Q-Learning Based on Dynamical Structure Neural Network for Robot Navigation in Unknown Environment.
Junfei QiaoRuiyuan FanHonggui HanXiaogang RuanPublished in: ISNN (3) (2009)
Keyphrases
- robot navigation
- autonomous mobile robot
- initially unknown
- topological map
- autonomous robots
- neural network
- map building
- robot localization
- mobile robot
- real time
- reinforcement learning
- scene understanding
- landmark recognition
- artificial neural networks
- multi agent
- indoor environments
- continuous state
- feature selection
- function approximation
- pairwise
- video sequences
- three dimensional
- learning algorithm