A Combination of Machine Learning and Cerebellar Models for the Motor Control and Learning of a Modular Robot

DOI
  • Ojeda Ismael Baira
    Center for Playware, Department of Electrical Engineering, Technical University of Denmark
  • Tolu Silvia
    Center for Playware, Department of Electrical Engineering, Technical University of Denmark
  • Pacheco Moisés
    Center for Playware, Department of Electrical Engineering, Technical University of Denmark
  • Christensen David Johan
    Center for Playware, Department of Electrical Engineering, Technical University of Denmark
  • Lund Henrik Hautop
    Center for Playware, Department of Electrical Engineering, Technical University of Denmark

説明

We scaled up a bio-inspired control architecture for the motor control and motor learning of a real modular robot. In our approach, the Locally Weighted Projection Regression algorithm (LWPR) and a cerebellar microcircuit coexist, forming a Unit Learning Machine. The LWPR optimizes the input space and learns the internal model of a single robot module to command the robot to follow a desired trajectory with its end-effector. The cerebellar microcircuit refines the LWPR output delivering corrective commands. We contrasted distinct cerebellar circuits including analytical models and spiking models implemented on the SpiNNaker platform, showing promising performance and robustness results.

収録刊行物

キーワード

詳細情報 詳細情報について

  • CRID
    1390845713073704320
  • DOI
    10.5954/icarob.2017.is-3
  • ISSN
    21887829
  • 本文言語コード
    en
  • データソース種別
    • JaLC
    • Crossref
  • 抄録ライセンスフラグ
    使用不可

問題の指摘

ページトップへ