• DocumentCode
    3563580
  • Title

    A relationship between ability of perception and learning efficiency

  • Author

    Onoue, Yukiko ; Kurashige, Kentarou

  • Author_Institution
    Muroran Inst. of Technol., Muroran
  • fYear
    2008
  • Firstpage
    1
  • Lastpage
    6
  • 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;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Automation Congress, 2008. WAC 2008. World
  • Print_ISBN
    978-1-889335-38-4
  • Electronic_ISBN
    978-1-889335-37-7
  • Type

    conf

  • Filename
    4698981