• 제어로봇시스템학회논문지
• /
• 제22권4호
• /
• pp.293-300
• /
• 2016

The Voice recognition is one of convenient methods to communicate between human and robots. This study proposes a speech recognition method using speech recognizers based on Hidden Markov Model (HMM) with a combination of techniques to enhance a biped robot control. In the past, Artificial Neural Networks (ANN) and Dynamic Time Wrapping (DTW) were used, however, currently they are less commonly applied to speech recognition systems. This Research confirms that the HMM, an accepted high-performance technique, can be successfully employed to model speech signals. High recognition accuracy can be obtained by using HMMs. Apart from speech modeling techniques, multiple feature extraction methods have been studied to find speech stresses caused by emotions and the environment to improve speech recognition rates. The procedure consisted of 2 parts: one is recognizing robot commands using multiple HMM recognizers, and the other is sending recognized commands to control a robot. In this paper, a practical voice recognition system which can recognize a lot of task commands is proposed. The proposed system consists of a general purpose microprocessor and a useful voice recognition processor which can recognize a limited number of voice patterns. By simulation and experiment, it was illustrated the reliability of voice recognition rates for application of the manufacturing process.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2248-2253
• /
• 2005

Although the progress in bipedal walking is impressive in recent years, biped robots still require very high torque and can walk only for a short time interval with their internal batteries. Therefore, further research needs to be carried out to enhance walking efficiency of these robots. In order to achieve this goal, we attempt to imitate human walking with pelvis and waist joint rotations in the frontal plane. In order to investigate the effect of the pelvis and waist joint rotations in the frontal plane motion, we study the frontal plane model with a triangular structure made up of a waist joint and two hip joints. Through simulation, we show that the pelvis rotation can reduce the maximum torque and the control effort, and the waist joint rotation can reduce the trunk sway caused by the pelvis rotation. The combination of these two rotations makes the bipedal walking in the frontal plane more efficient.

• 제어로봇시스템학회논문지
• /
• 제15권10호
• /
• pp.1029-1038
• /
• 2009

This paper proposes a gain switching algorithm for joint position control of a hydraulic humanoid robot. Accurate position control of the lower body is one of the basic requirements for robust balance and walking control. Joint position control is more difficult for hydraulic robots than it is for electric robots because of an absence of reduction gear and better back-drivability of hydraulic joints. Backdrivability causes external forces and torques to have a large effect on the position of the joints. External ground reaction forces therefore prevent a simple proportional-derivative (PD) controller from realizing accurate and fast joint position control. We propose a state feedback controller for joint position control of the lower body, define three modes of state feedback gains, and switch the gains according to the Zero Moment Point (ZMP) and linear interpolation. Dynamic equations of hydraulic actuators were experimentally derived and applied to a robot simulator. Finally, the performance of the algorithm is evaluated with dynamic simulations.

• 전기학회논문지
• /
• 제56권2호
• /
• pp.374-382
• /
• 2007

Robot mobility and intelligence become more important for robots to be used in various fields other than automation. The main purpose of providing mobility to a robot is to extend the robot's manipulability. In this paper, we introduce a small humanoid robot that can autonomously play golf as an example of incorporating robot intelligence, mobility, and manipulability. The robot has 12 degrees of freedom for legs and has various basic walking patterns. It can move to a desired position and change orientation by combining the basic waking patterns. The robot has a color CCD camera and can extract coordinates of the objects in the environments. The small humanoid robot has 8 degrees of freedom for arms and can play golf autonomously with two kinds of dexterous swing motions. Kinematic analysis of the robot arms, vision data processing for the recognition of the environments, algorithm for playing robotic golf have been performed or proposed. The experimental results show that the robot can play golf autonomously.

• Journal of Mechanical Science and Technology
• /
• 제19권spc1호
• /
• pp.227-236
• /
• 2005

Multibody system dynamics is based on classical mechanics and its engineering applications originating from mechanisms, gyroscopes, satellites and robots to biomechanics. Multibody system dynamics is characterized by algorithms or formalisms, respectively, ready for computer implementation. As a result simulation and animation are most convenient. Recent developments in multibody dynamics are identified as elastic or flexible systems, respectively, contact and impact problems, and actively controlled systems. Based on the history and recent activities in multibody dynamics, recursive algorithms are introduced and methods for dynamical analysis are presented. Linear and nonlinear engineering systems are analyzed by matrix methods, nonlinear dynamics approaches and simulation techniques. Applications are shown from low frequency vehicles dynamics including comfort and safety requirements to high frequency structural vibrations generating noise and sound, and from controlled limit cycles of mechanisms to periodic nonlinear oscillations of biped walkers. The fields of application are steadily increasing, in particular as multibody dynamics is considered as the basis of mechatronics.

• 제어로봇시스템학회논문지
• /
• 제18권9호
• /
• pp.837-844
• /
• 2012

We introduce a pattern generation method for a hopping one-legged robot and verify it experimentally. The pattern is derived from the liner and angular momentum of a COM (Center of Mass), which are pre-scheduled. Because of the relation between angular velocities of joints and momemtums of the COM, joint angle trajectories are easily obtained. In addition, the landing impact force is reduced by only adjusting the landing timing. In the experiment, the one-legged robot hops in place with 0.06 s of flying time, and makes continuous hopping. Based on our experimental results, the proposed method can be applied to hopping and running of biped humanoid robots.

• Structural Engineering and Mechanics
• /
• 제41권5호
• /
• pp.633-644
• /
• 2012

The paper presents the motion editor for the robotic movement in the study. The Motion Editor can edit all motions which we want to need. This method is easy when the beginners edit to motions of robots. And let them have interesting in robot control. This paper proposes two methods to edit movements. First, we edit the robot's movement in VB environment, and then we use the Motion Editor to make it. Finally, we compared merit and defect with two methods. Indeed, it is convenient when we use the Motion Editor.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.1762-1763
• /
• 2007

본 논문의 목적은 이족 로봇이 스스로의 위치, 속도, 자세 등을 판단할 수 있도록 하기위한 관성항법시스템을 설계하는 것이다. 관성항법시스템은 외부장치의 도움 없이 로봇의 위치, 속도 및 자세 결정이 가능한 독립적인 항법 시스템으로 전파장애나 환경변화에 영향을 받지 않으며, 비교적 정확한 위치정보를 제공한다. 반면 시간이 지남에 따라 오차가 누적된다는 단점이 있으나 좁은 공간에서 단시간 동작하는 이족로봇에 있어 큰 문제가 되지 않는다. 이 관성항법시스템을 이용하여 독립적인 이족 로봇이 위치, 속도 및 자세를 판단 가능하여 보다 지능적인 임무를 수행할 수 있다. 본 연구에서는 관성항법시스템의 구조와 이론적 배경을 통한 설계, 그리고 이족로봇에 적용을 위한 방법을 제시한다.

• 융합신호처리학회논문지
• /
• 제14권2호
• /
• pp.124-129
• /
• 2013

6족 보행 로봇은 2족 또는 4족 보행 로봇에 비하여 안정적인 보행이 가능한 장점이 있다. 따라서 6족 보행 로봇은 이러한 보행의 안정성을 기반으로 다양한 지능적인 동작을 수행하기에 유리한 구조이다. 본 논문에서는 전형적인 6족 보행 로봇과는 달리 로봇의 진행 방향에 대하여 전후 다리와 좌우에 각각 한 쌍의 다리를 갖는 6족 보행 로봇을 제안하고 제안된 로봇을 사용하여 다양한 지능형 동작을 수행한다. 26개의 모듈형 모터를 사용하여 로봇 기구부를 구성하고 호스트 PC, DSP 주제어기, AVR 보조 제어기, 스마트폰/스마트패드로 구성되는 제어기를 구현한다. 구현된 로봇은 스테레오 카메라, 적외선 센서, 초음파 센서, 접촉 센서 등 다양한 센서 데이터를 사용하여 비평탄면 보행, 공차기, 원격 제어 및 3차원 모니터링 등 다양한 지능형 동작을 수행할 수 있음을 실험을 통하여 검증한다.

• 한국엔터테인먼트산업학회논문지
• /
• 제8권2호
• /
• pp.283-297
• /
• 2014

미래 인간의 삶은 사회, 경제, 정치와 개인 등 삶의 전 영역에 걸쳐 다학제적 기술의 파급효과 증대에 의해 혁신될 것이다. 특히 로봇 분야와 로봇을 이용한 차세대 게임 분야에서는 다학제적 기여와 상호작용에 의해 더욱 더 기술간 융합화가 가속화 될 것으로 전망된다. 본 연구는 지금까지의 "인간-로봇 인터페이스 기술"의 기술적인 한계 및 시공간적 제약을 뛰어넘는 새로운 인터페이스 모델로, 기존 인간-로봇 인터페이스 기술에서 가질 수 없는 다양한 모달리티(modality)들의 융합을 통해 보다 신뢰성 있으며 편하고 자유로운 "인간-로봇 인터페이스 기술"의 연구이다. 이족보행의 휴먼로봇과 모바일 기기 화면의 3D 콘텐츠(contents) 로봇(가상로봇)의 동작과 위치 값을 실시간적으로 연동하는 동기화(Synchronization) 엔진을 개발하고, 상호간의 정보를 주고받기 위한 무선 프로토콜(Protocol) 및 효율적인 티칭(Teaching)을 위한 학습에 의한, 다이렉트 티칭앤플레이(Direct Teaching & Play)의 티칭 프로그램 개발과, 이를 이용한 로봇 게임 시스템을 연구한다.