• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.352-357
• /
• 2023

Since robotic assembly in an unstructured environment is very difficult with existing control methods, studies using artificial intelligence such as reinforcement learning have been conducted. However, since long-time operation of a robot for learning in the real environment adversely affects the robot, so a method to shorten the learning time is needed. To this end, a method based on a pre-trained neural network was proposed in this study. This method showed a learning speed about 3 times than the existing methods, and the stability of reward during learning was also increased. Furthermore, it can generate a more optimal policy than not using a pre-trained neural network. Using the proposed reinforcement learning-based assembly trajectory generator, 100 attempts were made to assemble the power connector within a random error of 4.53 mm in width and 3.13 mm in length, resulting in 100 successes.

• Journal of Korea Society of Industrial Information Systems
• /
• v.20 no.1
• /
• pp.9-18
• /
• 2015

Educational learning methods that take advantage of a robot provide opportunities for students to develop high dimensional thinking, a creative expression and discovery learning opportunity. It is also perceived as a suitable tool for STEAM systems which can be used in a variety of school curriculums. Therefore we designed and developed STEAM educational contents using robots in this study. This study analyze elementary text books and design the convergence contents from various subjects such as math, science, engineering and art through a robot. This study has developed educational materials by making a robot based on the designed contents. They have been applied to after school materials and then evaluated for comprehension, interest and participation. The results of this study have shown very encouraging evaluations from participating students. Accordingly, this study has shown that STEAM contents that take advantage of a robot have improved student participation, interests, and comprehension in the curriculums. Additionally, integrating STEAM educational content has proved more effective in contrast to being separated.

• The Journal of Korea Robotics Society
• /
• v.17 no.4
• /
• pp.455-462
• /
• 2022

Since electric connectors such as power connectors have a small assembly tolerance and have a complex shape, the assembly process is performed manually by workers. Especially, it is difficult to overcome the assembly error, and the assembly takes a long time due to the error correction process, which makes it difficult to automate the assembly task. To deal with this problem, a reinforcement learning-based assembly strategy using contact states was proposed to quickly perform the assembly process in an unstructured environment. This method learns to generate a search trajectory to quickly find a hole based on the contact state obtained from the force/torque data. It can also learn the stiffness needed to avoid excessive contact forces during assembly. To verify this proposed method, power connector assembly process was performed 200 times, and it was shown to have an assembly success rate of 100% in a translation error within ±4 mm and a rotation error within ±3.5°. Furthermore, it was verified that the assembly time was about 2.3 sec, including the search time of about 1 sec, which is faster than the previous methods.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.2
• /
• pp.107-116
• /
• 2016

Industrial robots have been usually controlled using text-based programming languages provided by each manufacturer with its button-based TP(Teaching Pendent) terminal. Unfortunately, when we consider that people who manipulate TPs in manufacturing sites are mostly unskilled with no background knowledge about computer programming, these text-based programming languages using button-based interaction on manufacturing sites are too difficult for them to learn and use. In order to overcome the weaknesses of the text-based programming language, we propose a visual programming language that can be easily used on gesture-enabled devices. Especially, in our visual programming environment, each command is represented as a block and robots are controlled by stacking those blocks using drag-and-drop gestures, which is easily learnable even by beginners. In this paper, we utilize a widely-spread device, Tablet PC as the gesture-enabled TP. Considering that Tablet PC has limited display space in contrast to PC environments, we designed different kinds of sets of command blocks and conducted user tests. Based on the experiment results, we propose an effective set of command blocks for Tablet PC environment.

• Journal of Internet Computing and Services
• /
• v.16 no.5
• /
• pp.99-105
• /
• 2015

Currently robots are widely used in schools for educational purpose. With wide spread of robot-based education, it is known that major advantage of robot-based education is to enhance creativity and logical thinking of students. Although robots can be very useful tools for assisting students' study activities, there have not been lots of teaching-learning models for robot-based education.In this paper, a teaching-learning model is presented for robot-based education. The proposed model is designed based on constructivism. The proposed model consists of 6 stages: preparation, design, assembling, demonstration run, evaluation, and application & extension. The proposed model has the following characteristics. First, the proposed model is designed to enhance creativity and logical thinking ability of learners. Learners are supposed to be involved in self-directed activities and required to provide results based on their own ideas. Teachers are supposed to mediate students only if necessary. Second, learners are encouraged to participate in activity via diverse interaction. The interaction in this model includes learner-to-learner interaction, learner-to-teacher interaction, and learner-to-expert interaction. The proposed model encourages learners to solve the problem with cooperating each other. Also, teachers are supposed to guide students if necessary and observe and monitor behavior of students all the time. Third, motivation is provided in the beginning stage of the instruction. Fourth, in the proposed model, both study results and study process are equally important. In the model, study process is reviewed at the final stage.

• The Journal of Korean Association of Computer Education
• /
• v.19 no.2
• /
• pp.87-98
• /
• 2016

Our study is composed of Arduino robot assembly, board connecting and collaborative programming learning, and it is to evaluate their effect on improving secondary mathematics-science gifted students' convergence capability. Research results show that interpersonal skills, information-scientific creativity and integrative thinking disposition are improved. Further, by analyzing the relationship between the sub-elements of each thinking element, persistence and imagination for solving problems, interest of scientific information, openness, sense of adventure, a logical attitude, communication, productive skepticism and so on are extracted as important factors in convergence learning. Thus, as the result of our study, we know that gifted students conducted various thinking activities in their learning process to solve the problem, and it can be seen that convergence competencies are also improved significantly.

• Composites Research
• /
• v.35 no.6
• /
• pp.371-377
• /
• 2022

Triboelectric nanogenerator (TENG) devices have generated a lot of interest in recent decades. TENG technology, which is one of the technologies for harvesting mechanical energy among the energy wasted in the environment, is obtained by the dual effect of electrostatic induction and triboelectric charging. Recently, a multilayer thin film stacking method (or layer-by-layer (LbL) self-assembly technique) is being considered as a method to improve the performance of TENG and apply it to new fields. This LbL assembly technology can not only improve the performance of TENG and successfully overcome the thickness problem in applications, but also present an inexpensive, environmentally friendly process and be used for large-scale and mass production. In this review, recent studies in the accomplishment of LbL-based materials for TENG devices are reviewed, and the potential for energy harvesting devices reviewed so far is checked. The advantages of the TENG device fabricated by applying the LbL technology are discussed, and finally, the direction and perspective of this fabrication technology for the implementation of various ultra-thin TENGs are briefly presented.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.2
• /
• pp.141-150
• /
• 2001

Manufacturing conb'ol applications consist of concurrent active components such as robots, AGV's (Automatic Guided Vehicles), and conveyors. Running of manufacturing control programs is interactions among those components. We can enhance the productivity and extendability of manufacturing control applications by using the object-oriented teclmology that models those components as reusable objects. But the objects in current object-oriented technology that encapsulate state and behavior infonnation are passive in a sense that those respond only when messages are sent to them. In this paper, we introduce the Distributed Active Object Systems (DAGS) approach that SUPPOltS active objects. Since active objects encapsulate control infonnation in addition to state and behavior information under COREA/Java-based distributed environment, they can represent manufacturing control components better than the objects in ordimuy object-oriented technology. TIus control infonnation provides an object with a featme that can monitor its own status as well as other object's status connected by intelface valiables. Active objects can initiate a behavior according to the change of those status. Therefore, we can sb-uctmally assemble self-initiating active objects by using intelface variables to construct a system without describing bow to control distributed objects by using message passing. As the DAOS approach supports object composability, we can enhal1ce the productivity and extendability of disbibuted manufactming control applications even better than the ordil1alY object-oriented approach. Also, the DAOS approach supports better component reusability with active objects that encapsulate control information .