Title :
Neural learning of stable dynamical systems based on data-driven Lyapunov candidates
Author :
Neumann, K. ; Lemme, Andre ; Steil, Jochen Jakob
Author_Institution :
Res. Inst. for Cognition & Robot. (CoR-Lab.), Bielefeld Univ., Bielefeld, Germany
Abstract :
Nonlinear dynamical systems are a promising representation to learn complex robot movements. Besides their undoubted modeling power, it is of major importance that such systems work in a stable manner. We therefore present a neural learning scheme that estimates stable dynamical systems from demonstrations based on a two-stage process: first, a data-driven Lyapunov function candidate is estimated. Second, stability is incorporated by means of a novel method to respect local constraints in the neural learning. We show in two experiments that this method is capable of learning stable dynamics while simultaneously sustaining the accuracy of the estimate and robustly generates complex movements.
Keywords :
Lyapunov methods; humanoid robots; neurocontrollers; nonlinear dynamical systems; stability; complex robot movements; data-driven Lyapunov function candidate; dynamical system stability; humanoid robots; neural learning scheme; nonlinear dynamical systems; Asymptotic stability; Lyapunov methods; Nonlinear dynamical systems; Stability analysis; Training data; Trajectory; Vectors;
Conference_Titel :
Intelligent Robots and Systems (IROS), 2013 IEEE/RSJ International Conference on
Conference_Location :
Tokyo
DOI :
10.1109/IROS.2013.6696505