• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.302-305
• /
• 1996

This paper presents a visual servoing combined by Neural Network with optimal structure and predictive control for robotic manipulators to tracking or grasping of the moving object. Using the four feature image information from CCD camera attached to end-effector of RV-M2 robot manipulator having 5 dof, we want to predict the updated position of the object. The Kalman filter is used to estimate the motion parameters, namely the state vector of the moving object in successive image frames, and using the multi layer feedforward neural network that permits the connection of other layers, evolutionary programming(EP) that search the structure and weight of the neural network, and evolution strategies(ES) which training the weight of neuron, we optimized the net structure of control scheme. The validity and effectiveness of the proposed control scheme and predictive control of moving object will be verified by computer simulation.

• Korean Chemical Engineering Research
• /
• v.57 no.2
• /
• pp.274-282
• /
• 2019

In recent years, big data analysis has been expanded to include automatic control through reinforcement learning as well as prediction through modeling. Research on the utilization of image data is actively carried out in various industrial fields such as chemical, manufacturing, agriculture, and bio-industry. In this paper, we applied NASNet, which is an AutoML reinforced learning algorithm, to DeepU-Net neural network that modified U-Net to improve image semantic segmentation performance. We used BRATS2015 MRI data for performance verification. Simulation results show that DeepU-Net has more performance than the U-Net neural network. In order to improve the image segmentation performance, remove dropouts that are typically applied to neural networks, when the number of kernels and filters obtained through reinforcement learning in DeepU-Net was selected as a hyperparameter of neural network. The results show that the training accuracy is 0.5% and the verification accuracy is 0.3% better than DeepU-Net. The results of this study can be applied to various fields such as MRI brain imaging diagnosis, thermal imaging camera abnormality diagnosis, Nondestructive inspection diagnosis, chemical leakage monitoring, and monitoring forest fire through CCTV.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.1
• /
• pp.142-148
• /
• 2003

Reinforcement learning is considered as an important tool for robotic learning in unknown/uncertain environments. In this paper, we propose an evaluation function expressed in a vector form to realize multi-dimensional reinforcement learning. The novel feature of the proposed method is that learning one behavior induces parallel learning of other behaviors though the objectives of each behavior are different. In brief, all behaviors watch other behaviors from a critical point of view. Therefore, in the proposed method, there is cross-criticism and parallel learning that make the multi-dimensional learning process more efficient. By ap-plying the proposed learning method, we carried out multi-dimensional evaluation (reward) and multi-dimensional learning simultaneously in one trial. A special neural network (Q-net), in which the weights and the output are represented by vectors, is proposed to realize a critic net-work for Q-learning. The proposed learning method is applied for behavior planning of mobile robots.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2000.04a
• /
• pp.199-203
• /
• 2000

This paper presents a new approach to the design of cruise control system of a mobile robot with two drive wheel. The proposed control scheme uses a Gaussian function as a unit function in the fuzzy-neural network, and back propagation algorithm to train the fuzzy-neural network controller in the framework of the specialized learning architecture. It is proposed a learning controller consisting of two neural network-fuzzy based on independent reasoning and a connection net with fixed weights to simply the neural networks-fuzzy. The performance of the proposed controller is shown by performing the computer simulation for trajectory tracking of the speed and azimuth of a mobile robot driven by two independent wheels.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.41.3-41
• /
• 2001

In this paper, we present a decentralized adaptive neural net(NN) controller for the transient stability and voltage regulation of a multimachine power system. First, an adaptively input-output linearizing controller using NN is designed to eliminate the nonlinearities and interactions between generators. Then, a robust control term which bounds terminal voltage to a neighborhood of the operating point within the desired value is introduced using only local information. In addition, we consider input saturation which exists in the SCR amplifier and prove that the stability of the overall closed-loop system is maintained regardless of the input saturation. The design procedure is tested on a two machine infinite bus power system.

• ETRI Journal
• /
• v.45 no.5
• /
• pp.735-745
• /
• 2023

This paper surveys recent multiagent reinforcement learning and neural Myerson auction deep learning efforts to improve mobility control and resource management in autonomous ground and aerial vehicles. The multiagent reinforcement learning communication network (CommNet) was introduced to enable multiple agents to perform actions in a distributed manner to achieve shared goals by training all agents' states and actions in a single neural network. Additionally, the Myerson auction method guarantees trustworthiness among multiple agents to optimize rewards in highly dynamic systems. Our findings suggest that the integration of MARL CommNet and Myerson techniques is very much needed for improved efficiency and trustworthiness.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.983-985
• /
• 1995

In this paper, we propose a Self Organizing Feature Map (SOFM) Type Neural Computation Algorithm for the Travelling Salesman Problem(TSP). The actual best solution to the TSP problem is computatinally very hard. The reason is that it has many local minim points. Until now, in neural computation field, Hopield-Tank type algorithm is widely used for the TSP. SOFM and Elastic Net algorithm are other attempts for the TSP. In order to apply SOFM type neural computation algorithms to the TSP, the object function forms a euclidean norm between two vectors. We propose a Largrangian for the above request, and induce a learning equation. Experimental results represent that feasible solutions would be taken with the proposed algorithm.

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.8
• /
• pp.662-668
• /
• 2005

This paper presents a realization of check valve condition monitoring system based on fault diagnosis algorithm and Fieldbus communication. We first acquired AE(acoustic emission) sensor data at the check valve test loop, extract fault features through the teamed neural network, and send the processed data to a remote site. The overall system has been implemented and experimented results are given to show its effectiveness.

• Journal of Korea Multimedia Society
• /
• v.24 no.2
• /
• pp.186-198
• /
• 2021

Security control using surveillance cameras is established when people observe all surveillance videos directly. However, this task is labor-intensive and it is difficult to detect all abnormal situations. In this paper, we propose a deep neural network model, called AT-Net, that automatically detects abnormal situations in the surveillance video, and introduces an automatic video surveillance system developed based on this network model. In particular, AT-Net alleviates the ambiguity of existing abnormal situation detection methods by mapping features representing relationships between people and objects in surveillance video to the new tensor structure based on sparse coding. Through experiments on actual surveillance videos, AT-Net achieved an F1-score of about 89%, and improved abnormal situation detection performance by more than 25% compared to existing methods.

• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.522-526
• /
• 1994

There are great needs for checking machine operation status precisely in the iron and steel plants. Rotating machines such as pumps, compressors, and motors are the most important objects in the plant maintenance. In this paper back-propagation neural network is utilized in diagnosing rotating machines. Like the finger print or the voice print of human, the abnormal vibrations due to axis misalignment, shaft bending, rotor unbalance, bolt loosening, and faults in gear and bearing have their own spectra. Like the pattern recognition technique, characteristic. feature vectors are obtained from the power spectra of vibration signals. Then we apply the characteristic feature vectors to a back propagation neural net for the weight training and pattern recognition.