Multi-Sensor Cooperative Tracking Using Distributed Nash Q-Learning

Jia Cai; Chang Qiang Huang; Hai Feng Guo

doi:10.4028/www.scientific.net/AMR.591-593.1475

Paper Titles

Mechanical Analysis of the Jumping Motion of a Spherical Robot
p.1457

Research on Dissolved Oxygen Intelligent Control System in Waste Water Treatment
p.1461

Application of Fourier Analysis to the Outline of Object
p.1465

A Sensor of Aero-Engine Real-Time Fault Detection System Based on ARM9
p.1470

Multi-Sensor Cooperative Tracking Using Distributed Nash Q-Learning
p.1475

Research on Data Processing Method of Three Dimensional Machine Vision System
p.1479

Backstepping Adaptive Fuzzy Control for Permanent Magnet Synchronous Motor Servo Systems
p.1483

Study on Multivariable System Based on PID Neural Network Control
p.1490

Robust Stabilization of Stochastic Singular Systems with Markovian Switching
p.1496

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 591-593Multi-Sensor Cooperative Tracking Using...

Multi-Sensor Cooperative Tracking Using Distributed Nash Q-Learning

Abstract:

Traditional target tracking algorithm has a disadvantage of excessive dependence on the environment model. Thus a multi-sensor cooperative tracking method using distributed Nash Q-learning was proposed. Distributed Nash Q-learning with model-free was firstly described. Then sensor action and reward function were defined, which both are very crucial to the learning. Sensor action was only subjected to angle control, and reward function was given by calculating the trace of one time-step prediction error covariance. Nash tragedy can not be directly calculated, therefore, a probability statistics method using Bayesian inference was used to update the Q function. Simulation of passive tracking merely with angle measurements shows that this algorithm can enhance the adaptation to environment change and the tracking accuracy.

You might also be interested in these eBooks

Manufacturing Engineering and Automation II

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 591-593)

Pages:

1475-1478

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.591-593.1475

Citation:

Cite this paper

Online since:

November 2012

Authors:

Jia Cai, Chang Qiang Huang, Hai Feng Guo

Keywords:

Distribution, Extended Kalman Flter (EKF), Multi-Sensor Cooperation, Nash Q-Learning, Reinforcement Learning, Target Tracking

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Y. He, G.H. Wang, D.J. Lu and Y.N. Peng: Multisensor Information Fusion with Application (Publishing House of Electronics Industry, China 2000), p.242

Google Scholar

[2] J. Ousingsawat and M.E. Campbell: AIAA Guidance, Navigation and Control Conference and Exhibit (Providence, Rhode Island, 2004), p.2188

Google Scholar

[3] K. Kirkpatrick and J. Valasek: AIAA Guidance, Navigation and Control Conference and Exhibit (Honolulu, Hawaii, 2008), p.5

Google Scholar

[4] D.D. Dier and S.S. Joshi: AIAA Guidance, Navigation and Control Conference and Exhibit (Hilton Head, South Carolina, 2007), p.7

Google Scholar

[5] C.J.C.H. Watkins and P. Dayan: Machine learning, Vol. 8 (1992), p.279

Google Scholar

[6] Y.W. Lin, V.B. Le, Y. Xue, Z.Y. Feng and Y.J. Zhang: High Technology Letters, Vol. 14 (2008), No.3, p.238

Google Scholar

[7] J.L. Hu and M.P. Wellman: Journal of Machine Learning Research, Vol.4 (2003), p.1039

Google Scholar

[8] J. Joseph and Jr. LaViola: Proc. the 2003 American Control Conference (Denver, CO, USA, 2003), Vol. 3, p.2435

Google Scholar