• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• Journal of the Korea Computer Graphics Society
• /
• v.14 no.3
• /
• pp.19-30
• /
• 2008

Fluid simulation for computer graphics is a field of generating the realistic movements of water, smoke, fire, explosion, sand and related phenomena to be used in motion pictures and video games. In this paper we review the fluid simulation technologies and present a trend analysis for the simulation methods used in the recent movies. First of all, for this purpose, the two methods that are most widely used for fluid simulation are explained as well as their technical issues. These two methods are classified into Eulerian grid-based and Lagrangian particle-based approaches. Next, focusing on the achievements of the scientists and engineers that the 2008 Sci-Tech Oscar Awards are given to, the features of their fluid simulation technologies are analyzed. Finally, we anticipate that there are and will be the needs for visualizing fluid interaction with rigid and soft bodies and topological change among solid, fluid and gas, creating digital creatures based on fluid simulation and presenting interaction between creature and fluid.

• Journal of Korea Game Society
• /
• v.12 no.1
• /
• pp.67-77
• /
• 2012

With the development of tangible interface in recent years, the interest in interactive exercise games to improve health-related physical fitness has been increased. We believe that this kind of serious game should provide not only motion sensing of the action required to play sports but also a specific effectiveness of exercise. This paper will show how a serious exercise game affects theirs heart rate and preference. For the experiments, we used an exercise game named GalaxyBike for aerobics exercise which is developed by the Interaction Media Research Center of Hoseo University. In the experiments, players' heart rate was measured during the warming-up, exercise and cooling-down periods by a wireless heart-rate measuring instrument. After they played the exercise game, a survey was conducted to see how they like this serious exercise game. The findings of the study suggest that the serious exercise game providing both video game and exercise would make a contribution to the improvement of health-related physical fitness since it serves to increase the heart rate and motivation.

• Journal of The Korean Association of Information Education
• /
• v.17 no.2
• /
• pp.211-224
• /
• 2013

The purpose of this study was to find the effective way of composition in terms of UX(user experience) when configuring UI(user interface) of educational game by utilizing ET(eye-tracking). Experimental material was a game related to the middle school 'force and motion'. SMI (SensoMotoric Instruments)' iView X TM RED was used in order to collect eye movement data. The results of this study was as follows. First, the lead element for fast visual attention should be placed in the center when the educational game UI is configured. Second, burton that changes character's features and the information about them should be placed close to each other. Third, learning quiz caught visual attention faster when it was placed on the left side of UI. Fourth, when one UI was overlapped by another, parts that were not overlapped was fixated, too.

• Korean Journal of Applied Biomechanics
• /
• v.13 no.3
• /
• pp.265-276
• /
• 2003

The objective of this research is to provide basic data for improving athletic performances, suggesting methods that can be utilized at games and coaching movements in the snatch, by analyzing the level of contribution of muscles to the movements of the snatch lift through three-dimensional imaging and EMG analysis between skilled and unskilled lifters. To this end, three high school students (the skilled group), three middle school student (the unskilled group) were selected; two digital video cameras and electromyography were used. The muscles measured by an EMG include gastrocnemius muscle, biceps femoris muscle, erector spinae, latissimus dorsi muscle, trapezius muscle, and brachioradialis. Based on the Ariel Performance Analysis System (APAS) program, the results of the analysis are summarized as follows. 1. In performing snatch pulls, the skilled lifters were found to simultaneously move the weight centers of the body and the barbell close to vertical, close to the shoulders in the pulling portion; in snatching and grabbing the barbell from a sited position, it was observed that the shorter the time for adjusting to change in the height of the barbell by using rotational inertia, the better it is to perform the movements. 2. The skilled lifters were observed to perform stable and efficient movements in grabbing the bar in a sited position, by moving the barbell and weight center of the body close to vertical and moving the shoulder joint under the bar fast. 3. The results of the EMG analysis of the entire movements from the snatching portion to the portion of grabbing the bar in a sited position show that when the skilled lifters lifted the barbell vertically during the pulling portion, their shoulder joints were extended to put more weight on biceps femoris muscle and brachioradialis; and in snatching and grabbing the bar from a sited position, it was found desirable to increase the myoelectrical activity of erector spinae in order to achieve a balance in the movements of the hip joint between font and rear, as the weight centers of the body and the barbell move higher. On the other hand, the unskilled lifters were found that in response to change in posture, they increase their muscular strength inefficiently in performing the movements throughout the entire lifting process.

• Journal of the Korea Computer Graphics Society
• /
• v.18 no.2
• /
• pp.55-62
• /
• 2012

This paper presents a new method to represent the secondary deformation effect using simple mass-spring simulation on the vertex shader of the GPU. For each skin vertex of a 3D character, a zero-length spring is connected to a virtual vertex that is to be rendered. When a skin vertex changes its position and velocity according to the character motion, the position of the corresponding virtual vertex is computed by mass-spring simulation in parallel on the GPU. The proposed method represents the secondary deformation effect very fast that shows the material property of a character skin during the animation. Applying the proposed technique dynamically can represent squash-and-stretch and follow-through effects which have been frequently shown in the traditional 2D animation, within a very small amount of additional computation. The proposed method is applicable to represent elastic skin deformation of a virtual character in an interactive animation environment such as games.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.718-723
• /
• 2011

In this paper, we propose a visual multi-touch air input device using vision cameras. The implemented device provides a barehanded interface which copes with the multi-touch operation. The proposed device is easy to apply to the real-time systems because of its low computational load and is cheaper than the existing methods using glove data or 3-dimensional data because any additional equipment is not required. To do this, first, we propose an image processing algorithm based on the HSV color model and the labeling from obtained images. Also, to improve the accuracy of the recognition of hand gestures, we propose a motion recognition algorithm based on the geometric feature points, the skeleton model, and the Kalman filter. Finally, the experiments show that the proposed device is applicable to remote controllers for video games, smart TVs and any computer applications.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.519-523
• /
• 2011

Today, one of the most important reasons that 3D software becomes a core part of the essential tools in the video contents field like the movies, animation, CF, motion graphic, games and etc. is that they can save budget of contents makings and can produce better effects than conventional methods like miniature, matt painting, extra mobilization and etc. and can save time and have the merit that they are not limited in space. In this paper, I analyzed IK(Inverse kinematics) system characteristics for the efficient education of 3D character animation particularly most used of 3D applications which is now supposed to be nearly necessary elements in game, animation, movie and contents. And by analyzing merits and demerits of each tool on Bone, Character studio and Character Animation Toolkit, systems which are most used practically in the various Inverse kinematics tools, I showed the result of analyses about the fact that educating which of the above three Inverse Kinematics tools is helpful and beneficial for the students for the efficient education in the university where should teach much in the limited time

• The KIPS Transactions:PartA
• /
• v.14A no.4
• /
• pp.209-214
• /
• 2007

In conventional game systems, virtual environments usually have just the role of a background without the direct relationships for game characters. nev do not consider the semantics about virtual environments. In this paper, we develop a game navigation system that provides semantic information about virtual environments including geographical, historical or my other location-dependent information. Then, the game character obtains the geographical location and its related information when it navigates through a virtual environment. It can be an implementation method for a semantic virtual environment because it can have the environment maintain its semantics depending on the specific location. In addition, we describe a method that can control a character's motion in the semantic virtual environment interactively, and that can input specific information according to the location of the character.

• Journal of Convergence for Information Technology
• /
• v.9 no.4
• /
• pp.146-151
• /
• 2019

In this paper, we developed a multi-view video content based on real-world technology and a pilot using the production technology, and provided realistic contents production technology that can select a desired direction at a user 's view point by providing users with various viewpoint images. We also created multi-view video contents that can indirectly experience local cultural tourism resources and produced cyber tour contents based on multi-view video (realistic technology). This technology development can be used to create 3D interactive real-world contents that are used in all public education fields such as libraries, kindergartens, elementary schools, middle schools, elderly universities, housewives classrooms, lifelong education centers, The domestic VR market is still in it's infancy, and it's expected to develop in combination with the 3D market related to games and shopping malls. As the domestic educational trend and the demand for social public education system are growing, it is expected to increase gradually.