• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.315-316
• /
• 2007

This paper presents a new methodology to improve movement database for a humanoid robot. The database is initially full of human motions so that the kinetics characteristics of human movement are immanent in it. then, the database is updated to the pseudo-optimal motions for the humanoid robot to perform more natural motions, which contain the kinetics characteristics of robot. for this, we use the evolutionary algorithm. the methodology consists of two processes : (1) the offline imitation learning of human movement and (2) the online generation of natural motion. The offline process improve the initial human motion database using the evolutionary algorithm and inverse dynamics-based optimization. The optimization procedure generate new motions using the movement primitive database, minimizing the joint torque. This learning process produces a new database that can endow the humanoid robot with natural motions, which requires minimal torques. In online process, using the linear combination of the motion primitive in this updated database, the humanoid robot can generate the natural motions in real time. The proposed framework gives a systematic methodology for a humanoid robot to learn natural motions from human motions considering dynamics of the robot. The experiment of catching a ball thrown by a man is performed to show the feasibility of the proposed framework.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1835-1845
• /
• 2021

To accurately identify black ice and warn the drivers of information in advance so they can control speed and take preventive measures. In this paper, we propose a lightweight black ice detection network based on infrared road images. A black ice recognition network model based on CNN transfer learning has been developed. Additionally, to further improve the accuracy of black ice recognition, an enhanced lightweight network based on MobileNetV2 has been developed. To reduce the amount of calculation, linear bottlenecks and inverse residuals was used, and four bottleneck groups were used. At the same time, to improve the recognition rate of the model, each bottleneck group was connected to a 3×3 convolutional layer to enhance regional feature extraction and increase the number of feature maps. Finally, a black ice recognition experiment was performed on the constructed infrared road black ice dataset. The network model proposed in this paper had an accurate recognition rate of 99.07% for black ice.

• ETRI Journal
• /
• v.42 no.1
• /
• pp.78-89
• /
• 2020

Human activity recognition (HAR) has become effective as a computer vision tool for video surveillance systems. In this paper, a novel biometric system that can detect human activities in 3D space is proposed. In order to implement HAR, joint angles obtained using an RGB-depth sensor are used as features. Because HAR is operated in the time domain, angle information is stored using the sliding kernel method. Haar-wavelet transform (HWT) is applied to preserve the information of the features before reducing the data dimension. Dimension reduction using an averaging algorithm is also applied to decrease the computational cost, which provides faster performance while maintaining high accuracy. Before the classification, a proposed thresholding method with inverse HWT is conducted to extract the final feature set. Finally, the K-nearest neighbor (k-NN) algorithm is used to recognize the activity with respect to the given data. The method compares favorably with the results using other machine learning algorithms.

• Communications of Mathematical Education
• /
• v.19 no.4 s.24
• /
• pp.715-731
• /
• 2005

There are five contexts of division algorithm of fractions such as measurement division, determination of a unit rate, reduction of the quantities in the same measure, division as the inverse of multiplication and analogy with multiplication algorithm of fractions. The division algorithm, however, should be taught by 'dividing by using reciprocals' via 'measurement division' because dividing a fraction by a fraction results in 'multiplying the dividend by the reciprocal of the divisor'. If a fraction is divided by a large fraction, then we can teach the division algorithm of fractions by analogy with 'dividing by using reciprocals'. To achieve the teaching-learning methods above in elementary school, it is essential for children to use the maniplatives. As Piaget has suggested, Cuisenaire color rods is the most efficient maniplative for teaching fractions. The instruction, therefore, of division algorithm of fractions should be focused on 'dividing by using reciprocals' via 'measurement division' using Cuisenaire color rods through analogy if necessary.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.1
• /
• pp.215-226
• /
• 2016

Modeling, control and implementation of a real redundant robot with five Degrees Freedom (DOF) of the SCARA (Selective Compliant Assembly Robot Arm) manipulator type is presented. Through geometric methods and structural and functional considerations, the inverse kinematics for redundant robot can be obtained. By means of a modification of the classical sliding mode control law through a hyperbolic function, we get a new algorithm which enables reducing the chattering effect of the real actuators, which together with the learning and adaptive controllers, is applied to the model and to the real robot. A simulation environment including the actuator dynamics is elaborated. A 5 DOF robot, a communication interface and a signal conditioning circuit are designed and implemented for feedback. Three control laws are executed in: a simulation structure (together with the dynamic model of the SCARA type redundant manipulator and the actuator dynamics) and a real redundant manipulator of the SCARA type carried out using MatLab/Simulink programming tools. The results, obtained through simulation and implementation, were represented by comparative curves and RMS indices of the joint errors, and they showed that the redundant manipulator, both in the simulation and the implementation, followed the test trajectory with less pronounced maximum errors using the adaptive controller than the other controllers, with more homogeneous motions of the manipulator.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.20 no.10
• /
• pp.3038-3047
• /
• 1996

In telerobot systems, visual servoing of a task object for a slave arm with an eye-in-hand has drawn an interesting attention. As such a task ingenerally conducted in an unstructured environment, it is very difficult to define the inverse feature Jacobian matrix. To overcome this difficulty, this paper proposes an auto-tuning fuzzy rule-based visual servo algorithm. In this algorithm, a visual servo controller composed of fuzzy rules, receives feature errors as inputs and generates the change of have position as outputs. The fuzzy rules are tuned by using steepest gradient method of the cost function, which is defined as a quadratic function of feature errors. Since the fuzzy rules are tuned automatically, this method can be applied to the visual servoing of a slave arm in real time. The effctiveness of the proposed algorithm is verified through a series of simulations and experiments. The results show that through the learning procedure, the slave arm and track object in real time with reasonable accuracy.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1994.10a
• /
• pp.266-272
• /
• 1994

An essential ingredient in precision machining is a positioning system that responds quickly and precisely to very small input signal. In this paper, two different positioning systems were presented fot the precision positioning control. The one is a friction drive system, the other is a ballscrew system. The friction drive system was composed of an air sliding guide and a friction drive. The ballscrew system was made of a ballscrew and a linear guide. Nonlinear behaviors of the given systems tend to make the system inaccurate. The paper looked at the phenomena that has caused the positioning error. These apparently nonlinear phenomena can be attributed mainly to the presence of the nonlinear friction and slip effect plus the dynamic change from the microdynamic to the macrodynamic and form the macrodynamic to the microdynamic. For the control of the positioning system, the control algorithm based on a neural network is suggested. The FEL(Feedback Error Learning) controller can learn the inverse dynamics of a nonlinear system by using the neural network controller, and stabilize the system by a linear controller. In the experiment, PTP control is implemented withen the maximum error of 0.05 .mu.m ~0.1 .mu. m when i .mu.m step reference input is applied and that of maximum 1 .mu. m when 100 .mu.m step reference input is given. Sinusoidal inputs with the amplitude of 1 .mu.m and 100 .mu. m are used for the tracking control of the positioning system. Experimental results of the proposed algorithm are shown to be superior to those of conventional PD controls.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2001.06a
• /
• pp.141-144
• /
• 2001

In this paper, we proposed a neural network controller with a fuzzy compensator which compensate a output of neural network controller. Even if learn by neural network controller, it can occur a bad results from disturbance or load variations. So in order to adjust above case. we used the fuzzy compensator to get an expected results. And the weight of main neural network can be changed with the result of learning an inverse model neural network of plant, so a expected dynamic characteristics of plant can be got. In order to confirm a performance of the proposed controller, we implemented the controller using the DSP processor and applied in a hydraulic servo system. And then we observed an experimental results.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.4
• /
• pp.233-237
• /
• 2012

In this paper, We propose a control system which compensate a output of a main Neual Network using a RTDNN(Recurrent Time Delayed Neural Network) with a FLC(Fuzzy Logic Controller)After a learn of main neural network, it can occur a Over shoot or Under shoot from a disturbance or a load variations. In order to adjust above case, we used the fuzzy compensator to get an expected results. And the weight of main neural network can be changed with the result of learning a inverse model neural network of plant, so a expected dynamic characteristics of plant can be got. We can confirm good response characteristics of proposed neural network controller by the results of simulation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.11
• /
• pp.1186-1193
• /
• 1991

This paper proposed a trajectory controlmethod for a robot manipulator by using neural networks. The total torque for a manipulator is a sum of the linear feedback controller torque and the neural network feedfoward controller torque. The proposed neural network is a multilayer neural network with time delay elements, and learns the inverse dynamics of manipulator by means of PD(propotional denvative)controller error torque. The error backpropagation (BP) learning neural network controller does not directly require manipulator dynamics information. Instead, it learns the information by training and stores the information and connection weights. The control effects of the proposed system are verified by computer simulation.