• The Journal of Korea Robotics Society
• /
• v.18 no.4
• /
• pp.419-426
• /
• 2023

Assembly tasks are difficult to fully automate due to uncertain errors occurring in unstructured environments. When assembling parts such as electrical connectors, advances in grasping and assembling technology have made it possible for the robot to assemble the connectors without the aid of humans. However, some parts with tight assembly tolerances should be assembled by humans. Therefore, task sharing with human-robot interaction is emerging as an alternative. The goal of this concept is to achieve shared autonomy, which reduces the efforts of humans when carrying out repetitive tasks. In this study, a task-sharing robotic system for assembly process has been proposed to achieve shared autonomy. This system consists of two parts, one for robotic grasping and assembly, and the other for monitoring the process for robot-human task sharing. Experimental results show that robots and humans share tasks efficiently while performing assembly tasks successfully.

• Proceedings of the ESK Conference
• /
• 1998.04a
• /
• pp.31-35
• /
• 1998

Many reaearchers have reproted that poor body postures are associated with pains or symptoms of musculoskeletal dissoders. Therefore, the ergonomic evaluation of postural stresses as well as biomechanical stresses is important when a job such as automobile assembly tasks involves highly repetitive and/or prolonged poor body postures. A macropostural classification shema was developed to characterise various body postures occurring in automobile assembly tasks in the study. To specify a postural code and stress level to each body posture, perceived joint discomforts were subjectively evaluated in the lab experiments for the full range of motion in five human body joints. Based on the reaults, a postural classification scheme was developed where the full range of motion in each body joint was classified into several codes repressenting different stress levels. The automobile tasks were clustered into 12 types based on the result walk-in-surveillance and the possible posture codes for each task type are defined. I was exposed that the poor postural problems in automobile assembly tasks were concerned in most part with arms, trunk and neck. Application of te developed schema to seven operations in automobile assembly tasks showed that the schema can be used as a tool to identify the operations and tasks involving highly stressful body postures. The schema can also be utilised as a basis to prioritise the candidate assembly operations for redesign of work methods.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.1 no.1
• /
• pp.1-6
• /
• 2007

Applying the gyroscopic technology, HeadZmouse has been developed to simulate left and right mouse click, double click, drag and drop, and even a wheel function for navigating web. This device was designed to work on both PC and Macintosh environments using a USB cable. The first time you use this device, you'll find out how much freedom it offers to someone who can't use his or her hands freely. Rather than being tied to your computer, simple manipulation such as blowing an air (breathing) into a sonic sensor can simulate all the functions which standard mouse has, even including a wheel function. Also, a macro-interface device has been developed. By storing repetitive tasks into a memory, you can carry out repetitive tasks just by clicking a button once.

• Journal of the Korea Safety Management & Science
• /
• v.11 no.3
• /
• pp.79-85
• /
• 2009

In this study, the effects of psychosocial stress (box color and precision demand) on muscle activity were evaluated in laboratory setting. Eight subjects performed sagittally symmetric lifting tasks. Box color (yellow, black), precision demand (yes, no), and box weight (5%MVC, 10%MVC, 15 %MVC) were varied and surface EMG signals from seven muscles(medial deltoid right, biceps brachii right, lateral triceps right, latissimus dorsi right, erector spinae right, external oblique right, internal oblique right) were recorded. EMG signals were band-pass filtered($10{\sim}400\;Hz$), rectified, RMS smoothed and normalized (NEMG). Analysis of variance tests were conducted on the total NEMG (TNEMG: the sum of the seven muscles' NEMGs) and on the individual muscle's NEMGs. Box color had no effect on the TNEMG and on the seven muscles activities(p>0.05). When precision demand was required at the end point of lifts, the mean NEMG showed higher values than no precision demand conditions: TNEMG (14% increase) and medial deltoid(40% increase), biceps brachii(10% increase), lateral triceps(26% increase), latissimus dorsi(25% increase) muscles. Those increases showed more conspicuous as the box weight increased in the muscles of medial deltoid, lateral triceps, and latissimus dorsi.

• Journal of the Ergonomics Society of Korea
• /
• v.21 no.2
• /
• pp.25-33
• /
• 2002

The purpose of study is to investigate the relationship between the trunk muscle fatigue and recovery time during repetitive extension by using a surface electromyogram(EMG). Ten healthy subjects particioated in a simulated lifting task with five levels of recovery time and three levels of sub-maximal contraction. EMG signals of the L1(Lumbar 1st Vertebrae) and L3(Lumbar 3rd Vertebrae) level of the erector spinae muscle were recorded. and analyzed in terms of MPF(mean power frequency) parameter to quantify the level of muscle fatigue. It was found that MPF significantly (p<0.05) decreased during repetitive extension task at 50% and 75% sub-maximal contractions. Then it took minutes for the trunk muscle to recover from fatigue during 50% sub-maximal contraction. and it took five minutes during 75% sub-maximal contraction. and it took five minutes during 75% sub-maximal contraction. The recovery time estimated by the maximum force needs to be re-evaluated for the trunk muscle to fully recover from fatigue. In conclusion. the work/rest cycle needs to be studied based upon the information of muscle fatigue in order to prevent workers from musculoskeletal injuries during repetitive lifting task.

• International conference on construction engineering and project management
• /
• 2007.03a
• /
• pp.530-539
• /
• 2007

Many construction projects such as highways, pipelines, tunnels, and high-rise buildings typically contain repetitive activities. Research has shown that the Critical Path Method (CPM) is not efficient in scheduling linear construction projects that involve repetitive tasks. Linear Scheduling Method (LSM) is one of the techniques that have been developed since 1960s to handle projects with repetitive characteristics. Although LSM has been regarded as a technique that provides significant advantages over CPM in linear construction projects, it has been mainly viewed as a graphical complement to the CPM. Studies of scheduling linear construction projects with resource consideration are rare, especially with multiple resource constraints. The objective of this proposed research is to explore a resource assignment mechanism, which assigns multiple critical resources to all activities to minimize the project duration while satisfying the activities precedence relationship and resource limitations. Resources assigned to an activity are allowed to vary within a range at different stations, which is a combinatorial optimization problem in nature. A heuristic multiple resource allocation algorithm is explored to obtain a feasible initial solution. The Simulated Annealing search algorithm is then utilized to improve the initial solution for obtaining near-optimum solutions. A housing example is studied to demonstrate the resource assignment mechanism.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.15 no.3
• /
• pp.176-182
• /
• 2005

American Conference of Governmental Industrial Hygienists (ACGIH) adopted the Lifting Threshold Limit Values ($TLVs^{(R)}$) in 2005 as a guideline for protecting the workers from work-related low back and shoulder disorders associated with repetitive lifting tasks. The TLVs consist of three tables with recommended weight limits for lifting tasks and their determination procedures are simple. The TLVs sans the material weight/the recommended values (LITLVs) were obtained from 45 lifting tasks in ship engine manufacturing factories. These values were compared and correlated with the Recommended Weight Limits (RWLs) and lifting indices (LIs) determined by the Revised Lifting Equation (LE) of the National Institute for Occupational Safety and Health (NIOSH). The average ratio, LITLVs/LIs, was 0.8 (LITLVs: $1.3{\pm}0.8$, LIs: $1.6{\pm}0.7$). Thus, the TLVs underestimated the risk than the LE. The LITLVs were highly correlated with LIs (r=0.82). The predicted value of LITLVs when LIs=1 wa 0.76. Using the predicted TLVs the higher risk ones of a large number of tasks can be screened to be further investigated.

• Journal of Korean Institute of Industrial Engineers
• /
• v.33 no.1
• /
• pp.44-51
• /
• 2007

The purpose of this study was to identify the relationship between the cumulative fatigue of trunk muscles andthe period of recovery time during repetitive lifting and lowering tasks with symmetric and asymmetric postures.Ten subjects participated in the experiment. Subjects had 1, 2, 3, 4 and 5 minutes recovery time respectivelywhile they were performing the lifting and lowering task repeatedly for 3 minutes with the weight equivalent to25% level of MVC. EMG signals from ten trunk muscles were collected and the fatigue level was analyzedquantitatively. In results, the local muscle fatigue was no longer accumulated when 5 minutes recovery time wasgiven in symmetric position. For asymmetric position, it took longer minutes to prevent the fatigue accumul-ation. Different trunk muscles indicated slightly different recovery patterns in terms of MPF (Mean Powerfrequency) value.This result would help ergonomist design the length of recovery time to control the cumulative fatigue of trunkmuscles in industry with repetitive lifting and lowering task.

• International Journal of Safety
• /
• v.4 no.2
• /
• pp.43-46
• /
• 2005

The construction workers might be at the risk of many occupational injuries and illnesses. To protect workers from various hazards, industrial health and hygiene systems were specified for the construction workers by law. It is important to know the actual health and safety(H&S) conditions by tasks and the characteristics of injuries and illnesses of construction workers. This study was designed to investigate the actual conditions of construction workers exposed to various harmful substances and work elements including evaluation of health status of each worker and general H&S system. Questionnaire was sent to 600 construction workers nationwide and totally 367 people responded to it having 61.67% of response rate. The common construction hazards were dust(29.6%), noise(19.3%), repetitive motions(12.0%), handling excessive heavy materials(11.2%) in order. The repetitive motions and handling heavy materials related to muscle disorders accounted for 23.2%. The accident and injury types were in order of overexertion, falling, overturning, dropping or flying, electric shock, collision, etc.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.2
• /
• pp.45-50
• /
• 2020

A Language model with neural networks commonly trained with likelihood loss. Such that the model can learn the sequence of human text. State-of-the-art results achieved in various language generation tasks, e.g., text summarization, dialogue response generation, and text generation, by utilizing the language model's next token output probabilities. Monotonous and boring outputs are a well-known problem of this model, yet only a few solutions proposed to address this problem. Several decoding techniques proposed to suppress repetitive tokens. Unlikelihood training approached this problem by penalizing candidate tokens probabilities if the tokens already seen in previous steps. While the method successfully showed a less repetitive generated token, the method has a large memory consumption because of the training need a big vocabulary size. We effectively reduced memory footprint by encoding words as sequences of subword units. Finally, we report competitive results with token level unlikelihood training in several automatic evaluations compared to the previous work.