Learning the expected utility of sensors and algorithms

Author

Lindner, John ; Murphy, Robin R. ; Nitz, Elizabeth

Author_Institution

Dept. of Math. & Comput. Sci., Colorado Sch. of Mines, Golden, CO, USA

fYear

1994

fDate

2-5 Oct 1994

Firstpage

583

Lastpage

590

Abstract

A method is proposed which estimates the expected utility of a sensor being used in a sensor fusion framework. The resulting values are used to predict the subset of sensors which should be read to minimize the total cost of an observation cycle. Preliminary results from experiments taken with three sensors mounted on a mobile robot indicate that the method is indeed capable of reducing the average cost of an observation cycle, and that it is also capable of dynamically tracking conditions which change the expected utility values

Keywords

decision theory; feature extraction; learning (artificial intelligence); mobile robots; path planning; sensor fusion; tracking; expected utility estimation; feature extraction; mobile robot; observation cycle cost; reinforcement learning; sensor fusion; subset of sensors; tracking; Costs; Feature extraction; Gas detectors; Glass; Mobile robots; Power demand; Robot sensing systems; Sensor fusion; Sensor phenomena and characterization; Utility theory;

fLanguage

English

Publisher

ieee

Conference_Titel

Multisensor Fusion and Integration for Intelligent Systems, 1994. IEEE International Conference on MFI '94.

Conference_Location

Las Vegas, NV

Print_ISBN

0-7803-2072-7

Type

conf

DOI

10.1109/MFI.1994.398401

Filename

398401