• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.46.2-46
• /
• 2001

A method of interactive human interface for motion modification of an articulated object model like a human body, a multiple joints robot, etc. has been developed, and implemented to a human body motion model. In the case of computer software models, the initial data setting for overall motion is rather easy. However, modifying or correcting the initially set motion is rather difficult for keeping consistency. In this research, the requirements shown below have mainly been set as the specifications ...

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.413-415
• /
• 2022

인간의 관절은 인간의 신체를 구성하는 요소로 인간의 행동을 분석하는데 유용한 정보로 활용될 수 있기 때문에 관절 정보를 이용한 행동인식에 대한 많은 연구가 진행되었다. 하지만 각각의 독립적인 관절 정보만을 이용해서 시시각각 변화하는 인간의 행동을 인식하는 것은 매우 복잡한 문제이다. 따라서 학습에 사용할 부가적인 정보 추출 방법과 과거의 상태를 기반으로 현재 상태를 판단하는 고려하는 알고리즘이 필요하다. 본 논문에서는 연결된 관절들의 위치 관계와 각 관절의 위치가 시간의 흐름에 따라 변화하는 것을 고려한 행동 인식 기법을 제안한다. 사전 학습된 관절 추출 모델을 이용하여 각 관절의 위치 정보를 획득하고 연결된 관절 사이의 차 벡터를 이용하여 뼈대 정보를 추출한다. 그리고 두 가지 형태의 입력에 맞춰 간소화된 신경망을 구성하고 LSTM을 더하여 시·공간적 특징을 추출하도록 한다. 9개의 행동으로 구성된 데이터 셋을 이용하여 실험한 결과 각 관절 및 뼈대의 시·공간적 관계 특징을 고려하여 행동 인식 정확도를 측정하였을 때 단일 관절 정보만을 이용한 결과에 비해 뛰어난 성능을 보임을 확인하였다.

• 제어로봇시스템학회논문지
• /
• 제11권6호
• /
• pp.543-549
• /
• 2005

This paper deals with modeling and analysis fer the landing motion of a human-body model. First, the dynamic model of a floating human body is derived. The external impulse exerted on the ground as well as the internal impulse experienced at the joints of the human body model is analyzed. Second, a motion planning algorithm exploiting the kinematic redundancy is suggested to ensure stability in terms of ZMP stability condition during a series of landing phases. Four phases of landing motion are investigated. In simulation, the external and internal impulses experienced at the human joints and the ZMP history resulting from the motion planning are analyzed for two different configurations. h desired landing posture is suggested by comparison of the simulation results.

• 한국지능시스템학회논문지
• /
• 제25권3호
• /
• pp.223-228
• /
• 2015

본 논문에서는 어떤 물체를 들어 올려서 전달하는 인간의 작업을 대신 수행하기 위한 인간형 로봇 팔의 어깨 및 팔꿈치 관절의 토오크 특성을 분석하고자 한다. 이러한 목적을 달성하기 위하여 인간의 일상적인 물체의 리프팅 행동을 고려하고, 단순한 구조의 어깨와 팔꿈치 관절을 갖는 인간형 로봇 팔 모델을 사용하여 어떤 물체를 다양한 경로로 이송하는 시뮬레이션을 수행한다. 이러한 시뮬레이션을 통하여 인간형 로봇 팔을 이용한 물체의 이송 작업에 있어서 요구되는 어깨 및 팔꿈치 관절의 토오크 패턴 및 범위를 사전에 파악할 수 있음을 보인다. 결과적으로, 이러한 어깨 및 팔꿈치 관절의 토오크 분석은 효과적인 로봇 팔 메커니즘 설계에 유용하게 활용될 수 있다.

• 제어로봇시스템학회논문지
• /
• 제6권8호
• /
• pp.710-718
• /
• 2000

In this paper we described an approach to automation of visual inspection of solder joint defects of SMC(Surface Mounted Components) on PCBs(Printed Circuit Board) by using neural network and fuzzy rule-based classification method. Inherently the surface of the solder joints is curved tiny and specular reflective it induces difficulty of taking good image of the solder joints. And the shape of the solder joints tends to greatly vary with the soldering condition and the shapes are not identical to each other even though the solder joints belong to a set of the same soldering quality. This problem makes it difficult to classify the solder joints according to their qualities. Neural network and fuzzy rule-based classification method is proposed to effi-ciently make human-like classification criteria of the solder joint shapes. The performance of the proposed approach is tested on numerous samples of commercial computer PCB boards and compared with the results of the human inspector performance and the conventional Kohonen network.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2005년도 추계학술대회논문집
• /
• pp.891-894
• /
• 2005

This paper describes a human finger model driven by shape memory alloy(SMA) wires. The finger model has three joints that are similar to human finger. Each joint is actuated with two wires in the antagonistic manner and six wires are used to actuate three finger joint. In order to obtain the desirable finger motion, the diameters of the SMA wires are designed with different diameters by considering the required actuating force and response time. The rotary sensors are used to measure the angle positions of the joints and PWM control using PID algorithm is used to achieve desired angle positions of the finger joints. After estimating the control performance of each finger joint for the desired angle position, the antagonistic motion control of the finger model is experimentally evaluated.

• 대한인간공학회지
• /
• 제15권2호
• /
• pp.125-135
• /
• 1996

The purpose of this research is to measure range of virtual hip joint and lower limb joints motion such as the hip, knee and ankle joints for 47 young male students. The results of ANOVA revealed that anthropometric dimensions including weight and stature did not show any significant effects on the range of virtual hip joint and lower limb joints motion and the range of motion with two degrees of freedom at the shoulder, virtual hip and hip joints. Anthropometric dimensions such as age, weight, statuire, arm length, shoulder height and leg length were found to be lowly correlated with the range of virtual hip joint and lower limb joints motion. It is expected that the data on the range of joint motion suggested in this study can be used as a valuable input data when designing workplace, predicting human posture and reach volume, etc.

• IEIE Transactions on Smart Processing and Computing
• /
• 제4권4호
• /
• pp.281-290
• /
• 2015

Human action recognition from a video scene has remained a challenging problem in the area of computer vision and pattern recognition. The development of the low-cost RGB depth camera (RGB-D) allows new opportunities to solve the problem of human action recognition. In this paper, we present a comprehensive review of recent approaches to human action recognition based on depth maps, skeleton joints, and other hybrid approaches. In particular, we focus on the advantages and limitations of the existing approaches and on future directions.

• 한국정밀공학회지
• /
• 제24권2호
• /
• pp.64-72
• /
• 2007

Many human-body motions such as walking, running, jumping, etc. require a significant amount of power. To achieve a high power-to-weight ratio of the humanoid robot system, this paper proposes a new design of the bio-mimetic leg mechanism resembling musculoskeletal system of the human body. The hip joints of the system considered here are powered by 5 human-like bi-and mono-articular muscles, and the joints of knee and ankle are redundantly actuated by both bi-articular muscles and joint actuators. The kinematics for the leg mechanism is derived and a kinematic index to measure force transmission ratio is introduced. It is demonstrated through simulation that incorporation of redundant muscles into the leg mechanism enhances the power of the mechanism approximately 2 times of the minimum actuation.

• Advances in Computational Design
• /
• 제4권4호
• /
• pp.343-365
• /
• 2019

Among the themes related to earthquake countermeasures at construction sites, those for tower cranes are particularly important. An accident involving the collapse of a crane during the construction of a skyscraper has serious consequences, such as human injury or death, enormous repair costs, and significant delays in construction. One of the causes of deadly tower crane collapses is the destruction of the site joints of the tower crane mast. This paper proposes a new design method by static elastoplastic finite element analysis using a supercomputer for the design of the end plate-type tensile bolted joints, which are generally applied to the site joints of a tower crane mast. This new design method not only enables highly accurate and reliable joint design but also allows for a design that considers construction conditions, such as the introduction of a pre-tension axial force on the bolts. By applying this new design method, the earthquake resistance of tower cranes will undoubtedly be improved.