• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.2
• /
• pp.76-80
• /
• 2005

In this paper, a Direct Learning Control (DLC) method is proposed for linear feedback systems to improve the tracking performance when the task of the control system is repetitive. DLC can generate the desired control input directly from the previously learned control inputs corresponding to other output trajectories. It is assumed that all the desired output functions given to the system have some relations called proportionality and it is shown by mathematical analysis that DLC can be utilized to genera additional control efforts for the perfect tracking. To show the validity and tracking performance of the proposed method, some simulations are performed for the tracking control of a linear system with a PI controller.

• 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 KIEE Conference
• /
• 1996.11a
• /
• pp.386-388
• /
• 1996

This paper presents the learning controller for robot manipulators to track the desired trajectory exactly. The learning controller, based on the Lyapunov theory, consists of a fixed PD action and a repetitive action for the purpose of feedforward compensation which is adjusted utilizing a linear combination of the velocity and position errors. The learning controller Is often used In case of the desired trajectories are periodic tasks, and has advantage that it periodically converges to zero even if we don't know the exact dynamic parameters. In this paper, we show that the position and velocity errors of robot manipulators converge to zero sa time goes infinite for the input is periodic function and show a good trajectory tracking performance In the cartesian space.

• Journal of Drive and Control
• /
• v.19 no.4
• /
• pp.110-116
• /
• 2022

Recently, various studies have been conducted to apply deep learning and AI to various fields of autonomous driving, such as recognition, sensor processing, decision-making, and control. This paper proposes a controller applicable to path following, static obstacle avoidance, and pedestrian avoidance situations by utilizing reinforcement learning in autonomous vehicles. For repetitive driving simulation, a reinforcement learning environment was constructed using virtual environments. After learning path following scenarios, we compared control performance with Pure-Pursuit controllers and Stanley controllers, which are widely used due to their good performance and simplicity. Based on the test case of the KNCAP test and assessment protocol, autonomous emergency steering scenarios and autonomous emergency braking scenarios were created and used for learning. Experimental results from zero collisions demonstrated that the reinforcement learning controller was successful in the stationary obstacle avoidance scenario and pedestrian collision scenario under a given condition.

• Journal of Korea Multimedia Society
• /
• v.22 no.4
• /
• pp.432-442
• /
• 2019

Most current human action recognition methods based on deep learning methods. It is required, however, a very high computational cost. In this paper, we propose an action change detection method to reduce repetitive human action recognition tasks. In reality, simple actions are often repeated and it is time consuming process to apply high cost action recognition methods on repeated actions. The proposed method decides whether action has changed. The action recognition is executed only when it has detected action change. The action change detection process is as follows. First, extract the number of non-zero pixel from motion history image and generate one-dimensional time-series data. Second, detecting action change by comparison of difference between current time trend and local extremum of time-series data and threshold. Experiments on the proposed method achieved 89% balanced accuracy on action change data and 61% reduced action recognition repetition.

• Toxicological Research
• /
• v.30 no.4
• /
• pp.267-276
• /
• 2014

Exposures to lead (Pb) are associated with neurological problems including psychiatric disorders and impaired learning and memory. Pb can be absorbed by iron transporters, which are up-regulated in hereditary hemochromatosis, an iron overload disorder in which increased iron deposition in various parenchymal organs promote metal-induced oxidative damage. While dysfunction in HFE (High Fe) gene is the major cause of hemochromatosis, the transport and toxicity of Pb in Hfe-related hemochromatosis are largely unknown. To elucidate the relationship between HFE gene dysfunction and Pb absorption, H67D knock-in Hfe-mutant and wild-type mice were given drinking water containing Pb 1.6 mg/ml ad libitum for 6 weeks and examined for behavioral phenotypes using the nestlet-shredding and marble-burying tests. Latency to nestlet-shredding in Pb-treated wild-type mice was prolonged compared with non-exposed wild-types (p < 0.001), whereas Pb exposure did not alter shredding latency in Hfe-mutant mice. In the marble-burying test, Hfe-mutant mice showed an increased number of marbles buried compared with wild-type mice (p = 0.002), indicating more repetitive behavior upon Hfe mutation. Importantly, Pb-exposed wild-type mice buried more marbles than non-exposed wild-types, whereas the number of marbles buried by Hfe-mutant mice did not change whether or not exposed to Pb. These results suggest that Hfe mutation could normalize Pb-induced behavioral alteration. To explore the mechanism of repetitive behavior caused by Pb, western blot analysis was conducted for proteins involved in brain dopamine metabolism. The levels of tyrosine hydroxylase and dopamine transporter increased upon Pb exposure in both genotypes, whereas Hfe-mutant mice displayed down-regulation of the dopamine transporter and dopamine D1 receptor with D2 receptor elevated. Taken together, our data support the idea that both Pb exposure and Hfe mutation increase repetitive behavior in mice and further suggest that these behavioral changes could be associated with altered dopaminergic neurotransmission, providing a therapeutic basis for psychiatric disorders caused by Pb toxicity.

• Physical Therapy Korea
• /
• v.10 no.3
• /
• pp.17-27
• /
• 2003

Repetitive transcranial magnetic stimulation (rTMS) modulates cortical excitability beyond the duration of the rTMS trains themselves. Depending on rTMS parameters, a lasting inhibition or facilitation of cortical excitability can be induced. Therefore, rTMS of high or low frequency over motor cortex may change certain aspects of motor learning performance and cortical activation. This study investigated the effect of high and low frequency subthreshold rTMS applied to the motor cortex on motor learning of sequential finger movements and brain activation using functional MRI (fMRI). Three healthy right-handed subjects (mean age 23.3) were enrolled. All subjects were trained with sequences of seven-digit rapid sequential finger movements, 30 minutes per day for 5 consecutive days using their left hand. 10 Hz (high frequency) and 1 Hz (low frequency) trains of rTMS with 80% of resting motor threshold and sham stimulation were applied for each subject during the period of motor learning. rTMS was delivered on the scalp over the right primary motor cortex using a figure-eight shaped coil and a Rapid(R) stimulator with two Booster Modules (Magstim Co. Ltd, UK). Functional MRI (fMRI) was performed on a 3T ISOL Forte scanner before and after training in all subjects (35 slices per one brain volume TR/TE = 3000/30 ms, Flip angle $60^{\circ}$, FOV 220 mm, $64{\times}64$ matrix, slice thickness 4 mm). Response time (RT) and target scores (TS) of sequential finger movements were monitored during the training period and fMRl scanning. All subjects showed decreased RT and increased TS which reflecting learning effects over the training session. The subject who received high frequency rTMS showed better performance in TS and RT than those of the subjects with low frequency or sham stimulation of rTMS. In fMRI, the subject who received high frequency rTMS showed increased activation of primary motor cortex, premotor, and medial cerebellar areas after the motor sequence learning after the training, but the subject with low frequency rTMS showed decreased activation in above areas. High frequency subthreshold rTMS on the motor cortex may facilitate the excitability of motor cortex and improve the performance of motor sequence learning in normal subject.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.541-546
• /
• 2005

Tracking control of an automatic pipe cutting robot (APCROMB) is studied. Using magnetic force APCROMB, which is designed and developed in Kyung Hee University, binds itself to the pipe and executes unmanned cutting process. The gravity effect on the movement of APCROMB varies as it rotates around the cylindrical pipe laid in the gravitational field. To maintain a constant velocity and consistent cutting performance against the varying gravitational effect, the authors adopt a multi-rate repetitive learning controller (MRLC), which learns the required effort to cancel the repetitive tracking errors caused by nonlinear effect. In addition to the varying gravity effect other types of nonlinear disturbances including backlash in the driving system and the slip between the wheels of APCROMB and the pipe also cause degradation in the cutting process. In order to identify those nonlinear disturbances the position estimation based on the encoder attached at the motor is not good enough. To identify the absolute angular position of APCROMB the authors propose the angular position estimation based on the signals from a MEMS-type two-axis accelerometer mounted on APCROMB. The tracking performances of APCROMB with a MRLC using the encoder-based position estimation is experimentally measured and results are shown. Also the difference between the encoder-based angular displacement measurement and the accelerometerbased angular displacement measurement is included.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.77-83
• /
• 2019

With the recent development of medical technology, the diagnosis rate of type 1 diabetes is increasing and patients are increasing. However, diabetes education content is not aligned with the interest level of children. As a result of the interviews with experts, It was found that the measures of coping with the change of blood sugar and the behavior therapy require steady and repetitive learning. Therefore, this study proposes Edutainment content which can be repeatedly Learned by 10~11year old children. For effective learning, the contents of the laboratory practice were constructed and the hybrid method was used for the repetitive learning. Usability test showed that this configuration is effective. This study is expected to contribute to the study of diabetic education content that is suitable for the children's level of understanding which will be developed easily in the future.

• Journal of the Korean Society for Precision Engineering
• /
• v.22 no.4
• /
• pp.92-98
• /
• 2005

The learning control develops controllers that learn to improve their performance at executing a given task, based on experience performing this specific task. In a previous work, the authors presented an iterative precision of linear decentralized learning control based on p-integrated learning method for the vertical dynamic multiple systems. This paper develops an indirect decentralized teaming control based on adaptive control method. The original motivation of the teaming control field was loaming in robots doing repetitive tasks such as on an assembly line. This paper starts with decentralized discrete time systems, and progresses to the robot application, modeling the robot as a time varying linear system in the neighborhood of the nominal trajectory, and using the usual robot controllers that are decentralized, treating each link as if it is independent of any coupling with other links. Some techniques will show up in the numerical simulation for vertical dynamic robot. The methods of learning system are shown up for the iterative precision of each link.