caa a22 4500 445294825 CHVBK 20180317142538.0 cr unu---uuuuu 170323e20100301xx s 000 0 eng 10.1007/s11571-009-9101-5 doi (NATIONALLICENCE)springer-10.1007/s11571-009-9101-5 Chaotic neural network applied to two-dimensional motion control [Elektronische Daten] [Hiroyuki Yoshida, Shuhei Kurata, Yongtao Li, Shigetoshi Nara] Chaotic dynamics generated in a chaotic neural network model are applied to 2-dimensional (2-D) motion control. The change of position of a moving object in each control time step is determined by a motion function which is calculated from the firing activity of the chaotic neural network. Prototype attractors which correspond to simple motions of the object toward four directions in 2-D space are embedded in the neural network model by designing synaptic connection strengths. Chaotic dynamics introduced by changing system parameters sample intermediate points in the high-dimensional state space between the embedded attractors, resulting in motion in various directions. By means of adaptive switching of the system parameters between a chaotic regime and an attractor regime, the object is able to reach a target in a 2-D maze. In computer experiments, the success rate of this method over many trials not only shows better performance than that of stochastic random pattern generators but also shows that chaotic dynamics can be useful for realizing robust, adaptive and complex control function with simple rules. Springer Science+Business Media B.V., 2009 Constrained chaos nationallicence Chaotic neural network nationallicence Motion control nationallicence 2-Dimensional maze nationallicence Ill-posed problem nationallicence Yoshida Hiroyuki Department of Electrical & Electronic Engineering, Faculty of Engineering, Okayama University, 700-8530, Okayama, Japan aut Kurata Shuhei Department of Electrical & Electronic Engineering, Faculty of Engineering, Okayama University, 700-8530, Okayama, Japan aut Li Yongtao Graduate School of Natural Science and Technology, Okayama University, 3-1-1 Tsushima-naka, 700-8530, Okayama, Japan aut Nara Shigetoshi Department of Electrical & Electronic Engineering, Faculty of Engineering, Okayama University, 700-8530, Okayama, Japan aut Cognitive Neurodynamics Springer Netherlands 4/1(2010-03-01), 69-80 1871-4080 4:1<69 2010 4 11571 https://doi.org/10.1007/s11571-009-9101-5 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s11571-009-9101-5 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Yoshida Hiroyuki Department of Electrical & Electronic Engineering, Faculty of Engineering, Okayama University, 700-8530, Okayama, Japan aut NATIONALLICENCE 700 1- Kurata Shuhei Department of Electrical & Electronic Engineering, Faculty of Engineering, Okayama University, 700-8530, Okayama, Japan aut NATIONALLICENCE 700 1- Li Yongtao Graduate School of Natural Science and Technology, Okayama University, 3-1-1 Tsushima-naka, 700-8530, Okayama, Japan aut NATIONALLICENCE 700 1- Nara Shigetoshi Department of Electrical & Electronic Engineering, Faculty of Engineering, Okayama University, 700-8530, Okayama, Japan aut NATIONALLICENCE 773 0- Cognitive Neurodynamics Springer Netherlands 4/1(2010-03-01), 69-80 1871-4080 4:1<69 2010 4 11571 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer