DocumentCode :
2963550
Title :
Visual robot homing using Sarsa(λ), whole image measure, and radial basis function
Author :
Altahhan, Abdulrahman ; Burn, Kevin ; Wermter, Stefan
Author_Institution :
Sch. of Comput. & Technol., Univ. of Sunderland, Sunderland
fYear :
2008
fDate :
1-8 June 2008
Firstpage :
3861
Lastpage :
3868
Abstract :
This paper describes a model for visual homing. It uses Sarsa(lambda) as its learning algorithm, combined with the Jeffery divergence measure (JDM) as a way of terminating the task and augmenting the reward signal. The visual features are taken to be the histograms difference of the current view and the stored views of the goal location, taken for all RGB channels. A radial basis function layer acts on those histograms to provide input for the linear function approximator. An on-policy on-line Sarsa(lambda) method was used to train three linear neural networks one for each action to approximate the action-value function with the aid of eligibility traces. The resultant networks are trained to perform visual robot homing, where they achieved good results in finding a goal location. This work demonstrates that visual homing based on reinforcement learning and radial basis function has a high potential for learning local navigation tasks.
Keywords :
control engineering computing; function approximation; learning (artificial intelligence); mobile robots; path planning; radial basis function networks; robot vision; Jeffery divergence measure; RGB channel; learning algorithm; linear function approximator; local navigation task; on-policy online Sarsa; radial basis function; reinforcement learning; visual robot homing; whole image measure; Animals; Biological system modeling; Current measurement; Histograms; Learning; Navigation; Object recognition; Pixel; Robots; Robustness;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on
Conference_Location :
Hong Kong
ISSN :
1098-7576
Print_ISBN :
978-1-4244-1820-6
Electronic_ISBN :
1098-7576
Type :
conf
DOI :
10.1109/IJCNN.2008.4634353
Filename :
4634353
Link To Document :
بازگشت