Design of Robot Lawn Mower Based on Computer Vision

Abstract

In this paper, we introduce a new research about mowing robot on obstacle avoidanceand path tracking controlling theoretically and practically, and propose the mowing control methodwhich based on computer vision. Lawn images collected by camera, through the extraction ofprogramming dealing with lawn, obstacles and boundary characteristics to achieve edge separation.Through special processing algorithm to determine boundary arises and obstacles location, size andspeed of the robot, with real-time capturing and processing. This paper gives the complete imagerecognition processing, and analyzes several methods of image filtering and edge detection, andproposes simple control algorithm for obstacle avoidance, and applies MATLAB for obstacleavoidance simulation. The results show that: the method can correctly identify the obstacles andboundaries, through the output about location, size of the obstacles and boundary, border slope andspeed of the robot to control robot mower. Most importantly, that computer vision applying in themowing robot itself is an innovation.