May 13, 2025

US12298106 - Line of sight bias for missile guidance

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.

Assignee: Arizona Board of Regents on Behalf of the University of Arizona
Inventors: Brian Gaudet, Roberto Furfaro
Filing date: 2023-03-31

This patent describes a missile guidance method that utilizes a curvature parameterization to improve the accuracy of targeting by calculating a curved line-of-sight direction vector. The method incorporates deep learning techniques to optimize the guidance system for various engagement scenarios, enhancing its adaptability to different target behaviors.

Claim 1

A missile guidance method, comprising: receiving, from a navigation system, a line-of-sight unit vector indicative of a direction from a missile position of a missile to a target position of a target; calculating a curved line-of-sight direction vector by applying a curvature parameterization to the line-of-sight unit vector; and deriving a line-of-sight rotation rate for guiding the missile to the target from the curved line-of-sight direction vector. receiving, from a navigation system, a line-of-sight unit vector indicative of a direction from a missile position of a missile to a target position of a target; calculating a curved line-of-sight direction vector by applying a curvature parameterization to the line-of-sight unit vector; and deriving a line-of-sight rotation rate for guiding the missile to the target from the curved line-of-sight direction vector.

Google Patents

https://patents.google.com/patent/US12298106

USPTO PDF

https://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/12298106