Applying an AI Planner to Military Operations Planning

Proceedings. The 21st Digital Avionics Systems Conference, 2002

1996

In this paper, we report on our past and recent experiences in applying an AI generative planning system, called System for Interactive Planning and Execution (SIPE-2), to the problem of generating crisis action operations plans in a joint military domain * . We describe our motivation for selecting a generative planner, the application itself (including the second Integrated Feasibility Demonstration, IFD-2) , and the lessons we learned in creating it. We also report on the applied research we performed to address the lessons learned in IFD-2. This involved integrating the generative planner with several complementary technologies that were available through the Planning Initiative (PI): a temporal reasoner, a case-based reasoner, and the capacity analysis component of a scheduling system. These technology integration experiments (TIEs) were executed within the Common Prototyping Environment (CPE). We discuss both the unique characteristics of each TIE and the general features that contributed to the success of each one. Finally, we discuss future work in the areas of new applications and further work on the scheduling system TIE.

Advances in Knowledge Representation, 2012

1994

This paper describes a system that uses AI planning and representation techniques as the core of a decision support system. * The planning technology is supplemented with other AI and non-AI technologies. The overall system and initial application domain, military operations planning, are described first. We then describe the integration of SIPE-2, a generative planning system, with three independently-developed AI systems: a temporal reasoning engine, a case-based force selection module, a system for scheduling and capacity analysis.

Agile Computer Generated Forces (CGF) for the Next Generation Training Systems and Planning Systems need to have a more agile and flexible behavior than the current commonly used CGF systems can deliver. This because of that the human behavior in a real crisis or military operation is adaptive. This paper describes one approach to enable such functionality by combining Threat Analysis and Goal-Oriented Action Planning (GOAP) into an architecture where the concepts and formalism of effects and Actions plays a central role.

2010

Military decision making demands an increasing ability to comprehend and structure the critical information on the battlefield. As the military evolves into a networked force, strain is placed on headquarters and others to collect and utilize information from across the battlefield in a timely and efficient manner. Human capability in analyzing all the data is not sufficient because the modern battlefield is characterized by dramatic movements, unexpected evolutions, chaotic behavior and non-linearities. It results a great need of powerful AI assistance in military decisions.

Ijcai, 1999

A view of plan recognition shaped by both operational and computational requirements is presented. Operational requirements governing the level of delity and nature of the reasoning process combine with computational requirements including performance speed and software engineering e ort to constrain the types of solutions available to the software developer. By adopting machine learning to provide spatio-temporal recognition of environmental events and relationships, an agent can be provided with a mechanism for mental state recognition qualitatively di erent from previous research. An architecture for integrating machine learning into a BDI agent is suggested and the results from the development of a prototype provide proof-of-concept.

2013

Abstract:- Planning under uncertainty is a research subject that has attracted big attention in the past few years. A planner that operates under uncertainty must take into consideration that actions may have several different outcomes, some of which may be more desirable than others. The first developed decision support planners (DSP), use conventional Operations Research (OR) tools such as decision theory for developing Courses of Actions (COAs). Besides the conventional planning methods, other planning methods based on more sophisticated OR techniques such as the Markov Decision Processes (MDP) and Partially Observable Markov Decision Processes (POMDP) have been considered recently as promising approaches to use in developing decision support planners. The OR oriented planners, which can be considered for planning military operations, will be classified into three categories: i) conventional planners (based on replanning), ii) planners using the MDP paradigm, and iii) planners us...

2000 Winter Simulation Conference Proceedings (Cat. No.00CH37165), 2000

A new approach to military planning and execution has been proposed. This approach seeks to merge planning and execution, and replaces reaction to events with anticipation of events. This paper presents a methodology for building an automated system to support Anticipatory Planning. A Plan Description is developed to manage the many tree-like branches that occur in planning and execution of an operation. A Planning Executive can use the differences between the plan and the actual operation to control the activities of Planners and Execution Monitors in anticipating future branches to the plan. At the heart of the system are inference mechanisms for determining branches in the plan and simulations for predicting future states. This methodology enables the development of a prototype Anticipatory Planning Support System for evaluation of this new approach to military planning and execution. This paper concentrates on the activities of the Execution Monitors and their use of simulation to support those activities.

2000

This paper argues that AI planning is a technology ripe for use on real world problems as shown by a number of current applications. An introduction is given to AI planning, and then followed by discussion of the successful application of this technology to generating operating procedures for chemical plants. A description is given of the methodology for developing planning domains and finally the results of its application to operating procedure synthesis are discussed.