ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper A Person-Following Robot Using Siamese Network-Based RGBD Tracking
Cited - time in scopus Share share facebook twitter linkedin kakaostory
Authors
Jiyong Oh, Joon-Goo Lee, Hea-Min Lee, Seung-Woo Nam, Man-Soo Shin, Sangjoon Choi
Issue Date
2021-10
Citation
International Conference on Control, Automation and Systems (ICCAS) 2021, pp.1-2
Publisher
IEEE
Language
English
Type
Conference Paper
Abstract
In this paper, we present a person-following robot equipped with an RGBD camera and a 2D LiDAR. Based on the data captured by the RGBD camera, it computes the location of a target person using a Siamese network-based tracker. Together with RGB image, our Siamese network utilizes depth information of the RGBD camera as another input of the network. Our robot moves using PI control based on the relative location between the target person and the robot. In addition to the simple navigation, our robot can avoid static obstacles such as corners and pillars between the robot and the person utilizing the 2D LiDAR.
KSP Keywords
2D LiDAR, Depth information, Network-based, PI control, Person-following robot, RGB image, RGB-D cameras, Relative location, Siamese network, Static obstacles