Hsien-I Lin

Hsien-I Lin
National Taipei University of Technology · Graduate Institute of Automation Technology

Doctor of Engineering

About

93
Publications
11,537
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
658
Citations
Citations since 2016
50 Research Items
522 Citations
2016201720182019202020212022020406080100
2016201720182019202020212022020406080100
2016201720182019202020212022020406080100
2016201720182019202020212022020406080100

Publications

Publications (93)
Article
Full-text available
In this study, we proposed a behavior analysis for increasing the efficiency of human–robot collaboration in an assembly task. This study was inspired by previous research, in which a set of operator intentions in assembly was translated into an intention graph to formulate a probabilistic decision model for planning robot actions in the presence o...
Article
Abstract-Despite advances in robotic automation, the grasping and insertion of connectors remains problematic. This can mainly be attributed to the fact that most connectors have only a few image features by which they can be identified and the wires lack sufficient rigidity to support the connector in a stationary position. Many robots use RGB-D s...
Article
Full-text available
The mating of the board-to-board (BtB) connector is rugged because of its design complexity, small pitch (0.4 mm), and susceptibility to damage. Currently, the assembly task of BtB connectors is performed manually because of these factors. A high chance of damage to the connectors can also occur during the mating process. Thus, it is essential to a...
Article
Full-text available
Current robot polishing techniques are available for objects with computer-aided design geometric models but not for objects without geometric models such as ceramic or clay pots. In this study, we developed a robotic polishing/fettling system to polish the molding defects of ceramic objects. The polishing force on the object surfaces is required t...
Article
Full-text available
The current trend in automated optical inspection (AOI) systems employs deep learning models to detect defects on a metal surface. The setback of deep learning models is that they are time-consuming because the images obtained after every lighting adjustment must be used to train the deep learning models again and confirm whether the detection resu...
Article
Full-text available
Manual detection of ColoRectal Cancers (CRC) is subject to bias and time-consuming. To be objective and efficient, this study proposes a semiautomated method to predict CRC based on the number of Circulating Tumor Cells (CTCs). To count CTCs, this method uses SVM to find possible CTCs using features such as cell size, the ratio of the image area of...
Article
Full-text available
This study proposed a calligraphy brush trajectory model for the behavior of brush movements and provided the three-dimensional handle coordinates for a robotic arm to write calligraphy. This study dealt with basic footprints and bent lines of calligraphy and proceeded as follows. The shape of brush footprints on paper was measured, which provided...
Article
In this study, an intelligent robotic precise assembly system for rapid teaching and admittance control was developed. The system comprised three parts, namely the teaching, trajectory learning, and controlling systems. The teaching system controlled the robotic arm through a haptic device and generated tactile feedback for the operator. The trajec...
Article
Full-text available
Automated optical inspection (AOI) is getting popular in quality of control in manufacturing. There is a huge demand to install AOI systems in production lines seamlessly. Usually, a conveyor is used in a product line to carry work-pieces. Thus, it becomes difficult to inspect the quality of products by images when work-pieces are moving. This pape...
Article
Previous studies involving robot skill learning have focused on learning to encode and regenerate a simple motion trajectory. Few studies have been conducted on robot skill learning of complex tasks. In this study, kinesthetic teaching was adopted to train basic robot motion blocks, which were adjusted according to the environmental situation and c...
Article
Full-text available
Data imbalance during the training of deep networks can cause the network to skip directly to learning minority classes. This paper presents a novel framework by which to train segmentation networks using imbalanced point cloud data. PointNet, an early deep network used for the segmentation of point cloud data, proved effective in the point-wise cl...
Article
Full-text available
Sports robots have become a popular research topic in recent years. For table-tennis robots, ball tracking and trajectory prediction are the most important technologies. Several methods were developed in previous research efforts, and they can be divided into two categories: physical models and machine learning. The former use algorithms that consi...
Conference Paper
Recent deep-learning methods have been paid more attention than shallow-learning ones because they have deep and complex structures to approximate functions. The salient feature of deep neural networks is to use many layers where many of them are used to extract data features and few are for classification or regression. The most severe problem of...
Chapter
In this paper, we designed the robotic polishing system for industrial polishing needs. The current robot polishing techniques are available for objects with CAD geometric models, but for an object whose geometric model is unavailable such as ceramic or clay pots, it is still a puzzle to derive robot polishing trajectories and force control. In our...
Article
Technologies for inserting electronic components are necessary within the electronics industry. Previously this was done by manual assembly, but todays customized machines have been specially designed for automatic assembly. A number of these machines even employ robot arms to insert nonconventional components. However, because special-purpose mach...
Article
Full-text available
Understanding human intention is an important ability for an intelligent robot to collaborate with a human to accomplish various tasks. During collaboration, a robot with such ability can predict the successive actions that a human partner intends to perform, provide necessary assistance and support, and remind for the missing and failure actions f...
Article
Full-text available
To operate a redundant manipulator to accomplish the end-effector trajectory planning and simultaneously control its gesture in online programming, incorporating the human motion is a useful and flexible option. This paper focuses on a manipulative instrument that can simultaneously control its arm gesture and end-effector trajectory via human tele...
Article
An indoor positioning method for robots is presented to improve the precision of displacement measurement using only low-cost inertial measurement units (IMUs). Firstly, a high-fidelity displacement estimation for linear motion is proposed. A new robot motion model is designed as well as an axis alignment that only uses a single axis of the acceler...
Conference Paper
Controlling humanoid robot posture with the consideration of balance is a difficult problem. In this paper, we present a posture-balance control approach for users to program humanoid robot postures. To regulate posture and balance control, the proposed idea is to develop a system which helps to program robot motion by human demonstration and maint...
Conference Paper
Inserting electronic components is a commonly-seen step in a manufacturing process of electronic products. Previously it was done by human operators. As long as the shortage of human labor advents, the insertion process of electronic components has been replaced by robots. Because pins of electronic components are usually curved and tilted from pie...
Article
Full-text available
The paper is concerned with the problem of multi-view three-dimensional (3D) point cloud registration. A novel global registration method is proposed to accurately register two series of scans into an object model underlying 3D imaging digitization by using the proposed oriented bounding box (OBB) regional area-based descriptor. A robot 3D scanning...
Article
The article presents a robot 3-D scanning system for generation of 3-D point clouds of an object by using multi-view 3-D scanning and novel data registration. Our approach mainly comprises two important elements in the determination of next best probe pose and multiple-view point clouds registration. A novel technique is proposed to register 3-D ob...
Article
Learning whole-body robot motion is a challenging task because balance control should be taken into consideration. An intuitive way to teach motion to a humanoid robot is to apply human demonstration data to the robot. Since balance control was usually done by presetting the zero-moment-point (ZMP) trajectory of a robot, the challenge became the co...
Article
Full-text available
The problem of multi-view 3-D point clouds registration is investigated and effectively resolved by the developed methodology. A registration method is proposed to register two series of scans into an object model by using the proposed oriented-bounding-box (OBB) regional area-based descriptor. Robot 3-D scanning is often employed to generate set o...
Article
Path planning is an essential task in robot soccer to enable the robot to quickly arrive at a desired location from which it can shoot or dribble the ball to a goal. Previous work in path planning used sonar or laser-based sensors to obtain local information for avoiding obstacles and reaching the goal. In the process, the robot may move slowly and...
Conference Paper
Full-text available
The paper is concerned with the problem of multiple three-dimensional point clouds registration. A novel global registration method is proposed to accurately register two series of scans into an object model underlying 3-D imaging digitization by using the proposed oriented-bounding-box (OBB) regional area-based descriptor. A robot 3-D scanning str...
Conference Paper
Full-text available
This paper presents a robot 3-D scanning system for generation of 3-D point clouds of an object by using multi-view 3-D scanning and novel data registration. Our approach mainly comprises of two important elements in the determination of next best robot pose and multiple-view point clouds registration. A novel technique is proposed to register 3-D...
Conference Paper
Robot manipulation for delicate industrial tasks has been a challenge and playing an important role in developing intelligent industrial robots. In this paper, we present force-field manipulation for an ethernet-case assembly task. Since the assembly trajectory is delicate, programming the trajectory is tedious and difficult by a robot teach pedant...
Conference Paper
With the continuous expansion of international terrorist organizations, terrorists have been looking for ways to cause massive destruction, in which one of dangerous weapons is a radiological source. The explosion of radiological sources makes radioactive particles scattered over a vast area, causing radiation contamination. To avoid radiation disa...
Conference Paper
Robotic calligraphy is an interesting problem and recently draws much attention. Two major problems in robotic calligraphy are stroke shape and stroke order. Most of previous work focused on controlling brush trajectory, pressure, velocity, and acceleration to draw a desired stroke shape. As for stroke order, it was manually given from a database....
Article
Full-text available
Programming robots by human demonstration is an intuitive approach, especially by gestures. Because robot pick-and-place tasks are widely used in industrial factories, this paper proposes a framework to learn robot pick-andplace tasks by understanding human hand gestures. The proposed framework is composed of the module of gesture recognition and t...
Conference Paper
This paper presents a robot vision system to recognize both different target objects and their poses that can be incorporated in robot programming by demonstration (robot PbD). In recent years, robot PbD has become a popular topic in the field of robotics. Programming robots is a time-consuming process and requires technical knowledge. However, rob...
Conference Paper
Humanoid robot motion imitation is a problem of controlling robot balance with given body motion. It is a simple method to program robot motion because many robot motion editing tools do not consider balance control. Thus, this paper proposes a concept that a RGB-D camera such as Kinect is used to capture human motion and apply the captured motion...
Article
Human intention recognition in human-robot interaction (HRI) has been a papular topic. This paper presents a human-intention recognition framework using Markov decision processes (MDPs). The framework is composed of the object and motion layers. The object and motion layers obtain the object information and human hand gestures, respectively. The in...
Article
Full-text available
Intuitive kinematic control of a redundant robot arm to track a specified end-effector trajectory is achieved via haptic devices or homogenous robots with the same degrees of freedom (DOFs) and similar mechanical structures. To improve intuitive control, this work proposes a novel method to control directly by human motion the kinematics of a redun...
Article
Endowing a robot with skills to perform manipulative tasks has an important role in developing an intelligent robot. To manipulate objects, a robot needs perception and action skills. However, designing the programming framework to integrate a variety of skills in a robot system is a challenging task and significantly influences the robot performan...
Conference Paper
Full-text available
Automatic human gesture recognition from camera images is an interesting topic for developing intelligent vision systems. In this paper, we propose a convolution neural network (CNN) method to recognize hand gestures of human task activities from a camera image. To achieve the robustness performance, the skin model and the calibration of hand posit...
Conference Paper
Searching radiation sources in a nuclear environment plays an important role in securing nuclear safety. In this paper, we present a search strategy of a mobile robot for radiation sources in an unknown environment. The proposed method enables a mobile robot to find radiation sources autonomously because it is harmless to expose the robot to an env...
Article
Previous work in robot teleoperation focused on the movement of a robot's end-effector by a human operator. However, a lack of pose control in teleoperation resulted in the robot arm frequently colliding with obstacles. Furthermore, even with pose control, it is still difficult for the robot to quickly and accurately move to the target due to mecha...
Article
The article presents an in situ clouds-powered radioactive source detection and localization approach, namely color-depth-radiation mapping, using 3-D land mapping within hazardous indoor environment and incorporating sensor fusion between a RGB-D camera and a portable radiation detector. In the approach, to achieve fast and robust image registrati...
Article
Full-text available
The most important tool for controlling an industrial robotic arm is a teach pendant, which controls the robotic arm movement in work spaces and accomplishes teaching tasks. A good teaching tool should be easy to operate and can complete teaching tasks rapidly and effortlessly. In this study, a new teaching system is proposed for enabling users to...
Conference Paper
Programming by human demonstration is an intuitive methodology to program robots. Since pick-and-place tasks are common, this paper proposes a framework to learn robot pick-and-place tasks by human demonstration. To recognize human motion, we adopt Gilbreth's therbligs to represent it. For each therblig, this work uses a corresponding robot motion...
Article
Human-to-Humanoid motion imitation is an intuitive method to teach a humanoid robot how to act by human demonstration. For example, teaching a robot how to stand is simply showing the robot how a human stands. Much of previous work in motion imitation focuses on either upper-body or lower-body motion imitation. In this paper, we propose a novel app...
Article
A gait measurement system is a useful tool for rehabilitation applications. Such a system is used to conduct gait experiments in large workplaces such as laboratories where gait measurement equipment can be permanently installed. However, a gait measurement system should be portable if it is to be used in clinics or community centers for aged peopl...
Conference Paper
Gesture semantic recognition is a vital process of motion recognition. An accurate and stable recognition method helps to identify semantic meaning of a continuous motion. In this work, the semantic meaning is represented by a sequence of motion primitives. This work proposes a method based on spatial and temporal reasoning. Both spatial and tempor...
Article
In robot trajectory planning, finding the minimum-jerk joint trajectory is a crucial issue in robotics because most robots are asked to perform a smooth trajectory. Jerk, the third derivative of joint position of a trajectory, influences how smoothly and efficiently a robot moves. Thus, the minimum-jerk joint trajectory makes the robot control algo...
Article
Full-text available
Robot motor capability is a crucial factor for a robot, because it affects how accurately and rapidly a robot can perform a motion to accomplish a task constrained by spatial and temporal conditions. In this paper, we propose and derive a pseudo-index of motor performance (pIp) to characterize robot motor capability with robot kinematics, dynamics...
Conference Paper
The article presents an efficient method in detecting critical 3-D feature points for efficient and accurate data registration required in real-time indoor environment mapping by using RDB-D cameras. To achieve fast and accurate data correspondence between different 3-D scanned images, in the proposed method, RGB images are first used to detect two...
Article
Finding the hip joint center (HJC) is crucial in human gait analysis since it affects kinematics and kinetics calculation of human lower limbs. Currently, the HJC location is found by either functional or prediction approaches. Prediction approaches simply use the pelvic geometric parameters to predict the HJC location. Functional approaches have b...
Article
Endowing robots with the ability of skill learning enables them to be versatile and skillful in performing various tasks. This paper proposes a neuro-fuzzy-based, self-organizing skill-learning framework, which differs from previous work in its capability of decomposing a skill by self-categorizing it into significant stimulus-response units (SRU,...
Conference Paper
Reaching is a fundamental skill for a robot. The purpose of robot reaching is to bring a robot hand to an object without any obstacle collision. Conventional handcrafted methods were complicated to implement reaching skill. Thus, this paper proposes a method using primitives acquired from human demonstrations to learn collision-free reaching skill....
Conference Paper
Reaching to an object is a fundamental skill to a robot. The purpose of robot reaching aims at bringing the robot hands to the object location without obstacle collision. Since implementing such robot reaching movement is a tedious task, this paper proposes a method to synthesize robot reaching movement by human demonstration. However, human demons...
Article
In robot trajectory planning, finding the minimum-jerk joint trajectory is a crucial issue in robotics because most robots are asked to perform a smooth trajectory. Jerk, the third derivative of joint position of a trajectory, influences how smoothly and efficiently a robot moves. Thus, the minimum-jerk joint trajectory makes the robot control algo...
Conference Paper
Robot skill learning by imitation is an intuitive approach to learn robot skills from the observation of human behaviors. However, due to the discrepancy of mechanism between humans and robots such as the type of joint and the number of degree of freedom (DOF), a robot may not be able to imitate a human's movements faithfully. For a robot arm, the...
Article
Tele-operated robotics has been widely-used to manipulate heavy or hazardous objects in an unknown or dangerous environment. Nowadays, it is adopted in assistive robots to help the elderly in accomplishing household tasks. This paper proposes a hybrid control policy of robot arm motion to semi-automatically control a remote robot arm, which differs...
Article
Laser range finder (LRF) is commonly utilized in a position measurement system to measure the locations of objects in an environment. Conventional approaches employ a laser range finder and a reference marker placed at the location of the object to measure the distance between them. The drawbacks of these methods are cost-ineffectiveness and labor...
Article
Full-text available
A graphic modeling approach for fast fault section estimation via Boolean rule matrix transformations is proposed in this paper. This study extends matrix-based inference in fault diagnosis from radial distribution networks to mesh transmission networks. The proposed approach offers a clear framework, rapid reasoning, and has no problem of converge...
Article
The aims of this study were to compare the clinical features of patients with extensively drug-resistant tuberculosis (XDRTB) and multidrug-resistant tuberculosis (MDRTB) and the genotypic characteristics of these Mycobacterium tuberculosis isolates. A total of 90 non-HIV-infected patients having MDRTB (n = 80, not including XDRTB, 88.9%) and XDRTB...
Article
Clin Microbiol Infect 2011; 17: 190–192 We describe five patients with positive blood culture for Kocuria species. Three patients had catheter-related bacteraemia and one had infective endocarditis caused by Kocuria kristinae, and one had a K. marina isolate, which was considered to be a contaminant. Identification of the isolates was further confi...
Article
Health-care and assistive robotics is the emerging industrial in the coming decades due to the increase of the elderly population. Assistive robots are demanded to assist aged people in performing various tasks. Thus, it is essential to endow assistive robots with the ability to adapt learned skills for performing different tasks. This paper propos...
Conference Paper
Robot skills are usually learned from the so-called learning-from-human-demonstration methods. However, with the limitation of robot motor capability, a robot may not be able to duplicate human motor skills with the same motor performance. To alleviate the problem, one of the possible solutions is to know robot motor capability in advance. Thus, we...
Article
The inability of conventional identification systems to accurately identify Gordonia spp. often results in the misdiagnosis of infections by these rare pathogens, which require genomic sequencing for precise identification. In the present study, we describe nine cases of the various types of infection caused by Gordonia spp. From 1997 to 2008, 66 i...