Title :
A relationship between ability of perception and learning efficiency
Author :
Onoue, Yukiko ; Kurashige, Kentarou
Author_Institution :
Muroran Inst. of Technol., Muroran
Abstract :
ldquoRobot learningrdquo is researched well in recent years. In each research, various types of robot are used. Here, robotpsilas sensor is selected and is set by each researcher. If each robot has different sensor, it perceives different environment. This fact causes that whether a given task can be achieved or not depends on kinds of robotpsilas sensor, even if in same environment. In this paper, we investigate a relationship between number of kinds of robotpsilas sensors and robotpsilas learning efficiency. We experiment to investigate it on computer simulation. And we discuss a relationship between ability of perception and learning efficiency.
Keywords :
control engineering computing; learning (artificial intelligence); robots; sensors; learning efficiency; perception efficiency; robot learning; robot sensor; Computer simulation; Frequency; Learning systems; Robot sensing systems; Sampling methods; Sense organs; Learning-efficiency; Reinforcement Learning; Robot’s Perception; Soft-computing;
Conference_Titel :
Automation Congress, 2008. WAC 2008. World
Print_ISBN :
978-1-889335-38-4
Electronic_ISBN :
978-1-889335-37-7
