WALL CLASSIFIER FOR GONDOLA-TYPED ROBOT USING KALMAN FILTER

ISARC

*D. Y. Kim, J. Yoon, and C.-W. Park

Korea Electronics Technology Institute

193, Yakdae-dong, Wonmi-gu

Bucheon-si, Gyeonggi-do, Republic of Korea

(*Corresponding author: sword32@keti.re.kr)

This paper shows an approach that a gondola-typed robot recognizes walls on building facades. It is applicable for autonomous or teleoperated building façade painting robots. The robot may react based on the wall classification data. This approach is based on 2D LRF(two-dimensional Laser Range Finder). The robot acquires relative distances to walls, and a Kalman filter decides correspondence of walls. An ARS(Attribute Reference System) sensor helps convert LRF coordinate to global coordinate. The experimental results demonstrate the conversion of LRF data.
Keywords: Sensors; Filters; Data; Systems; Classifiers; Calibration; classification; Robotics; Methodology;
Full Access to Technical Paper
PDF version for $20.00
Other papers from ISARC