Concerns multisensor data fusion (MSDF) for situational assessmentfor real time complex processes. All three elements of the SHORE(stimulus-hypothesis-response) paradigm have been considered by the ISISgroup for demonstrating this architecture for systems integration of afully autonomous road, cross-country and drilling vehicle on CEC ProjectPanorama. MSDF is a continuous process dealing with the associationcorrelation, and combination of data and information from multipledisparate sources to achieve a refined state estimate about theenvironment and timely assessment of the situation. Here we onlyconsider the processes of data integration and state estimation. Tointegrate data from disparate data sources such as sensors, look-uptables, human experiences/observations, data bases, etc a commoncurrency of information content and data representation is required.Existing theories such as Bayesian, Dempster-Shafer, artificial neuralnetworks (ANN), case-based reasoning, method of endorsement, blackboardexpert systems, fuzzy logic etc.-all of which have been used forMSDF-are inadequate or inappropriate. We propose neurofuzzy algorithms,since they readily incorporate database knowledge/symbolic/linguisticknowledge in the form of fuzzy rules, and sensory data in a singleenvironment/processor
展开▼
