Real-time Path Planning Algorithms for Autonomous UAV

With the increasing complexity of UAV missions, path planning, as a key issue, is receiving more and more attention. Currently, most of the literatures related to this problem are concerned about off-line path planning. However, the dynamic and complex environment with uncertainty makes it more challenging for UAVs to complete their missions autonomously, safely and quickly, which calls for path planning in real time. In the paper, several representative algorithms for UAV real-time path planning are reviewed, from perspective on path searching and trajectory optimization. Therein, Artificial Potential Field (APF) method, Markov Decision Process (MDP) based method and Artificial Neural Network (ANN) algorithm are set forth, while their performance, fusion and improvement are analyzed. Finally, we propose a series of challenging real-time path planning problems for future research.