• Journal of Biosystems Engineering
• /
• v.22 no.3
• /
• pp.317-324
• /
• 1997

This study was conducted to develope a machine vision system for a robotic transplanter for bedding plants. Specific objectives of this study were 1) to get coordinates of the healthy seedlings in high-density plug tray, and 2) to get the angle of the leaves of the healthy seedlings to avoid the damage to seedlings by gripper. Results of this study were summarized as follows. (1) The machine vision system of a robotic transplanter was developed. (2) Success rates of detecting empty cell and bad seedlings for 72-cell and 128-cell plug-trays were 98.8% and 94, 9% respectively. (3) Success rates of calculating the angle of leaves fer 72-cell and 128-cell plug-trays were 93.5% and 91.0% respectively.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.25 no.6
• /
• pp.522-531
• /
• 2016

In this study, we propose an object identification method for bin-picking developed for industrial robots. We identify the grasp posture and the associated geometric parameters of grasp objects using the joint data of a robotic gripper. Prior to grasp identification, we analyze the grasping motion in a low-dimensional space using principle component analysis (PCA) to reduce the dimensions. We collected the joint data from a human hand to demonstrate the grasp-identification algorithm. For data acquisition of the human grasp data, we conducted additional research on the motion characteristics of a human hand. We explain the method for using the algorithm of grasp identification for bin-picking. Finally, we present a subject for future research using our proposed algorithm of grasp model and identification.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1993.10a
• /
• pp.850-858
• /
• 1993

Germinatin and early growth of tobacco seedlings in trays containing many cells is increasing in popularity . Since 100 % germination is not likely , a major problem is to locate and replace the content of those cells which contain either no seedling or a stunted seedling with a plug containing a viable seedling. Empty cells and seedlings of poor quality take up valuable space in a greenhouse. They may also cause difficulty when transplanting seedlings into the field. Robotic technology, including the implementation of computer vision, appears to be an attractive alternative to the use of manual labor for accomplishing this task. Operating AGBOT, short for Agricultural ROBOT, involved four steps : (1) capturing the image, (2) processing the image, (3) moving the manipulator, (4) working the gripper. This research seedlings within a cell-grown environment. the configuration of the cell-grown seedling environment dictated the design of a Cartesian robot suitable for working ov r a flat plane. Experiments of AGBOT performance in transferring large seedlings produced trays which were more than 98% survived one week after transfer. In general , the system generated much better than expected.

• The Journal of Korea Robotics Society
• /
• v.15 no.2
• /
• pp.91-99
• /
• 2020

Fruit and vegetable harvesting robots have been widely studied and developed in recent years to reduce the cost of harvesting tasks such as labor and time. However, harvesting robots have many challenges due to the difficulty and uncertainty of task. In this paper, we characterize the crop environment related to the harvesting robot and analyzes state-of-the-art of the harvesting robot especially, in the viewpoint of robotic end-effector. The end-effector, an one of most important element of the harvesting robot, was classified into gripper and harvesting module, which were reviewed in more detail. Performance measures for the evaluation of harvesting robot such as test, detachment success, harvest success, and cycle time were also introduced. Furthermore, we discuss the current limitations of the harvesting robot and challenges and directions for future research.

• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.16-22
• /
• 2024

Robotic grasping in unstructured environments poses a significant challenge, demanding precise estimation of gripping positions for diverse and unknown objects. Generative Grasping Convolution Neural Network (GG-CNN) can estimate the position and direction that can be gripped by a robot gripper for an unknown object based on a three-dimensional depth map. Since GG-CNN uses only a depth map as an input, the precision of the depth map is the most critical factor affecting the result. To address the challenge of depth map precision, we integrate the Segment Anything Model renowned for its robust zero-shot performance across various segmentation tasks. We adjust the components corresponding to the segmented areas in the depth map aligned through external calibration. The proposed method was validated on the Cornell dataset and SurgicalKit dataset. Quantitative analysis compared to existing methods showed a 49.8% improvement with the dataset including surgical instruments. The results highlight the practical importance of our approach, especially in scenarios involving thin and metallic objects.

• The Journal of Korea Robotics Society
• /
• v.4 no.2
• /
• pp.155-162
• /
• 2009

A main distributing frame(MDF) is an interface unit that is used to connect office equipment cables in a telephone company to subscriber cables. Until now, there is no automated switching system for MDFs in Korea. Manual handling of an MDF has some drawbacks; It is time-consuming, very cumbersome, and expensive. It also makes maintenance hard. An automated main distributing frame system is proposed and commercialized in Japan. In that system, a robot gripper inserts connecting pins into the cross point holes of a matrix board, which reveals several disadvantages in the aspects of space, maintenance, fault tolerance, and economical efficiency. This paper describes a newly developed robotic switch board system for MDFs. In the developed system, switches are placed at the cross point of a matrix board. There is one robot in between two switch units, so one robot deals with two switch units. In the system, positioning the robot, opening and closing switches can be done by using only a pair of motors and a pair of solenoids. The newly developed system is compact in size, reduces cost, and shows high reliability.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.5
• /
• pp.685-690
• /
• 2022

Recent research on soft adhesives has sought to understand in depth how their chemical or mechanical structures interact strongly with living tissues. The aim is to optimally address the unmet needs of patients with acute or chronic diseases. Synergy adhesion, which includes both electrostatic (hydrogen bonds) and mechanical interactions (capillary stress), appears to be effective in overcoming challenges related to long-term unstable bonds to wet surfaces. Here, we report electrostatic and mechanically synergistic mechanisms of adhesion without chemical residues. To infer the mechanism, a thermodynamic model based on custom combination adhesives has been proposed. The model supported experimental results that thermodynamically controlled swelling of hydrogels embedded in elastomeric structures improves biofluidic insensitive on-site adhesion to wet surfaces and improves detachment without chemical residues in the direction of peeling.

• Journal of the Korean Society of Industry Convergence
• /
• v.20 no.3
• /
• pp.233-243
• /
• 2017

This paper proposes a structure of direct-printed flexible tactile-sensor. These flexible tactile sensors are based on pressure-sensing materials that allow pressure to be measured according to resistance change that in turn results from changes in material size because of compressive force. The sensing material consists of a mixture of multi walled carbon nanotubes (MWCNTs) and TangoPlus, which gives it flexibility and elasticity. The tactile sensors used in this study were designed in the form of array structures composed of many lines so that single pressure points can be measured. To evaluate the performance of the flexible tactile sensor, we used specially designed signal-processing electronics and tactile sensors to experimentally verify the sensors' linearity. To test object grasp, tactile sensors were attached to the surface of the fingers of grippers with three degrees of freedom to measure the pressure changes that occur during object grasp. The results of these experiments indicate that the flexible tactile sensor-based robotic gripper can grasp objects and hold them in a stable manner.

• International Journal of Control, Automation, and Systems
• /
• v.2 no.3
• /
• pp.279-288
• /
• 2004

This paper presents a novel design for a tubular linear brushless permanent-magnet motor. In this design, the magnets in the moving part are oriented in an NS-NS―SN-SN fashion which leads to higher magnetic force near the like-pole region. An analytical methodology to calculate the motor force and to size the actuator was developed. The linear motor is operated in conjunction with a position sensor, three power amplifiers, and a controller to form a complete solution for controlled precision actuation. Real-time digital controllers enhanced the dynamic performance of the motor, and gain scheduling reduced the effects of a nonlinear dead band. In its current state, the motor has a rise time of 30 ms, a settling time of 60 ms, and 25% overshoot to a 5-mm step command. The motor has a maximum speed of 1.5 m/s and acceleration up to 10 g. It has a 10-cm travel range and 26-N maximum pull-out force. The compact size of the motor suggests it could be used in robotic applications requiring moderate force and precision, such as robotic-gripper positioning or actuation. The moving part of the motor can extend significantly beyond its fixed support base. This reaching ability makes it useful in applications requiring a small, direct-drive actuator, which is required to extend into a spatially constrained environment.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.2
• /
• pp.127-134
• /
• 2004

In this paper, human motor behaving model based sensory motor coordination(SMC) algorithm is implemented on robotic grasping task. Compare to conventional SMC models which connect sensor to motor directly, the proposed method used biologically inspired human behaving system in conjunction with SMC algorithm for fast grasping force control of robot arm. To characterize various grasping objects, pressure sensors on hand gripper were used. Measured sensory data are simultaneously transferred to perceptual mechanism(PM) and long term memory(LTM), and then the sensory information is forwarded to the fastest channel among several information-processing flows in human motor system. In this model, two motor learning routes are proposed. One of the route uses PM and the other uses short term memory(STM) and LTM structure. Through motor learning procedure, successful information is transferred from STM to LTM. Also, LTM data are used for next moor plan as reference information. STM is designed to single layered perception neural network to generate fast motor plan and receive required data which comes from LTM. Experimental results showed that proposed method can control of the grasping force adaptable to various shapes and types of greasing objects, and also it showed quicker grasping-behavior lumining time compare to simple feedback system.