Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Physical Sciences and Mathematics
Developing Realistic Cooperative Behaviors For Autonomous Agents In Air Combat Simulation, Dean P. Hipwell
Developing Realistic Cooperative Behaviors For Autonomous Agents In Air Combat Simulation, Dean P. Hipwell
Theses and Dissertations
This thesis investigated, developed and implemented cooperative decision-making behaviors in an air combat simulation by using a knowledge-based system. Knowledge-based systems were well suited for this task because of built- in features such as inference engines and rule-based constructs. This thesis addresses the specific problem of generating autonomous forces for inclusion in the Advanced Research Projects Agency Distributed Interactive Simulation program. Existing autonomous forces implementations lacked flexibility, realistic behaviors, real-time planning and other features. The simulation system in this thesis addresses the problem of realistic behavior by modeling pilot decision processes rather than aircraft platforms. The system is based on …
Developing Realistic Behaviors In Adversarial Agents For Air Combat Simulation, George S. Hluck
Developing Realistic Behaviors In Adversarial Agents For Air Combat Simulation, George S. Hluck
Theses and Dissertations
This thesis describes an initial effort into creating a rule-based, reactive system for air combat simulation. This program uses the object-oriented extension of the expert system tool known as the C Language Integrated Production System CLIPS. This effort rose out of the need for creating and integrating semi-autonomous forces for the Distributed Interactive System DIS. This thesis describes the basic maneuvers a pilot uses in present air-to-air combat. The methodology includes the design decisions, knowledge-base development, phase architecture, and maneuver architecture development. The actual implementation of the selected architecture is described. This thesis also discusses the results of experimental runs …
Using Discovery-Based Learning To Prove The Behavior Of An Autonomous Agent, David N. Mezera
Using Discovery-Based Learning To Prove The Behavior Of An Autonomous Agent, David N. Mezera
Theses and Dissertations
Computer-generated autonomous agents in simulation often behave predictably and unrealistically. These characteristics make them easy to spot and exploit by human participants in the simulation, when we would prefer the behavior of the agent to be indistinguishable from human behavior. An improvement in behavior might be possible by enlarging the library of responses, giving the agent a richer assortment of tactics to employ during a combat scenario. Machine learning offers an exciting alternative to constructing additional responses by hand by instead allowing the system to improve its own performance with experience. This thesis presents NOSTRUM, a discovery-based learning DBL system …