A Vision based Voice Controlled Indoor Assistant Robot for Visually Impaired People

Abstract

Due to ever-increasing number of visually impaired people, the demands of assistant robots have been growing significantly. For the visually impaired, "independent living" which is the key to rebuild the dignity and self-confidence that can be achieved by assistant robot. This paper describes the design and development of a personal assistant robot, which is controlled by voice commands to find and determine the relative location of the object in the indoor environment with a corelation factor (CRF) algorithm developed in this study. The proposed assistant robot is a semi-humanoid robot consists of several cameras on the different location of its body. The cameras are used for autonomous movement, object detection, distance measurement, and motion planning. In addition, the robot keeps the user informed about the outcomes of its actions increases the usefulness of the robot. To justify the proposed system and measure its performance, successful experiments were conducted in indoor environments. The experimental results demonstrate that the proposed assistant robot performs all of its actions with high accuracy which will make visually impaired people feel the indoor environment safe, convenient and comfortable.