Control design and visual autonomous navigation of quadrotor

Abstract

Starting from the fact that quadrotors are nonlinear MIMO system that operates in 3D space, the task of stabilizing and generating suitable control commands have been the interest of many researches. Another challenging task is the autonomous navigation as both the weight and the computation capacity are limited which constrains the type of sensors and algorithms. In this project, an autonomous navigation and obstacle avoidance system based on monocular camera has been implemented which enables the quadrotor navigates in previously unknown GPS-denied environment. Moreover, four controllers have been designed and their performance were compared.The mathematical model of a quadrotor has been derived using Newton’s and Euler’s laws, where a linear and nonlinear version of the model are presented, based on that various control strategies such as LQR, PID, Feedback Linearization with pole placement and Sliding Mode control Have been implemented in MATLAB/Simulink and discussed. Sensor data and the camera video stream have been used by a Keyframe visual SLAM system to compute the location of the drone and generate the 3D map of the environment in the form of point cloud. This point cloud data is clustered and used for obstacle detection. Moreover a PRM algorithm has been used to generate a collision-free path that will be followed by the drone based on the PID controller designed. We implemented our approach on a real Parrot ARDrone2.0, and our approach has been validated with experiments. All computations are performed on a ground station, which isconnected to the drone via wireless LAN.