Behavioral control through evolutionary neurocontrollers for autonomous mobile robot navigation

被引:20
作者
Fernandez-Leon, Jose A. [1 ,4 ]
Acosta, Gerardo G. [2 ,4 ]
Mayosky, Miguel A. [3 ,5 ]
机构
[1] Univ Sussex, Ctr Computat Neurosci & Robot, Brighton, E Sussex, England
[2] UNCPBA, Fac Engn, Grp INTELYMEC, Buenos Aires, DF, Argentina
[3] UNLP, Fac Engn, LEICI Lab, Buenos Aires, DF, Argentina
[4] Consejo Nacl Invest Cient & Tecn, Natl Council Sci & Technol Res, RA-1033 Buenos Aires, DF, Argentina
[5] Comis Invest Cient Gob Prov Buenos Aires, Buenos Aires, DF, Argentina
关键词
Evolutionary robotics; Adaptive systems; Behavior emergence; ARCHITECTURE;
D O I
10.1016/j.robot.2008.06.012
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper deals with the study of scaling up behaviors in evolutive robotics (ER). Complex behaviors were obtained from simple ones. Each behavior is Supported by an artificial neural network (ANN)-based controller or neurocontroller. Hence, a method for the generation of a hierarchy of neurocontrollers, resorting to the paradigm of Layered Evolution (LE), is developed and verified experimentally through computer simulations and tests in a Khepera (R) micro-robot. Several behavioral modules are initially evolved using specialized neurocontrollers based oil different ANN paradigms. The results show that simple behaviors coordination through LE is a feasible strategy that gives rise to emergent complex behaviors. These complex behaviors can then solve real-world problems efficiently. From a pure evolutionary perspective, however, the methodology presented is too much dependent on user's prior knowledge about the problem to solve and also that evolution take place in a rigid, prescribed framework. Mobile robot's navigation in an unknown environment is used as a test bed for the proposed scaling strategies. (c) 2008 Elsevier B.V. All rights reserved.
引用
收藏
页码:411 / 419
页数:9
相关论文
共 38 条
[1]   Synaptic computation [J].
Abbott, LF ;
Regehr, WG .
NATURE, 2004, 431 (7010) :796-803
[2]  
Acosta GG, 2005, OCEANS 2005 - EUROPE, VOLS 1 AND 2, P389
[3]  
[Anonymous], 1896, Am. Nat, DOI DOI 10.1086/276408
[4]  
Arkin R.C., 1998, Behavior-Based Robotics
[5]  
Beer R. D., 1996, From Animals to Animats 4. Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior, P421
[6]   INTELLIGENCE WITHOUT REPRESENTATION [J].
BROOKS, RA .
ARTIFICIAL INTELLIGENCE, 1991, 47 (1-3) :139-159
[7]   A ROBUST LAYERED CONTROL-SYSTEM FOR A MOBILE ROBOT [J].
BROOKS, RA .
IEEE JOURNAL OF ROBOTICS AND AUTOMATION, 1986, 2 (01) :14-23
[8]  
BROOKS RA, 1992, FROM ANIM ANIMAT, P3
[9]   Duplication of modules facilitates the evolution of functional specialization [J].
Calabretta, R ;
Nolfi, S ;
Parisi, D ;
Wagner, GP .
ARTIFICIAL LIFE, 2000, 6 (01) :69-84
[10]  
CALABRETTA R, 1999, P 5 INT C SIM AD BEH, P497