Acquisition of a page turning skill for a multifingered hand using reinforcement learning
Authors:
- Jun UedaJUJun Ueda
- Ryoji NegiRNRyoji Negi
- Tsuneo YoshikawaTYTsuneo Yoshikawa
- 1 January 2004
- journal article
- Published by Taylor & Francis in Advanced Robotics
- Vol. 18 (1) , 101-114
Abstract
This paper proposes a method of acquisition of a page turning skill for a multifingered robotic hand using reinforcement learning. The goal of this paper is generation of the manipulation skill of a flexible object without its explicit model and tactile sensation during its control. In this paper, a page turning task is considered as an example of such tasks, where a sheet of paper, generally used in books, is a flexible object. The fingertip trajectories are obtained by reinforcement learning based on simulation. The reward considering a friction condition is given, so that a page turning skill without slip between the finger and the paper is obtained. The validity is confirmed by an experimental system which consists of a 2-d.o.f. manipulator and two 2-d.o.f. fingers.Keywords
This publication has 6 references indexed in Scilit:
- A sufficient condition for manipulation of Envelope FamilyIEEE Transactions on Robotics and Automation, 2002
- Robot Manipulation of Deformable Objects2000
- Modeling of Flexible Manipulators Using Virtual Rigid Links and Passive JointsThe International Journal of Robotics Research, 1996
- The Analysis of Deformation and Behavior of Flexible Materials. 1st Report. Study of Spring-Mass Beam Model of the Sheet.TRANSACTIONS OF THE JAPAN SOCIETY OF MECHANICAL ENGINEERS Series A, 1992
- Reinforcement Learning1992
- Dynamics and Stability in Coordination of Multiple Robotic MechanismsThe International Journal of Robotics Research, 1989