Virtual reality simulation of a quadrotor to monitor dependent people at home

Abstract

Unmanned aerial vehicles (UAVs) represent an assistance solution for home care of dependent persons. These aircraft can cover the home, accompany the person, and position themselves to take photographs that can be analyzed to determine the person's mood and the assistance needed. In this context, this work principally aims to design a tool to aid in the development and validation of the navigation algorithms of an autonomous vision-based UAV for monitoring dependent people. For that, a distributed architecture has been proposed based on the real-time communication of two modules, one of them in charge of the dynamics of the UAV, the trajectory planning and the control algorithms, and the other devoted to visualizing the simulation in an immersive virtual environment. Thus, a system has been developed that allows the evaluation of the behavior of the assistant UAV from a technological point of view, as well as to carry out studies from the assisted person's viewpoint. An initial validation of a quadrotor model monitoring a virtual character demonstrates the advantages of the proposed system, which is an effective, safe and adaptable tool for the development of vision-based UAVs to help dependents at home.