63 citations · 122 across the 63 of their papers we have counts for
5 papers · 1 filter
Safe Reinforcement Learning using Data-Driven Predictive Control
Mahmoud Selim, Amr Alanwar, M. Watheq El-Kharashi +2
Reinforcement learning (RL) algorithms can achieve state-of-the-art performance in decision-making and continuous control tasks. However, applying RL algorithms on safety-critical…
Resilient Set-based State Estimation for Linear Time-Invariant Systems Using Zonotopes
Muhammad Umar B. Niazi, Amr Alanwar, Michelle S. Chong +1
This paper considers the problem of set-based state estimation for linear time-invariant (LTI) systems under time-varying sensor attacks. Provided that the LTI system is stable and…
Robust Data-Driven Predictive Control of Unknown Nonlinear Systems using Reachability Analysis
Mahsa Farjadnia, Amr Alanwar, Muhammad Umar B. Niazi +2
This work proposes a robust data-driven predictive control approach for unknown nonlinear systems in the presence of bounded process and measurement noise. Data-driven reachable se…
Logical Zonotopes: A Set Representation for the Formal Verification of Boolean Functions
Amr Alanwar, Frank J. Jiang, Samy Amin +1
A logical zonotope, which is a new set representation for binary vectors, is introduced in this paper. A logical zonotope is constructed by XOR-ing a binary vector with a combinati…
Safe Reinforcement Learning Using Black-Box Reachability Analysis
Mahmoud Selim, Amr Alanwar, Shreyas Kousik +3
Reinforcement learning (RL) is capable of sophisticated motion planning and control for robots in uncertain environments. However, state-of-the-art deep RL approaches typically lac…