Gaussian Process based Model Predictive Control for Linear Time Varying Systems

被引：0

作者：

Cao, Gang ^{[1
]}

Lai, Edmund M-K ^{[1
]}

Alam, Fakhrul ^{[1
]}

机构：

[1] Massey Univ, Sch Engn & Adv Technol, Auckland, New Zealand

来源：

2016 IEEE 14TH INTERNATIONAL WORKSHOP ON ADVANCED MOTION CONTROL (AMC) | 2016年

关键词：

OPTIMIZATION; STABILITY;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Two main issues associated with Model Predictive Control (MPC) are learning the unknown dynamics of the system and handling model uncertainties. In this paper, unknown Linear Time-Varying (LTV) system with external noise is represented by using probabilistic Gaussian Process (GP) models. In this way, we can explicitly evaluate model uncertainties as variances. As a result, it is possible to directly take obtained variances into account when planing the policy. In addition, through using analytical gradients that are available during the GP modelling process, the optimization problem in GP based MPC can be solved faster. The performance of proposed approach is demonstrated by simulations on trajectory tracking problem of a LTV system.

引用

页码：251 / 256

页数：6

共 33 条

[1]

[Anonymous], 2009, MODEL PREDICTIVE CON

[2]

[Anonymous], 2003, P ADV NEUR INF PROC

[3]

Bemporad A, 1999, LECT NOTES CONTR INF, V245, P207

[4] Scenario-based Model Predictive Control of Stochastic Constrained Linear Systems [J].

Bernardini, Daniele ;

Bemporad, Alberto .

PROCEEDINGS OF THE 48TH IEEE CONFERENCE ON DECISION AND CONTROL, 2009 HELD JOINTLY WITH THE 2009 28TH CHINESE CONTROL CONFERENCE (CDC/CCC 2009), 2009, :6333-6338

[5]

Candela JQ, 2003, INT CONF ACOUST SPEE, P701

[6] Stochastic Tubes in Model Predictive Control With Probabilistic Constraints [J].

Cannon, Mark ;

Kouvaritakis, Basil ;

Rakovic, Sasa V. ;

Cheng, Qifeng .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2011, 56 (01) :194-200

[7]

Cao G, 2014, IEEE IJCNN, P1573, DOI 10.1109/IJCNN.2014.6889408

[8]

Chowdhary Girish., 2013, ADV AEROSPACE GUIDAN, P29

[9]

Deisenroth M. P., 2010, THESIS

[10] Gaussian Processes for Data-Efficient Learning in Robotics and Control [J].

Deisenroth, Marc Peter ;

Fox, Dieter ;

Rasmussen, Carl Edward .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2015, 37 (02) :408-423

← 1 2 3 4 →