The problem of dynamic distributed sensor fusion, where time critical
sensor readings are fused concurrently by physically isolated modules,
is considered. A large number of critical applications including targ
et tracking, remote sensing, and autonomous vehicle navigation can dep
end on interpreting sensor readings in real time. Independent sensor m
odules receive partially contradictory data, but their answers must ag
ree within computed accuracy bounds. Real-time constraints cause addit
ional uncertainty factors. The dynamic nature of this problem requires
that the problem be viewed in four dimensions and processed efficient
ly. We present a new method that robustly tolerates a limited number o
f component failures. This method has complexity O(f(4)N log N), where
N is the total number of modules and f is the number of faulty module
s tolerated. Experimental results are given showing the merits of the
proposed method, (C) 1997 Society of Photo-Optical Instrumentation Eng
ineers.