간행물
로봇학회논문지 KCI 등재 The Journal of Korea Robotics Society
- 발행기관 한국로봇학회
- 자료유형 학술지
- 간기 계간
- ISSN 1975-6291 (Print)2287-3961 (Online)
- 수록기간 2006 ~ 2020
- 주제분류 공학 > 제어계측공학 공학 분류의 다른 간행물
- 십진분류KDC 559DDC 629
권호리스트/논문검색
제15권 제2호(통권 제56호) (2020년 6월) 14건
1.
2020.06
서비스 종료(열람 제한)
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.
2.
2020.06
서비스 종료(열람 제한)
In the agricultural field, interests in research using robots for fruit harvesting are continuously increasing. Dual arm manipulators are promising because of its abilities like task-distribution and role-sharing. To operate it efficiently, the task sequence must be planned adequately. In our previous study, a collision-free path planning method based on a genetic algorithm is proposed for dual arm manipulators doing tasks cooperatively. However, in order to simplify the complicated collision-check problem, the movement between tasks of two robots should be synchronized, and thus there is a problem that the robots must wait and resume their movement. In this paper, we propose a heuristic algorithm that can reduce the total time of the optimal solution obtained by using the previously proposed genetic algorithm. It iteratively desynchronizes the task sequence of two robots and reduces the waiting time. For evaluation, the proposed algorithm is applied to the same work as the previous study. As a result, we can obtain a faster solution having 22.57 s than that of the previous study having 24.081 s. It will be further studied to apply the proposed algorithm to the fruit harvesting.
3.
2020.06
서비스 종료(열람 제한)
In robotic harvesting, a gripper to manipulate the fruits needs to be attached to the robot system. We proposed a flexible robot gripper that can actively respond to the shape of an object such as fruits in the previous work. However, we found that there is a possibility of not being reliably gripped when the object slides during contact with a finger. In this paper, the improved gripper design is proposed to fundamentally solve the problems of the previous gripper. The position of the finger and the maximum closed position are changed, and the design improvement is performed to increase the grip stability by changing the installation angle of the link portion of the finger. Based on the improved design, a modified gripper is fabricated by 3-D printing, and then gripping experiments are performed on spherical object and fruit model object. It is shown that the gripper can stably grip the objects without excessive bending of the finger link of the gripper. The contact pressure between the finger and the surface of the object is measured, and it is verified that it is a sufficiently small pressure that does not cause damage to the fruit. Therefore, the proposed gripper is expected to be successfully applied in harvesting.
4.
2020.06
서비스 종료(열람 제한)
Farmers using conventional sprayer system are exposed to pesticide poisoning and soil pollution due to pesticide application. In order to reduce this problem, the effective sprayer system is required. In this paper, we propose development of intelligent sprayer system using tree recognition. This intelligent sprayer system consists of an image recognition module, a remote control, a sprayer system, an air blower, and a control module. It is possible to spray pesticides automatically and manually through remote control using cameras and controls. We conducted a total of four experiments in tree recognition experiment, test of attachment and water sensitive papers, measurement of pesticide consumption, and measurement of worker exposure. The test results showed that the consumption of pesticides could be reduced while giving the same effect as conventional controls.
5.
2020.06
서비스 종료(열람 제한)
This paper designed modular agricultural robotic platform capable of a variety of agricultural tasks to address the problems caused by a decline in agricultural populations and an increase in average age. We propose a modular robotic platform that can perform many tasks required in field farming by replacing only work modules with common robotic platforms. This platform is capable of steering while driving on four wheels in an upland environment where farm work is performed, and an attitude control module is attached to each drive module to control the attitude of the platform. In addition, the width of the platform is designed to be variable in order to operate in various ridges according to the crop cultivation method. Finally, we evaluated five items: variable width, gradient, attitude control angle, step and road speed in order to carry out the farming industry while maintaining a stable posture.
6.
2020.06
서비스 종료(열람 제한)
This paper proposes a low-cost robotic surgery system composed of a general purpose robotic arm, an interface for daVinci surgical robot tools and a modular haptic controller utilizing smart actuators. The 7 degree of freedom (DOF) haptic controller is suspended in the air using the gravity compensation, and the 3D position and orientation of the controller endpoint is calculated from the joint readings and the forward kinematics of the haptic controller. Then the joint angles for a general purpose robotic arm is calculated using the analytic inverse kinematics so that that the tooltip reaches the target position through a small incision. Finally, the surgical tool wrist joints angles are calculated to make the tooltip correctly face the desired orientation. The suggested system is implemented and validated using the physical UR5e robotic arm.
7.
2020.06
서비스 종료(열람 제한)
In this paper, the slope of the footplate is adjusted to compensate for the centrifugal force with a series elastic actuator (SEA) attached to the Segway’s body to improve the cornering characteristics during turning. To ensure Segway’s driving safety in the curvature motion, it is necessary to compensate for the centripetal force by tilting the footplate to generate inward force from gravity. When the footplate is tilted under the control of SEA, the vertical load on both wheels has been changed accordingly. The frictional force of the wheel has been changed by the change of the vertical force, which requires adjustment of driving torque to keep the curvature trajectory. That is, the driving torque has been controlled to keep the curvature trajectory considering the frictional force caused by the turning motion. Four SEAs are attached to the footplate to control the slope of the footplate and the real curvature motion has been demonstrated to verify the effects of SEAs in the high- speed curvature motion.
8.
2020.06
서비스 종료(열람 제한)
Over the last years, a number of different path following methods for the autonomous parking system have been proposed for tracking planned paths. However, it is difficult to find a study comparing path following methods for a short path length with large curvature such as a parking path. In this paper, we conduct a comparative study of the path following methods for perpendicular parking. By using Monte-Carlo simulation, we determine the optimal parameters of each controller and analyze the performance of the path following. In addition, we consider the path following error occurred at the switching point where forward and reverse paths are switched. To address this error, we conduct the comparative study of the path following methods with the one thousand switching points generated by the Monte-Carlo method. The performance of each controller is analyzed using the V-rep simulator. With the simulation results, this paper provides a deep discussion about the effectiveness and limitations of each algorithm.
9.
2020.06
서비스 종료(열람 제한)
There exists a popular belief that the elderly are more conservative than the younger people in acceptability of new technology. This study explores whether the generation gap in technology acceptance exists in the case of using telepresence robots, which project the presence and mobility of remote operator, for the universal purpose of social participation rather than for specific applications. Two groups of senior citizens and undergraduate students in their twenties personally experienced the telepresence robots operation and conducted a survey on how they perceived the social participation of a remote operator mediated by telepresence robot and to what extent the remote operator deserve equal rights to be treated as if one really exists in the local environment. The results show that the elderly have higher expectation on the role and functions of telepresence robots, and more favorable in principle for a remote operator to exercise equal rights by operating telepresence robot. It suggests that the stereotypes, the elderly lag behind younger generation in accepting new technology, is unlikely to fit into the telepresence robot market, for the elderly have more favor and support using telepresence robots as an universal avatar for social participation.
10.
2020.06
서비스 종료(열람 제한)
This paper studied the collision detection of robot manipulators for safe collaboration in human-robot interaction. Based on sensor-based collision detection, external torque is detached from subtracting robot dynamics. To detect collision using joint torque sensor data, a comparative study was conducted using data-based machine learning algorithm. Data was collected from the actual 3 degree-of-freedom (DOF) robot manipulator, and the data was labeled by threshold and handwork. Using support vector machine (SVM), decision tree and k-nearest neighbors KNN method, we derive the optimal parameters of each algorithm and compare the collision classification performance. The simulation results are analyzed for each method, and we confirmed that by an optimal collision status detection model with high prediction accuracy.
11.
2020.06
서비스 종료(열람 제한)
Collaborative Robot (Cobot) that can collaborate with humans by fusion with many advanced technologies among industrial robots in the industrial field are attracting attention. In this study, the engineers of Small and Medium Enterprises can directly participate in the cobot design, and ultimately, the possibility of deriving the shape design of the differentiated cobot was studied. The method applied to derive the shape design of differentiated cobot is ‘Morphological Analysis’. First, the design elements of the form of cobots were derived as ‘Link’ and ‘Joint’. In addition, by analyzing the image form of the Link and Joint of the existing cobot, a new form element of the Link and Joint was proposed. In order to quantitatively identify the most discriminating cobot shape design, FGI (Focus Group Interview) was conducted to derive image types of 4 Link and 3 Joint. Then, the most important ‘Shape Combination’ was carried out in morphological analysis, and 12 new cobot shape designs were drawn. Through this, the applicability of the morphological analysis method in the derivation of differentiated cobot shape design was examined.
12.
2020.06
서비스 종료(열람 제한)
This paper is a study on data augmentation for small dataset by using deep learning. In case of training a deep learning model for recognition and classification of non-mainstream objects, there is a limit to obtaining a large amount of training data. Therefore, this paper proposes a data augmentation method using perspective transform and image synthesis. In addition, it is necessary to save the object area for all training data to detect the object area. Thus, we devised a way to augment the data and save object regions at the same time. To verify the performance of the augmented data using the proposed method, an experiment was conducted to compare classification accuracy with the augmented data by the traditional method, and transfer learning was used in model learning. As experimental results, the model trained using the proposed method showed higher accuracy than the model trained using the traditional method.
13.
2020.06
서비스 종료(열람 제한)
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.
14.
2020.06
서비스 종료(열람 제한)
In this paper, we present a learning platform for robotic grasping in real world, in which actor-critic deep reinforcement learning is employed to directly learn the grasping skill from raw image pixels and rarely observed rewards. This is a challenging task because existing algorithms based on deep reinforcement learning require an extensive number of training data or massive computational cost so that they cannot be affordable in real world settings. To address this problems, the proposed learning platform basically consists of two training phases; a learning phase in simulator and subsequent learning in real world. Here, main processing blocks in the platform are extraction of latent vector based on state representation learning and disentanglement of a raw image, generation of adapted synthetic image using generative adversarial networks, and object detection and arm segmentation for the disentanglement. We demonstrate the effectiveness of this approach in a real environment.
