Generalization of the tacit learning controller based on periodic tuning functions

Vincent Berenz, Mitsuhiro Hayashibe, Fady Alnajjar, Shingo Shimoda

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Living organisms are characterized by their smooth adaptability to environmental changes and their robustness against morphological modifications. To investigate the computational mechanisms behind such learning scheme, we proposed tacit learning as a novel learning method. In tacit learning, there are no clear distinctions between learning and motor control: learning is a simple accumulation process embedded in the controller. In previous work, tacit learning was applied with success to bipedal locomotion of a 36 DoF humanoid robot. In this paper, we generalize the structure of the controller such as applying adaptive integration to a wider range of systems and behaviors. This is achieved by applying the principle of tacit learning in a hierarchical fashion, in which the value of a virtual periodic dynamic variable is tuned for continuous adaptation. This resulting PD-PI (proportional-derivative periodic-integration) controller preserves the advantages of tacit learning that the controllers do not include any prior knowledge of the system in which they are embedded. It also shares with biological systems the property that control and adaptation progress without explicit distinction between them.

Original languageEnglish
Title of host publication"2014 5th IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2014
EditorsRaffaella Carloni, Lorenzo Masia, Jose Maria Sabater-Navarro, Marko Ackermann, Sunil Agrawal, Arash Ajoudani, Panagiotis Artemiadis, Matteo Bianchi, Antonio Padilha Lanari Bo, Maura Casadio, Kevin Cleary, Ashish Deshpande, Domenico Formica, Matteo Fumagalli, Nicolas Garcia-Aracil, Sasha Blue Godfrey, Islam S.M. Khalil, Olivier Lambercy, Rui C. V. Loureiro, Leonardo Mattos, Victor Munoz, Hyung-Soon Park, Luis Eduardo Rodriguez Cheu, Roque Saltaren, Adriano A. G. Siqueira, Valentina Squeri, Arno H.A. Stienen, Nikolaos Tsagarakis, Herman Van der Kooij, Bram Vanderborght, Nicola Vitiello, Jose Zariffa, Loredana Zollo
PublisherIEEE Computer Society
Pages893-898
Number of pages6
ISBN (Electronic)9781479931262
DOIs
Publication statusPublished - 2014 Sep 30
Externally publishedYes
Event5th IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2014 - Sao Paulo, Brazil
Duration: 2014 Aug 122014 Aug 15

Publication series

NameProceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics
ISSN (Print)2155-1774

Other

Other5th IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2014
CountryBrazil
CitySao Paulo
Period14/8/1214/8/15

ASJC Scopus subject areas

  • Artificial Intelligence
  • Biomedical Engineering
  • Mechanical Engineering

Fingerprint Dive into the research topics of 'Generalization of the tacit learning controller based on periodic tuning functions'. Together they form a unique fingerprint.

Cite this