• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.328-335
• /
• 2022

With the advance of robot capabilities and functionalities, construction robots assisting construction workers have been increasingly deployed on construction sites to improve safety, efficiency and productivity. For close-proximity human-robot collaboration in construction sites, robots need to be aware of the context, especially construction worker's behavior, in real-time to avoid collision with workers. To recognize human behavior, most previous studies obtained 3D human poses using a single camera or an RGB-depth (RGB-D) camera. However, single-camera detection has limitations such as occlusions, detection failure, and sensor malfunction, and an RGB-D camera may suffer from interference from lighting conditions and surface material. To address these issues, this study proposes a novel method of 3D human pose estimation by extracting 2D location of each joint from multiple images captured at the same time from different viewpoints, fusing each joint's 2D locations, and estimating the 3D joint location. For higher accuracy, the probabilistic representation is used to extract the 2D location of the joints, considering each joint location extracted from images as a noisy partial observation. Then, this study estimates the 3D human pose by fusing the probabilistic 2D joint locations to maximize the likelihood. The proposed method was evaluated in both simulation and laboratory settings, and the results demonstrated the accuracy of estimation and the feasibility in practice. This study contributes to ensuring human safety in close-proximity human-robot collaboration by providing a novel method of 3D human pose estimation.

• 로봇학회논문지
• /
• 제15권2호
• /
• pp.190-196
• /
• 2020

Mechanical systems using tendon-driven actuators have been widely used for bionic robot arms because not only the tendon based actuating system enables the design of robot arm to be very efficient, but also the system is very similar to the mechanism of the human body's operation. The tendon-driven actuator, however, has a drawback caused by the friction force of the sheath. Controlling the system without considering the friction force between the sheath and the tendon could result in a failure to achieve the desired dynamic behaviors. In this study, a mathematical model was introduced to determine the friction force that is changed according to the geometrical pathway of the tendon-sheath, and the model parameters for the friction model were estimated by analyzing the data obtained from dedicated tests designed for evaluating the friction forces. Based on the results, it is possible to appropriately predict the friction force by using the information on the pathway of the tendon.

• Journal of Biosystems Engineering
• /
• 제29권3호
• /
• pp.281-286
• /
• 2004

The end-effector is the one of the important factors on development of the cucumber robot to harvester a cucumber. Three end-effectors were designed the single blade end-effector with one blade, the double blade end-effector with two blades and the triple blade end-effector with three blades. Performance tests of the end-effector, the fully integrated system, were conducted to determine the cutting rate by using two different kinds of cucumber. The success rates of cucumber cutting ratio of single end-effector, double end-effector and triple end-effector in laboratory. were 61.7%, 95%, 86.7%, respectively. The cutting rate of single blade or double blade was a little difference with respect to the different diameters of cucumber stem. However, the success cutting rate of the end-effector with triple blade was 61.7% under 29mm diameter of a grabbing stem section. The triple end-effector was not suitable for harvesting a cucumber, but was considered to be suitable for harvesting a grape, an apple and a tomato. The success rate of cucumber cutting ratio of triple end-effectors in greenhouse was 84%. The failure cutting rate was 16% which are due to abnormal shape of cucumber fruit.

• 제어로봇시스템학회논문지
• /
• 제15권6호
• /
• pp.604-611
• /
• 2009

Modular snake-like robots are robust for failure and have flexible locomotion for environments, but are difficult to control. Various phase and evolutionary approaches for modular robots have been studied for many years, but there are few comparisons among these methods. In this paper, Phase, GAps, GA and GP approaches are implemented and compared for flat, stairs, and slope environments. In addition, simulations of the locomotion evolution for modular snake-like robot are executed in Webots environments.

• 로봇학회논문지
• /
• 제15권4호
• /
• pp.398-403
• /
• 2020

Robot's throwing control is difficult to accurately calculate because of air resistance and rotational inertia, etc. This complexity can be solved by using machine learning. Reinforcement learning using reward function puts limit on adapting to new environment for robots. Therefore, this paper applied deep reinforcement learning using neural network without reward function. Throwing is evaluated as a success or failure. AI network learns by taking the target position and control policy as input and yielding the evaluation as output. Then, the task is carried out by predicting the success probability according to the target location and control policy and searching the policy with the highest probability. Repeating this task can result in performance improvements as data accumulates. And this model can even predict tasks that were not previously attempted which means it is an universally applicable learning model for any new environment. According to the data results from 520 experiments, this learning model guarantees 75% success rate.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.1149-1154
• /
• 1991

For a robotic workcell, which consists of multiple robots, several interconnection methods are presented in terms of the processor based architecture. Since few attempts have been made to formulate and analyze multiple robot system(MRS), we turn the knowledge of multiple processor system(MPS) or multiple computer system(MCS) to good account. The performance evaluation is achieved through queueing analysis, the aim being to compare their response time, utilization, probability of service failure under different workload. To verify the validity of the proposed analysis methods, a computer simulation is performed. The results together with comments presented here give some useful guidelines for the selection of an appropriate interconnection method.

• 한국CDE학회논문집
• /
• 제17권3호
• /
• pp.198-207
• /
• 2012

This paper presents an overview of automated robotic system for skull drilling, which is performed to access for some neurosurgical interventions, such as brain tumor resection. Currently surgeons use automatic-releasing cranial perforators. The drilling procedure must be performed very carefully to avoid penetration of brain nerve structures; however failure cases are reported. The presented prototype system utilizes both preoperative and intraoperative information. Preoperative CT image is used for robot path planning. A NeuroMate robot with a six-DOF force sensor at the end effector is used for intraoperative operation. Intraoperative cutting force from the force sensor is the key information to revise an initial registration and preoperative path plans. Some possibilities are verified by path simulation but cadaver experiments are required for validation of this prototype.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.60-60
• /
• 2000

CAN(Controller Area Network) is a serial communication protocol which specifies very low cost and high performance. It is widely used in rea1-time control applications such as automobiles, aircraft, and automated factories. The main application fields are industrial control systems and embedded network. In this paper, the CAN monitoring system is proposed and implemented. Also its performance is tested in the mobile robot which is integrated by CAN and its performance lot receipt failure rate is evaluated. This can be used to analyze the performance of the network. It can tie also used to manage and monitor the network.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제8권3호
• /
• pp.243-251
• /
• 2016

Autonomous Underwater Vehicles (AUVs) generally work in complex marine environments. Any fault in AUVs may cause significant losses. Thus, system reliability and automatic fault diagnosis are important. To address the actuator failure of AUVs, a fault diagnosis method based on the Gaussian particle filter is proposed in this study. Six free-space motion equation mathematical models are established in accordance with the actuator configuration of AUVs. The value of the control (moment) loss parameter is adopted on the basis of these models to represent underwater vehicle malfunction, and an actuator failure model is established. An improved Gaussian particle filtering algorithm is proposed and is used to estimate the AUV failure model and motion state. Bayes algorithm is employed to perform robot fault detection. The sliding window method is adopted for fault magnitude estimation. The feasibility and validity of the proposed method are verified through simulation experiments and experimental data.

• 한국산학기술학회논문지
• /
• 제12권6호
• /
• pp.2760-2769
• /
• 2011

지능형 자율 로봇은 주어진 목표를 달성하기 위하여 계획을 수립한다. 계획은 로봇이 목표를 달성하기 위한 행위들의 나열이며 모든 행위들이 순차적으로 그리고 성공적으로 실행되었을 때 목표를 달성하게 된다. 그러나 복잡하고 역동적인 현실 세계에서는 여러 가지 요인에 의하여 발생할 수 있는 예상하지 못한 상황으로 인하여 로봇이 계획한 행위들을 더 이상 실행하지 못하는 경우가 발생할 수 있다. 그러므로 지능형 자율 로봇은 이러한 돌발 상황을 적절히 대처하여 주어진 임무를 성공적으로 완수할 수 있는 효과적인 처리 방법을 가지고 있어야 한다. 이정표 상태를 이용한 계획 보정 방법은 이러한 상황을 효과적으로 처리할 수 있는 방법으로서 다른 계획 보정 방법들의 장점을 가지고 있다. 본 논문은 이정표 상태를 생성하는 방법으로 후진 방법과 이정표 상태들을 구성하는 조건들에 가중치를 부여하는 방법을 제안한다. 오류 보정 방법은 부여된 가중치를 보정해야 할 조건들의 우선순위로 사용할 수 있다. 후진 방법에 의하여 생성된 이정표 상태들은 복잡정도가 낮고 또한 적당한 값의 가중치를 가지게 되므로 이정표를 이용한 효율적인 계획 오류 보정 방법을 보장하게 된다.