Design and Implementation of an Autonomous Wheeled Robot Using IoT with Human Recognition Capability

Abstract

The internet of things, or IoT, is a networked system of connected computing devices, mechanical and digital equipment, and items that may exchange data without requiring human-to-human or human-to-computer interaction. In this work, we evaluate the use of Internet of Things (IoT) devices in the design and development of a wheeled robot to autonomously navigate in an uncharted region, avoid obstacles, and identify human presence on the scene. We demonstrate how to obtain helpful environmental data from the wheeled robot using IoT devices like ultrasonic sensors, a GPS module, and an IR camera. We go into further detail on how to detect human shape using the SSD inception V2 model. Through some basic scenarios, we demonstrate both the capabilities and challenges faced when IoT devices are interconnected to navigate a path and detect human shape. We anticipate that our findings will motivate researchers to conduct additional research into the presented technologies and approaches in order to develop advanced robotic devices with computer vision capabilities that can be deployed in real-world settings.