activity
20182026
most citedOVERT: An Algorithm for Safety Verification of Neural Network Control Policies for Nonlinear Systems

5 citations · 6 across the 5 of their papers we have counts for

collaborators

6 papers

cs.RO2026

Marinarium: A Modular Experimental Facility for Reproducible Maritime and Space-Analog Field Robotics

Ignacio Torroba, David Dorner, Victor Nan Fernandez-Ayala +14

Field robotics research in maritime and space domains is constrained by a persistent gap between low-cost, low-fidelity simulation and costly offshore experimentation. Instrumented…

eess.SY2025

Polyhedral Enclosures: An Efficient Combinatorial Abstraction for Nonlinear Neural Feedback Systems

I. Samuel Akinwande, Chelsea Sidrane, Mykel J. Kochenderfer +1

As dynamical systems equipped with neural network controllers (neural feedback systems) become increasingly prevalent, it is critical to develop methods to ensure their safe operat…

eess.SY2022

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…

cs.LG2022★ 1 cited

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…

cs.LG2021★ 5 cited

OVERT: An Algorithm for Safety Verification of Neural Network Control Policies for Nonlinear Systems

Chelsea Sidrane, Amir Maleki, Ahmed Irfan +1

Deep learning methods can be used to produce control policies, but certifying their safety is challenging. The resulting networks are nonlinear and often very large. In response to…

cs.RO2018

HG-DAgger: Interactive Imitation Learning with Human Experts

Michael Kelly, Chelsea Sidrane, Katherine Driggs-Campbell +1

Imitation learning has proven to be useful for many real-world problems, but approaches such as behavioral cloning suffer from data mismatch and compounding error issues. One attem…