Q-Learning based on dynamical structure neural network for robot navigation in unknown environment - Details

Author：

Qiao, Junfei (Qiao, Junfei.) (Scholars：乔俊飞) | Fan, Ruiyuan (Fan, Ruiyuan.) | Han, Honggui (Han, Honggui.) (Scholars：韩红桂) | Ruan, Xiaogang (Ruan, Xiaogang.)

Indexed by：

EI Scopus

Abstract：

An　automation　learning　and　navigation　strategy　based　on　dynamical　structure　neural　network　and　reinforcement　learning　was　proposed　in　this　paper.　The　neural　network　can　adjust　its　structure　according　to　the　complexity　of　the　working　environment.　New　nodes　or　even　new　hidden-layers　can　be　inserted　or　deleted　during　the　training　process.　In　such　a　way,　the　mapping　relations　between　environment　states　and　responding　action　were　established,　and　the　dimension　explosion　problem　was　solved　at　the　same　time.　Simulation　and　Pioneer3-DX　mobile　robot　navigation　experiments　were　done　to　test　the　proposed　algorithm.　Results　show　that　the　robot　can　learn　the　correct　action　and　finish　the　navigation　task　without　people＇s　guidance,　and　the　performance　was　better　than　artificial　potential　field　method.　©　2009　Springer　Berlin　Heidelberg.

Keyword：

Mobile robots Navigation Reinforcement learning Neural networks

Author Community：

[ 1 ] [Qiao, Junfei]Institute of Intelligence System, College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100000, China
[ 2 ] [Fan, Ruiyuan]Institute of Intelligence System, College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100000, China
[ 3 ] [Han, Honggui]Institute of Intelligence System, College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100000, China
[ 4 ] [Ruan, Xiaogang]Institute of Intelligence System, College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100000, China