Games have been an important tool for motivating undergraduate students majoring in computer science and engineering. However, it is difficult to build an entire game for education from scratch, because the task requires high-level programming skills and expertise to understand the graphics and physics. Recently, there have been many different game artificial intelligence (AI) competitions, ranging from board games to the state-of-the-art video games (car racing, mobile games, first-person shooting games, real-time strategy games, and so on). The competitions have been designed such that participants develop their own AI module on top of public/commercial games. Because the materials are open to the public, it is quite useful to adopt them for an undergraduate course project. In this paper, we report our experiences using the Angry Birds AI Competition for such a project-based course. In the course, teams of students consider computer vision, strategic decision-making, resource management, and bug-free coding for their outcome. To promote understanding of game contents generation and extensive testing on the generalization abilities of the student's AI program, we developed software to help them create user-created levels. Students actively participated in the project and the final outcome was comparable with that of successful entries in the 2013 International Angry Birds AI Competition. Furthermore, it leads to the development of a new parallelized Angry Birds AI Competition platform with undergraduate students aiming to use advanced optimization algorithms for their controllers.
Recently, the production of big games is expensive, and it is very difficult to gain attention from players. Although gamers' expectations are very high, game companies' resources are limited to maximize the quality of the games. Mod (game content editing) can be one of the solutions to this problem. It allows gamers satisfy themselves by creating and sharing their Mod. It increases the gamers' playing time and sales. However, few users have the knowledge and special ability to create Mods, so most gamers just use a Mod made by someone else. In this article, we propose a method to generate contents for 3D game objects and textures. Our method enables the construction of a three-dimensional object using the grown building footprints by the L-system or the combination of polygons, and it also provides a web-based interactive genetic algorithm interface to users for changing shapes. Furthermore, it also provides a function to evolve various texture images from an original texture file. We demonstrated the possibility of our systems using The Open Racing Car Simulator (TORCS). These results reveal that three-dimensional objects and textures can be created from our method by amateur users.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.