Designing and Implementation of a Wireless Gesture Controlled Robot for Disabled and Elderly People

Abstract

Gesture controlled robot should perform its job with the embedded system, combination of hardware and software that is designed for performing dedicated tasks for specific users which can be controlled by hand gestures. In this paper, we propose a gesture controlled robot for physically challenged and elderly people. The robot uses motion sensors to recognize five gestures of hand. These five hand gestures are employed to control five directions such as stop or steady, forward, backward, left and right. In this paper, the gesture has been recognized by motion sensors and without any image processing to keep the system simple & efficient. The prototype device can be modified into a wheelchair, trolley bed or any physical platform consisting of more than two wheels. An Arduino Nano v3 embedded system with accelerometer gyroscope held by the user and the signals will be transferred wirelessly to the motors of the platform intended to move it as per the users hand gestures in order to carry themselves in their surrounding environment. Machine learning is used to classify hand gesture accurately. The result shows that the classification accuracy is near to 94% (93.8%).