RESEARCH METHODS OF MOBILE ROBOTS BASED ON STRUCTURAL REPRESENTATION OF VISUAL INFORMATION

RESEARCH METHODS OF MOBILE ROBOTS BASED ON STRUCTURAL REPRESENTATION OF VISUAL INFORMATION

V.P. Makarychev
PhD, Russian State Scientific Center for Robotics and Technical Cybernetics (RTC), Senior Research Scientist, Tikhoretskiy, 21, Saint-Petersburg, Russia, tel.: +7(812)552-07-80, This email address is being protected from spambots. You need JavaScript enabled to view it. 


Abstract

The new approach and the corresponding mobile robots control methods are proposed based on a structured visual information in two forms: geometric and frequency. The approach refers to the visual servoing when the feedback for the robot control is performed by using machine vision. In contrast to the classical visual servoing, when used features an image of the external environment in place of robot coordinates, the approach based on the definition of continuous transformations of the plane linking two images, first of all affine. To find such a transformation are used spatial methods based on local correlations of an image, optical flow and frequency methods, based on the theory of group representations.

Key words

Visual servoing, robot, group of trasformations, optical flow, furie transformation.

Year 2015 Issue number 1 Consecutive issue number 6 Pages 41-45

UDC identifier: 621.8:681.5

 

Editorial office address: 21, Tikhoretsky pr., Saint-Petersburg, Russia, 194064, tel.: +7(812) 552-13-25 e-mail: zheleznyakov@rtc.ru