公开(公告)号：US20230314104A1

公开(公告)日：2023-10-05

申请号：US18194610

申请日：2023-03-31

申请人： Arizona Board of Regents on behalf of the University of Arizona

发明人： Brian Gaudet ,  Roberto Furfaro

IPC分类号： F41G7/22

CPC分类号： F41G7/2253

摘要： A missile guidance method that applies a curvature parameterization to a line-of-sight unit vector between a missile and a target. A line-of-sight rotation rate is derived from the line-of-sight unit vector with the applied curvature parameterization. In some embodiments, the curvature parameterization is learned by a deep learning network (e.g., a deep neural network that includes a recurrent layer). The deep neural network may be optimized using meta reinforcement learning over an ensemble of engagement scenarios with varying target behavior.