Acquisition of a page turning skill for a multifingered hand using reinforcement learning

Authors: Ueda J.; Negi R.; Yoshikawa T.

Source: Advanced Robotics, Volume 18, Number 1, 2004 , pp. 101-114(14)

Buy & download fulltext article:

Price: $35.00 plus tax (Refund Policy)

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: FLEXIBLE MATERIALS; MANIPULATION; REINFORCEMENT LEARNING; PAGE TURNING SKILL; MULTIFINGERED; ROBOT; HAND.

Document Type: Regular paper

DOI: http://dx.doi.org/10.1163/156855304322753326

Publication date: 2004-02-01