DocumentCode
1164831
Title
Risk-sensitive estimation and a differential game
Author
Banavar, Ravi N. ; Speyer, Jason L.
Author_Institution
Dept. of Syst. & Control Eng., Indian Inst. of Technol., Bombay, India
Volume
39
Issue
9
fYear
1994
fDate
9/1/1994 12:00:00 AM
Firstpage
1914
Lastpage
1918
Abstract
A large deviation result is employed to solve the state estimation problem of a continuous time Gauss-Markov system with an exponential cost. The exponential cost is the expected value of an exponential function of the state estimation-error. A scalar θ appearing in the cost, termed as the risk factor, determines the penalty on the higher order moments of the error. In contrast to the minimum variance estimate, penalty on large deviations of the estimation error is possible
Keywords
state estimation; continuous time Gauss-Markov system; differential game; estimation error; exponential function; risk-sensitive estimation; state estimation problem; state estimation-error; Control systems; Cost function; Differential equations; Lyapunov method; Mechanical variables control; Nonlinear equations; Nonlinear systems; Pulse width modulation; Sliding mode control; State estimation;
fLanguage
English
Journal_Title
Automatic Control, IEEE Transactions on
Publisher
ieee
ISSN
0018-9286
Type
jour
DOI
10.1109/9.317123
Filename
317123
Link To Document