Results 1 to 10 of about 758 (209)
Koopman Operator–Based Knowledge-Guided Reinforcement Learning for Safe Human–Robot Interaction [PDF]
Frontiers in Robotics and AI, 2022 We developed a novel framework for deep reinforcement learning (DRL) algorithms in task constrained path generation problems of robotic manipulators leveraging human demonstrated trajectories.
Anirban Sinha, Yue Wang
doaj +2 more sources
Vehicular Applications of Koopman Operator Theory—A Survey
IEEE Access, 2023 Koopman operator theory has proven to be a promising approach to nonlinear system identification and global linearization. For nearly a century, there had been no efficient means of calculating the Koopman operator for applied engineering purposes.
Waqas A. Manzoor +2 more
doaj +3 more sources
Closed-loop Koopman operator approximation
Machine Learning: Science and TechnologyThis paper proposes a method to identify a Koopman model of a feedback-controlled system given a known controller. The Koopman operator allows a nonlinear system to be rewritten as an infinite-dimensional linear system by viewing it in terms of an ...
Steven Dahdah, James Richard Forbes
doaj +3 more sources
Temporally consistent Koopman autoencoders for forecasting dynamical systems [PDF]
Scientific ReportsAbsence of sufficiently high-quality data often poses a key challenge in data-driven modeling of high-dimensional spatio-temporal dynamical systems.
Indranil Nayak +4 more
doaj +2 more sources
Koopman operator for Burgers's equation [PDF]
Physical Review Fluids, 2021 The Koopman decomposition of the Burgers' flow is explicitly derived, the frequencies and the coefficients of this decomposition are identified as eigenvalues and eigenfunctionals of the Koopman operator, and the convergence of the Koopman decomposition is proven for $tg0$ for small Cauchy data, and up to $t=0$ for regular Cauchy data.
Mikhael Balabane +2 more
openaire +3 more sources
On the Koopman Operator of Algorithms [PDF]
SIAM Journal on Applied Dynamical Systems, 2020 27 pages, 11 ...
Felix Dietrich +2 more
openaire +3 more sources
Model-Free Geometric Fault Detection and Isolation for Nonlinear Systems Using Koopman Operator
IEEE Access, 2022 This paper presents a model-free fault detection and isolation (FDI) method for nonlinear dynamical systems using Koopman operator theory and linear geometric technique.
Mohammadhosein Bakhtiaridoust +3 more
doaj +1 more source
Koopman Operators and the $3x+1$-Dynamical System [PDF]
SIAM Journal on Applied Dynamical Systems, 2021 The $3x+1$-problem (or Collatz problem) is a notorious conjecture in arithmetic. It can be viewed as iterating a map and, therefore, it is a dynamical system on the discrete space $\mathbb{N}$ of natural numbers. The emerging dynamical system is studied in the present work with methods from the theory of Koopman operators and $C^*$-algebras.
John Leventides, Costas Poulios
openaire +3 more sources
Measurement + Control, 2022 Omnidirectional mobile manipulators (OMMs) have been widely used due to their high mobility and operating flexibility. However, since OMMs are complex nonlinear systems with uncertainties, the dynamic modeling and control are always challenging problems.
Xuehong Zhu +3 more
doaj +1 more source
Symplectic Geometry of the Koopman Operator [PDF]
Doklady Mathematics, 2021 Abstract We consider the Koopman operator generated by an invertible transformation of a space with a finite countably additive measure. If the square of this transformation is ergodic, then the orthogonal Koopman operator is a symplectic transformation on the real Hilbert space of square summable functions with zero ...
openaire +1 more source