Robot control and the evolution of modular neurodynamics

被引:0
|
作者
Frank Pasemann
Uli Steinmetz
Martin Hülse
Bruno Lara
机构
[1] Universität Jena,TheorieLabor
[2] Max-Planck-Institute for Mathematics in the Sciences,undefined
来源
Theory in Biosciences | 2001年 / 120卷
关键词
Recurrent neutral networks; neurocontrollers; evolutionary algorithms; autonomous robots;
D O I
暂无
中图分类号
学科分类号
摘要
A modular approach to neural behavior control of autonomous robots is presented. It is based on the assumption that complex internal dynamics of recurrent neural networks can efficiently solve complex behavior tasks. For the development of appropriate neural control structures an evolutionary algorithm is introduced, which is able to generate neuromodules with specific functional properties, as well as the connectivity structure for a modular synthesis of such modules. This so called ENS3-algorithm does not use genetic coding. It is primarily designed to develop size and connectivity structure of neuro-controllers. But at the same time it optimizes also parameters of individual networks like synaptic weights and bias terms. For demonstration, evolved networks for the control of miniature Khepera robots are presented. The aim is to develop robust controllers in the sense that neuro-controllers evolved in a simulator show comparably good behavior when loaded to a real robot acting in a physical environment. Discussed examples of such controllers generate obstacle avoidance and phototropic behaviors in non-trivial environments.
引用
收藏
页码:311 / 326
页数:15
相关论文
共 50 条
  • [21] Control system of a modular and reconfigurable multilegged robot
    Chen, Xuedong
    Pu, Huayan
    Wang, Xinjie
    Sun, Yi
    Jia, Wenchuan
    2007 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION, VOLS I-V, CONFERENCE PROCEEDINGS, 2007, : 1926 - +
  • [22] MODULAR CONTROL SYSTEM ARCHITECTURE FOR A MOBILE ROBOT
    Hrbacek, J.
    Hrbacek, R.
    Vechet, S.
    ENGINEERING MECHANICS 2011, 2011, : 211 - 214
  • [23] GeRoNa: Generic Robot Navigation: A Modular Framework for Robot Navigation and Control
    Huskic, Goran
    Buck, Sebastian
    Zell, Andreas
    JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, 2019, 95 (02) : 419 - 442
  • [24] GeRoNa: Generic Robot NavigationA Modular Framework for Robot Navigation and Control
    Goran Huskić
    Sebastian Buck
    Andreas Zell
    Journal of Intelligent & Robotic Systems, 2019, 95 : 419 - 442
  • [25] Modular Robot Control: Efficient and easy to control without Programming
    不详
    ATP MAGAZINE, 2019, (6-7): : 16 - 16
  • [26] Control and amplification of cortical neurodynamics
    Liljenström, H
    Aronsson, P
    NINTH WORKSHOP ON VIRTUAL INTELLIGENCE/DYNAMIC NEURAL NETWORKS: ACADEMIC/INDUSTRIAL/NASA/DEFENSE TECHNICAL INTERCHANGE AND TUTORIALS, 1999, 3728 : 46 - 66
  • [27] Robust Stabilization of a Wheeled Mobile Robot Using Model Predictive Control Based on Neurodynamics Optimization
    Xiao, Hanzhen
    Li, Zhijun
    Yang, Chenguang
    Zhang, Lixian
    Yuan, Peijiang
    Ding, Liang
    Wang, Tianmiao
    IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2017, 64 (01) : 505 - 516
  • [28] Cortical Neurodynamics of Inhibitory Control
    Hwang, Kai
    Ghuman, Avniel S.
    Manoach, Dara S.
    Jones, Stephanie R.
    Luna, Beatriz
    JOURNAL OF NEUROSCIENCE, 2014, 34 (29): : 9551 - 9561
  • [29] Modeling and Control of a Cable Driven Modular Snake Robot
    Racioppo, Peter
    Ben-Tzvi, Pinhas
    2017 IEEE CONFERENCE ON CONTROL TECHNOLOGY AND APPLICATIONS (CCTA 2017), 2017, : 468 - 473
  • [30] Design of a Modular Snake Robot and Control of with Internet of Things
    Zhu, Wei
    Guo, Xian
    Fang, Yongchun
    2017 CHINESE AUTOMATION CONGRESS (CAC), 2017, : 850 - 854