WCSE 2015
ISBN: 978-981-09-5471-0 DOI: 10.18178/wcse.2015.04.005

A Fuzzy Controller: Using Monocular Computer Vision to See and Avoid Obstacle for Quadcopter

Geng Keke, Liu Wei, Tan Liguo

Abstract— In this paper use the monocular computer vision, which is in the direction forward of quadcopter, to calculate the spatial distribution of these feature points matching.So that we can find out the approximate contour of the obstacle. A fuzzy controller was designed to command quadcopter for avoiding collision, the sensors used to accomplish this task are a forward camera and inertial measurement unit (IMU). In order to evaluate the performance of this controller a big amount of tests was carried out with real web camera and simulation in MATLAB.

Index Terms— monocular computer vision, 3-D reconstructions, PID, fuzzy controller.

Geng Keke, Liu Wei, Tan Liguo
Bauman Moscow State Technical University, RUSSIA

[Download]


Cite: Geng Keke, Liu Wei, Tan Liguo, "A Fuzzy Controller: Using Monocular Computer Vision to See and Avoid Obstacle for Quadcopter," 2015 The 5th International Workshop on Computer Science and Engineering-Information Processing and Control Engineering (WCSE 2015-IPCE), pp. 26-32, Moscow, Russia, April 15-17, 2015.