• 한국지능시스템학회논문지
• /
• 제19권1호
• /
• pp.108-114
• /
• 2009

본 논문에서는 3차원 작업 환경에서 휴머노이드 로봇의 행동 프리미티브를 이용한 행동 계획 방법을 제안하였다. 또한 휴머노이드 로봇이 효과적으로 다양한 작업을 수행하기 위하여 행동 프리미티브를 정의하였다. 행동 프리미티브를 이용함으로써 다양한 장애물을 갖는 복잡한 작업 환경에서 로봇에 장착한 센서로 외부 환경 정보를 받아들이고 이를 이용하여 실시간 대응 및 작업이 가능하도록 하였다. 제안한 행동 계획방법은 임베디드 비전 시스템을 사용한 휴머노이드 로봇을 실제 제작하여 실험을 통해 성능을 검증하였다.

• 대한기계학회논문집A
• /
• 제32권10호
• /
• pp.882-889
• /
• 2008

A humanoid is a robot with its overall appearance based on that of the human body. When the humanoid moves or walks, dynamic forces act on the body structure. Although the humanoid keeps the balance by using a precise control, the dynamic forces generate unexpected deformation or vibration and cause difficulties on the control. Generally, the structure of the humanoid is designed by the designer's experience and intuition. Then the structure can be excessively heavy or fragile. A humanoid design scenario for a systematic design is proposed to reduce the weight of the structure while sufficient strength is kept. Lower parts of the humanoid are selected to apply the proposed design scenario. Multi-body dynamics is employed to calculate the external dynamic forces on the parts and structural optimization is carried out to design the lower parts. Because structural optimization using dynamic forces directly is fairly difficult, linear dynamic response structural optimization using equivalent static loads is utilized. Topology and shape optimizations are adopted for two steps of initial and detailed designs, respectively. Various commercial software systems are used for analysis and optimization. Improved designs are obtained and the design results are discussed.

• 한국기계가공학회지
• /
• 제15권2호
• /
• pp.125-130
• /
• 2016

In this paper, we deal with the dynamic walking of a humanoid robot. In our method, the inverted pendulum model is used as a dynamic model for a humanoid robot in which the Zero Moment Point (ZMP) and COG constraints of the robot are analyzed by considering the motion of the robot as that of an inverted pendulum. The motion of a humanoid robot should be generated by considering the dynamics of the robot, which commonly requires a large amount of computation. If a robot walks from one position to another while keeping the ZMP in the stable region, then the robot remains dynamically stable. The linear inverted pendulum model regards the whole robot as a point mass. It is simple, and relatively less computation is needed; however, it cannot model the whole dynamics of a humanoid robot. We propose a method for modeling a humanoid robot as an inverted pendulum system having 14 point masses. We also show that the dynamic stability of a humanoid robot can be determined more precisely by our method.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제54권6호
• /
• pp.376-382
• /
• 2005

In this paper, practical biped humanoid robot is presented, designed, and modeled by fuzzy system. The humanoid robot is a popular research area in robotics because of the high adaptability of a walking robot in an unstructured environment. But owing to the lots of circumstances which have to be taken into account it is difficult to generate stable and natural walking motion in various environments. As a significant criterion for the stability of the walk, ZMP (zero moment point) has been used. If the ZMP during walking can be measured, it is possible for a biped humanoid robot to realize stable walking by a control method that makes use of the measured ZMP. In this study, measuring the ZMP trajectories in real time situations throughout the whole walking phase on the flat floor and slope are conducted. And the obtained ZMP data are modeled by fuzzy system to explain empirical laws of the humanoid robot. By the simulation results, the fuzzy system can be effectively used to model practical humanoid robot and the acquired trajectories will be applied to the humanoid robot for the human-like walking motions.

• 센서학회지
• /
• 제33권1호
• /
• pp.18-23
• /
• 2024

Humanoid robots, designed to interact in human environments, require stable mobility to ensure safety. When a humanoid robot falls, it causes damage, breakdown, and potential harm to the robot. Therefore, fall detection is critical to preventing the robot from falling. Prevention of falling of a humanoid robot requires an operator controlling a crane. For efficient and safe walking control experiments, a system that can replace a crane operator is needed. To replace such a crane operator, it is essential to detect the falling conditions of humanoid robots. In this study, we propose falling detection methods using Convolution Neural Network (CNN) model. The image data of a humanoid robot are collected from various angles and environments. A large amount of data is collected by dividing video data into frames per second, and data augmentation techniques are used. The effectiveness of the proposed CNN model is verified by the experiments with the humanoid robot MAX-E1.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2007년도 춘계학술대회A
• /
• pp.933-938
• /
• 2007

These days, up-to-date humanoid robots are continuously developed. Among them, Qrio, Asimo[1,2] are famous for its unique walking technology and natural movement. These robots could show manufacturers' technological improvement and leave a good impression to the customer. In accordance with global trends, Samsung is also producing humanoid robot. The humanoid robot, however, could walk like a human compared to the industrial robot fixed in the factory. This feature could cause another dynamic effect while walking. In this paper, the robot's feet were examined to find out parameters that affect stability of the humanoid robot's feet. With the sensitivity analysis, the optimization procedure in design of experiments finds the most suitable performance of robot. Maximum deflection of the frame upon various cases was minimized, and rubber coefficients for shock absorption were optimized.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2007년도 춘계학술대회A
• /
• pp.1344-1349
• /
• 2007

Biped humanoids maintain their stability through precise controls during locomotion or operation. Dynamic forces are applied to the humanoid structure during locomotion or operation. If the humanoid has weakness from a structural viewpoint, these forces cause severe deformation or vibration of the structure, which can make the humanoid unstable. In this research, a design scenario is proposed to design a robust humanoid structure under the dynamic loads. The pelvis part is selected for design practice. Multibody dynamics is adopted to calculate the dynamic loads and a structural optimization technique is employed to design the pelvis structures. Since it is extremely difficult directly consider the dynamic loads in the optimization process, equivalent static loads are evaluated from the dynamic loads and the design result are discussed.

• 전기학회논문지
• /
• 제56권1호
• /
• 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.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2271-2274
• /
• 2005

The desired ZMP is different from the actual ZMP of a humanoid robot during actual walking and stand upright. A humanoid robot must maintain its stable posture although external force is given to the robot. A humanoid robot can know its stability with ZMP. Actual ZMP may be moved out of the foot-print polygons by external disturbance or uneven ground surfaces. If the position of ZMP moves out of stable region, the stability can not be guaranteed. Therefore, The control of the ZMP is necessary. In this paper, ZMP control algorithm is proposed. Herein, the ZMP control uses difference between desired ZMP and actual ZMP. The proposed algorithm gives reaction moment with ankle joint when external force is supplied. 3D simulator shows motion of a humanoid robot and calculated data.

• 제어로봇시스템학회논문지
• /
• 제13권4호
• /
• pp.358-364
• /
• 2007

Intelligent walking modeling of humanoid robot using learning based neuro-fuzzy system is presented in this paper. Walking pattern, trajectory of the zero moment point (ZMP) in a humanoid robot is used as an important criterion for the balance of the walking robots but its complex dynamics makes robot control difficult. In addition, it is difficult to generate stable and natural walking motion for a robot. To handle these difficulties and explain empirical laws of the humanoid robot, we are modeling practical humanoid robot using neuro-fuzzy system based on the two types of natural motions which are walking trajectories on a t1at floor and on an ascent. Learning based neuro-fuzzy system employed has good learning capability and computational performance. The results from neuro-fuzzy system are compared with previous approach.