• The Journal of the Korea Contents Association
• /
• v.10 no.4
• /
• pp.1-9
• /
• 2010

Authoring tools for sketching the motion of characters to be animated have been studied. However the natural interface for sound editing has not been sufficiently studied. In this paper, I present a novel method that sound sample is selected by speaking sound-imitation words(onomatopoeia). Experiment with the method based on statistical models, which is generally used for pattern recognition, showed up to 97% in the accuracy of recognition. In addition, to address the difficulty of data collection for newly enrolled sound samples, the GLR Test based on only one sample of each sound-imitation word showed almost the same accuracy as the previous method.

• Proceedings of the KIEE Conference
• /
• 2006.07d
• /
• pp.1939-1940
• /
• 2006

휴머노이드 로봇의 동작 생성에 있어 최대 관심사 중 하나는 '얼마나 인간처럼 행동하는가?' 이다. 이를 위해 동작 획득 장비를 사용하여 얻은 인간 동작을 로봇으로 전이함으로써 인간과 유사한 움직임을 구현하는 것이 일반적인 방법이다. 인간의 동작 전환 과정에서 동작을 구분하고 그 구분된 동작을 재결합하는 과정이 빈번이 발생한다. 지금까지 동작을 구분하고 재결합하는 것은 많은 부분 수동적으로 처리되었다. 그러한 방법들이 실효적인 성과를 얻었지만 보다 더 효과적이고 체계적으로 인간다운 동작을 구현 할 수 있는 시스템이 필요하다. 본 연구에서는, 기구학에 근거하여 인간의 상체 동작을 구분하고 가중 함수를 이용하여 구분한 동작을 재결합함으로써 새로운 연속 동작을 생성한다. 생성된 연속 동작을 휴머노이드 로봇에 구현하여 제안한 동작모방시스템의 실효성을 검증한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.571-574
• /
• 2023

애니메이션은 주어진 키프레임(key frame)에 맞추어 움직이기 때문에, 다른 객체와 상호작용할 때 상대편 물체의 위치나 방향을 애니메이션에 맞추어 변환해야 한다. 이 논문에서는 모방학습으로 애니메이션을 학습하고, 모션 블렌딩(motion blending) 기법으로 객체 간 상호작용을 학습하여 새로운 애니메이션을 생성하는 방법을 제안한다. 에이전트(agent)는 오브젝트의 상태를 관측하고 주어진 모션들을 블렌딩하는 방법으로 다양한 행동을 취하고 목적에 대한 보상을 받는다. 에이전트가 행동하는 과정에서 모션 블렌딩 비율에 대한 가중치를 계산하는 함수를 설계하고, 생성되는 애니메이션이 사람이 취할 수 있는 동작에 가깝도록 회전 각도 clamping 함수와 보상 시스템을 설계하여 반영한다. 모방학습 기반 모션 블렌딩 기법은 객체의 변화에 상호작용하는 애니메이션을 기존 강화학습 기반 애니메이션 생성 기법보다 적은 학습량으로 생성할 수 있음을 확인했다.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.831-836
• /
• 2007

This paper proposes an optimal galloping trajectory which costs low energy and guarantees the stability of the quadruped robot. In the realization of the fast galloping, the trajectory design is important. As a galloping trajectory, we propose an elliptic leg trajectory, which provides simplified locomotion to complex galloping motions of animals. However, the elliptic trajectory, as an imitation of animal galloping motion, does not guarantee stability and minimal energy consumption. We propose optimization based on the energy and stability using a genetic algorithm, which provides the robust and global solution to a multi-body, highly nonlinear dynamic system. To evaluate and verify the effectiveness of the proposed trajectory, computer simulations were carried out.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.315-316
• /
• 2007

This paper presents a new methodology to improve movement database for a humanoid robot. The database is initially full of human motions so that the kinetics characteristics of human movement are immanent in it. then, the database is updated to the pseudo-optimal motions for the humanoid robot to perform more natural motions, which contain the kinetics characteristics of robot. for this, we use the evolutionary algorithm. the methodology consists of two processes : (1) the offline imitation learning of human movement and (2) the online generation of natural motion. The offline process improve the initial human motion database using the evolutionary algorithm and inverse dynamics-based optimization. The optimization procedure generate new motions using the movement primitive database, minimizing the joint torque. This learning process produces a new database that can endow the humanoid robot with natural motions, which requires minimal torques. In online process, using the linear combination of the motion primitive in this updated database, the humanoid robot can generate the natural motions in real time. The proposed framework gives a systematic methodology for a humanoid robot to learn natural motions from human motions considering dynamics of the robot. The experiment of catching a ball thrown by a man is performed to show the feasibility of the proposed framework.

• Journal of the Korean Society of Costume
• /
• v.52 no.1
• /
• pp.21-36
• /
• 2002

The Miaos have their own unique and luxurious culture traditional and modern formed as they have experienced repeated fusion into and resistance against the Han Race or the Chinese in their long and old history. Taijiang County of Guizhou Provice, in which whey have been living, is endowed with natural beauty. Thus their culture enjoys abundant and diverse contents of artificial and natural character. Naturally, their costume reflects cultural and natural features in abundance and variety. This dissertation aims to investigate the artistic character of Miaos' traditional costume as reflected in patterns for their embroidery. As for the artistic character of the patterns for embroidery, the following were found. To begin with, the space in the Miaos' embroidery is, unlike the measurable three-dimensional space found in Greek art, unmeasurable and fantastic with its beauty, majesty and peculiarity. It is as if immersed in limitless space, they were in communion with gods and universe. Another characteristic is the use of image construction beyond mere imitation. Their mode of image construction was realistic in that patterns as a whole reveal an abstract form or meaning but separately they portray visual representations of concrete thins in nature. Still another is that sense of motion conveyed by the basic curve line is full of life. It was the result of using light rhythm breaking stereotypic balance and symmetry. Finally, the colouring was abstract, and a strong contrast between black and white was gorgeous and fantastic.