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
  • [41] Modularity in the evolution of yeast protein interaction network
    Ogishima, Soichi
    Tanaka, Hiroshi
    Nakaya, Jun
    BIOINFORMATION, 2015, 11 (03) : 127 - 130
  • [42] Utilizing Function Approximation Technique and Neural Network Controllers on a 2-DOF Painter Robot
    Hadian, Mohammad Hosein
    Salehian, Melika
    Sharifi, Iman
    Menhaj, Mohammad Bagher
    2022 10TH RSI INTERNATIONAL CONFERENCE ON ROBOTICS AND MECHATRONICS (ICROM), 2022, : 202 - 208
  • [43] Comparison of Neural Network Based Adaptive Controllers Using Hypercomplex Numbers for Controlling Robot Manipulator
    Takahashi, Kazuhiko
    IFAC PAPERSONLINE, 2019, 52 (29): : 67 - 72
  • [44] Neural network controllers for magnetostrictive actuator
    Rubio, JCC
    Santoro, FG
    Gee, AE
    Duduch, JG
    Porto, AJV
    PROCEEDINGS OF THE THIRTEENTH ANNUAL MEETING OF THE AMERICAN SOCIETY FOR PRECISION ENGINEERING, 1998, : 264 - 269
  • [45] Composite multimodel and neural network controllers
    Dieulot, J. -Y.
    Borne, P.
    Mrizak, W.
    2006 IMACS: MULTICONFERENCE ON COMPUTATIONAL ENGINEERING IN SYSTEMS APPLICATIONS, VOLS 1 AND 2, 2006, : 509 - +
  • [46] On certainty equivalence neural network controllers
    Chen, LJ
    Mehra, RK
    PROCEEDINGS OF THE 2003 AMERICAN CONTROL CONFERENCE, VOLS 1-6, 2003, : 4243 - 4248
  • [47] Stable and robust neural network controllers
    Sterud, Camilla
    Moe, Signe
    Gravdahl, Jan Tommy
    2021 EUROPEAN CONTROL CONFERENCE (ECC), 2021, : 1452 - 1458
  • [48] Neural Network Controllers in Chemical Technologies
    Kis, Karol
    Klauco, Martin
    Meszaros, Alajos
    2020 IEEE 15TH INTERNATIONAL CONFERENCE OF SYSTEM OF SYSTEMS ENGINEERING (SOSE 2020), 2020, : 397 - 401
  • [49] Task-dependent evolution of modularity in neural networks
    Hüsken, M
    Igel, C
    Toussaint, M
    CONNECTION SCIENCE, 2002, 14 (03) : 219 - 229
  • [50] Evolutionary robot controllers with competitive and cooperative neural networks
    Masayoshi Tabuse
    Tetsuro Kitazoe
    Tatsuro Shinchi
    Akinobu Todaka
    Artificial Life and Robotics, 2002, 6 (1-2) : 52 - 58
12345