High-level Closed-loop Fusion and Decision Making with INFORM Lab

摘要

The INFORM Lab testbed allows experimenting with high-level distributed information fusion dynamic resource management and configuration management, given multiple constraints on the resources and their communications networks. The paper describes the architecture, the concepts of goals and situation evidence, algorithms for distributed information and dynamic resource management, and auto-configurable information fusion architectures. The testbed provides general services which include a multi-layer plug-and-play architecture, and a general multi-agent framework based on John Boyd's OODA loop. The testbed's performance is demonstrated on scenarios/vignettes for 2 types of Coastal Wide Area Surveillance scenarios/vignettes: a cooperative search-and-rescue effort and a non- cooperative smuggling scenario. INFORM Lab's usefulness as a research and teaching tool are also discussed.