A low-cost autonomous navigation system for a quadrotor in complex outdoor environments

Abstract

In this article, we design a low-cost navigation system for a quadrotor working in unknown outdoor environments. To reduce the computing burden of the quadrotor, we build a separated system and transfer the computing resources from onboard side to ground station side. Both sides’ communication is guaranteed by 5G wireless networks. We utilize a stereo camera to acquire point clouds and build Octomap for the quadrotor’s navigation. Then, the trajectory is generated in two stages. In the first stage, a modified RRT*-CONNECT algorithm is adopted to generate a set of collision-free waypoints. In the second stage, a curve fitting algorithm is utilized to get a smooth piecewise Bezier trajectory. The advantage of the proposed method is to optimize the path into a safe, smooth, and dynamically feasible trajectory in real time. The modules of the state estimation, dense mapping, and motion planning are integrated into a DJI Matrice 100 quadrotor. Finally, simulation and experiments are both conducted to show the validity and practicality of our method.