Collision avoidance for quadrotor using stereo vision depth maps

Abstract

A collision avoidance algorithm for a quadrotor unmanned aerial vehicle using a stereo vision sensor is proposed. A mathematical model for the quadrotor is developed, and the underactuated problem of the quadrotor is treated by introducing virtual inputs. Stereo vision is used to obtain depth map information, which is used to detect an obstacle. The collision cone approach is adopted to avoid collisions between the quadrotor and the detected obstacle. The collision prediction is conducted by using the relation between the velocity vector of the quadrotor and the collision cone. Information of the detected obstacles is accumulated to determine the location and size of the obstacles, which is used to prevent the quadrotor from colliding with the obstacle. Multiple obstacles can also be managed by creating obstacle clusters in the image plane. A waypoint guidance law and controller are designed using a feedback linearization scheme and a linear quadratic tracker. Numerical simulations are performed to demonstrate the performance of the proposed algorithm.