Skip to Main content Skip to Navigation
Book sections

Tacit learning for emergence of task-related behavior through signal accumulation

Vincent Berenz 1 Fady Alnajjar 1 Mitsuhiro Hayashibe 2 Shingo Shimoda 1
2 DEMAR - Artificial movement and gait restoration
CRISAM - Inria Sophia Antipolis - Méditerranée , LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
Abstract : Control of robotic joints movements requires generation of appropriate torque and force patterns, coordinating the kinematically and dynamically complex multijoints systems. Control theory coupled with inverse and forward internal models are commonly used to map a desired endpoint trajectory into suitable force patterns. In this paper, we propose the use of tacit learning to successfully achieve similar tasks without using any kinematic model of the robotic system to be controlled. Our objective is to design a new control strategy that can achieve levels of adaptability similar to those observed in living organism and be plausible from a neural control view point. If the neural mechanisms used for mapping goal expressed in the task-space into control-space related commands without using internal models remain largely unknown, many neural systems rely on data accumulation. The presented controller does not use any internal model and incorporates knowledge expressed in the task space using only accumulation of data. Tested on a simulated two links robot system, the controller showed flexibility by developing and updating its parameters through learning. This controller reduces the gap between reflexive motion based on simple accumulation of data and execution of voluntary planned actions in a simple manner that does not require complex analysis of the dynamics of the system.
Document type :
Book sections
Complete list of metadata

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00853694
Contributor : Mitsuhiro Hayashibe <>
Submitted on : Friday, August 23, 2013 - 11:39:54 AM
Last modification on : Tuesday, December 15, 2020 - 7:32:02 PM

Identifiers

Collections

Citation

Vincent Berenz, Fady Alnajjar, Mitsuhiro Hayashibe, Shingo Shimoda. Tacit learning for emergence of task-related behavior through signal accumulation. Emergent Trends in Robotics and Intelligent Systems. Where is the Role of Intelligent Technologies in the Next Generation of Robots?, Advances in Intelligent Systems and Computing (316), Springer, pp.31-38, 2015, Emergent Trends in Robotics and Intelligent Systems, 978-3-319-10782-0. ⟨10.1007/978-3-319-10783-7_3⟩. ⟨lirmm-00853694⟩

Share

Metrics

Record views

703