• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.936-939
• /
• 1996

In this paper, two specially designed associative mapping memories, called Associative Mapping Elements(AME) and Multiple-Digit Overlapping AME(MDO-AME), are presented for learning of nonlinear functions including kinematics and dynamics of robot manipulators. The proposed associative mapping memories consist of associative mapping rules(AMR) and weight update rules(WUR) which guarantee generalization and specialization of input-output relationship of learned nonlinear functions. Two simulation results, one for supervised learning and the other for unsupervised learning, are given to demonstrate the effectiveness of the proposed associative mapping memories.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.944-947
• /
• 1996

Realization of autonomous agents that organize their own internal structure in order to behave adequately with respect to their goals and the world is the ultimate goal of AI and Robotics. Reinforcement learning gas recently been receiving increased attention as a method for robot learning with little or no a priori knowledge and higher capability of reactive and adaptive behaviors. In this paper, we present a method of reinforcement learning by which a multi robots learn to move to goal. The results of computer simulations are given.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.1149-1152
• /
• 1996

Recently visual servo control is an important feature of an intelligent robot system. In this paper, we presents a Kalman filter approach for estimation of the linear optic flow model which is utilized in the visual servoing of a mobile robot. The proposed method is also compared with the conventional least mean square method via computer simulation.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.379-382
• /
• 1996

Evolution Strategy is used as an effective search algorithm in optimization problems and Sliding Mode Control is well known as a robust control algorithm. In this paper, we propose a Sliding Mode Control Method for robot manipulator using Evolution Strategy. Evolution Strategy is used to estimate Sliding Mode Control Parameters such as sliding surface gradient, continuous function boundary layer, unknown plant parameters and switching gain. Experimental results show the proposed control scheme has accurate and robust performances with effective search ability.

• 제어로봇시스템학회:학술대회논문집
• /
• 1987.10a
• /
• pp.870-875
• /
• 1987

The payload variation and modeling error can lye parameterized in such a way that known nonlinear functions are multiplied linearly by parameter errors. An adaptive control algorithm is derived for a perturbed linear system with such parameterization. Hence, in this approach no linear approximation of robot system is needed for the application of an adaptive law. The stability of the adaptive control algorithm is established and also supported by a computer simulation result.

• 제어로봇시스템학회:학술대회논문집
• /
• 1987.10a
• /
• pp.921-925
• /
• 1987

This paper presents the recent findings for collision avoidance of two manipulators in addition to the results shown in Lee [4]. The collision situation we assume here is that the prespecified final time $K_{f}$ and the prespecified path of one robot can be modified for the purpose of collision avoidance with the other robot. The collision avoidance problem is resolved into three independent categories for a systematic approach.h.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.145-146
• /
• 2008

LEGO Mindstorms NXT is a powerful robot programming target. It has ARM7, sensor and motor ports, and bluetooth support. and G-Code, C-Based, JAVA programming support, too. In this paper, we introduce the effectiveness of NXT via computer science education at college and university.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.61.6-61
• /
• 2001

In this paper, we propose a method to analyze measured data from 3D Laser tracking system and to enhance precision performance of a Cartesian robot. Position data are obtained over the stroke of a Cartesian robot with variable speeds. The measured data is need to model errors with several different sources. In general, the error is a function of part accuracy, assembly accuracy, temperature, and control etc. After the sources of errors are identified, they are used to enhance precision performance. The proposed method is more complete than others because we use very accurate 3D Laser tracking system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.37.5-37
• /
• 2001

A robust control for robot manipulators actuated by induction motors using neural networks(NNs) is considered. The control is designed to compensate for nonlinear dynamics associated with the mechanical subsystem and the electrical subsystems only with the measurements of link position, link velocity and stator winding currents. Two-layer NNs are used to approximate unknown functions occurring from parameter variation during backstepping design process. Specially, through the use of nonlinear observers for rotor flux, observed backstepping controller is designed to achieve uniform ultimately bounded link position tracking of the given reference signal ...

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.44.3-44
• /
• 2001

This articles describes a novel design elastic joint manipulator for a mobile robot, which works in an office environment with humans. The primary goal of this manipulator design is safeness on collision and contact. To achieve this, each joint is made of an elastic element and this is driver with a high ratio gear tram. The performance was verified, however, it has a serious drawback. It produce vibration, due to the elastic joints and high ratio gear train. We found that a sliding mode controller has an excellent performance for reducing such vibration. Results of computer simulation and experiments are shown.