• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.319-321
• /
• 2002

본 논문에서는 대표적인 3차원 일인칭 액션 게임(first-person action game)인 Unreal Tournament 게임과 이것에 기초한 Gamebots시스템을 소개하고, 이러한 환경에서 효과적으로 동작하는 지능형 NPC인 KGBot의 설계와 구현에 대해 설명한다. KGBot는 Gamebots시스템에서 하나의 보트 클라이언트(bot client)로 동작하면서 지형이 복잡한 3차원 가상환경 안에서 적들에 대항해 아군과 연합하여 특정 목표 지점(domination point)들을 찾아 점령하는 자율 NPC이다. KGBot는 BDI기반의 범용 에이전트 구조인 UM-PRS를 제어엔진으로 채용하고 있으며, 복잡한 행위들을 효과적으로 구현하기 위해 계충화된 지식베이스를 가지고 있다. 본 논문에서는 특히 제한적인 센서정보와 이동점(waypoint)에 기초하여 자신이 놓여진 월드의 전체지도를 작성하고 임의의 목적지까지 효율적인 이동경로를 계획할 수 있는 KGBot의 행위의 구현과 실험에 대해 설명한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.12
• /
• pp.5083-5088
• /
• 2010

An implementation of NPC AI(artifical intelligence) is similar with real world's flocking can increase fun factor of game. To this end, we design fish flocking patten of analyzed real world, implement using Ogre engine in this paper. To determine the usefulness of implemented fish flocking, we compare fish flocking in real world with implemented fish flocking. Implemented behavioral patterns of fish flocking show similar behavioral patterns of fish flocking in real world.

• Journal of Korea Game Society
• /
• v.17 no.4
• /
• pp.169-178
• /
• 2017

In order for the game industry to grasp the initiative of the global industry, it is time to positively need storytelling that can move the emotions of gamers over graphical appearance. Also, in the era of the 4th industrial revolution where the point of contact between virtual and reality spreads widely, it seems that the game character industry will rapidly emerge. Therefore, the author recognizes the importance of the character industry in the future, and based on the accumulated game research, he has identified 10 elements necessary for character storytelling. The ten elements are as follows. Design of life, design of race, design of occupation, design of PC and NPC, design of monster, design of personality, design of conflict, design of protagonist, design of external image, design of birth and death.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.2
• /
• pp.113-118
• /
• 2024

In this study, we designed and analyzed two main structures for effectively implementing the behavior of intelligent NPCs the Hierarchical Finite State Machine (HFSM) and the Behavior Tree, by creating experimental games. The HFSM was found to be efficient for complex interaction-centered actions where state changes and transitions are crucial, while the Behavior Tree was effective in dynamic environments where ease of modification and expansion are required for dynamic responses under various conditions. These structures were experimentally applied using the Unity engine to verify their efficiency. This study focused on the basic structure design and plans to apply these structures to an upcoming action-adventure escape game. The results of this research are expected to assist game developers in efficiently implementing intelligent NPCs, thereby contributing to the improvement of game quality and player satisfaction.

• Journal of Korea Game Society
• /
• v.6 no.2
• /
• pp.13-22
• /
• 2006

As the development of games continues, the intelligence of NPC is becoming more and more important. Nowadays, the NPCs of MMORPGS are not only capable of simple actions like moving and attacking players, but also utilizing variety of skills and tactics as human-players do. This study suggests a method that grants characters used in RPG(Role-Playing Game) an ability of training and adaptation using Neural network and Genetic Algorithm. In this study, a simple game-play model is constructed to test how suggested intellect characters could train and adapt themselves to game rules and tactics. In the game-play model, three types of characters(Tanker, Dealer, Healer) are used. Intellect character group constructed by NN and GA, and trained by combats against enemy character group constructed by FSM. As the result of test, the proposed intellect characters group acquire an appropriate combat tactics by themselves according to their abilities and those of enemies, and adapt change of game rule.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.135-138
• /
• 2004

MMORPG(Massively Multiplayer Online Role Playing Game)에서의 게임 서버는 모든 플레이어에게 게임 정보(오브젝트, NPC, 이벤트, 다른 플레이어들의 정보 등)를 실시간으로 전송해야 한다. 그러나, MMORPG에 참여하는 플레이어의 증가로 인해 전송되는 정보의 양이 많아지면 네트워크 전송 지연과 서버의 부담으로 인해 플레이어들간 정보 전송의 문제가 발생한다. 이를 해결하기 위해 본 논문에서는 AOI(Area Of Interest, 관심영역)를 이용하여 자원 이동 및 동기화를 효율적으로 관리할 수 있는 구성요소들과 적용방안을 제시한다.

• Journal of Korea Game Society
• /
• v.8 no.1
• /
• pp.79-90
• /
• 2008

This paper describes a motivation-based hierarchical behavior planning framework to allow autonomous agents to select adaptive actions in simulation game environments. The combined behavior planning system is formed by four levels of specification, which are motivation extraction, goal list generation, action list determination and optimization. Our model increases the complexity of virtual human behavior planning by adding motivation with sudden and cumulative attributes. The motivation selection by probability distribution allows NPC to make multiple decisions in certain situations in order to embody realistic virtual humans. Hierarchical goal tree enhances the effective reactivity. Optimizing for potential actions provides NPC with safe and satisfying actions to adapt to the virtual environment. A restaurant simulation game was used to elucidate the mechanism of the framework.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.01a
• /
• pp.267-269
• /
• 2016

본 논문에서는 언리얼 엔진4의 Behavior Tree(행동 트리)를 이용하여 NPC의 다양한 상태와 움직임을 가진 어드벤처 게임 AI를 설계 및 개발하였고, 그 효율성을 분석하였다. Behavior Tree는 상태와 행동을 계층적으로 나누어 AI의 행동을 결정하는 알고리즘으로 FSM(Finite State Machine, 유한상태기계)과 비교하여 유지보수와 행동 규칙 검증의 어려움을 해결하는 데 장점이 있음을 확인하였다.

• Journal of KIISE:Software and Applications
• /
• v.34 no.4
• /
• pp.368-376
• /
• 2007

How to represent the search space is as important as which search algorithm to use for finding natural-looking paths for moving NPC (non-player character) in computer games. Recently, various state space representation methods which have been developed for computer games are being used while A* algorithm dominates as the preferred search algorithm. These representation methods show some drawbacks such as the size of state space is too large, there is no guarantee for optimality, the path found is not natural-looking, and the generation of nodes and links is not automatic by depending on a level designer. In this paper the requirements for natural-looking paths are introduced and to find paths satisfying these requirements, the use of the generalized visibility graphs which is the extended version of the visibility graph in Robotics is proposed.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.01a
• /
• pp.189-192
• /
• 2012

게임 인공지능에서 경로 찾기는 매우 중요한 분야이다. 캐릭터나 NPC(Non Player Charater)가 목적지까지의 경로를 탐색하기 위해서는 복잡하게 구성된 게임 맵에서 오브젝트나 벽 등의 장애물을 회피하면서 가능한 최단 경로를 찾아야 한다. 기존의 일반적인 경로 찾기 알고리즘은 캐릭터의 움직임이 자유로운 간단한 게임 맵에서는 전역 최소해 탐색이 가능하다. 그러나 다양한 오브젝트 등이 배치된 큰 규모의 게임 맵에서는 캐릭터가 목적지까지의 경로를 탐색하는 과정에서 지역 최소해(Local Minima)로의 수렴이 발생함으로써 이를 탈피하는 것이 어렵고, 결국에는 목적지까지 도달하지 못하는 상황이 발생하게 된다. 본 논문에서는 이러한 기존 경로 찾기 알고리즘의 단점을 해결하기 위해 시뮬레이티드 어닐링 알고리즘을 제안하였다.