Path planning for remotely controlled UAVs using Gaussian process filter

Most of the recent results in control of unmanned aerial vehicles (UAVs) have focused on motion stability and navigation in well-structured environments, without considering communication delay influences. In order to deal with time delays and packet losses in networked UAVs, this paper suggests a machine learning based Gaussian process (GP) filter for a path planning problem. The developed GP filter estimates the UAV states accurately given delayed observation by learning the pattern of network-induced effects on UAV maneuvers. We validate that the GP filter produces the lower error rate than Kalman filter by analyzing error covariances. The proposed algorithm is evaluated on a collaborative trajectory tracking task for two networked-UAVs and the better control performance is achieved.