Distributed Episodic Exploratory Planning (DEEP)
Abstract
This report presents an overview of the work performed on the Distributed Episodic Exploratory Planning (DEEP) project. DEEP is a mixed-initiative decision support system that utilizes past experiences to suggest courses of action for new situations. It has been designed as a distributed multi-agent system, using agents to maintain and exploit the experiences of individual commanders, as well as to transform suggested past plans into potential solutions for a new situation or world state. The system is mixed-initiative in the sense that a commander, through his or her agent, can view and modify the contents of the shared repository as needed. The agents interact through a common knowledge repository and managed by a blackboard architecture. The blackboard architecture is well suited for dealing with ill-described, complex situations that are part of modern warfare. Additional aspects of the work include development of a common plan representation and design of the case repository feature space. Much of the work has been documented in numerous other papers, reports and presentations, as referenced in the bibliography, and is only summarized in this report.
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 01, 2012
- Accession Number
- ADA558965
Entities
People
- Anthony Ford
- Chad Destefano
- Dale Richards
- Gennady Staskevich
- Kurt Lachevet
Organizations
- Air Force Research Laboratory