A new means of action selection via utility fusion is introduced as an alte
rnative to both sensor fusion and command fusion. Distributed asynchronous
behaviors indicate the utility of various possible states and their associa
ted uncertainty. A centralized arbiter then combines these utilities and pr
obabilities to determine the optimal action based on the maximization of ex
pected utility. The construction of a utility map allows the system being c
ontrolled to be modeled and compensated for; experimental results verify th
at this approach improves performance.