The invention discloses an unmanned ship displacement attitude high-precision fusion method based on adaptive Kalman filtering, and belongs to the technical field of ship sensing positioning, and the method comprises the steps: building a discrete time
state space model of a navigation data state through employing a discrete integration mode based on the navigation data state; obtaining a
system state equation by means of a
rotation matrix and a median theorem; obtaining an observation
transfer matrix through coordinate
system information, a geodesic
line length between two points and an
azimuth angle, and obtaining a state observation equation by combining
noise data; based on the
system state equation and the state observation equation, using an adaptive
Kalman filtering algorithm to obtain displacement attitude information of the unmanned ship; detecting the prediction data of the unmanned ship by using a sliding window method; and when the predicted data is detected to be abnormal, substituting the predicted data into Kalman filtering for correction. According to the invention, through state modeling, fusion
algorithm,
anomaly detection and anomaly correction, the precision, reliability and robustness of obtaining the displacement attitude information of the unmanned ship are improved.