Trajectory planning of a quadrotor to monitor dependent people

Abstract

This article introduces a framework for assisting dependent people at home through a vision-based autonomous unmanned aerial vehicle (UAV). Such an aircraft equipped with onboard cameras can be useful for monitoring and recognizing a dependent's activity. This work is focused on the problem of planning the flight path of a quadrotor to perform monitoring tasks. The objective is to design a trajectory planning algorithm that allows the UAV to position itself for the sake of capturing images of the dependent person's face. These images will be later treated by a base station to evaluate the persons emotional state, together with his/her behavior, this way determining the assistance needed in each situation. Numerical simulations have been carried out to validate the proposed algorithms. The results show the effectiveness of the trajectory planner to generate smooth references to our previously designed GPI (generalized proportional integral) controller. This demonstrates that a quadrotor is able to perform monitoring flights with a high motion precision.