A vision based robot navigation and human tracking for social robotics

Author

Capi, Genci ; Toda, Hideki ; Nagasaki, Takuya

Author_Institution

Univ. of Toyama, Toyama, Japan

fYear

2010

fDate

15-16 Oct. 2010

Firstpage

1

Lastpage

6

Abstract

In this paper, we introduce a new vision based method for robot navigation and human tracking. For robot navigation, we convert the captured image in a binary one, which after the partition is used as the input of the neural controller. The neural control system, which maps the visual information to motor commands, is evolved online using real robots. For human tracking, after face detection, the color of human´s clothing is extracted. Then the robot starts tracking the human in the environment. The performance of proposed method is evaluated using the TateRob mobile robot. The experimental results and analysis are presented.

Keywords

face recognition; feature extraction; image colour analysis; mobile robots; neurocontrollers; object tracking; path planning; robot vision; service robots; TateRob mobile robot; binary image; face detection; human tracking; image color; neural control system; social robotics; vision based robot navigation; visual information map; Clothing; Humans; Navigation; Robot sensing systems; Visualization;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotic and Sensors Environments (ROSE), 2010 IEEE International Workshop on

Conference_Location

Phoenix, AZ

Print_ISBN

978-1-4244-7147-8

Type

conf

DOI

10.1109/ROSE.2010.5675255

Filename

5675255