Title :
Generation of behavior automaton on neural network
Author :
Ogata, Tetsuya ; Hayashi, Kazuki ; Kitagishi, Ikuo ; Sugano, Shigeki
Author_Institution :
Dept. of Mech. Eng., Waseda Univ., Tokyo, Japan
Abstract :
To plan behavior procedures, it is necessary for an agent to have a world model concerning the temporal sequences information. In this paper, a temporal information learning algorithm is proposed with a three layer neural network implementing the “effectiveness of simulation accumulation” algorithm. This algorithm can construct a “behavior automaton” in the neural network. From the results of some learning experiments using a mobile robot simulation, the generated automaton expresses the complexity of the simulation environments. The robot agent acquires a behavior automaton for obstacle avoidance behavior which is influenced by the simulation environment
Keywords :
intelligent control; learning (artificial intelligence); mobile robots; multilayer perceptrons; path planning; behavior automaton; behavior procedures; effectiveness of simulation accumulation algorithm; learning experiments; mobile robot simulation; obstacle avoidance behavior; temporal information learning algorithm; temporal sequences; three layer neural network; world model; Artificial intelligence; Batteries; Data mining; Genetic programming; Learning automata; Low voltage; Mobile robots; Neural networks; Robot sensing systems; Robotics and automation;
Conference_Titel :
Intelligent Robots and Systems, 1997. IROS '97., Proceedings of the 1997 IEEE/RSJ International Conference on
Conference_Location :
Grenoble
Print_ISBN :
0-7803-4119-8
DOI :
10.1109/IROS.1997.655074
