• Transactions on Control, Automation and Systems Engineering
• /
• 제3권3호
• /
• pp.170-175
• /
• 2001

Q-learning is a kind of reinforcement learning where the agent solves the given task based on rewards received from the environment. Most research done in the field of Q-learning has focused on discrete domains, although the environment with which the agent must interact is generally continuous. Thus we need to devise some methods that enable Q-learning to be applicable to the continuous problem domain. In this paper, an extended fuzzy rule is proposed so that it can incorporate Q-learning. The interpolation technique, which is widely used in memory-based learning, is adopted to represent the appropriate Q value for current state and action pair in each extended fuzzy rule. The resulting structure based on the fuzzy inference system has the capability of solving the continuous state about the environment. The effectiveness of the proposed structure is shown through simulation on the cart-pole system.

• 제어로봇시스템학회논문지
• /
• 제18권12호
• /
• pp.1115-1121
• /
• 2012

This paper proposes a method to extract accurate plane of an object in unstructured environment for a humanoid robot by using a laser scanner. By panning and tilting 2D laser scanner installed on the head of a humanoid robot, 3D depth map of unstructured environment is generated. After generating the 3D depth map around a robot, the proposed plane extraction method is applied to the 3D depth map. By using the hierarchical clustering method, points on the same plane are extracted from the point cloud in the 3D depth map. After segmenting the plane from the point cloud, dimensions of the planes are calculated. The accuracy of the extracted plane is evaluated with experimental results, which show the effectiveness of the proposed method to extract planes around a humanoid robot in unstructured environment.

• 제어로봇시스템학회논문지
• /
• 제14권1호
• /
• pp.13-20
• /
• 2008

Sensor network consists of a large number of sensor node distributed in the environment being sensed and controlled. The resource-constrained sensor nodes tend to have various and heterogeneous architecture. Thus, it is important to make its software environment platform-independent and reprogrammable. In this paper, we present BeeVM, a Java operating system designed for sensor networks. BeeVM offers a platform-independent Java programming environment with its efficiently executable file format and a set of class APIs for basic operating functions, sensing and wireless networking. BeeVM's high-level native interface and layered network subsystem allow complex program for sensor network to be short and readable. Our platform has been ported on two currently popular hardware platforms and we show its effectiveness through the evaluation of a simple application.

• 제어로봇시스템학회논문지
• /
• 제14권5호
• /
• pp.496-501
• /
• 2008

Recently, many automotive companies tend to apply an air quality system (AQS), which prevents polluted air such as smoke or dust by controlling air intake actuator of vehicle, to satisfy the consumer's need for agreeable in-vehicle environment. However, performance of the traditional AQS is not satisfactory because a polluted air may enter into the inside of vehicle through the breaks of windows. Especially, the commercial vehicles such as bus or truck need to be prevented polluted air from the breaks of vehicle. Hence, as an alternative to the traditional AQS, this paper presents the architecture of smart AQS for commercial vehicle and implementation of the smart AQS. Also, the performance of the suggested system is evaluated through an experimental testbed.

• 한국지능시스템학회논문지
• /
• 제7권5호
• /
• pp.67-76
• /
• 1997

In this paper, a theoretical study is presented for the force control of a miniature robotic manipulator which is driven by a pair of piezo-electric bimorph cells. In the theoretical analysis, one finger is modeled as a flexible cantilevers with a force sensor at the tip and the finger is a solid beam. The robotic finger is used to hold the objects with different stiffness such as an iron block and a living insect and a moving objcet. So it is very important to develop an adequate controller for the holding operation of the finger. The main problems in force controlling are overdamping, overshoot and unknown environment(such as the stiffness of object and unknown plant parameters). So, the main target is propose the new fuzzy compensation for unknown environment and incease the system performance. The fuzzy compensation is implemented by using PI-type fuzzy approach to identified unknown environment. And the result of proposed controller was compared with the conventaional PID and optimal controller.

• 한국지능시스템학회논문지
• /
• 제5권3호
• /
• pp.3-10
• /
• 1995

This paper proposedan on-line learning controller which can be applied to nonlinear systems. The proposed on-line learning controller is based on the universal approximation by the local affine mapping-based neural networks. It has self-organizing and learning capability to adapt itself to the new environment arising from the variation of operating point of the nonlinear system. Since the learning controller retains the knowledge of trained dynamics, it can promptly adapt itself to situations similar to the previously experienced one. This prompt adaptability of the proposed control system is illustrated through simulations.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.468-468
• /
• 2000

In our laboratory, the control aspects are investigated in the photovoltaic power generation systems (PV systems). The PV system is very good for earth environment, but if it connects to power network system, many problems are raised (protection, voltage, harmonics etc.). In this paper, we present the result of the basic studies for the building of the PV system that amplifies the electric energy obtained from the solar cell. We consider electronic circuits in order to protect the PV system from power surge induced by lightning and also design an electronic circuit in order to detect defaults in the power network system. We would like to integrate these circuits into the PV system by considering its control equipment build by 8-bit microcomputer using various control theory (fuzzy, neural network etc.).

• 한국산업융합학회 논문집
• /
• 제25권2_2호
• /
• pp.193-198
• /
• 2022

In this paper, we introduce the improved control method are communicated between a master and a slave robot in the teleoperation systems. When the master and slave robots are located in different places, time delay is unavoidable under the network environment and it is well known that the system can become unstable when even a small time delay exists in the communication channel. The time delay may cause instability in teleoperation systems especially if those systems include haptic feedback. This paper presents a control scheme based on the estimator with virtual master model in teleoperation systems over the network. As the behavior of virtual model is tracking the one of master model, the operator can control real master robot by manipulating the virtual robot. And LQG/LTR scheme was adopted for the compensation of un-modeled dynamics. The approach is based on virtual master model, which has been implemented on a robot over the network. Its performance is verified by the computer simulation and the experiment.

• 제어로봇시스템학회논문지
• /
• 제18권9호
• /
• pp.878-886
• /
• 2012

This paper investigates the implementation and flight test of realtime vision guided autopilot system based on virtual instrumentation platform. A graphical design process via virtual instrumentation platform is fully used for the image processing, communication between systems, vehicle dynamics control, and vision coupled guidance algorithms. A significatnt ojective of the algorithm is to achieve an environment robust autopilot despite wind and an irregular image acquisition condition. For a robust vision guided path tracking and hovering performance, the flight path guidance logic is combined in a multi conditional basis with the position estimation algorithm coupled with the vehicle attitude dynamics. An onboard flight test equipped with the developed realtime vision guided autopilot system is done using the rotary UAV system with full attitude control capability. Outdoor flight test demonstrated that the designed vision guided autopilot system succeeded in UAV's hovering on top of ground target within about several meters under geenral windy environment.

• 제어로봇시스템학회논문지
• /
• 제13권2호
• /
• pp.121-127
• /
• 2007

Frequent occurrences of a fire cause tremendous loss of human lives and their property. Recently, in order to cope with such catastrophic accidents, researches on fire-fighting robots are carried out in developed countries. Under the dangerous situations, it is sometimes impossible for fire-fighting men to access the firing place because of explosive materials, smoke, high temperature and so on. In such an environment, fire-fighting robots can be useful to extinguish the fire. It is usually very dangerous place where fire-fighting robots operate. Hence, these robots should be controlled by remote users who are for away from the firing place exploiting remote communication systems. This paper considers the communication systems between fire-fighting robots and remote users. The communication systems consist of two parts; digital packet communication systems and analog image communication systems. Digital packet communication systems transfer data packets in order to control fire-fighting robots and to check the state of the fire-fighting robots. Remote users watch the video around the fire-fighting robots by exploiting the analog image communication systems. In the future, the more prosperous the commercial communication network systems will be, the more evolved the communication systems for fire-fighting robots are.