Development of system model for audio visual control of mobile robots with voice and gesture commands

Abstract

There are many methods for controlling the movement of mobile robots. Some of them are based on received information from the audio and video sensors of the robot. Some methods are using separately the audio or the video information, but the purpose of the current article is to combine both, using audio and video input in parallel, and by this to increase the effectiveness of controlling the movement of the mobile robot. This is very important in the cases when the human operator using both gestures and voice commands to navigate and control the robot.