Model predictive neural control of a high-fidelity helicopter model

Alexander A. Bogdanov; Eric A. Wan; Magnus Carlsson; Yinglong Zhang; Richard Kieburtz; Antonio Baptista

Model predictive neural control of a high-fidelity helicopter model

Alexander A. Bogdanov, Eric A. Wan, Magnus Carlsson, Yinglong Zhang, Richard Kieburtz, Antonio Baptista

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper we present a method for optimal control of a nonlinear highly realistic helicopter model based on a combination of a neural network (NN) feedback controller and a state-dependent Riccati equation (SDRE) controller. Optimization of the NN is performed within a receding horizon model predictive control (MPC) framework, subject to dynamic and kinematic constraints. The SDRE controller utilizes a simplified 6DOF rigid body dynamic model, and augments the NN controller by providing an initial feasible solution and improving stability. While the SDRE control provides robustness based on a pseudo-linear formulation of the dynamics, the MPNC utilizes the highly accurate numerical helicopter model.

Original language	English (US)
Title of host publication	AIAA Guidance, Navigation, and Control Conference and Exhibit
State	Published - 2001
Event	AIAA Guidance, Navigation, and Control Conference and Exhibit 2001 - Montreal, QC, Canada Duration: Aug 6 2001 → Aug 9 2001

Publication series

Name	AIAA Guidance, Navigation, and Control Conference and Exhibit

Other

Other	AIAA Guidance, Navigation, and Control Conference and Exhibit 2001
Country/Territory	Canada
City	Montreal, QC
Period	8/6/01 → 8/9/01

ASJC Scopus subject areas

Aerospace Engineering
Control and Systems Engineering
Electrical and Electronic Engineering

Cite this

Bogdanov, AA, Wan, EA, Carlsson, M, Zhang, Y, Kieburtz, R & Baptista, A 2001, Model predictive neural control of a high-fidelity helicopter model. in AIAA Guidance, Navigation, and Control Conference and Exhibit. AIAA Guidance, Navigation, and Control Conference and Exhibit, AIAA Guidance, Navigation, and Control Conference and Exhibit 2001, Montreal, QC, Canada, 8/6/01.

@inproceedings{6498b291b3da49a9a91a0991220b3117,

title = "Model predictive neural control of a high-fidelity helicopter model",

abstract = "In this paper we present a method for optimal control of a nonlinear highly realistic helicopter model based on a combination of a neural network (NN) feedback controller and a state-dependent Riccati equation (SDRE) controller. Optimization of the NN is performed within a receding horizon model predictive control (MPC) framework, subject to dynamic and kinematic constraints. The SDRE controller utilizes a simplified 6DOF rigid body dynamic model, and augments the NN controller by providing an initial feasible solution and improving stability. While the SDRE control provides robustness based on a pseudo-linear formulation of the dynamics, the MPNC utilizes the highly accurate numerical helicopter model.",

author = "Bogdanov, {Alexander A.} and Wan, {Eric A.} and Magnus Carlsson and Yinglong Zhang and Richard Kieburtz and Antonio Baptista",

year = "2001",

language = "English (US)",

isbn = "9781563479786",

series = "AIAA Guidance, Navigation, and Control Conference and Exhibit",

booktitle = "AIAA Guidance, Navigation, and Control Conference and Exhibit",

note = "AIAA Guidance, Navigation, and Control Conference and Exhibit 2001 ; Conference date: 06-08-2001 Through 09-08-2001",

}

TY - GEN

T1 - Model predictive neural control of a high-fidelity helicopter model

AU - Bogdanov, Alexander A.

AU - Wan, Eric A.

AU - Carlsson, Magnus

AU - Zhang, Yinglong

AU - Kieburtz, Richard

AU - Baptista, Antonio

PY - 2001

Y1 - 2001

N2 - In this paper we present a method for optimal control of a nonlinear highly realistic helicopter model based on a combination of a neural network (NN) feedback controller and a state-dependent Riccati equation (SDRE) controller. Optimization of the NN is performed within a receding horizon model predictive control (MPC) framework, subject to dynamic and kinematic constraints. The SDRE controller utilizes a simplified 6DOF rigid body dynamic model, and augments the NN controller by providing an initial feasible solution and improving stability. While the SDRE control provides robustness based on a pseudo-linear formulation of the dynamics, the MPNC utilizes the highly accurate numerical helicopter model.

AB - In this paper we present a method for optimal control of a nonlinear highly realistic helicopter model based on a combination of a neural network (NN) feedback controller and a state-dependent Riccati equation (SDRE) controller. Optimization of the NN is performed within a receding horizon model predictive control (MPC) framework, subject to dynamic and kinematic constraints. The SDRE controller utilizes a simplified 6DOF rigid body dynamic model, and augments the NN controller by providing an initial feasible solution and improving stability. While the SDRE control provides robustness based on a pseudo-linear formulation of the dynamics, the MPNC utilizes the highly accurate numerical helicopter model.

UR - http://www.scopus.com/inward/record.url?scp=8744280898&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=8744280898&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:8744280898

SN - 9781563479786

T3 - AIAA Guidance, Navigation, and Control Conference and Exhibit

BT - AIAA Guidance, Navigation, and Control Conference and Exhibit

T2 - AIAA Guidance, Navigation, and Control Conference and Exhibit 2001

Y2 - 6 August 2001 through 9 August 2001

ER -

Model predictive neural control of a high-fidelity helicopter model

Abstract

Publication series

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this