Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Sidrane, Chelsea"'
Autor:
Kiessling, Alexander, Torroba, Ignacio, Sidrane, Chelsea Rose, Stenius, Ivan, Tumova, Jana, Folkesson, John
Informative path planning (IPP) applied to bathymetric mapping allows AUVs to focus on feature-rich areas to quickly reduce uncertainty and increase mapping efficiency. Existing methods based on Bayesian optimization (BO) over Gaussian Process (GP) m
Externí odkaz:
http://arxiv.org/abs/2410.15720
Autor:
Sidrane, Chelsea, Tumova, Jana
Reachable set computation is an important tool for analyzing control systems. Simulating a control system can show that the system is generally functioning as desired, but a formal tool like reachability analysis can provide a guarantee of correctnes
Externí odkaz:
http://arxiv.org/abs/2407.14394
Backward Reachability Analysis of Neural Feedback Loops: Techniques for Linear and Nonlinear Systems
Autor:
Rober, Nicholas, Katz, Sydney M., Sidrane, Chelsea, Yel, Esen, Everett, Michael, Kochenderfer, Mykel J., How, Jonathan P.
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. This paper presents a set of backward reachability approaches for
Externí odkaz:
http://arxiv.org/abs/2209.14076
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. When the forward model that produced the observations is nonlinear and s
Externí odkaz:
http://arxiv.org/abs/2202.02429
OVERT: An Algorithm for Safety Verification of Neural Network Control Policies for Nonlinear Systems
Publikováno v:
Journal of Machine Learning Research 23 (2022) 1-45
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 this challenge, we present OVERT: a sound algorithm for safety verifi
Externí odkaz:
http://arxiv.org/abs/2108.01220
Autor:
Sidrane, Chelsea, Fitzpatrick, Dylan J, Annex, Andrew, O'Donoghue, Diane, Gal, Yarin, Biliński, Piotr
Flooding is a destructive and dangerous hazard and climate change appears to be increasing the frequency of catastrophic flooding events around the world. Physics-based flood models are costly to calibrate and are rarely generalizable across differen
Externí odkaz:
http://arxiv.org/abs/1910.06521
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 attempt to address these limitations is the DAgger algorithm, which uses th
Externí odkaz:
http://arxiv.org/abs/1810.02890
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.