Anthony L. Corso, Christopher A. Strong +1
Neural networks are often used to process information from image-based sensors to produce control actions. While they are effective for this task, the complex nature of neural netw…
Preference-based Learning of Reward Function Features
Sydney M. Katz, Amir Maleki, Erdem Bıyık +1
Preference-based learning of reward functions, where the reward function is learned using comparison data, has been well studied for complex robotic tasks such as autonomous drivin…
Generating Probabilistic Safety Guarantees for Neural Network Controllers
Sydney M. Katz, Kyle D. Julian, Christopher A. Strong +1
Neural networks serve as effective controllers in a variety of complex settings due to their ability to represent expressive policies. The complex nature of neural networks, howeve…
Learning an Urban Air Mobility Encounter Model from Expert Preferences
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. As Urban Air Mobility…