Planning in the Tactical Air Domain
Michael Van Lent
John Laird1995
Sign up for access to the world's latest research
checkGet notified about relevant papers
checkSave papers to use in your research
checkJoin the discussion with peers
checkTrack your impact
Abstract
TAcAm-SoAR is a reactive system that uses recognition-driven problem solving to plan and generate behavior in the domain of tactical air combat simulation. Our current research efforts focus on integrating more deliberative planning and learning mechanisms into the system. This paper discusses characteristics of the domain that influence potential planning solutions, together with our approach for integrating reactive and deliberative
Related papers
A real-time planner for tactical air combat
8th Computing in Aerospace Conference, 1991
This paper discusses the design and implementation of a generative planner for the Pilot's Associate (PA) Program.* We focus on issues that are related to achieving real-time performance, particularly techniques for driving flow of control in the planner. Methods for efficiently organizing knowledge in the system are also considered.
Automated Intelligent Pilots for Combat Flight Simulation
Ai Magazine, 1999
TacAir-Soar is an intelligent, rule-based system that generates believable human-like" behavior for military simulations. The innovation of the application is primarily a matter of scale and integration. The system is capable of executing most of the airborne missions that the United States military ies in xed-wing aircraft. It accomplishes this by i n tegrating a wide variety o f i n telligent capabilities, including reasoning about interacting goals, reacting to rapid changes in real time or faster, communicating and coordinating with other agents including humans, maintaining situational awareness, and accepting new orders while in ight. The system is currently deployed at the Oceana Naval Air Station WIS-SARD, and its most dramatic use to date was in the Synthetic Theater Of War 1997, an operational training exercise consisting of 48 straight hours and approximately 700 xed-wing aircraft ights, all own by instances of the TacAir-Soar system.
Reasoning, Planning, and Goal Seeking for Small Combat Unit Modeling and Simulation
The current state of Modeling and Simulation (M&S) scenario creation is difficult, requiring too much time and effort on the part of Subject Matter Experts (SMEs) and analysts to produce scenarios that are sufficiently realistic for valid analysis, as well as a need for more realistic M&S agent behavior and decision making in simulation. Additionally, there also is a critical need for decision support tools to support Soldier and Small Unit (SU) decision making in the field. TSE is currently developing algorithms for the automation of combat operation simulation behaviors on the individual Soldier and SU level that may also be leveraged for Soldier and SU decision support tools to meet these critical Computer-Human Interaction (CHI) domain problems. TSE is researching and developing the Reasoning, Planning, and Goal-Seeking (RPGS) architecture , which is targeted at the next generation of constructive simulations requiring autonomous and intelligent agents that are capable of problem solving ; considering multiple courses of action; coordinating with friendly forces; following chain of command; and using Tactics, Techniques, and Procedures (TTPs) to guide operations. Intelligent agents guided by RPGS methodologies and algorithms will be able to execute complex tasks given mission goals, ini-tial/boundary conditions, constraints, and access to a battlespace knowledge base. TSE is creating a formal model of the Soldier and SU battlespace on which reasoning can be conducted. TSE will integrate two technical standards into the battlespace knowledge model; the Joint Consultation, Command, and Control Information Exchange Data Model (JC3IEDM) and the Coalition Battle Management Language (C-BML). This paper discusses the application of these standards and the design and development of a battlespace knowledge base and new RPGStechnologies.
MACBETH: a multi-agent constraint-based planner [autonomous agent tactical planner]
Proceedings. The 21st Digital Avionics Systems Conference, 2002
Implementing planning as tactical reasoning
1992
I n this p a p e r we present a system (called MRG) for the development of planners that have t o work in real-world, complex and unpredictable application domains. The idea underlying MRG is that domain independent problem solving architectures, instead of featuring powerful but fixed control mechanisms, should provide powerful and flexible tools for the definition of domain dependent control mechanisms. Complex strategies and control mechanisms are uniformly represented an MRG b y tactics, explicit data structures that can be reused, modified, reasoned about and executed. A t the m oment, MRG is being successfully used within a c o mplex real world application under development at IRS T.
Improving Air-to-Air Combat Behavior Through Transparent Machine Learning
2014
Training simulations, especially those for tactical training, require properly behaving computer generated forces (CGFs) in the opponent role for an effective training experience. Traditionally, the behavior of such CGFs is controlled through scripts. There are two main problems with the use of scripts for controlling the behavior of CGFs: (1) building an effective script requires expert knowledge, which is costly, and (2) costs further increase with the number of 'learning events' in a scenario (e.g. a new opponent tactic). Machine learning techniques may offer a solution to these two problems, by automatically generating, evaluating and improving CGF behavior. In this paper we describe an application of the dynamic scripting technique to the generation of CGF behavior for training simulations. Dynamic scripting is a machine learning technique that searches for effective scripts by combining rules from a rule base with predefined behavior rules. Although dynamic scripting was initially developed for artificial intelligence (AI) in commercial video games, its computational and functional qualities are also desirable in military training simulations. Among other qualities, dynamic scripting generates behavior in a transparent manner. Also, dynamic scripting's learning method is robust: a minimum level of effectiveness is guaranteed through the use of domain knowledge in the initial rule base. In our research, we investigate the application of dynamic scripting for generating behaviors of multiple cooperating aircraft in air-to-air combat. Coordination in multi-agent systems remains a non-trivial problem. We enabled explicit team coordination through communication between team members. This coordination method was tested in an air combat simulation experiment, and compared against a baseline that consisted of a similar dynamic scripting setup, without explicit coordination. In terms of combat performance, the team using the explicit team coordination was 20% more effective than the baseline. Finally, the paper will discuss the application of dynamic scripting in a practical setting.
Weasel: A Mixed-Initiative System to Assist in Military Planning
2002
This paper describes a mixed initiative planning system, called Weasel and its evaluation. Weasel was developed to assist military decision makers in the task of enemy course of action generation. The evaluation assesses Weasel's impact on the decision making performance of two potential user groups. When designing Weasel, we aimed to maximize benefits delivered by the software by focusing support functions on key areas in which expert analysts exhibited difficulties. We also aimed to minimize development, training and maintenance costs by designing displays to reflect expert analysts' representations and relying on human problem solving skills where possible. The goals of the evaluation are to 1) assess whether Weasel increases users' problem solving performance, where performance is measured in terms of overall solution quality, 2) identify the most appropriate user group by assessing whether domain intermediates are helped or hindered more than domain experts, and 3) identify possible negative consequences that may occur when Weasel generates a "brittle" solution. The issues explored in Weasel's development and evaluation are common to many mixed initiative systems.
Intelligent Agents for the Synthetic Battlefield: A Company of Rotary Wing Aircraft
1997
We have constructed a team of intelligent agents that perform the tasks of an attack helicopter company for a synthetic battlefield environment used for running largescale military exercises. We have used the Soar integrated architecture to develop: (1) pilot agents for a company of helicopters, (2) a command agent that makes decisions and plans for the helicopter company, and (3) an approach to teamwork that enables the pilot agents to coordinate their activities in accomplishing the goals of the company. This case study describes the task domain and architecture of our application, as well as the benefits and lessons learned from applying AI technology to this domain.
LDRD project final report : hybrid AI/cognitive tactical behavior framework for LVC
2012
This LDRD sought to develop technology that enhances scenario construction speed, entity behavior robustness, and scalability in Live-Virtual-Constructive (LVC) simulation. We investigated issues in both simulation architecture and behavior modeling. We developed pathplanning technology that improves the ability to express intent in the planning task while still permitting an efficient search algorithm. An LVC simulation demonstrated how this enables "one-click" layout of squad tactical paths, as well as dynamic re-planning for simulated squads and for real and simulated mobile robots. We identified human response latencies that can be exploited in parallel/distributed architectures. We did an experimental study to determine where parallelization would be productive in Umbra-based FOF simulations. We developed and implemented a data-driven simulation composition approach that solves entity class hierarchy issues and supports assurance of simulation fairness. Finally, we proposed a flexible framework to enable integration of multiple behavior modeling components that model working memory phenomena with different degrees of sophistication.
Goal‐Driven Autonomy for Responding to Unexpected Events in Strategy Simulations
2012
To operate autonomously in complex environments, an agent must monitor its environment and determine how to respond to new situations. To be considered intelligent, an agent should select actions in pursuit of its goals, and adapt accordingly when its goals need revision. However, most agents assume that their goals are given to them; they cannot recognize when their goals should change. Thus, they have difficulty coping with the complex environments of strategy simulations that are continuous, partially observable, dynamic, and open with respect to new objects. To increase intelligent agent autonomy, we are investigating a conceptual model for goal reasoning called Goal-Driven Autonomy (GDA), which allows agents to generate and reason about their goals in response to environment changes. Our hypothesis is that GDA enables an agent to respond more effectively to unexpected events in complex environments. We instantiate the GDA model in ARTUE (Autonomous Response to Unexpected Events), a domain-independent autonomous agent. We evaluate ARTUE on scenarios from two complex strategy simulations, and report on its comparative benefits and limitations. By employing goal reasoning, ARTUE outperforms an off-line planner and a discrepancy-based replanner on scenarios requiring reasoning about unobserved objects and facts and on scenarios presenting opportunities outside the scope of its current mission.
Related papers
Automated intelligent pilots for combat flight simulation : Special articles on innovative applications
The Ai Magazine, 1999
TacAir-Soar is an intelligent, rule-based system that generates believable "human-like" behavior for large scale, distributed military simulations. The innovation of the application is primarily a matter of scale and integration. The system is capable of executing most of the airborne missions that the United States military flies in fixed-wing aircraft. It accomplishes this by integrating a wide variety of intelligent capabilities, including real-time hierarchical execution of complex goals and plans, communication and coordination with humans and simulated entities, maintenance of situational awareness, and the ability to accept and respond to new orders while in flight. The system is currently deployed at the Oceana Naval Air Station WISSARD Lab and the Air Force Research Laboratory in Mesa, AZ. Its most dramatic use was in the Synthetic Theater of War 1997, which was an operational training exercise that ran for 48 continuous hours during which TacAir-Soar flew all U.S. fixed-wing aircraft.
Dynamic Scripting with Team Coordination in Air Combat Simulation
Traditionally, behavior of Computer Generated Forces (CGFs) is controlled through scripts. Building such scripts requires time and expertise, and becomes harder as the domain becomes richer and more life-like. These downsides can be reduced by automatically generating behavior for CGFs using machine learning techniques. This paper focuses on Dynamic Scripting (DS), a technique tailored to generating agent behavior. DS searches for an optimal combination of rules from a rule base. Under the assumption that intra-team coordination leads to more effective learning, we propose an extension of DS, called DS+C, with explicit coordination. In a comparison with regular DS we find that the addition of team coordination results in earlier convergence to optimal behavior. In addition, we achieved a performance increase of 20% against an unpredictable enemy. With DS+C, behavior for CGFs can be generated that is more effective since the CGFs act on knowledge achieved by coordination and the behavior converges more efficiently than under regular DS.
Learning by demonstration to support military planning and decision making
Proc. of the 21st …, 2009
While the concept of learning by demonstration has been around for many years, recent advances in artificial intelligence technology have led to a resurgence of work in the field. We describe the development and application of learning by demonstration technology to support user creation of automated procedures for a rich collaborative planning environment that is in widespread use by the U.S. Army. User feedback and evaluation results show that the technology can be used effectively by the target user community and that it has tremendous potential for improving the speed and quality of performance for a range of critical tasks.
Intelligent automated agents for tactical air simulation: A progress report
1994
knowledge about two classes of one-versus-This article reports on recent progress one (1-v-1) Beyond Visual Range (BVR) in the development of TacAir-Soar, an tactical air scenarios. In the non-jinking intelligent automated agent for tactical air bogey scenarios, one plane (the non-jinking simulation. This includes progress in bogey) is unarmed and maintains a straightexpanding the agent's coverage of the and-level flight path. The other plane is tactical air domain, progress in enhancing armed with long-range radar-guided, the quality of the agent's behavior, and medium-range radar-guided, and short-range progress in building an infrastructure for infrared-guided missiles. Its task is to set up research and development in this area. for a sequence of missile shots, at increasingly shorter ranges, until the non
Plan Recognition in Military Simulation: Incorporating Machine Learning with Intelligent Agents
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.
Automating the Acquisition of Tactical Knowledge for Military Missions
The Journal of Defense Modeling and Simulation: Applications, Methodology, Technology, 2005
It is widely accepted that acquisition of the knowledge behind military tactics has been one limiting factor in the development of computer generated forces (CGF) for training simulations. This has been addressed by several researchers with varying degrees of success. A system capable of building a knowledge base directly from a dialogue with a subjectmatter expert (SME) could significantly reduce the human effort involved in capturing the knowledge and representing it directly in the modeling language. Because of its highly modular and hierarchical nature, the context-based reasoning (CxBR) modeling paradigm lends itself very well to facilitating the knowledge acquisition process for tactical behaviors. This paper describes an investigation into using CxBR as the foundation for a system that creates a (partial) model of tactical behavior through an interactive process with an SME. Through a sequence of queries from the system, the SME is progressively asked to provide details about the contexts that compose the context-based model of the expert's tactical know-how. A prototype was built and evaluated. A comparison to the effort taken to manually develop a knowledge base is reported. We use the simulation of a non-trivial maritime military confrontation as the benchmark for the comparisons.
Artificial intelligence in air combat games
Computers & Mathematics with Applications, 1987
A general framework for the utilization of large numbers of optimal pursuit-evasion algorithms, as applied to air combat, is described. The framework is based upon and is driven by artificial intelligence concepts. The method employed involves the valuation of alternative tactical stratcgies and maneuvers through a goal system and pilot-derived expert data bases. The system is designed to display the most promising strategies to the pilot for a final decision. Two aspects of the concept above are described here: the general framework and a specific implementation for a synthetic method of flight and fire control system optimization. Details of the implementation, based on off-the-shelf hardware and a standard programming lanuage, are also given. Potential utilization of these concepts includes other areas as well: submarine warfare and satellite based weapon systems are two possible additional applications. Nonmilitary applications are air trafl~c control and optimal scheduling.
Thinking quickly: Agents for modeling air warfare
Lecture Notes in Computer Science, 1998
Within Air Operations Division of DSTO 1 intelligent agents are used to model the tactical decision making processes of pilots and ghter-controllers involved in air combat. One of the largest hurdles to be overcome by software engineers and analysts, when developing simulations of the air defence environment, is the acquisition of domain knowledge. Primarily the source of this knowledge is the pilots and other operational personnel, whose availability is limited and who have little experience with the design or development of simulation software. The adoption of agent oriented technologies has realized a number of signicant bene ts. High amongst these is the ability for operational air force personnel to become actively involved in the modi cation, design and development of these simulations. This involvement has dramatically reduced the time taken to prototype, test, and commission software and has resulted in simulations that have the con dence of the RAAF.
<title>Achieving realistic performance and decison-making capabilities in computer-generated air forces</title>
Modeling, Simulation, and Visualization of Sensory Response for Defense Applications, 1997
For a computer-generated force (CGF) system to be useful in training environments, it must be able to operate at multiple skill levels, exhibit competency at assigned missions, and comply with current doctrine. Because ofthe rapid rate cf change in Distributed Interactive Simulation (DIS) and the expanding set of performance objectives for any computergenerated force, the system must also be modifiable at reasonable cost and incorporate mechanisms for learning. Therefore, CGF applications must have adaptable decision mechanisms and behaviors and perform automated incorporation of past reasoning and experience into its decision process. The CGF must also possess multiple skill levels for classes of entities, gracefully degrade its reasoning capability in response to system stress, possess an expandable modular knowledge structure, and perform adaptive mission planning. Furthermore, correctly performing individual entity behaviors is not sufficient. Issues related to complex inter-entity behavioral interactions, such as the need to maintain formation and share information, must also be considered. The CGF must also be able to acceptably respond to unforeseen circumstances and be able to make decisions in spite ofuncertain information. Because ofthe need for increased complexity in the virtual battlespace, the CGF should exhibit complex, realistic behavior patterns within the battlespace.
Soar-RWA: Planning, teamwork, and intelligent behavior for synthetic rotary wing aircraft
1998
1. Abstract We have constructed a team of intelligent agents that perform the tasks of an Army attack helicopter company and a Marine transport/escort combined team for a synthetic battlefield environment used for running largescale military exercises.
Loading Preview
Sorry, preview is currently unavailable. You can download the paper by clicking the button above.