Control of Robot Directions Based on Online Hand Gestures

Abstract

The evolution of wireless communication technology increases human machine interactioncapabilities especially in controlling robotic systems. This paper introduces an effective wireless system incontrolling the directions of a wheeled robot based on online hand gestures. The hand gesture images arecaptured and processed to be recognized and classified using neural network (NN). The NN is trained usingextracted features to distinguish five different gestures; accordingly it produces five different signals. Thesesignals are transmitted to control the directions of the cited robot. The main contribution of this paper is, thetechnique used to recognize hand gestures is required only two features, these features can be extracted in veryshort time using quite easy methodology, and this makes the proposed technique so suitable for onlineinteraction. In this methodology, the preprocessed image is partitioned column-wise into two half segments;from each half one feature is extracted. This feature represents the ratio of white to black pixels of the segmenthistogram. The NN showed very high accuracy in recognizing all of the proposed gesture classes. The NN outputsignals are transmitted to the robot microcontroller wirelessly using Bluetooth. Accordingly the microcontrollerguides the robot to the desired direction. The overall system showed high performance in controlling the robotmovement directions.