Episodic Koopman Learning of Nonlinear Robot Dynamics with Application to Fast Multirotor Landing
Carl Folkestad,Daniel Pastor,Joel W. Burdick,Carl Folkestad,Daniel Pastor,Joel W. Burdick
This paper presents a novel episodic method to learn a robot's nonlinear dynamics model and an increasingly optimal control sequence for a set of tasks. The method is based on the Koopman operator approach to nonlinear dynamical systems analysis, which models the flow of observables in a function space, rather than a flow in a state space. Practically, this method estimates a nonlinear diffeomorph...
