Date of Award
Master of Science in Computer Science
Department of Electrical and Computer Engineering
Gary B. Lamont, PhD.
The real time strategy (RTS) environment is a strong platform for simulating complex tactical problems. The overall research goal is to develop artificial intelligence (AI) RTS planning agents for military critical decision making education. These agents should have the ability to perform at an expert level as well as to assess a players critical decision-making ability or skill-level. The nature of the time sensitivity within the RTS environment creates very complex situations. Each situation must be analyzed and orders must be given to each tactical unit before the scenario on the battlefield changes and makes the decisions no longer relevant. This particular research effort of RTS AI development focuses on constructing a unique approach for tactical unit positioning within an RTS environment. By utilizing multiobjective evolutionary algorithms (MOEAs) for finding an \optimal" positioning solution, an AI agent can quickly determine an effective unit positioning solution with a fast, rapid response. The development of such an RTS AI agent goes through three distinctive phases. The first of which is mathematically describing the problem space of the tactical positioning of units within a combat scenario. Such a definition allows for the development of a generic MOEA search algorithm that is applicable to nearly every scenario. The next major phase requires the development and integration of this algorithm into the Air Force Institute of Technology RTS AI agent. Finally, the last phase involves experimenting with the positioning agent in order to determine the effectiveness and efficiency when placed against various other tactical options. Experimental results validate that controlling the position of the units within a tactical situation is an effective alternative for an RTS AI agent to win a battle.
DTIC Accession Number
Ball, Christopher D., "A Multi-Objective Approach to Tactical Maneuvering Within Real Time Strategy Games" (2016). Theses and Dissertations. 457.