A Deep Reinforcement Learning Strategy for UAV Path Following Control Under Sensor Fault

Unmanned Aerial Vehicles (UAVs) have been extensively used in civil and industrial applications due to the rapid development of the involved technologies. Especially, using deep reinforcement learning methods for motion control acquires a major progress recently since deep Q-learning has successfully applied to the continuous action domain problem. This paper proposes a new Deep Deterministic Policy Gradient (DDPG) algorithm for path following control problem of UAV with sensor faults. Firstly, the model of UAV path following problem has been established. After that, the DDPG framework is constructed. Then, the proposed DDPG algorithm is formulated to the path following problem. Finally, simulation results are carried out to show the efficiency and effectiveness of the proposed methodology.