Implementation of a home appliance mobile platform based on computer vision: self-charging and mapping

Abstract

One of the key features of a fully autonomous mobile robot is represented by the ability to recharge itself with energy. This paper proposes a solution for recharging an autonomous mobile robot with power so that it can perform tasks with little or no human intervention. This paper continues our work on the implementation of a mobile platform based on computer vision. In a previous paper, we implemented the foundation of the platform, in which a mobile robot detected several targets and navigated autonomously between them. We have shown that a small-size computer is perfectly capable of performing multiple tasks such as object detection, processing input data from distance sensors, sending movement commands to electric motors. The charging areas are marked with specific signs that the mobile robot can recognize using computer vision software and specific algorithms. The robot can navigate to such an area, connect to a socket, fully recharge with energy, disconnect and resume its preset activities. The prototype for this study uses in-house developed software based on OpenCV graphic library, Python language, Unix-like operating system - Debian Jessie and low-cost, high performance computer Raspberry Pi 3, model B with a CPU at 1.2 GHz 64bit quad-core ARM, 1GB of RAM, commercial robotic kits, ultrasonic sensors, Raspberry Pi camera, commercial Li-Po rechargeable battery and adaptor, a wireless charging kit, and a digital compass. The paper presents a series of promising results obtained with this structure, which could be used as a platform for future applications in various fields.