DocumentCode :
2493842
Title :
Robot planning by cooperation of Hopfield networks - A case of Warehouse Keeper Puzzle (sokoban) -
Author :
Miyazaki, Kairi ; Matsuda, Satoshi
Author_Institution :
Grad. Sch. of Ind. Technol., Nihon Univ., Narashino, Japan
fYear :
2010
fDate :
18-23 July 2010
Firstpage :
1
Lastpage :
6
Abstract :
Based on the hypothesis that all intellectual activities of human beings are performed as optimization processes, we design Hopfield networks that can coordinately achieve robot planning. Planning is a typical intellectual activity of a logical task, which is considered difficult for neural networks to do. For an example of robot planning, we take the Warehouse Keeper Puzzle, called sokoban, the goal of which is for the robot to carry a block to a goal only by pushing it and by avoiding many obstacles.
Keywords :
Hopfield neural nets; collision avoidance; game theory; mobile robots; neurocontrollers; optimisation; Hopfield network; Warehouse Keeper Puzzle; human being; intellectual activity; logical task; neural network; obstacle avoidance; optimization process; robot planning; sokoban; Artificial neural networks; Robots;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks (IJCNN), The 2010 International Joint Conference on
Conference_Location :
Barcelona
ISSN :
1098-7576
Print_ISBN :
978-1-4244-6916-1
Type :
conf
DOI :
10.1109/IJCNN.2010.5596723
Filename :
5596723
Link To Document :
بازگشت