Agents are self-contained objects within a software model that are capable of autonomously interacting with the environment and with other agents. Basing a model around agents (building an agent-based model, or ABM) allows the user to build complex models from the bottom up by specifying agent behaviors and the environment within which they operate. This is often a more natural perspective than the system-level perspective required of other modeling paradigms, and it allows greater flexibility to use agents in novel applications. This flexibility makes them ideal as virtual laboratories and testbeds, particularly in the social sciences where direct experimentation may be infeasible or unethical. ABMs have been applied successfully in a broad variety of areas, including heuristic search methods, social science models, combat modeling, and supply chains. This tutorial provides an introduction to tools and resources for prospective modelers, and illustrates ABM flexibility with a basic war-gaming example.

The Advanced Framework for Simulation, Integration and Modeling (AFSIM) is an engagement and mission level simulation environment written in C++ originally developed by Boeing and now managed by the Air Force Research Laboratory (AFRL). AFSIM was developed to address analysis capability shortcomings in existing legacy simulation environments as well as to provide an environment built with more modern programming paradigms in mind. AFSIM can simulate missions from subsurface to space and across multiple levels of model fidelity. The AFSIM environment consists of three pieces of software: the framework itself which provides the backbone for defining platforms and interactions, an integrated development environment (IDE) for scenario creation and scripting, and a visualization tool called VESPA. AFSIM also provides a flexible and easy to use agent modeling architecture which utilizes behavior trees and hierarchical tasking called the Reactive Integrated Planning aRchitecture (RIPR). AFSIM is currently ITAR restricted and AFRL only distributes AFSIM within the DoD community. However, work is under way to modify the base architecture facilitating the maintenance of AFSIM versions across multiple levels of releasability.

My Summer 2014 internship consisted of contributing to the Autonomy for Air Combat Missions (ATACM) project at the Knexus Research Corporation, a largely collaborative effort involving the Naval Research Lab (NRL), the Naval Air Systems Command (NAVAIR) and the Air Force Research Lab (AFRL). The ATACM project’s main purpose is to create an autonomous Unmanned Aerial Vehicle (UAV) capable of flying alongside a human pilot in BVR (Beyond Visual Range) air combat missions. My job as part of Knexus, subcontracted under NRL, consisted of working on the reasoning systems for the UAV, with the label the Tactical Battle Manager (TBM). NAVAIR and AFRL were responsible for interfacing the TBM with their respective simulators and providing domain specific knowledge in the realm of air combat. My contribution to the ATACM project took the form of a predictor, under the name PEPR (the Planned Ex-pected State Predictor), for use in the goal reasoning components of the TBM.

SAIC公司开发了RAVE系统，跟AFSIM和ModelCenter整合起来，构成了导弹防御系统的仿真平台。

Advanced Framework for Simulation, Integration and Modeling (AFSIM)