A Method for UAV Tracking Target in Obstacle Environment
Zheng Zhi, Hongyu Yao · 2019
Aiming at the problem of autonomous tracking of moving target on the ground by UAV in the environment of dense obstacles, a real-time obstacle avoidance tracking method for UAV is proposed. In this method, Kalman filter is used to predict the state of the target, so that the UAV can track the target more effectively. The characteristics of concave obstacles with feasible area of depression and the problems caused by traditional genetic algorithm in practical application are analyzed. An improved Bayesian genetic algorithm is proposed in the process of UAV tracking. This method combines tracking and obstacle avoidance model, so that the UAV will not fall into the sag area and bypass the concave obstacles. The simulation results show that the proposed method can make UAV avoid obstacles in the process of tracking ground moving targets.