An intelligent vision system for object localization and obstacle avoidance for an indoor service robot

Abstract

Housekeeping robots are service robots specially designed to perform housekeeping tasks such as cleaning and vacuuming. In this research an intelligent vision system for object localization and obstacle avoidance for an indoor service robot was developed. The vision system aids in identifying objects and obstacles in a controlled environment. The system comprises of a digital camera which is placed on the front panel of the robot. Captured images are processed to segment object of the image. A simple neural network model was developed to identify obstacles and objects. Visual servoing is used to locate the object that fall out of the gripper range and visual range as well. The developed vision system has successfully tested on the house keeping robot for real time navigation and pick & place operation.