• Journal of Advanced Navigation Technology
• /
• v.25 no.1
• /
• pp.115-123
• /
• 2021

Pine nuts are Korea's representative nut forest products and profitable crops. However, pine nuts are harvested by climbing the trees themselves, thus the risk is high. In order to solve this problem, it is necessary to harvest pine nuts using a robot or an unmanned aerial vehicle(UAV). In this paper, we propose a deep learning based detection method for harvesting pine nut in UAV aerial images. For this, a video was recorded in a real pine forest using UAV, and a data augmentation technique was used to supplement a small number of data. As the data for 3D detection, Unity3D was used to model the virtual pine nut and the virtual environment, and the labeling was acquired using the 3D transformation method of the coordinate system. Deep learning algorithms for detection of pine nuts distribution area and 2D and 3D detection of pine nuts objects were used DeepLabV3+, YOLOv4, and CenterNet, respectively. As a result of the experiment, the detection rate of pine nuts distribution area was 82.15%, the 2D detection rate was 86.93%, and the 3D detection rate was 59.45%.

• Journal of the Korean Solar Energy Society
• /
• v.34 no.4
• /
• pp.17-22
• /
• 2014

The design of a fuel cells stack is important to get optimal output power. This study focuses on the evaluation of fuel cell system for unmaned aerial vehicles (UAVs). Low temperature proton exchange membrane (LTPEM) fuel cells are the most promising energy source for the robot applications because of their unique advantages such as high energy density, cold startup, and quick response during operation. In this paper, a 600 W open cathode LTPEM fuel cell was tested to evaluate the performance and to determine optimal operating conditions. The open cathode design reduces the overall size of the system to meet the requirement for robotic application. The cruise power requirement of 600 W was supported entirely by the fuel cell while the additional power requirements during takeoff was extended using a battery. A peak of power of 900 W is possible for 10 mins with a lithium polymer (LiPo) battery. The system was evaluated under various load cycles as well as start-stop cycles. The system response from no load to full load meets the robot platform requirement. The total weigh of the stack was 2 kg, while the overall system, including the fuel processing system and battery, was 4 kg.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.2
• /
• pp.137-148
• /
• 2014

A multi-rotor is an autonomous flying robot with multiple rotors. Depending on the number of the rotors, multi-rotors are categorized as tri-, quad-, hexa-, and octo-rotor. Given their rapid maneuverability and vertical take-off and landing capabilities, multi-rotors can be used in various applications such as surveillance and reconnaissance in hostile urban areas surrounded by high-rise buildings. In this paper, the unified dynamic model of each tri-, quad-, hexa-, and octo-rotor are presented. Then, based on derived mathematical equations, the operation and control techniques of each multi-rotor are derived and analyzed. For verifying and validating the proposed models, operation and control technique simulations are carried out.

• Journal of Digital Convergence
• /
• v.19 no.12
• /
• pp.145-150
• /
• 2021

In order to continuously perform quarantine in public places, it is not easy to secure manpower, but using self-driving-based robots can solve problems caused by manpower. Self-driving-based quarantine robots can continuously prevent the spread of harmful viruses and diseases in public institutions and hospitals without additional manpower. The location of the autonomous driving function was estimated by applying the Pinnacle filter algorithm, and the UV sterilization system and chlorine dioxide injection system were applied for quarantine. The driving time is more than 3 hours and the position error is 0.5m.Soon, the stop-avoidance function was operated at 95% and the obstacle detection distance was 1.5 m, and the automatic charge recovery was charged by moving to the charging cradle at the remaining 10% of the battery capacity. As a result of quarantine with an unmanned quarantine system, UV sterilization is 99% and chlorine dioxide is sterilized more than 95%, which can contribute to reducing enormous social costs.

• Design & Manufacturing
• /
• v.15 no.3
• /
• pp.56-61
• /
• 2021

The increase in automation facilities in the injection molding industry is a very important process control item. The most important item when constructing an unmanned machine using a take-out robot is the "mold opening stroke" of the mold. The injection molding machine control method is divided into hydraulic type and electric type, and there have been few studies on the mold opening distance according to the control method. In this study, the correlation was confirmed by increasing the injection speed to 20, 50, 80, and 100% for the three types of hydraulic control method, open loop and close loop, and electric control method. Through the experiment, the following results were obtained. (1) It can be seen that the reproducibility is excellent with the electric, close loop, and open loop control methods. (2) When the injection speed is set to 50%, the mold opening distance is 263.10~263.27 mm, which is the most reproducible. (3) As a result of ANOVA, both injection speed and mold opening distance showed a significant difference in the hydraulic control method (p<0.05), but it was verified through experiments that there was no significant difference in the electric control method. Based on these results, when electric control is selected rather than hydraulic control, the reproducibility of the mold opening distance is excellent, so it is thought that the taking-out robot can take the object out of the mold more safely.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.11-19
• /
• 2024

Multi-agent systems can be utilized in various real-world cooperative environments such as battlefield engagements and unmanned transport vehicles. In the context of battlefield engagements, where dense reward design faces challenges due to limited domain knowledge, it is crucial to consider situations that are learned through explicit sparse rewards. This paper explores the collaborative potential among allied agents in a battlefield scenario. Utilizing the Multi-Robot Warehouse Environment(RWARE) as a sparse reward environment, we define analogous problems and establish evaluation criteria. Constructing a learning environment with the QMIX algorithm from the reinforcement learning library Ray RLlib, we enhance the Agent Network of QMIX and integrate Random Network Distillation(RND). This enables the extraction of patterns and temporal features from partial observations of agents, confirming the potential for improving the acquisition of sparse reward experiences through intrinsic rewards.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.6
• /
• pp.35-41
• /
• 2008

The most important requirement for the automotive radars is the simultaneous target range and velocity measurement under environment of multi-target, clutters, multi-path, and so on. If the many vehicles with 77GHz FMCW(Frequency Modulation Continuous Wave) radar system are in the near area we should consider the interference signals occurred by other radar systems because these signals reduce exact detection of range and velocity. In this paper, we propose the interference cancellation method, which each vehicle radar transmits chirp trains with the different frequency sweep shapes. The proposed method is applied into the various applications such as an intelligent vehicle, Robot, and UGV(Unmanned Ground Vehicle).

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.233-236
• /
• 2008

Recently, the development and application of unmaned robots are increasing in various fields including surveillance and reconnaissance, planet exploration and disaster relief. Unmaned robots are usually controlled from distance using radio communications but they should be equipped with autonomous travelling function to cope with unexpected terrains and obstacles. This means that unmanned robots should be able to evaluate terrain's characteristics quantitatively using mounted sensors so as to traverse harsh natural terrains autonomously. For this purpose, this paper presents an algorithm for extracting terrain information from elevation maps as an early step of traversability analysis. Slope and roughness information are extracted from a world terrain map based on least squares method and fractal theory, respectively. The effectiveness of the proposed algorithm is verified on both fractal and real terrain maps.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.4
• /
• pp.326-333
• /
• 2001

This paper focuses on a method to connect mobile devices such as mobile robot. Automated Guided Vehicle (AGV) and Unmanned Container Transporter(UCT) to a fieldbus. In this paper, the IEEE 802.11 wireless LAN is used to extend a Profibus network for the mobile devices. In order to integrate these two networks, a gateway is developed using two threads and an internal buffer. Furthermore, a polling algorithm is applied at the gateway in order to satisfy real-time requirements on data communication, Finally, the performance measures such as data latency and throughput are experimentally evaluated on a wirelessly-extended Profibus network. The results shows the feasibility of the wireless extension of Profilbus for various mobile device.

• International journal of advanced smart convergence
• /
• v.9 no.4
• /
• pp.173-178
• /
• 2020

As the fourth industrial revolution, in which people, objects, and information are connected as one, various fields such as smart energy, smart cities, artificial intelligence, the Internet of Things, unmanned cars, and robot industries are becoming the mainstream, drawing attention to big data. Among them, Smart Grid is a technology that maximizes energy efficiency by converging information and communication technologies into the power grid to establish a smart grid that can know electricity usage, supply volume, and power line conditions. Smart meters are equient that monitors and communicates power usage. We start with the goal of building a virtual smart grid and constructing a virtual environment in which real-time data is generated to accommodate large volumes of data that are small in capacity but regularly generated. A major role is given in creating a software/hardware architecture deployment environment suitable for the system for test operations. It is necessary to identify the advantages and disadvantages of the software according to the characteristics of the collected data and select sub-projects suitable for the purpose. The collected data was collected/loaded/processed/analyzed by the Hadoop ecosystem-based big data platform, and used to predict power demand through deep learning.