APPLICATION OF REINFORCEMENT LEARNING ON LASER GUIDE BOMBS FOR INCREASED LETHALITY
Loading...
Authors
Bhatnagar, Nikhil
Subjects
machine learning
laser guided weapons
pursuit guidance
Paveway
laser guided weapons
pursuit guidance
Paveway
Advisors
Karpenko, Mark
Wade, Brian M.
Date of Issue
2024-06
Date
Publisher
Monterey, CA; Naval Postgraduate School
Language
Abstract
The Enhanced Paveway II laser guided bomb is one of the most prevalent and cost-effective all-weather air-to-ground precision-guided munitions in today’s military arsenal employed by multiple airborne platforms against stationary and moving targets. It utilizes a “bang-bang” control system with a pursuit guidance algorithm to engage laser and/or Global Position System–designated targets. The “bang-bang” control system reduces weapon employment range and diminishes kinetic energy on impact due to energy loss during operational guidance. This thesis investigates the application of reinforcement learning (RL) to enhance weapon lethality by increasing kinetic energy on impact through the replacement of the pursuit guidance algorithm with a trained RL model. The RL model is trained in a 2DOF/3DOF Simulink environment to include second-order effects such as drag, lift, and guidance refresh rate. The hypothesis posited that an RL model would successfully increase the lethality of a “bang-bang” guidance-based laser guided bomb by augmenting kinetic energy on impact. The findings confirmed this hypothesis, albeit with only marginal improvements. This study demonstrates the potential of RL in transforming traditional “bang-bang” guidance systems into smarter weapons and suggests further research into trajectory energy optimization with higher fidelity models.
Type
Thesis
Description
Series/Report No
Department
Mechanical and Aerospace Engineering (MAE)
Organization
Identifiers
NPS Report Number
Sponsors
Funder
Format
Citation
Distribution Statement
Distribution Statement A. Approved for public release: Distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.