• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.2
• /
• pp.186-191
• /
• 2003

Skills in tracing of the MR divide into following, approaching, avoiding and warning and so on. It is difficult to have all these skills learned as neural network. To make this up for, skills consisted of each module, and Mobile Robot was controlled by the output of module adequate for the situation. A mobile Robot was equipped multi-ultrasonic sensor and a USB Camera, which can be in place of human sense, and the measured environment information data is learned through Modular Neural Network. MNN consisted of optimal combination of activation function in the Expert Network and its structure seemed to improve learning time and errors. The Gating Network(GN) used to control output values of the MNN by switching for angle and speed of the robot. In the paper, EN of Modular Neural network was designed optimal combination. Traveling with a real MR was performed repeatedly to verity the usefulness of the MNN which was proposed in this paper. The robot was properly controlled and driven by the result value and the experimental is rewarded with good fruits.

• The Journal of Korea Robotics Society
• /
• v.15 no.2
• /
• pp.147-159
• /
• 2020

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.

• Journal of Ocean Engineering and Technology
• /
• v.23 no.5
• /
• pp.61-70
• /
• 2009

An AUV (Autonomous Underwater Vehicle) is an unmanned underwater vessel to investigate sea environments and deep sea resource. To be completely autonomous, AUV must have the ability to home and dock to the launcher. In this paper, we consider a class of homing trajectory planning problem for an AUV with kinematic and tactical constraints in horizontal plane. Since the AUV under consideration has underactuated characteristics, trajectory for this kind of AUV must be designed considering the underactuated characteristics. Otherwise, the AUV cannot follow the trajectory. Proposed homing trajectory panning method that called VGM (Virtual Goal Method) based on visibility graph takes the underactated characteristics into consideration. And it guarantees shortest collision free trajectory. For tracking control, we propose a PD controller by simple guidance law. Finally, we validate the trajectory planning algorithm and tracking controller by numerical simulation and ocean engineering basin experiment in KORDI.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.11
• /
• pp.1417-1423
• /
• 2020

This paper proposes a waypoint guidance algorithm for the Autonomous Underwater Vehicle(AUV). The proposed simplified guidance algorithm is presented, which is combined LOS guidance and cross-track guidance for path following. Cross-track error is calculated using the position of the AUV and reference path. LOS guidance and cross-track guidance are appropriately changed according to cross-track error. And the stability of the system has been improved using variable cross-track control gain by cross-track error. Also, in this paper, navigation hardware in-the loop simulation(HILS) is implemented to verify navigation algorithm of AUV that performs combined navigation using inertial navigation device and doppler velocity log(DVL). Finally, we design integrated system HILS (including navigation HILS) for performance verification of guidance algorithm of the autonomous underwater vehicle. By comparing the sea test result with HILS result, the proposed guidance algorithm and HILS configuration were confirmed be correct.

• The Journal of Korea Robotics Society
• /
• v.16 no.3
• /
• pp.250-259
• /
• 2021

Path planning is one of the important technologies for automated parking. It requires to plan a collision-free path considering the vehicle's kinematic constraints such as minimum turning radius or steering velocity. In a complex parking lot, Rapidly-exploring Random Tree^* (RRT^*) can be used for planning a parking path, and Reeds-Shepp or Hybrid Curvature can be applied as a tree-extension method to consider the vehicle's constraints. In this case, each of these methods may affect the computation time of planning the parking path, path-tracking error, and parking success rate. Therefore, in this study, we conduct comparative analysis of two tree-extension functions: Reeds-Shepp (RS) and Hybrid Curvature (HC), and show that HC is a more appropriate tree-extension function for parking path planning. The differences between the two functions are introduced, and their performances are compared by applying them with RRT^*. They are tested at various parking scenarios in simulation, and their advantages and disadvantages are discussed by computation time, cross-track error while tracking the path, parking success rate, and alignment error at the target parking spot. These results show that HC generates the parking path that an autonomous vehicle can track without collisions and HC allows the vehicle to park with lower alignment error than those of RS.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.1
• /
• pp.76-90
• /
• 2022

The platooning refers to a form in which one or more following vehicles along the path of the leading vehicle(directly driven by the driver) drive in one platoon using V2V, V2I communication and vehicle-mounted sensor. Platooning has emerged in line with the increasing demand for cargo volume and advanced transportation logistics systems, and is expected to have effects such as increasing capacity, reducing labor costs, and reducing fuel consumption. However, compared to general passenger cars, research on autonomous driving of trucks and verification of their effects are insufficient. Therefore, in this study, meta-analysis was conducted on the theme of the effect of truck platooning, and the results of existing studies related to platooning effects were integrated into one reliable, generalized, and objective summary estimate. In conclusion, it was analyzed that the introduction of truck platooning would have an effect of 13.93% increase in capacity, 38.76% decrease in conflict, and 8.13% decrease in fuel consumption.

• Journal of Drive and Control
• /
• v.20 no.4
• /
• pp.27-34
• /
• 2023

Weeding in orchards is closely associated with productivity and quality. The customary weeding process is both labor-intensive and time-consuming. To solve the problems, there is need for automation of agricultural robots and machines in the agricultural field. On the other hand, orchards have complicated working areas due to narrow spaces between trees and amorphous terrain. Therefore, it is necessary to develop customized robot technology for unmanned weeding work within the department. This study developed a path generation and path control method for unmanned weeding according to the orchard environment. For this, the width of the weeding span, the number of operations, and the width of the weeding robot were used as input parameters for the orchard environment parameters. To generate a weeding path, a weeding robot was operated remotely to obtain GNSS-based location data along the superheated center line, and a driving performance test was performed based on the generated path. From the results of orchard field tests, the RMSE in weeding period sections was measured at 0.029 m, with a maximum error of 0.15 m. In the steering period within row and steering to the next row sections, the RMSE was 0.124 m, and 0.047 m, respectively.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.17 no.2
• /
• pp.130-137
• /
• 2012

The underwater glider using conception of Lagrangian method, is a new observation platform to understand the properties of the ocean vertically. In 2011 March, KORDI made a first successful autonomous trip from Hupo to west coast of Uleungdo piloting Littoral Glider of Alaska Native Technology LLC. The journey considered many environmental variables and route vigilantly selected, the glider covered 177 km horizontally and took approximately 6 days (153 hours). Despite the existence of 1 kt eddy current, Sound velocity sampling was conducted from 5 meters and reaching maximum of 200 meters depth at each dive. It successfully collected sound velocity and temperature profile at every 5 seconds totaling up to 1408 profiles using SVT&P sensor. During the flight it was also a mission to check the diverse modes of the glider i.e. spiral, waypoints, heading, drift and hover could function without a defect in a given situation. These modes were thoroughly monitored and it could be considered that the glider handled it well during the flight. As a result of this test flight, it was evident that the given underwater glider could operate under 2kt current environment with users defined heading and depth, also with the payload up to 5 kg without changing internal buoyancy.

• Journal of Digital Convergence
• /
• v.15 no.12
• /
• pp.127-136
• /
• 2017

The purpose of this study is to explore some directions and alternatives for reforming the school education system, which is one of the core policy agendas of the Korean society that has met the upcoming 4th industrial revolution era and intelligence information society. Korean school education is a supplier-oriented system that does not take into consideration student's individual needs and aptitudes, and maintains uniform educational and learning practices while strengthening the characteristics of factory school model of the early 20th century. Especially, according to the excessive follow-up of the college entrance examination of the people the de-contextualization of knowledge and the instrumentation and learning of the education has been deepened. For the reform of the education system, first, it should transform the curriculum delegation system from the current administrative to teacher-based system. Second, we need to dismantle the bureaucratic corps of teacher that erodes the autonomy of the teacher and should establish the professional teacher system. Third, we should overcome egoism of each curriculum territory and reform the teacher education system. Fourth, it is necessary to overhaul the system of education and administrative bureaucracy as well as to overhaul the system of educational law. Fifth, it is necessary for the school administration to provide more effective communication between learners and teachers.