• The Journal of Korea Robotics Society
• /
• v.3 no.4
• /
• pp.287-299
• /
• 2008

People have expected a humanoid robot to move as naturally as a human being does. The natural movements of humanoid robot may provide people with safer physical services and communicate with persons through motions more correctly. This work presented a methodology to generate the natural motions for a humanoid robot, which are converted from human motion capture data. The methodology produces not only kinematically mapped motions but dynamically mapped ones. The kinematical mapping reflects the human-likeness in the converted motions, while the dynamical mapping could ensure the movement stability of whole body motions of a humanoid robot. The methodology consists of three processes: (a) Human modeling, (b) Kinematic mapping and (c) Dynamic mapping. The human modeling based on optimization gives the ZMP (Zero Moment Point) and COM (Center of Mass) time trajectories of an actor. Those trajectories are modified for a humanoid robot through the kinematic mapping. In addition to modifying the ZMP and COM trajectories, the lower body (pelvis and legs) motion of the actor is then scaled kinematically and converted to the motion available to the humanoid robot considering dynamical aspects. The KIST humanoid robot, Mahru, imitated a dancing motion to evaluate the methodology, showing the good agreement in the motion.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.5
• /
• pp.486-494
• /
• 2014

Intelligent homes consist of ubiquitous sensors, home networks, and a context-aware computing system. These homes are expected to offer many services such as intelligent air-conditioning, lighting control, health monitoring, and home security. In order to realize these services, many researchers have worked on various research topics including smart sensors with low power consumption, home network protocols, resident and location detection, context-awareness, and scenario and service control. This paper presents the real-time metabolic rate estimation method that is based on measured heart rate for human adaptive appliance (air-conditioner, lighting etc.). This estimation results can provide valuable information to control smart appliances so that they can adjust themselves according to the status of residents. The heart rate based method has been experimentally compared with the location-based method on a test bed.

• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.4
• /
• pp.359-367
• /
• 2015

The forces and moments exerted on humanoid robot foot are important information for controlling or monitoring the robot. Multi-axis force/moment sensor can be installed under humanoid robot foot to measure forces and moments. The sensor should have large stiffness to support the robot weight and small size not to disturb the motion of the robot. In this paper, we designed a 6-aixs force/moment sensor which has good accuracy, large measuring range, and new compact structure. In addition, the proposed sensor is evaluated using analytical method and FEM(Finite Elements Method) method. Finally, it turned out that it has good performance.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.1
• /
• pp.45-50
• /
• 2003

Recently, robots technique has been developed remarkably. Emotion recognition is necessary to make an intimate robot. This paper shows the simulator and simulation result which recognize or classify emotions by learning pitch pattern. Also, because the pitch is not sufficient for recognizing emotion, we added acoustic elements. For that reason, we analyze the relation between emotion and acoustic elements. The simulator is composed of the DRNN(Dynamic Recurrent Neural Network), Feature extraction. DRNN is a learning algorithm for pitch pattern.

• Journal of the Korean Society for Precision Engineering
• /
• v.26 no.4
• /
• pp.72-81
• /
• 2009

The purpose of this paper is to accomplish the stable humanoid robot walking on the soft terrains. The goal of the humanoid robot development is to make the robotic system perform some tasks in human living environment. However, human dwelling environments are very different from those of laboratories, where varied experiments are performed by the robot. In many cases, the ground is soft or elastic unlike the floor of a laboratory. When a robot walks on the soft ground, the sole of robot contacts the uneven ground. This results in unstable walking or walking may be impossible according to the degree of softness. Therefore, the algorithm that facilitates stable walking on the soft ground surface is required. In this paper, we suggest an algorithm that controls the ankle to help the robot walk stably on the soft ground using the humanoid robot (ISHURO-II) as a real model. A humanoid robot walking on the soft ground was simulated to verify that the proposed algorithm results in stable walking.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.4
• /
• pp.129-143
• /
• 2021

This paper proposes actuator fault detection and adaptive fault-tolerant control algorithms using performance index and human-like learning for longitudinal autonomous vehicles. Conventional longitudinal controller for autonomous driving consists of supervisory, upper level and lower level controllers. In this paper, feedback control law and PID control algorithm have been used for upper level and lower level controllers, respectively. For actuator fault-tolerant control, adaptive rule has been designed using the gradient descent method with estimated coefficients. In order to adjust the control parameter used for determination of adaptation gain, human-like learning algorithm has been designed based on perceptron learning method using control errors and control parameter. It is designed that the learning algorithm determines current control parameter by saving it in memory and updating based on the cost function-based gradient descent method. Based on the updated control parameter, the longitudinal acceleration has been computed adaptively using feedback law for actuator fault-tolerant control. The finite window-based performance index has been designed for detection and evaluation of actuator performance degradation using control error.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.681-683
• /
• 2004

This paper describes the control of a geared DC motor having a backlash for implementation of a humanoid robot using disturbance observer. Critical problem of the humanoid robot is caused by the nonlinearity such as a backlash. To meet this problem, a control method using disturbance observer has been proposed. The disturbance observer is designed to estimate the effects of nonlinearities in the system, to make the nonlinear system behave linearly. To design the low-pass filter in the disturbance observer, cut-off frequency of the output should be found. The goal of this paper is the implementation of the proposed system, compensating the backlash effect. To accomplish the goat, PD control and disturbance observer are employed to the system with no load and full load. As a result, system stability can be guaranteed by compensating the effect of backlash. In addition, real experiment shows the proposed control methodology will satisfy the stable working of a humanoid type in the future.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.11a
• /
• pp.257-260
• /
• 2005

This paper discusses a human body extraction method for mobile robot system. The skeleton features are used to analyze human motion and pose estimation. The intelligent robot system requires more robust silhouette extraction method because it has internal vibration and low resolution. The new hybrid silhouette extraction method is proposed to overcome this constrained environment. Finally, the experimental results show the superiority of the Proposed method.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.1
• /
• pp.167-173
• /
• 2007

This paper describes a redundancy resolution based method for determining an optimal initial configuration of a humanoid robot for holding an object. There are three important aspects for a humanoid robot to be able to hold an object. Those three aspects are the reachability that guarantees the robot to reach the object, the stability that guarantees the robot to remain stable while moving or holding the object, and the manipulability that makes the robot manipulate the object dexterously. In this paper, a humanoid robot with 20 degrees of freedom is considered. The humanoid robot is kinematically redundant and has infinite number of solutions for the initial configuration problem. The complex three-dimensional redundancy resolution problem is divided into two simple two-dimensional redundancy resolution problems by incorporating the symmetry of the problem, robot's moving capability, and the geometrical characteristics of the given robot. An optimal solution with respect to the reachability, the stability, and the manipulability is obtained by solving these two redundancy resolution problems.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.487-490
• /
• 2004

상황 인식(context-awrare)은 인간-컴퓨터 상호작용의 단점을 극복하기 위한 방법으로써 많은 주목을 받고 있다. 이 논문에서는 SoC(System-on-a-Chip)로 구현될 수 있는 상황 인식 시스템 구조를 제안한다. 제안한 구조는 센서 추상화, 컨텍스트 변경에 대한 통지 메커니즘, 모듈식 개발, if-then규칙을 이용한 쉬운 서비스 구성과 유연한 상황 인식 서비스 구현을 지원한다. 이 구조는 통신 모듈, 처리 모듈, 블랙보드를 포함하는 SoC 마이크로프로세서 부분과 규칙 기반 시스템 모듈을 구현한 하드웨어로 구성된다. 규칙 기반 시스템 하드웨어는 모든 규칙의 조건부에 대해 매칭 연산을 병렬로 수행하고, 규칙의 결론부는 마이크로프로세서에 내장된 행위 모듈을 호출함으로써 작업을 수행한다. 제안한 구조의 SoC 시스템은 SystemC SoC 개발 환경에서 설계되고, 성공적으로 테스트되었다. 제안한 SoC 기반의 상황 인식 시스템 구조는 주거 환경에서 컨텍스트를 인식하여 노인을 보조하는 지능형 이동 로봇 등에 적용될 수 있을 것으로 기대된다.