Spontaneous Evolution of Structural Modularity in Robot Neural Network Controllers

被引：0
|
作者：
Bongard, Josh C. [1 ]
机构：
[1] Univ Vermont, Dept Comp Sci, Burlington, VT 05405 USA
来源：
GECCO-2011: PROCEEDINGS OF THE 13TH ANNUAL GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE | 2011年
关键词：
Evolutionary Robotics; Modularity; Evolutionary Algorithms; BEHAVIOR;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In order to evolve large robot controllers for increasingly complex tasks, fully connected neural networks are not feasible. However, manually designing sparse neural connectivity is not intuitive, and thus should be placed under evolutionary control. Here I show how spontaneous structural modularity can arise in the connectivity of evolved robot controllers if the controllers are boolean networks, and are selected to converge on point attractors that correspond to successful robot behaviors.
引用
收藏
页码：251 / 258
页数：8
相关论文
共 50 条
  • [21] Network Modularity as a Foundation for Neural Reuse
    Stanley, Matthew L.
    Gessell, Bryce
    De Brigard, Felipe
    PHILOSOPHY OF SCIENCE, 2019, 86 (01) : 23 - 46
  • [22] Modularity in network neuroscience and neural reuse
    Stanley, Matthew L.
    De Brigard, Felipe
    BEHAVIORAL AND BRAIN SCIENCES, 2016, 39 : e133
  • [23] The Case for Engineering the Evolution of Robot Controllers
    Silva, Fernando
    Duarte, Miguel
    Oliveira, Sancho Moura
    Correia, Luis
    Christensen, Anders Lyhne
    ALIFE 2014: THE FOURTEENTH INTERNATIONAL CONFERENCE ON THE SYNTHESIS AND SIMULATION OF LIVING SYSTEMS, 2014, : 703 - 710
  • [24] Modularity and Centrality in Metabolic Network Evolution
    Jolley, Craig C.
    Mazurie, Aurelien
    Young, Mark
    Douglas, Trevor
    BIOPHYSICAL JOURNAL, 2010, 98 (03) : 740A - 740A
  • [25] Fuzzy and neural network controllers
    Dote, Yasuhiko
    Proceedings of the Workshop on Neural Networks: Academic/Industrial/NASA/Defense, 1991,
  • [26] Universal neural network controllers
    Chak, CK
    Feng, G
    Jian, MA
    Palaniswami, M
    1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, 1997, : 815 - 820
  • [27] SVR Versus Neural-Fuzzy Network Controllers for the Sagittal Balance of a Biped Robot
    Ferreira, Joao P.
    Crisostomo, Manuel M.
    Coimbra, A. Paulo
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2009, 20 (12): : 1885 - 1897
  • [28] Neural network-based sliding mode controllers applied to robot manipulators: A review
    Truong, Thanh Nguyen
    Vo, Anh Tuan
    Kang, Hee-Jun
    NEUROCOMPUTING, 2023, 562
  • [29] Three hybrid control schemes consisting of neural network and adaptive controllers for robot manipulators
    Tomiyama, K
    Furuta, T
    Noguchi, T
    1998 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS - PROCEEDINGS, VOLS 1-3: INNOVATIONS IN THEORY, PRACTICE AND APPLICATIONS, 1998, : 1987 - 1992
  • [30] Emerging Modularity During the Evolution of Neural Networks
    Praczyk, Tomasz
    JOURNAL OF ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING RESEARCH, 2023, 13 (02) : 107 - 126
12345