Information value in nonparametric Dirichlet-process Gaussian-process (DPGP) mixture models

被引：10

作者：

Wei, Hongchuan ^{[1
]}

Lu, Wenjie ^{[2
]}

Zhu, Pingping ^{[3
]}

Ferrari, Silvia ^{[4
]}

Liu, Miao ^{[5
]}

Klein, Robert H. ^{[6
]}

Omidshafiei, Shayegan ^{[5
]}

How, Jonathan P. ^{[7
]}

机构：

[1] Duke Univ, 104 Misty Woods Circle,Apt L, Chapel Hill, NC 27514 USA

[2] Duke Univ, CB11-09-203,15 Broadway, Ultimo, NSW 2007, Australia

[3] Cornell Univ, 529 Upson Hall, Ithaca, NY 14853 USA

[4] Cornell Univ, 543 Upson Hall, Ithaca, NY 14853 USA

[5] MIT, 77 Massachusetts Ave, Cambridge, MA 02139 USA

[6] MIT, 1970 Harvard Ave E,Apt 1, Seattle, WA 98102 USA

[7] MIT, Bldg 33,Room 326, Cambridge, MA 02139 USA

来源：

AUTOMATICA | 2016年 / 74卷

关键词：

Information theory; Bayesian nonparametric models; Gaussian process; Dirichlet process; Information gain; SENSOR; TRACKING;

D O I：

10.1016/j.automatica.2016.07.018

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper presents tractable information value functions for Dirichlet-process Gaussian-process (DPGP) mixture models obtained via collocation methods and Monte Carlo integration. Quantifying information value in tractable closed form is key to solving control and estimation problems for autonomous information-gathering systems. The properties of the proposed value functions are analyzed and then demonstrated by planning sensor measurements so as to minimize the uncertainty in DPGP target models that are learned incrementally over time. Simulation results show that sensor planning based on expected KL divergence outperforms algorithms based on mutual information, particle filters, and randomized methods. (C) 2016 Elsevier Ltd. All rights reserved.

引用

页码：360 / 368

页数：9

共 26 条

[1]

[Anonymous], 2007, Numerical Recipes: The Art of Scientific Computing

[2]

Bar-Shalom Y., 2000, Multitarget-Multisensor Tracking Applications and Advances, VIII

[3] TRACKING IN A CLUTTERED ENVIRONMENT WITH PROBABILISTIC DATA ASSOCIATION [J].

BARSHALOM, Y ;

TSE, E .

AUTOMATICA, 1975, 11 (05) :451-460

[4]

Bernstein D. S., 2005, Matrix Mathematics

[5]

Bogachev VI., 2007, MEASURE THEORY, VI, II

[6]

Caflisch R. E., 1998, Acta Numerica, V7, P1, DOI 10.1017/S0962492900002804

[7]

Cover TM., 1991, ELEMENTS INFORM THEO, V1, P279

[8]

Ferrari S, 2012, P NEUR INF PROC SYST

[9] Probabilistic navigation in dynamic environment using Rapidly-exploring Random Trees and Gaussian Processes [J].

Fulgenzi, Chiara ;

Tay, Christopher ;

Spalanzani, Anne ;

Laugier, Christian .

2008 IEEE/RSJ INTERNATIONAL CONFERENCE ON ROBOTS AND INTELLIGENT SYSTEMS, VOLS 1-3, CONFERENCE PROCEEDINGS, 2008, :1056-1062

[10] Fast Nonparametric Clustering of Structured Time-Series [J].

Hensman, James ;

Rattray, Magnus ;

Lawrence, Neil D. .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2015, 37 (02) :383-393

← 1 2 3 →