• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.295-297
• /
• 2002

컴퓨터 게임에서의 인공지능은 규칙 기반 추론을 기반으로 한 추론 엔진을 사용하고 있다. 이 규칙 기반 주론 엔진은 비교적 간단하고 구현하기 쉽지만 규칙이 몇 가지 되지 않는다는 것과 규칙 변화가 없는 단점으로 게임 플레이어가 그 규칙들을 쉽게 알아버린다는 문제가 있다. 게임 제작자들은 이런 단점을 극복하고자 게임 플레이어끼리 경쟁을 붙이기 위해서 베틀 넷 등 네트워크 쪽으로 그 단점을 보안하려고 하고 있다. 하지만 오히려 네트워크로의 발전은 더욱 더 인간에 가까운 게임 캐릭터 인공지능을 요구하게 되었으며 규칙 기반 추론 방법으로는 이러한 요구를 충족할 수 없기 때문에 새로운 방법이 필요하게 된 것이다 이 논문에서는 그 새로운 방법에 대한 대척으로 신경망 알고리즘과 유전자 알고리즘을 사용한 인공생명 방법론으로 그 해결책을 모색하려 한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.241-243
• /
• 2000

컴퓨터 게임에서의 인공지능은 규칙 기반 추론을 기반으로 한 추론 엔진을 사용하고 있다. 이 규칙 기반 추론 엔진은 비교적 간단하고 구현하기 쉽지만 규칙이 몇 가지 되지 않는다는 것과 규칙 변화가 없는 단점으로 게임 플레이어가 그 규칙들을 쉽게 알아버린다는 문제가 있다. 게임 제작자들은 이런 단점을 극복하고자 게임 플러이어끼리 경쟁을 붙이기 위해서 베틀넷 등 네트워크 쪽으로 그 단점을 보안하려고 하고 있다. 하지만 오히려 네트워크론의 발전은 더욱 더 인간에 가까운 게임 캐릭터 인공지능을 요구하게 되었으며 규칙 기반 추론 방법으로는 이러한 요구를 충족할 수 없기 때문에 새로운 방법이 필요하게 된 것이다. 이 논문에서는 그 새로운 방법에 대한 대책으로 신경망 알고리즘과 유전자 알고리즘을 사용한 인공생명 방법론으로 그 해결책을 모색해려 한다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.3 s.303
• /
• pp.17-28
• /
• 2005

Recently intelligent characters in computer games have been an important element more and more because they continually stimulate gamers' interests. As a typical method for implementing such intelligent characters, neural networks have been used for training action patterns of opponent's characters and game rules. However, some of the game rules can be abruptly changed and action properties of garners in on-line game environments are quite different according to gamers. In this paper, we address how a neural network adapts to those environmental changes. Our adaptation solution includes two components: an individual adaptation mechanism and a group adaptation mechanism. With the individual adaptation algorithm, an intelligent character steadily checks its game score, assesses the environmental change with taking into consideration of the lastly earned scores, and initiates a new learning process when a change is detected. In multi-user games, including massively multiple on-line games, intelligent characters confront diverse opponents that have various action patterns and strategies depending on the gamers controlling the opponents. The group adaptation algorithm controls the birth of intelligent characters to conserve an equilibrium state of a game world by using a genetic algorithm. To show the performance of the proposed schemes, we implement a simple fighting action game and experiment on it with changing game rules and opponent characters' action patterns. The experimental results show that the proposed algorithms are able to make intelligent characters adapt themselves to the change.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2009.01a
• /
• pp.159-162
• /
• 2009

캐릭터가 발전하는 이유 중 사람의 감정을 충족시키려는 욕구는 움직이지 않은 캐릭터에게 반영되어 인터랙티브 캐릭터로 발전되었고 현재 인터랙티브 캐릭터는 사람들의 많은 관심을 받고 있다. 그 중 최근에는 기존의 인터랙티브 캐릭터인 타마고치와 포스트 팻의 장점을 가져온 휴대용 게임기기인 NDSL의 게임 '닌텐독스'가 등장했다. '닌텐독스'는 터치스크린, 마이크와 같은 체감형 인터페이스를 사용하고 있다. 또한 사람들에게 친근한 강아지라는 캐릭터를 사용하여 사람들이 캐릭터를 애완동물과 비슷하게 느끼고 감정을 교류하게끔 유도하고 있다. 하지만 인터랙티브 캐릭터들이 감정을 표현하기에는 기존의 인공지능으로는 해결할 수 없기 때문에 인공감정을 사용하여 인터랙티브 캐릭터의 감정을 표현하도록 제안한다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.6
• /
• pp.69-80
• /
• 2004

This paper proposes a method to learn action patterns of opponent characters for intelligent characters. For learning action patterns, intelligent characters learn the past actions as well as the current actions of opponent characters. Therefore, intelligent characters react more properly than ones without the knowledge on action patterns. In addition, this paper proposes a method to learn moving actions whose fitness is hard to evaluate. To evaluate the performance of the proposed algorithm, we experiment with four repeated action patterns in a game similar to real games. The results show that intelligent characters learn the optimal actions for action patterns and react properly against to random action opponent characters. The proposed method can be applied to various games in which characters confront each other, e.g. massively multiple of line games.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05b
• /
• pp.1063-1066
• /
• 2003

지능형 게임 개발을 위하여 게임 이론의 정의, 게임의 구성요소, 전략적 게임의 분석을 통해 게임에 대한 배경 환경을 살펴보고, 보다 사실적 느낌 전달을 위한 게임 애니메이션과 게임에 적용되는 인공지능 기술을 퍼지 이론, 뉴럴네트웍으로 분류하여 적용 현황을 살펴보았다. 즉 게임처럼 수학적 표현이 어려운 경우 해결점을 퍼지 이론에서, 캐릭터의 움직임을 제어하는 퍼지 Rule Base를 찾아내는 연구를 신경망 인공지능을 통해 해결하는 과정을 살펴보고 국부해의 단점을 갖는 신경망 인공지능의 불투명성 해결 방법을 유전자 알고리즘에서 찾았다. 결론적으로 게임에서 이루어지는 물리적 특성인 충돌에 대한 충돌검사 알고리즘, 충돌반응에 대한 최적화를 유전자 알고리즘을 적용하여 해결하였다.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.449-456
• /
• 2006

This paper proposes intelligent characters for fighting action games to which energy points are applied for more realistic implementation than those of previous researches. The intelligent characters decide their actions in consideration of their energy level as well as a current action, the step of the action, the distance, and past actions of opponent characters that were used in existing intelligent ones. We used two types of energy, HP(Health Point) and MP(Mana Point) that were frequently employed in recent on-line games. We experimented with proposed intelligent characters to investigate whether the intelligent characters learn proper actions and cope with opponent characters in consideration of their energy levels. Experimental results showed that the intelligent characters reacted with the best actions to obtain high score if their energy is sufficient, Otherwise, they did the actions to(that?) recharge their energy. From this observation, we could conclude that the proposed intelligent characters worked well and did effective actions in consideration of the their energy.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.4
• /
• pp.383-389
• /
• 2004

This paper proposes a method to provide intelligence for characters in fighting action games by using a neural network. Each action takes several time units in general fighting action games. Thus the results of a character's action are not exposed immediately but some time units later. To design a suitable neural network for such characters, it is very important to decide when the neural network is taught and which values are used to teach the neural network. The fitness of a character's action is determined according to the scores. For learning, the decision causing the score is identified, and then the neural network is taught by using the score change, the previous input and output values which were applied when the decision was fixed. To evaluate the performance of the proposed algorithm, many experiments are executed on a simple action game (but very similar to the actual fighting action games) environment. The results show that the intelligent character trained by the proposed algorithm outperforms random characters by 3.6 times at most. Thus we can conclude that the intelligent character properly reacts against the action of the opponent. The proposed method can be applied to various games in which characters confront each other, e.g. massively multiple online games.

• The KIPS Transactions:PartB
• /
• v.13B no.1 s.104
• /
• pp.15-20
• /
• 2006

This paper describes research on intelligent game character through performance enhancements of physics engine in computer games. The algorithm that recognizes the physics situation uses momentum back-propagation neural networks. Also, we present an experiment and its results, integration methods that display optimum performance based on the physics situation. In this experiment on integration methods, the Euler method was shown to produce the best results in terms of fps in a simulation environment with collision detection. Simulation with collision detection was shown similar fps for all three methods and the Runge-kutta method was shown the greatest accuracy. In the experiment on physics situation recognition, a physics situation recognition algorithm where the number of input layers (number of physical parameters) and output layers (destruction value for the master car) is fixed has shown the best performance when the number of hidden layers is 3 and the learning count number is 30,000. Since we tested with rigid bodies only, we are currently studying efficient physics situation recognition for soft body objects.

• Journal of Korea Game Society
• /
• v.8 no.1
• /
• pp.91-101
• /
• 2008

Most designers use professional 3D animation tools such as 3DS MAX to manually create animation. This manual method requires a great deal of time and efforts, and does not allow animation characters to interact with one another. In this paper, we design an AI middleware of form as 3DS MAX plug-in to solve these issues. We present an AI expression structure and internal processing method for this middleware, and the method for creating AI character's structure. It creates AI character's structure by drawing figures and lines for representing AI elements. For experiment, we have produced same animations with the traditional method and our method, and measured the task volume in both methods. This result verifies that the task volume is similar or higher than the traditional method in small-scale tasks, but up to 43% of the task volume is reduced in large-scale tasks. Using the method proposed in this paper, we see that characters in an animation interact each other, and task volume in large-scale tasks are reduced.