• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.644-649
• /
• 2021

Self-Imitation Learning is a simple off-policy actor-critic algorithm that makes an agent find an optimal policy by using past good experiences. In case that Self-Imitation Learning is combined with reinforcement learning algorithms that have actor-critic architecture, it shows performance improvement in various game environments. However, its applications are limited to reinforcement learning algorithms that have actor-critic architecture. In this paper, we propose a method of applying Self-Imitation Learning to Deep Q-Network which is a value-based deep reinforcement learning algorithm and train it in various game environments. We also show that Self-Imitation Learning can be applied to Deep Q-Network to improve the performance of Deep Q-Network by comparing the proposed algorithm and ordinary Deep Q-Network training results.

• Journal of Korea Multimedia Society
• /
• v.23 no.10
• /
• pp.1318-1330
• /
• 2020

The purpose of this study is to identify the effect of the innovation characteristics that AI Elderly Care Robots have on elderly consumers and to verify the acceptance or mediated resistance by the elderly of the innovation characteristics. Research was conducted throughout this study of the characteristics of the elderly so that the study results could contribute to the improvement of the quality and manufacture of AI Elderly Care Robots by lowering the psychological resistance of the elderly. Survey questions were answered by senior citizens aged 65 and older. The SPSS25 and AMOS22 programs were used for analysis. The analysis confirmed that innovation resistance has a significant mediated effect on the characteristics of elderly consumers and their willingness to accept the innovation characteristics of the AI Elderly Care Robots. Through this study, Ram's innovation resistance model has been verified empirically and it is estimated that by considering the specificities of elderly consumers and using the information to contribute to the development and modification of AI Elderly Care Robots will increase the willingness of the elderly to accept the innovation characteristics of the AI Elderly Care Robots.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.3
• /
• pp.375-381
• /
• 2005

Usually genetic algorithms are used to design optimal system. However the performance of the algorithm is determined by the fitness function and the system environment. It is expected that a co-evolutionary algorithm, two populations are constantly interact and co-evolve, is one of the solution to overcome these problems. In this paper we propose three types of co-evolutionary algorithm to solve GA-Hard problem. The first model is a competitive co-evolutionary algorithm that solution and environment are competitively co-evolve. This model can prevent the solution from falling in local optima because the environment are also evolve according to the evolution of the solution. The second algorithm is schema co-evolutionary algorithm that has host population and parasite (schema) population. Schema population supply good schema to host population in this algorithm. The third is game model-based co-evolutionary algorithm that two populations are co-evolve through game. Each algorithm is applied to visual servoing, robot navigation, and multi-objective optimization problem to verify the effectiveness of the proposed algorithms.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.1-6
• /
• 2023

Uncanny Valley is a theory proposed by Japanese robot engineer Masahiro Mori in 1970, and refers to the point where the likability drops sharply when the appearance of a robot becomes very similar to a human being without a fully equipped robot. In this study, the theory of existing literature, related papers, and experimental data were analyzed to examine the Uncanny Valley effect that affects character design. The purpose of this study is to analyze whether the Uncanny Valley effect is applied to modeling virtual characters distributed in the Unreal Engine Marketplace. To this end, 15 characters were selected based on the similarity with humans in the Marketplace of the Unreal Engine, and similarity with humans and likability were investigated and analyzed. As a result of the experiment, it was confirmed that the Uncanny Valley effect was similarly applied to virtual character modeling, and through this, guidelines for the use of characters by indie game developers or individual developers using Unreal engines were presented. In addition, through result analysis, we tried to examine the direction to be pursued when designing characters.

• Journal of Korea Game Society
• /
• v.10 no.6
• /
• pp.115-124
• /
• 2010

In the beginning brain waves were used for monkeys to control robot arm with neural activity. In recent years there are research that measured brain waves are used for the control of programs which monitor the progression of dementia or enhance of attention in children diagnosed with Attention Deficit Hyperactivity Disorder (ADHD). Moreover, low-price devices that can be used as a game control interface have become available. One of the problems associated with control using brain waves is that the mean amplitude, mean wavelength, and mean vibrational frequency of the brain waves differ from individual to individual. This paper attempts to propose a method to normalize measured brain waves using normal distribution and calculate the waveforms that can be used in controlling games. For this, a framework in which brain waves are converted in seven stages has been suggested. In addition, the estimation process in each stage has been described. In an experiment the waveforms of two subjects have been compared using the proposed method in the BCI English word learning program. The level of similarity between two subjects' waveforms has been compared with correlation coefficient. When the proposed method was applied, both meditation and concentration increased by 13% and 8%, respectively. Because the proposed regularization method is converted into a waveform fit for control functions by reducing personal characteristics reflected in the brain waves, it is fitting for application programs such as games.

• The Journal of Society for e-Business Studies
• /
• v.25 no.4
• /
• pp.143-154
• /
• 2020

With the increasing trend of making manufacturing system intelligent and autonomous, the introduction of robot-assist automation, like machine tending system for automated operation of CNC machine tools, is being actively carried out at many industrial sites. Most important part of this intelligent system to install machine tending system, is interface programming between the CNC machine tools and the industrial robot. Despite this importance, however, the machine tending system has many setup problems. it is necessary for difficult re-program of both controllers whenever a new CNC machine tool or robot is introduced. And, the helps of external engineers is required even though trivial changes due to the complex structure of the machine tending system. Authors of this paper introduces the integrated system of the interface between heterogeneous CNC machine tools and industrial robots. In addition, the digital twin implemented inside the machine tool controller enable shop-floor operators to change the interface programming easily. To implement this system, an integrated development environment for 1) an intelligent HMI platform that provide standardized interfaces to heterogeneous CNC machine tools and 2) a robot platform developing application software of various robots, was established. For easy un-tact environment, this paper explain the development of 3) a game-engine based web program of controlling and monitoring machine tending system remotely.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.2
• /
• pp.45-50
• /
• 2017

This paper proposes a novel resource allocation scheme which allows to guarantee the user-perceived service quality for various high-quality mobile multimedia service such as interactive game, tactile internet service, remote emergency medical service or remote disaster handling robot control to a certain level in the mobile networks. In our proposed scheme, Mean Opinion Score(MOS), which represents the degree of user satisfaction for perceived quality, is determined based on the delay limit allowable to each service. Moreover resources are allocated in consideration of this MOS. Simulation results show that our proposed scheme can decrease the outage probability in comparison with existing schemes Moreover it can increase the total throughput as well.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.327-328
• /
• 2008

로봇과 상호 작용하기 위한 수단으로 손동작 인식 시스템이 많이 사용되고 있으며, 본 논문에서는 손에 부가적인 장치를 장착하지 않은 상태에서 영상 처리를 이용하여 손동작을 인식하는 시스템을 구현하였다. 먼저 로봇은 영상 입력 장치로써 웹캠을 사용하고, 손 영상을 스킨 컬러를 바탕으로 영상 처리를 하여 추출해내고, 그 이미지를 분석하여 그 모양이 가위인지 바위인지 보인지 인식한다. 가위 바위 보 게임을 위하여 로봇이 손동작을 표현할 수 있도록 손가락이 네 개인 손을 설계 및 구현하였다. 이때, 기존의 와이어 방식이 아닌 제어를 이용한 손가락을 설계하였고, 각각의 손가락이 독립적으로 제어될 수 있기 때문에 가위 바위 보의 손동작을 표현할 수 있다. 그리고 음성 인식을 이용하여 사람과 동시에 가위 바위 보 중 하나를 결정한 후 표현하기 때문에 가위 바위 보 게임이 가능하다. 뿐만 아니라 로봇이 승패도 알 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.11a
• /
• pp.465-468
• /
• 2005

강화 학습이란 개체가 동적인 환경에서 시행착오를 통해 자신의 최적 행동을 찾아내는 기법이다. 특히 Q-learning과 같은 비(非)모델 기반의 강화학습은 사전에 환경에 대한 모델을 필요로 하지 않으며, 다양한 상태와 행동들을 충분히 경험한다면 최적의 행동 전략에 도달할 수 있으므로 여러 분야에 적용되고 있다. 본 논문에서는 로봇의 행동을 효율적으로 제어하기 위하여 Q-learning을 이용하였다. 로봇 축구 시스템은 공과 여러 대의 로봇이 시시각각 움직이는 시변 환경이므로 모델링이 상당히 복잡하다. 공을 골대 가까이 보내는 것이 로봇 축구의 목표지만 때로는 공을 무조건 골대 방향으로 보내는 것보다 더 효율적인 전략이 있을 수도 있다. 어떤 상황에서 어떤 행동을 하여야 장기적으로 보았을 때 더 우수한지 학습을 통해 로봇 스스로가 판단해가도록 시스템을 구현하고, 학습된 결과를 분석한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37C no.11
• /
• pp.1094-1103
• /
• 2012

Recently, software industry regarding national defense increases system development of distributed simulation system of M&S based to overcome limit of resource and expense. It is one of key technologies for offering of mutual validation among objects and reuse of objects which are discussed for developing these systems. RTI, implementation of HLA interface specification as software providing these technologies uses Federation Object Model for exchanging information with joined federates in the federation and each federate has a characteristic that is supposed to have identical FOM in the federation. This technology is a software which is to provide the core technology which was suggested by the United state's military M&S standard framework. Simulator, virtual simulation, and inter-connection between military weapons system S/W which executes on network which is M&S's core base technology, and it is a technology which also can be used for various inter-connection between S/W such as game and on-line phone. These days although RTI is used in military war game or tactical training unit field, there is none in Korea. Also, it is used in mobile-game, distribution game, net management, robot field, and other civilian field, but the number of examples are so small and informalized. Through this developing project, we developed the core technique and RTI software and provided performance of COTS level to improve communication algorithms.