A FUZZY-LOGIC ARCHITECTURE FOR AUTONOMOUS MULTISENSOR DATA FUSION

Fuzzy logic techniques have become popular to address various processe s for multisensor data fusion. Examples include the following: 1) fuzz y membership functions for data association; 2) evaluation of alternat ive hypotheses in multiple hypothesis trackers; 3) fuzzy-logic-based p attern recognition (e.g., for feature-based object identification); an d 4) fuzzy inference schemes for sensor resource allocation. These app roaches have been individually successful but are limited to only a si ngle subprocess within a data fusion system. At The Pennsylvania State University, Applied Research Laboratory, a general-purpose fuzzy-logi c architecture has been developed that provides for control of sensing resources, fusion of data for tracking, automatic object recognition, control of system resources and elements, and automated situation ass essment. This general architecture has been applied to implement an au tonomous vehicle capable of self-direction, obstacle avoidance, and mi ssion completion. The fuzzy logic architecture provides interpretation and fusion of multisensor data (i.e., perception) as well as logic fo r process control (action). This paper provides an overview of the fuz zy-logic architecture and a discussion of its application to data fusi on in the context of the Department of Defense (DoD) Joint Directors o f Laboratories (JDL) Data Fusion Process Model. A new, robust, fuzzy c alculus is introduced, An application example is provided.