Distributed Data Fusion Architecture for
نویسندگان
چکیده
Lockheed Martin Canada is currently developing on its blackboard-based architecture a distributed data fusion system that will be used to study the performance of various information sharing processes between collaborative platforms. The requirements for this project are consistent with those of the NCW that are to insure a timely exchange of secured (uncorrupted) information through the network whose topology is unknown (i.e. the cooperating platforms does not need to know how many they are, who they are and where they are); the circulation of information will not be affected if a platform is not capable of communicating or is destroyed. Each platform involved in the collaborative effort has its own sensor suite and communicates with the other with a LINK-type broadcast. This paper presents the design architecture of the distributed data fusion system that has been selected by Lockheed Martin Canada. This system will permit to evaluate various measures of performances selected from the Single Integrated Air Picture metrics (commonality, consistency, timeliness) to quantify the quality of the common operating picture built by fusing the information exchanged between collaborative platforms. The proposed approach is an alternative to a full-scale decentralized architecture that uses fusion algorithms such as the Covariance Intersection aiming to provide scalability and reliability. Results reported so far in the literature show poor performances with such an algorithm and authors are reconsidering the operational validity of the full scale decentralized architecture by introducing a priori knowledge about the source and destination of the shared information. Such knowledge exist in the use tracklet approach that provides as the CI a mean to avoid data incest at the cost of sending additional information to keep track of the history of the data fusion process. In the network architecture proposed by Lockheed Martin Canada, each platform maintains two tracks database. A local track database that contain the local track estimates produced by the fusion of the measurements created from the local sensor tracks. A global track database that contain the fused RTO-MP-0 Paper presented at the RTO SCI Symposium on “Multi-Platform Integration of Sensors and Weapons Systems for Maritime Applications”, held in Norfolk, USA, 21-23 October 2002, and published in RTO-MP-097(I).
منابع مشابه
Community Model Architecture – A New Data Fusion Paradigm for Implementation
Data fusion in today’s context has a huge impact in terms of the cognizance and decision paradigms. The data fusion paradigms are either model based or architecture based. The popular data fusion architectures are Thomopoulos Architecture, Distributed Blackboard Data Fusion Architecture, System-based Data Fusion Architecture, Hierarchical Data Fusion Architecture, Distributed Data Fusion Archit...
متن کاملA Distributed Architecture for Symbolic Data Fusion
This paper presents a distributed knowledge representation and data fusion system designed for highly integrated Ambient Intelligence applications. The architecture, based on the idea of an ecosystem of interacting artificial entities, is a framework for collaborating agents to perform an intelligent multi-sensor data fusion. In particular, we focus on the cognitive layers leading the overall d...
متن کاملProposing A Distributed Model For Intrusion Detection In Mobile Ad-Hoc Network Using Neural Fuzzy Interface
Security term in mobile ad hoc networks has several aspects because of the special specification of these networks. In this paper a distributed architecture was proposed in which each node performed intrusion detection based on its own and its neighbors’ data. Fuzzy-neural interface was used that is the composition of learning ability of neural network and fuzzy Ratiocination of fuzzy system as...
متن کاملProposing A Distributed Model For Intrusion Detection In Mobile Ad-Hoc Network Using Neural Fuzzy Interface
Security term in mobile ad hoc networks has several aspects because of the special specification of these networks. In this paper a distributed architecture was proposed in which each node performed intrusion detection based on its own and its neighbors’ data. Fuzzy-neural interface was used that is the composition of learning ability of neural network and fuzzy Ratiocination of fuzzy system as...
متن کاملFlood Forecasting Using Artificial Neural Networks: an Application of Multi-Model Data Fusion technique
Floods are among the natural disasters that cause human hardship and economic loss. Establishing a viable flood forecasting and warning system for communities at risk can mitigate these adverse effects. However, establishing an accurate flood forecasting system is still challenging due to the lack of knowledge about the effective variables in forecasting. The present study has indicated that th...
متن کاملDistributed Multisensor Data Fusion under Unknown Correlation and Data Inconsistency
The paradigm of multisensor data fusion has been evolved from a centralized architecture to a decentralized or distributed architecture along with the advancement in sensor and communication technologies. These days, distributed state estimation and data fusion has been widely explored in diverse fields of engineering and control due to its superior performance over the centralized one in terms...
متن کامل