Title :
On sensor management in decentralized data fusion
Author :
Manyika, J.M. ; Durrant-Whyte, H.F.
Author_Institution :
Dept. of Eng. Sci., Oxford Univ., UK
Abstract :
A probabilistic framework for decentralized data fusion and sensor management based on the notion of Bayesian information value is presented. Use is made of information as the expected utility of actions within a framework of decentralized decision-theory. Entropy is used as an information metric. Some preliminary results justifying this approach are shown
Keywords :
Bayes methods; decision theory; information theory; probability; sensor fusion; Bayesian information value; decentralized data fusion; decentralized decision-theory; entropy; expected utility; information metric; probability; sensor management; Additive noise; Bayesian methods; Computer architecture; Data engineering; Decision making; Engineering management; Entropy; Robot sensing systems; Sensor fusion; Sensor systems; Utility theory;
Conference_Titel :
Decision and Control, 1992., Proceedings of the 31st IEEE Conference on
Conference_Location :
Tucson, AZ
Print_ISBN :
0-7803-0872-7
DOI :
10.1109/CDC.1992.371006
