A Spiking Neural Network with Dynamic Memory for a Real Autonomous Mobile Robot in Dynamic Environment

被引:10
作者
Alnajjar, Fady [1 ,2 ]
Zin, Indra Bin Mohd [1 ,2 ]
Murase, Kazuyuki [2 ]
机构
[1] Univ Fukui, Grad Sch Engn, 3-9-1 Bunkyo, Fukui 9108507, Japan
[2] Univ Fukui, Grad Sch Engn, Res & Educ Program Life Sci, Fukui 9108507, Japan
来源
2008 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-8 | 2008年
关键词
D O I
10.1109/IJCNN.2008.4634103
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This work concerns practical issues surrounding the application of learning and memory in a real mobile robot towards optimal navigation in dynamic environments. A novel control system that contains two-level units (low-level and high-level) is developed and trained in a physical mobile robot "e-Puck". In the low-level unit, the robot's task is to navigate in a various local environments, by training N numbers of Spiking Neural Networks (SNN) that have the property of spike time-dependent plasticity. All the trained SNNs are stored in a tree-type memory structure, which is located in the high-level unit These stored networks are used as experiences for the robot to enhance its navigation ability in new and previously trained environments. The memory is designed to hold memories of various lengths and has a simple searching mechanism. For controlling the memory size, forgetting and On-line dynamic clustering techniques are used. Experimental results have proved that the proposed model can provide a robot with learning and memorizing capabilities enable it to survive in complex and dynamic environments.
引用
收藏
页码:2207 / +
页数:2
相关论文
共 22 条
[1]  
ALNAJJAR F, 2007, ADAPTIVE BEHAV UNPUB
[2]  
ALNAJJAR F, 2006, P 3 INT C SOFT COMP, P207
[3]  
ALNAJJAR F, 2008, P INT JOINT IN PRESS
[4]   Self-organization of spiking neural network that generates autonomous behavior in a real mobile robot [J].
Alnajjar, Fady ;
Murase, Kazuyuki .
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2006, 16 (04) :229-239
[5]  
Branke J., 2002, EVOLUTIONARY OPTIMIZ
[6]  
Connell J.H., 1993, ROBOT LEARNING
[7]   A solution to the simultaneous localization and map building (SLAM) problem [J].
Dissanayake, MWMG ;
Newman, P ;
Clark, S ;
Durrant-Whyte, HF ;
Csorba, M .
IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION, 2001, 17 (03) :229-241
[8]   From wheels to wings with evolutionary spiking circuits [J].
Floreano, D ;
Zufferey, JC ;
Nicoud, JD .
ARTIFICIAL LIFE, 2005, 11 (1-2) :121-138
[9]  
KIRA Z, 2004, P IEEE RSJ INT C INT, V4, P3145
[10]  
Leake DB, 1999, LECT NOTES ARTIF INT, V1650, P218