• Journal of Digital Contents Society
• /
• v.10 no.4
• /
• pp.615-623
• /
• 2009

Games are usually composed with several units such as monsters, weapons etc.. There are often intransitive relationships between units, like the one among rock, scissors and paper. Intransitive relationships guarantee the variation of strategy choices while playing. But AIs in many games have been ignored intransitive relationships because decision making with those relationships is complex to model. This paper suggests how to use intransitive relationships to modify influence map. With the modified influence map game AI can make a different decision to win the game. With path-finding technique, this paper shows that the modified influence map makes AI's behaviors better.

• Journal of Internet of Things and Convergence
• /
• v.10 no.3
• /
• pp.49-55
• /
• 2024

This study was conducted with the purpose of developing a checklist of questions to measure middle school students' AI capabilities. To achieve the goal of the study, literature analysis and question development Delphi survey were used. For literature analysis, two domestic studies, five international studies, and the Ministry of Education's curriculum report were collected through a search. The collected data was analyzed to construct core competency measurement elements. The core competency measurement elements are understanding of artificial intelligence (5 elements), artificial intelligence thinking (5 elements), utilization of artificial intelligence (4 elements), artificial intelligence ethics (6 elements), and artificial intelligence social-emotion (6 elements). elements). Considering the knowledge, skills, and attitudes of the constructed measurement elements, 31 questions were developed. The developed questions were verified through the first Delphi survey, and 10 questions were revised according to the revision opinions. The validity of 31 questions was verified through the second Delphi survey. The checklist items developed in this study are measured by teacher evaluation based on performance and behavioral observations rather than a self-report questionnaire. This has the implication that the level of reliability of measurement results increases.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.3
• /
• pp.259-265
• /
• 2006

Learning and emotions are very important parts to implement intelligent robots. In this paper, we implement intelligent virtual character based on reinforcement learning which interacts with user and have internal emotion model. Virtual character acts autonomously in 3D virtual environment by internal state. And user can learn virtual character specific behaviors by repeated directions. Mouse gesture is used to perceive such directions based on artificial neural network. Emotion-Mood-Personality model is proposed to express emotions. And we examine the change of emotion and learning behaviors when virtual character interact with user.

• Journal of KIISE:Software and Applications
• /
• v.28 no.7
• /
• pp.493-500
• /
• 2001

사이버 캐릭터(이하 캐릭터라 함)는 가사 환경에서 동작하는 인공 생명체이다. 캐릭터는 기본적으로 센서 시스템과 동작 제어 시스템으로 구성된다. 캐릭터는 센서 시스템을 통하여 가상 환경과 실세계를 인지하고, 사용자의 명령을 인식한다. 동작 제어 시스템은 과제를 수행하기 위한 계획을 수립하고, 적합한 행위를 선택하여 캐릭터를 동작시킨다. 사용자는 캐릭터와의 상호작용과 더불어 지능적인 행동을 직접 경험함으로써 가상 환경 속에서 현실감을 느끼게 된다. 본 논문에서는 현실감 있는 캐릭터와 가상 환경의 구축을 위한 3차원 그래픽 모델, 애니메이션 및 동작 제어 시스템, 실시간 영상 분석 시스템에 대하여 설명하고, 본 연구실에서 개발한 실험 결과를 소개한다.

• Journal of Korea Multimedia Society
• /
• v.25 no.2
• /
• pp.432-439
• /
• 2022

This paper introduces deliberative behavior tree using utility theory. The proposed approach combine the strengths of behavior trees and utility theory to implement complex behavior of AI agents in an easier and more concise way. To achieve this goal, we devised and implemented three types of additional behavior tree nodes, which evaluate utility values of its own node or its subtree while traversing and selecting its child nodes based on the evaluated values. In order to validate our approach, we implemented a sample scenario using conventional behavior tree and our proposed deliberative tree respectively. And then we compared and analyzed the simulation results.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.834-837
• /
• 2020

CNN(Convolution Neural Network)은 합성곱(Convolution)을 이용해서 시각적 이미지를 분석하는데 사용되는 인공지능 기술이다. 본 논문에서는 CNN을 이용한 실시간 심리 상담 서비스에 대해 논한다. 상담 서비스에 심리학과 CNN을 접목시킴으로써 내담자의 사진을 심리학적 비언어 행동을 기반으로 분석하여 내담자의 예상 심리를 파악하고, 유의미한 상담 자료를 생성해 상담의 질을 향상시킬 수 있도록 한다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.25 no.1
• /
• pp.7-14
• /
• 2024

This study conducted a comparative experiment on the continuity of time series data and the classification performance of artificial intelligence models. In BCI research using EEG signals, the performance of behavior and thought classification improved as the continuity of the data decreased. In particular, LSTM achieved a high performance of 0.8728 on data with low continuity, and DNN showed a performance of 0.9178 when continuity was not considered. This suggests that data without continuity may perform better. Additionally, data without continuity showed better performance in task classification. These results suggest that BCI research based on EEG signals can perform better by showing various data characteristics through shuffling rather than considering data continuity.

• Journal of the Korea Society for Simulation
• /
• v.29 no.1
• /
• pp.39-46
• /
• 2020

The utilization of artificial intelligence (AI) in the engagement has been a key research topic in the defense field during the last decade. To pursue this utilization, it is imperative to acquire a realistic simulation to train an AI engagement agent with a synthetic, but realistic field. This paper is a case study of training an AI agent to operate with a hardware realism in the air-warfare dog-fighting. Particularly, this paper models the pursuit of an opponent in the dog-fighting setting with a gun-only engagement. In this context, the AI agent requires to make a decision on the pursuit style and intensity. We developed a realistic hardware simulator and trained the agent with a reinforcement learning. Our training shows a success resulting in a lead pursuit with a decreased engagement time and a high reward.

• Journal of Advanced Navigation Technology
• /
• v.23 no.4
• /
• pp.296-301
• /
• 2019

Artificial intelligence is closely linked to our real lives, leading innovation in various fields. Especially, as a means of transportation possessing artificial intelligence, autonomous unmanned vehicles are actively researched and are expected to be put into practical use soon. Autonomous cars and autonomous unmanned aerial vehicles are required to equip accurate navigation system so that they can find out their present position and move to their destination. At present, the navigation of transportation that we operate is mostly dependent on GPS. However, GPS is vulnerable to external intereference. In fact, since 2010, North Korea has jammed GPS several times, causing serious disruptions to mobile communications and aircraft operations. Therefore, in order to ensure safety in the operation of the autonomous unmanned vehicles and to prevent serious accidents caused by the intereference, rapid situation judgment and countermeasure are required. In this paper, based on big data and machine learning technology, we propose a countermeasure system for GPS interference that supports decision making by applying John Boyd's OODA loop cycle (detection - direction setting - determination - action).

• Journal of IKEEE
• /
• v.25 no.2
• /
• pp.337-343
• /
• 2021

Deep reinforcement learning is an artificial intelligence algorithm that enables learners to select optimal behavior based on raw and, high-dimensional input data. A lot of research using this is being conducted to create an optimal movement path of a mobile robot in an environment in which obstacles exist. In this paper, we selected the Dueling Double DQN (D3QN) algorithm that uses the prioritized experience replay to create the moving path of mobile robot from the image of the complex surrounding environment. The virtual environment is implemented using Webots, a robot simulator, and through simulation, it is confirmed that the mobile robot grasped the position of the obstacle in real time and avoided it to reach the destination.