Real-Time Robotic Arm Control using Static Hand Gestures: An Approach towards the Natural Human Machine Interaction

The main objective of this paper is to explore the utility of a human hand gesture for natural Human Machine Interaction. Hand gestures are a powerful communication channel and can be used as an interface device to achieve a natural and immersive Human Machine Interaction. In this paper, we have proposed a vision based system for controlling a robotic arm, in which system is able to recognize a set of fourteen specific static hand gestures and use them to control a 5 degree of freedom robotic arm. In the proposed method hand gesture images are acquired using HD web-camera and then passed through three stages; Image pre-processing, feature extraction, and recognition. For gesture recognition multi-layer feed-forward neural network classifier with back-propagation learning algorithm is used. Once a hand gesture is recognized, an appropriate command is sent to a robotic arm to perform a pre-defined task. The proposed system has been extensively tested with success. The proposed recognition technique for static hand gestures has been implemented in MATLAB. The average performance of the system to recognize hand gestures is more than 98% and the robotic arm is able to do jobs by using hand gesture commands as its input. Citation: Bhavin Changela, Atulkumar Narotamdas Kataria. "Real-Time Robotic Arm Control using Static Hand Gestures: An Approach towards the Natural Human Machine Interaction." Global Research and Development Journal For Engineering 5.12 (2020): 8 - 15.