Neural Computation Scheme of Compound Control : Tacit Learning for Bipedal Locomotion

Access this Article

Search this Article

Author(s)

Abstract

The growing need for controlling complex behaviors of versatile robots working in unpredictable environment has revealed the fundamental limitation of model-based control strategy that requires precise models of robots and environments before their operations. This difficulty is fundamental and has the same root with the well-known frame problem in artificial intelligence. It has been a central long standing issue in advanced robotics, as well as machine intelligence, to find a prospective clue to attack this fundamental difficulty. The general consensus shared by many leading researchers in the related field is that the body plays an important role in acquiring intelligence that can conquer unknowns. In particular, purposeful behaviors emerge during body-environment interactions with the help of an appropriately organized neural computational scheme that can exploit what the environment can afford. Along this line, we propose a new scheme of neural computation based on compound control which represents a typical feature of biological controls. This scheme is based on classical neuron models with local rules that can create macroscopic purposeful behaviors. This scheme is applied to a bipedal robot and generates the rhythm of walking without any model of robot dynamics and environments.

Journal

  • SICE Journal of Control, Measurement, and System Integration

    SICE Journal of Control, Measurement, and System Integration 1(4), 275-283, 2008-07-31

    The Society of Instrument and Control Engineers

References:  25

Cited by:  1

Codes

  • NII Article ID (NAID)
    10024291997
  • NII NACSIS-CAT ID (NCID)
    AA12293218
  • Text Lang
    ENG
  • Article Type
    Journal Article
  • ISSN
    18824889
  • Data Source
    CJP  CJPref  J-STAGE 
Page Top