Presentation 2002/11/4
A Ping-pong Robot which Learn from Failure
Yoshirou HATADA, Hiroyuki MIYAMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is one of the important subjects of robot learning that a robot applies trial-and-error method like human, and adapts itself to various situations flexibly. In this paper, we propose the learning algorithm for desired action from the past experiences including the failure. The ping-pong robot had the simulation performed for algorithm verification. The proper racket angle for rebounds the ball which flies from various position to the goal is not known. Then, we used the racket angle and the position where the ball was actually rebound into an input-and-output signal for the RBF network. The result of a simulation, the ball was rebounded to the goal.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Robot Learning / Neural Network / Radial Basis Function (RBF) / Learn from Failure
Paper # NC2002-71
Date of Issue

Conference Information
Committee NC
Conference Date 2002/11/4(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Ping-pong Robot which Learn from Failure
Sub Title (in English)
Keyword(1) Robot Learning
Keyword(2) Neural Network
Keyword(3) Radial Basis Function (RBF)
Keyword(4) Learn from Failure
1st Author's Name Yoshirou HATADA
1st Author's Affiliation Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology()
2nd Author's Name Hiroyuki MIYAMOTO
2nd Author's Affiliation Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology
Date 2002/11/4
Paper # NC2002-71
Volume (vol) vol.102
Number (no) 430
Page pp.pp.-
#Pages 5
Date of Issue