no code implementations • 18 Mar 2024 • Hussein Sibai, Sacha Huriot, Tyler Martin, Murat Arcak
We propose an efficient symbolic control synthesis algorithm for equivariant continuous-time dynamical systems to satisfy reach-avoid specifications.
no code implementations • 13 Nov 2023 • Hussein Sibai, Enrique Mallada
In this paper, we introduce the notion of recurrence entropy in the context of nonlinear control systems.
no code implementations • 27 Feb 2023 • Piergiuseppe Mallozzi, Hussein Sibai, Inigo Incer, Sanjit A. Seshia, Alberto Sangiovanni-Vincentelli
It can be thought of as a building block for any design exploration and optimization algorithm.
no code implementations • 28 Dec 2022 • Junlin Wu, Hussein Sibai, Yevgeniy Vorobeychik
Our experiments demonstrate both the efficacy of the proposed approach for certifying safety in adversarial environments, and the value of the PSRL framework coupled with adversarial training in improving certified safety while preserving high nominal reward and high-quality predictions of true state.
no code implementations • 21 Nov 2020 • Hussein Sibai, Yangge Li, Sayan Mitra
We presentSceneChecker, a tool for verifying scenarios involving vehicles executing complex plans in large cluttered workspaces.
no code implementations • 20 Nov 2020 • Hussein Sibai, Sayan Mitra
We investigate the relation between {$\epsilon$}-estimation entropy and a previous notion for switched nonlinear systems and derive a new upper bound for the latter, showing the generality of our results on systems with uncertain inputs.
no code implementations • 1 Apr 2020 • Yu Wang, Hussein Sibai, Mark Yen, Sayan Mitra, Geir E. Dullerud
We also show that the standard exponential mechanism that randomizes the output of an algorithm to achieve differential privacy fails to do so in the context of sequential algorithms.
no code implementations • 12 Oct 2019 • Peter Du, Zhe Huang, Tianqi Liu, Ke Xu, Qichao Gao, Hussein Sibai, Katherine Driggs-Campbell, Sayan Mitra
As autonomous systems begin to operate amongst humans, methods for safe interaction must be investigated.
Robotics Multiagent Systems Signal Processing
no code implementations • ICLR 2019 • Hussein Sibai, Sayan Mitra
We consider an environment with multiple reward functions.
no code implementations • 7 Dec 2017 • Jiajun Lu, Hussein Sibai, Evan Fabry
An adversarial example is an example that has been adjusted to produce a wrong label when presented to a system at test time.
no code implementations • 9 Oct 2017 • Jiajun Lu, Hussein Sibai, Evan Fabry, David Forsyth
Finally, an adversarial pattern on a physical object that could fool a detector would have to be adversarial in the face of a wide family of parametric distortions (scale; view angle; box shift inside the detector; illumination; and so on).
no code implementations • 12 Jul 2017 • Jiajun Lu, Hussein Sibai, Evan Fabry, David Forsyth
Instead, a trained neural network classifies most of the pictures taken from different distances and angles of a perturbed image correctly.