• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.3
• /
• pp.135-142
• /
• 2015

As the importance of software to society has grown, more and more schools worldwide teach coding basics in the classroom. Despite the rapid spread of coding instruction in grade schools, experience in the classroom is certainly limited because there is a gap between the curriculum and the existing computing environment such as the mobile and cloud computing. We propose an approach to fill this gap by using a mobile environment and the robot on the cloud-based platform for effective teaching. In this paper, we propose an architecture called Cloudboard that enables knowledge sharing and collaboration among knowledge providers in the cloud-based robot platforms. We also describe five representative architectural patterns that are referenced and analyzed to design the Cloudboard architecture. Our early experimental results show that the Cloudboard can be effective in the development of collective robotic systems.

• Phonetics and Speech Sciences
• /
• v.11 no.3
• /
• pp.39-47
• /
• 2019

We propose a method to improve the performance of spontaneous speech recognizers by extending their phone set using speech data. In the proposed method, we first extract variable-length phoneme-level segments from broadcast speech signals, and convert them to fixed-length latent vectors using an long short-term memory (LSTM) classifier. We then cluster acoustically similar latent vectors and build a new phone set by choosing the number of clusters with the lowest Davies-Bouldin index. We also update the lexicon of the speech recognizer by choosing the pronunciation sequence of each word with the highest conditional probability. In order to analyze the acoustic characteristics of the new phone set, we visualize its spectral patterns and segment duration. Through speech recognition experiments using a larger training data set than our own previous work, we confirm that the new phone set yields better performance than the conventional phoneme-based and grapheme-based units in both spontaneous speech recognition and read speech recognition.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.8
• /
• pp.659-665
• /
• 2000

In this paper a platoon merging control system is considered as a remotely located system with state represented by a stochastic process. in the system it is common to encounter situations where a single decision maker controls a large number of subsystems and observation and control signals are sent over a communication channel with finite capacity and significant transmission delays. Unlike a classical estimation problem where the observation is a continuous process corrupted by additive noise there is a constraint that the observation must be coded and transmitted over a digital communication channel with fintie capacity. A recursive coder-estimator sequence is a state estimation scheme based on observations transmitted with finite communication capacity constraint. in this paper we introduce a stochastic model for the lead vehicle in a platoon of vehicles in a lane considering the angle between the road surface and a horizontal plane as a stochastic process. In order to merge two platoons the lead vehicle of the following platoon is controlled by a remote control station. Using the observation transmitted over communication channel the remote control station designs the feedback controller. The simulation results show that the intervehicle spacings and the deviations from the desired intervehicle spacing are well regulated.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.4
• /
• pp.353-358
• /
• 2012

Human detection is a challenging task in many fields because it is difficult to detect humans due to their variable appearance and posture. Furthermore, it is also hard to track the detected human because of their dynamic and unpredictable behavior. The evaluation speed of method is also important as well as its accuracy. In this paper, we propose unified detection and tracking method for humans using Gaussian-PSO (Gaussian Particle Swarm Optimization) with the HOG (Histograms of Oriented Gradients) features to achieve a fast and accurate performance. Keeping the robustness of HOG features on human detection, we raise the process speed in detection and tracking so that it can be used for real-time applications. These advantages are given by a simple process which needs just one linear-SVM classifier with HOG features and Gaussian-PSO procedure for the both of detection and tracking.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.6
• /
• pp.477-486
• /
• 2001

Many physical systems can be modeled by incorporating continuous and discrete event nature together. Such hybrid systems contain both continuous and discrete states that influence the dynamic be-havior of the systems. There has been an increasing interest in thers types of systems during the last dec-ade, mostly due to the growing usage of computers in the control of physical plants but also as a result of the hybrid nature of physical processes. The stability theory for hybrid systems is considered as extension of Lyapunov theory where the existence of an abstract energy function satisfying certain properties verifies stability, called multiple Lyapunov theory. In this paper, a hybrid stabilizing controller is proposed using the control Lyapunov function method and multiple Lyapunov theory, and the proposed method is applied to lon-gitudinal spacing control in a vehicle platoon for intelligent transportation systems(ITS).

• The Journal of Korea Robotics Society
• /
• v.14 no.4
• /
• pp.285-292
• /
• 2019

Path planning is an important problem to solve in robotics and there has been many related studies so far. In the previous research, we proposed the Heterogeneous-Ants-Based Path Planner (HAB-PP) for the global path planning of mobile robots. The conventional path planners using grid map had discrete state transitions that constrain the only movement of an agent to multiples of 45 degrees. The HAB-PP provided the smoother path using the heterogeneous ants unlike the conventional path planners based on Ant Colony Optimization (ACO) algorithm. The planner, however, has the problem that the optimization of the path once found is fast but it takes a lot of time to find the first path to the goal point. Also, the HAB-PP often falls into a local optimum solution. To solve these problems, this paper proposes an improved ant-inspired path planner using the Rapidly-exploring Random Tree-star ($RRT^*$). The key ideas are to use $RRT^*$ as the characteristic of another heterogeneous ant and to share the information for the found path through the pheromone field. The comparative simulations with several scenarios verify the performance of the improved HAB-PP.

• The Journal of Korea Robotics Society
• /
• v.14 no.4
• /
• pp.301-310
• /
• 2019

A new algorithm has been propose to detect the reflected light region as disturbances in a real-time vision system. There have been several attempts to detect existing reflected light region. The conventional mathematical approach requires a lot of complex processes so that it is not suitable for a real-time vision system. On the other hand, when a simple detection process has been applied, the reflected light region can not be detected accurately. Therefore, in order to detect reflected light region for a real-time vision system, the detection process requires a new algorithm that is as simple and accurate as possible. In order to extract the reflected light, the proposed algorithm has been adopted several filter equations and clustering processes in the HSI (Hue Saturation Intensity) color space. Also the proposed algorithm used the pre-defined reflected light data generated through the clustering processes to make the algorithm simple. To demonstrate the effectiveness of the proposed algorithm, several images with the reflected region have been used and the reflected regions are detected successfully.

• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.117-129
• /
• 2024

This paper introduces collective navigation through a narrow gap using a curriculum-based deep reinforcement learning algorithm for a swarm of unmanned aerial vehicles (UAVs). Collective navigation in complex environments is essential for various applications such as search and rescue, environment monitoring and military tasks operations. Conventional methods, which are easily interpretable from an engineering perspective, divide the navigation tasks into mapping, planning, and control; however, they struggle with increased latency and unmodeled environmental factors. Recently, learning-based methods have addressed these problems by employing the end-to-end framework with neural networks. Nonetheless, most existing learning-based approaches face challenges in complex scenarios particularly for navigating through a narrow gap or when a leader or informed UAV is unavailable. Our approach uses the information of a certain number of nearest neighboring UAVs and incorporates a task-specific curriculum to reduce learning time and train a robust model. The effectiveness of the proposed algorithm is verified through an ablation study and quantitative metrics. Simulation results demonstrate that our approach outperforms existing methods.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.3 no.2
• /
• pp.119-125
• /
• 2008

This paper presents the polygon-based Q-leaning and Cascade Support Vector Machine algorithm for object search with multiple robots. We organized an experimental environment with ten mobile robots, twenty five obstacles, and an object, and then we sent the robots to a hallway, where some obstacles were lying about, to search for a hidden object. In experiment, we used four different control methods: a random search, a fusion model with Distance-based action making (DBAM) and Area-based action making (ABAM) process to determine the next action of the robots, and hexagon-based Q-learning and dodecagon-based Q-learning and Cascade SVM to enhance the fusion model with DBAM and ABAM process.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1884-1885
• /
• 2011

In the wireless sensor network (WSN) environment, the approximate point-in-triangulation (APIT) is a kind of range-free localization algorithm. This algorithm provides high precision, however, the coverage rate is somewhat poor. In this paper, we propose an improved APIT algorithm for the localization of swarm robots, which is based on the received signal strength indicator (RSSI) and the center of gravity (COG) methods.