Missile homing-phase guidance law design using reinforcement learning

Brian Gaudet, Roberto Furfaro

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

A new approach to missile guidance law design is proposed, where reinforcement learning (RL) is used to learn a homing-phase guidance law that is optimal with respect to the missile's airframe dynamics as well as sensor and actuator noise and delays. It is demonstrated that this new approach results in a guidance law giving superior performance to either PN guidance or enhanced PN guidance laws developed using Lyapunov theory. Although optimal control theory can be used to derive an optimal control law under certain idealized modeling assumptions, we discuss how the RL approach gives more flexibility and higher expected performance for real-world systems.

Original languageEnglish (US)
Title of host publicationAIAA Guidance, Navigation, and Control Conference 2012
StatePublished - 2012
EventAIAA Guidance, Navigation, and Control Conference 2012 - Minneapolis, MN, United States
Duration: Aug 13 2012Aug 16 2012

Other

OtherAIAA Guidance, Navigation, and Control Conference 2012
CountryUnited States
CityMinneapolis, MN
Period8/13/128/16/12

Fingerprint

Electronic guidance systems
Reinforcement learning
Missiles
Airframes
Control theory
Actuators
Sensors

ASJC Scopus subject areas

  • Aerospace Engineering
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Gaudet, B., & Furfaro, R. (2012). Missile homing-phase guidance law design using reinforcement learning. In AIAA Guidance, Navigation, and Control Conference 2012

Missile homing-phase guidance law design using reinforcement learning. / Gaudet, Brian; Furfaro, Roberto.

AIAA Guidance, Navigation, and Control Conference 2012. 2012.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Gaudet, B & Furfaro, R 2012, Missile homing-phase guidance law design using reinforcement learning. in AIAA Guidance, Navigation, and Control Conference 2012. AIAA Guidance, Navigation, and Control Conference 2012, Minneapolis, MN, United States, 8/13/12.
Gaudet B, Furfaro R. Missile homing-phase guidance law design using reinforcement learning. In AIAA Guidance, Navigation, and Control Conference 2012. 2012
Gaudet, Brian ; Furfaro, Roberto. / Missile homing-phase guidance law design using reinforcement learning. AIAA Guidance, Navigation, and Control Conference 2012. 2012.
@inproceedings{99f4298e98334e588c6ad435014a52de,
title = "Missile homing-phase guidance law design using reinforcement learning",
abstract = "A new approach to missile guidance law design is proposed, where reinforcement learning (RL) is used to learn a homing-phase guidance law that is optimal with respect to the missile's airframe dynamics as well as sensor and actuator noise and delays. It is demonstrated that this new approach results in a guidance law giving superior performance to either PN guidance or enhanced PN guidance laws developed using Lyapunov theory. Although optimal control theory can be used to derive an optimal control law under certain idealized modeling assumptions, we discuss how the RL approach gives more flexibility and higher expected performance for real-world systems.",
author = "Brian Gaudet and Roberto Furfaro",
year = "2012",
language = "English (US)",
isbn = "9781600869389",
booktitle = "AIAA Guidance, Navigation, and Control Conference 2012",

}

TY - GEN

T1 - Missile homing-phase guidance law design using reinforcement learning

AU - Gaudet, Brian

AU - Furfaro, Roberto

PY - 2012

Y1 - 2012

N2 - A new approach to missile guidance law design is proposed, where reinforcement learning (RL) is used to learn a homing-phase guidance law that is optimal with respect to the missile's airframe dynamics as well as sensor and actuator noise and delays. It is demonstrated that this new approach results in a guidance law giving superior performance to either PN guidance or enhanced PN guidance laws developed using Lyapunov theory. Although optimal control theory can be used to derive an optimal control law under certain idealized modeling assumptions, we discuss how the RL approach gives more flexibility and higher expected performance for real-world systems.

AB - A new approach to missile guidance law design is proposed, where reinforcement learning (RL) is used to learn a homing-phase guidance law that is optimal with respect to the missile's airframe dynamics as well as sensor and actuator noise and delays. It is demonstrated that this new approach results in a guidance law giving superior performance to either PN guidance or enhanced PN guidance laws developed using Lyapunov theory. Although optimal control theory can be used to derive an optimal control law under certain idealized modeling assumptions, we discuss how the RL approach gives more flexibility and higher expected performance for real-world systems.

UR - http://www.scopus.com/inward/record.url?scp=84880624458&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880624458&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84880624458

SN - 9781600869389

BT - AIAA Guidance, Navigation, and Control Conference 2012

ER -