• Korean Journal of Artificial Intelligence
• /
• v.11 no.4
• /
• pp.15-20
• /
• 2023

Machine learning is comprised of supervised learning, unsupervised learning and reinforcement learning as the type of data and processing mechanism. In this paper, as input and output are unclear and it is difficult to apply the concrete modeling mathematically, reinforcement learning method are applied for crawling robot in this paper. Especially, Q-Learning is the most effective learning technique in model free reinforcement learning. This paper presents a method to implement a crawling robot that is operated by finding the most optimal crawling method through trial and error in a dynamic environment using a Q-learning algorithm. The goal is to perform reinforcement learning to find the optimal two motor angle for the best performance, and finally to maintain the most mature and stable motion about EV3 Crawling robot. In this paper, for the production of the crawling robot, it was produced using Lego Mindstorms with two motors, an ultrasonic sensor, a brick and switches, and EV3 Classroom SW are used for this implementation. By repeating 3 times learning, total 60 data are acquired, and two motor angles vs. crawling distance graph are plotted for the more understanding. Applying the Q-learning reinforcement learning algorithm, it was confirmed that the crawling robot found the optimal motor angle and operated with trained learning, and learn to know the direction for the future research.

• Journal of Institute of Control, Robotics and Systems
• /
• v.2 no.1
• /
• pp.21-25
• /
• 1996

In this paper we suggest a general purpose RNN training algorithm which is derived on the optimal control concepts and variational methods. First, learning is regared as an optimal control problem, then using the variational methods we obtain optimal weights which are given by a two-point boundary-value problem. Finally, the modified gradient descent algorithm is applied to RNN for on-line training. This algorithm is intended to be used on learning complex dynamic mappings between time varing I/O data. It is useful for nonlinear control, identification, and signal processing application of RNN because its storage requirement is not high and on-line learning is possible. Simulation results for a nonlinear plant identification are illustrated.

• Journal of Advanced Marine Engineering and Technology
• /
• v.37 no.7
• /
• pp.743-751
• /
• 2013

In this paper, an approach to deal with model uncertainty using norm-optimal iterative learning control (ILC) is mentioned. Model uncertainty generally degrades the convergence and performance of conventional learning algorithms. To deal with model uncertainty, a worst-case norm-optimal ILC is introduced. The problem is then reformulated as a convex minimization problem, which can be solved efficiently to generate the control signal. The paper also investigates the relationship between the proposed approach and conventional norm-optimal ILC; where it is found that the suggested design method is equivalent to conventional norm-optimal ILC with trial-varying parameters. Finally, simulation results of the presented technique are given.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.49 no.4
• /
• pp.185-194
• /
• 2000

The learning automaton is an automaton to update systematically the strategy for enhancing the performance in response to the output results, and several schemes of learning automata have been presented. In this paper, S-model learning automata are applied in order to achieve the best compromise solution between an optimal solution for economic operation and an optimal solution for stable operation of the power system under the circumstance that the loads vary randomly. It is shown that learning automata are applied satisfactorily to the multiobjective optimization problem for obtaining the best tradeoff among the conflicting economy and stability objectives of power systems.

• Structural Engineering and Mechanics
• /
• v.87 no.4
• /
• pp.305-315
• /
• 2023

The idea of the combination of the fractional-order operators with the brain emotional learning-based intelligent controller (BELBIC) is developed for implementation in seismic-excited structures equipped with active mass damper (AMD). For this purpose, a new design framework of the mentioned combination namely fractional-order BEBIC (FOBELBIC) is proposed based on a modified-teaching-learning-based optimization (MTLBO) algorithm. The seismic performance of the proposed controller is then evaluated for a 15-story building equipped with AMD subjected to two far-field and two near-field earthquakes. An optimal BELBIC based on the MTLBO algorithm is also introduced for comparison purposes. In comparison with the structure equipped with a passive tuned mass damper (TMD), an average reduction of 44.7% and 42.8% are obtained in terms of the maximum absolute and RMS top floor displacement for FOBELBIC, while these reductions are obtained as 30.4% and 30.1% for the optimal BELBIC, respectively. Similarly, the optimal FOBELBIC results in an average reduction of 42.6% and 39.4% in terms of the maximum absolute and RMS top floor acceleration, while these reductions are given as 37.9% and 30.5%, for the optimal BELBIC, respectively. Consequently, the superiority of the FOBELBIC over the BELBIC is concluded in the reduction of maximum and RMS seismic responses.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.358-358
• /
• 2000

An iterative learning control technique based on a linear quadratic optimal criterion is proposed for temperature uniformity control of a silicon wafer in rapid thermal processing.

• International Journal of Control, Automation, and Systems
• /
• v.6 no.2
• /
• pp.194-203
• /
• 2008

Iterative learning control (ILC) is a simple and effective method for the control of systems that perform the same task repetitively. ILC algorithm uses the repetitiveness of the task to track the desired trajectory. In this paper, we propose a PID (proportional plus integral and derivative) type ILC update law for control discrete-time single input single-output (SISO) linear time-invariant (LTI) systems, performing repetitive tasks. In this approach, the input of controlled system in current cycle is modified by applying the PID strategy on the error achieved between the system output and the desired trajectory in a last previous iteration. The convergence of the presented scheme is analyzed and its convergence condition is obtained in terms of the PID coefficients. An optimal design method is proposed to determine the PID coefficients. It is also shown that under some given conditions, this optimal iterative learning controller can guarantee the monotonic convergence. An illustrative example is given to demonstrate the effectiveness of the proposed technique.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.160-161
• /
• 2023

Currently, the ship's passage planning relies on the navigator officer's knowledge and empirical methods. However, as ship autonomous navigation technology has recently developed, automation technology for passage planning has been studied in various ways. In this study, we intend to generate an optimal route for a ship based on Q-learning, one of the reinforcement learning techniques. Reinforcement learning is applied in a way that trains experiences for various situations and makes optimal decisions based on them.

• The Journal of Information Systems
• /
• v.27 no.3
• /
• pp.123-140
• /
• 2018

Purpose The purpose of this study is to explore the optimal trading frequency which is useful for stock price prediction by using deep learning for charting image data. We also want to identify the appropriate time for accurate forecasting of stock price when performing pattern analysis. Design/methodology/approach In order to find the optimal trading frequency patterns and forecast timings, this study is performed as follows. First, stock price data is collected using OpenAPI provided by Daishin Securities, and candle chart images are created by data frequency and forecasting time. Second, the patterns are generated by the charting images and the learning is performed using the CNN. Finally, we find the optimal trading frequency patterns and forecasting timings. Findings According to the experiment results, this study confirmed that when the 10 minute frequency data is judged to be a decline pattern at previous 1 tick, the accuracy of predicting the market frequency pattern at which the market decreasing is 76%, which is determined by the optimal frequency pattern. In addition, we confirmed that forecasting of the sales frequency pattern at previous 1 tick shows higher accuracy than previous 2 tick and 3 tick.

• Journal of KIBIM
• /
• v.12 no.2
• /
• pp.1-11
• /
• 2022

Road traffic accidents (RTAs) are the leading cause of accidental death among children. RTA reduction is becoming an increasingly important social issue among children. Municipalities aim to resolve this issue by introducing "Smart Pedestrian Crosswalks" that help prevent traffic accidents near children's facilities. Nonetheless such facilities tend to be installed in relatively limited number of areas, such as the school zone. In order for budget allocation to be efficient and policy effects maximized, optimal location selection based on machine learning is needed. In this paper, we employ machine learning models to select the optimal locations for smart pedestrian crosswalks to reduce the RTAs of children. This study develops an optimal location index using variable importance measures. By using k-means clustering method, the authors classified the crosswalks into three types after the optimal location selection. This study has broadened the scope of research in relation to smart crosswalks and traffic safety. Also, the study serves as a unique contribution by integrating policy design decisions based on public and open data.