Presentation 1997/3/17
Self-Supervised Learning System for Robot by Integrating Information from Several Sensors
Satoshi SUGIURA, Koichiro YAMAUCHI, Naohiro ISHII,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In biological systems, several sensors are used to recognize objects. Using this strategy, they can recognize objects correctly under wrong conditions where a part of sensors do not work well. From the point of view, we propose a robot which learns and recognizes objects using several sensors. This robot consists of several neural networks each of which receives inputs from corresponding sensor. In the learning phase, each neural network modifies its parameters so as to yield the same output vector as the other neural networks. In the recognition phase, the system integrates the output vectors of all neural networks with controlling priorities of sensors. The priorities are controlled according to the confidence of each sensory input. The integrated output is the motor control signal for the robot.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural Network / Self-Supervised Learning system / Sensory Fusion / Robot
Paper # NC96-140
Date of Issue

Conference Information
Committee NC
Conference Date 1997/3/17(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) Self-Supervised Learning System for Robot by Integrating Information from Several Sensors
Sub Title (in English)
Keyword(1) Neural Network
Keyword(2) Self-Supervised Learning system
Keyword(3) Sensory Fusion
Keyword(4) Robot
1st Author's Name Satoshi SUGIURA
1st Author's Affiliation Department of Intelligence and Computer Science, Nagoya Institute of Technology()
2nd Author's Name Koichiro YAMAUCHI
2nd Author's Affiliation Department of Intelligence and Computer Science, Nagoya Institute of Technology
3rd Author's Name Naohiro ISHII
3rd Author's Affiliation Department of Intelligence and Computer Science, Nagoya Institute of Technology
Date 1997/3/17
Paper # NC96-140
Volume (vol) vol.96
Number (no) 583
Page pp.pp.-
#Pages 8
Date of Issue