Date of Award

2017

Publisher

North Dakota State University

Document Type

Master's Paper

Degree Awarded

Master of Science (MS)

Program

Computer Science

Department

Computer Science

College

Engineering

Faculty Advisor

Ludwig, Simone

Description

This paper deals with current an existing evolutionary algorithm used in procedural terrain generation content for video games which is gaining interest to lessen the development costs and meet desired user requirements in creating levels, maps, and 3D terrain. Our approach demonstrates the advantages of a two-level interactive parent selection mechanism with seamless patching done during the generation process, using genetic algorithm and evolutionary strategies. Genetic algorithm is applied with crossover and mutation to evolve the layout of the patches. On the other hand, evolutionary strategy is also evaluated. We have conducted a series of runs, resulting in visually comparing the terrains evolved through genetic and evolutionary strategy to find the best fitness for the generated terrains. Since the evolution is done through a two-level interactive process, the final selected terrains from the genetic and the evolutionary approach are evaluated by comparing the features that meet the user’s expectations.

Rights

NDSU Policy 190.6.2

Rights Link

https://www.ndsu.edu/fileadmin/policy/190.pdf

Handle Identifier

https://hdl.handle.net/10365/25948

Download

Share

COinS