• The Journal of Korea Robotics Society
• /
• v.17 no.1
• /
• pp.76-85
• /
• 2022

One of the most fundamental challenges when designing controllers for dynamic systems is the adjustment of controller parameters. Usually the system model is used to get the initial controller, but eventually the controller parameters must be manually adjusted in the real system to achieve the best performance. To avoid this manual tuning step, data-driven methods such as machine learning were used. Recently, reinforcement learning became one alternative of this problem to be considered as an agent learns policies in large state space with trial-and-error Markov Decision Process (MDP) which is widely used in the field of robotics. However, on initial training step, as an agent tries to explore to the new state space with random action and acts directly on the controller parameters in real systems, MDP can lead the system safety-critical system failures. Therefore, the issue of 'safe exploration' became important. In this paper we meet 'safe exploration' condition with Control Barrier Function (CBF) which converts direct constraints on the state space to the implicit constraint of the control inputs. Given an initial low-performance controller, it automatically optimizes the parameters of the control law while ensuring safety by the CBF so that the agent can learn how to predict and control unknown and often stochastic environments. Simulation results on a quadrotor UAV indicate that the proposed method can safely optimize controller parameters quickly and automatically.

• Earthquakes and Structures
• /
• v.24 no.1
• /
• pp.1-9
• /
• 2023

A model for calculating structure interacted mechanics is proposed. A structural interaction model and controller design based on tuned mass damping (TMD) was developed to control the induced vibration. A key point is to introduce a new analytical model to evaluate the properties of the TMD that recognizes the motion-dependent nonlinear response observed in the simulations. Aiming at the problem of increased current harmonics and low efficiency of permanent magnet synchronous motors for electric vehicles due to dead time effect, a dead time compensation method based on neural network filter and current polarity detection is proposed. Firstly, the DC components and the higher harmonic components of the motor currents are obtained by virtue of what the neural network filters and the extracted harmonic currents are adjusted to the required compensation voltages by virtue of what the neural network filters. Then, the extracted DC components are used for current polarity dead time compensation control to avert the false compensation when currents approach zero. The neural network filter method extracts the required compensation voltages from the speed component and the current polarity detection compensation method obtains the required compensation voltages by discriminating the current polarity. The combination of the two methods can more precisely compensate the dead time effect of the control system to improve the control performance. Furthermore, based on the relaxed method, the intelligent approach of stability criterion can be regulated appropriately and the artificial TMD was found to be effective in reducing cross-wind vibrations.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.2
• /
• pp.51.1-51.1
• /
• 2021

Merger shocks with M_s < ~ 3 - 4 have been detected in galaxy clusters through radio observations of synchrotron radiations emitted from cosmic-ray (CR) electrons. The CR electrons are believed to be produced by the so-called diffusive shock acceleration (DSA) at the merger shocks. To describe the acceleration of electrons, the injection into DSA has to be understood. Recent studies have showed that electrons could be energized through stochastic shock drift acceleration (SSDA), a mechanism mediated by multi-scale plasma waves at shock transition zone. However, such preacceleration process seems to be effective only at the supercritical shocks with M_s > ~ 2.3, implying that further studies should be done to explain radio relics with weaker shocks. In this talk, we present the results obtained by fully kinetic 2D particle-in-cell (PIC) simulations, which include pre-existing suprathermal electrons possibly ejected from active galactic nuclei (AGNs) or produced by previous episodes of turbulence/shocks. The simulations indicate that the pre-existing electrons enhance the upstream plasma waves in shocks with M_s < ~ 2.3. However, the wavelength of such waves is not long enough to scatter off suprathermal electrons and energize them to the injection momentum for DSA. Hence, we conclude that preexciting suprathermal electrons alone would not solve the problem of electron acceleration at radio relic shocks.

• Journal of Korean Society of Transportation
• /
• v.22 no.7 s.78
• /
• pp.99-106
• /
• 2004

This paper presents some comparisons between Cournot-Nash and Stackelberg game in bi-level program, composed of both upper level program and lower level one. The upper level can be formulated to optimize a specific objective function, while the lower formulated to express travelers' behavior patterns corresponding to the design parameter of upper level problem. This kind of hi-level program is to determine a design parameter, which leads the road network to an optimal state. Bi-level program includes traffic signal control, traffic information provision, congestion charge and new transportation mode introduction as well as road expansion. From the view point of game theory, many existing algorithms for bi-level program such as IOA (Iterative Optimization Assignment) or IEA (Iterative Estimation Assignment) belong to Cournot-Nash game. But sensitivity-based algorithms belongs to Stackelberg one because they consider the reaction of the lower level program. These two game models would be compared by using an example network and show some results that there is no superiority between the models in deterministic case, but in stochastic case Stackelberg approach is better than that of Cournot-Nash one as we expect.

• Journal of Korean Society of Transportation
• /
• v.29 no.1
• /
• pp.71-79
• /
• 2011

Traditionally, a dynamic network model is considered as a tool for solving real-time traffic problems. One of useful and practical ways of using such models is to use it to produce and disseminate forecast travel time information so that the travelers can switch their routes from congested to less-congested or uncongested, which can enhance the performance of the network. This approach seems to be promising when the traffic congestion is severe, especially when sudden incidents happen. A consideration that should be given in implementing this method is that travel time information may affect the future traffic condition itself, creating undesirable side effects such as the over-reaction problem. Furthermore incorrect forecast travel time can make the information unreliable. In this paper, a network-wide travel time prediction model under incidents is developed. The model assumes that all drivers have access to detailed traffic information through personalized in-vehicle devices such as car navigation systems. Drivers are assumed to make their own travel choice based on the travel time information provided. A route-based stochastic variational inequality is formulated, which is used as a basic model for the travel time prediction. A diversion function is introduced to account for the motorists' willingness to divert. An inverse function of the diversion curve is derived to develop a variational inequality formulation for the travel time prediction model. Computational results illustrate the characteristics of the proposed model.

• Environmental and Resource Economics Review
• /
• v.30 no.4
• /
• pp.557-579
• /
• 2021

Collective energy is an intermediate stage in energy conversion and has a great influence on the power structure as a distributed power source. However, the problem of the collective energy business has recently emerged due to the worsening profitability of some collective energy operators. This study measured the technical efficiency of major operators through the estimation of the production efficiency of Korean collective energy operators, and based on this, we looked at ways to improve the profit structure of operators. After collecting detailed data from 16 collective energy operators between 2016 and 2019, the production efficiency of operators was estimated using the panel stochastic frontier model. As a result of the estimation, combined steam power operators showed the highest production efficiency and reverse CHP operators showed the lowest efficiency. Furthermore, as a result of examining the factors influencing profitability, it was confirmed that production efficiency has a positive effect on overall profitability. However, businesses with a high proportion of heat production, such as small district electricity operators, profitability was lower. This phenomenon is due to the structural limitations of the current heat sales market. Hence, the adjustment of the heat sales unit price is necessary to improve profitability of collective energy operators.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.11
• /
• pp.493-504
• /
• 2023

The Republic of Korea is located far from the boundary of the earthquake plate, and the intra-plate earthquake occurring in these areas is generally small in size and less frequent than the interplate earthquake. Nevertheless, as a result of investigating and analyzing earthquakes that occurred on the Korean Peninsula between the past two years and 1904 and earthquakes that occurred after observing recent earthquakes on the Korean Peninsula, it was found that of a magnitude of 9. In this paper, the Korean Peninsula Historical Earthquake Record (2 years to 1904) published by the National Meteorological Research Institute is used to analyze the relationship between earthquakes on the Korean Peninsula and statistical self-similarity. In addition, the problem solved through this paper was the first to investigate the relationship between earthquake data occurring on the Korean Peninsula and statistical self-similarity. As a result of measuring the degree of self-similarity of earthquakes on the Korean Peninsula using three quantitative estimation methods, the self-similarity parameter H value (0.5 < H < 1) was found to be above 0.8 on average, indicating a high degree of self-similarity. And through graph visualization, it can be easily figured out in which region earthquakes occur most often, and it is expected that it can be used in the development of a prediction system that can predict damage in the event of an earthquake in the future and minimize damage to property and people, as well as in earthquake data analysis and modeling research. Based on the findings of this study, the self-similar process is expected to help understand the patterns and statistical characteristics of seismic activities, group and classify similar seismic events, and be used for prediction of seismic activities, seismic risk assessments, and seismic engineering.

• Journal of Korean Society of Transportation
• /
• v.22 no.2 s.73
• /
• pp.145-154
• /
• 2004

The growing demand for customer-responsive, made-to-order manufacturing is stimulating the need for improved dynamic decision-making processes in commercial fleet operations. Moreover, the rapid growth of electronic commerce through the internet is also requiring advanced and precise real-time operation of vehicle fleets. Accompanying these demand side developments/pressures, the growing availability of technologies such as AVL(Automatic Vehicle Location) systems and continuous two-way communication devices is driving developments on the supply side. These technologies enable the dispatcher to identify the current location of trucks and to communicate with drivers in real time affording the carrier fleet dispatcher the opportunity to dynamically respond to changes in demand, driver and vehicle availability, as well as traffic network conditions. This research investigates key aspects of real time dynamic routing and scheduling problems in fleet operation particularly in a truckload pickup-and-delivery problem under various settings, in which information of stochastic demands is revealed on a continuous basis, i.e., as the scheduled routes are executed. The most promising solution strategies for dealing with this real-time problem are analyzed and integrated. Furthermore, this research develops. analyzes, and implements hybrid algorithms for solving them, which combine fast local heuristic approach with an optimization-based approach. In addition, various partitioning algorithms being able to deal with large fleet of vehicles are developed based on 'divided & conquer' technique. Simulation experiments are developed and conducted to evaluate the performance of these algorithms.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.657-664
• /
• 2003

Reliable tracking of moving humans is essential to motion estimation, video surveillance and human-computer interface. This paper presents a new approach to human motion tracking that combines appearance-based and model-based techniques. Monocular color video is processed at both pixel level and object level. At the pixel level, a Gaussian mixture model is used to train and classily individual pixel colors. At the object level, a 3D human body model projected on a 2D image plane is used to fit the image data. Our method does not use inverse kinematics due to the singularity problem. While many others use stochastic sampling for model-based motion tracking, our method is purely dependent on nonlinear programming. We convert the human motion tracking problem into a nonlinear programming problem. A cost function for parameter optimization is used to estimate the degree of the overlapping between the foreground input image silhouette and a projected 3D model body silhouette. The overlapping is computed using computational geometry by converting a set of pixels from the image domain to a polygon in the real projection plane domain. Our method is used to recognize various human motions. Motion tracking results from video sequences are very encouraging.

• Journal of Advanced Navigation Technology
• /
• v.5 no.1
• /
• pp.1-10
• /
• 2001

Speech has a good characteristics of which car drivers busy to concern with miscellaneous operation can make use in convenient handling and manipulating of devices. By utilizing this, this works proposes a speaker verification method for protecting cars from being stolen and identifying a person trying to access critical on-line services. In this, continuant phonemes recognition which uses language information of speech and MLP(mult-layer perceptron) which has some advantages against previous stochastic methods are adopted. The recognition method, though, involves huge computation amount for learning, so it is somewhat difficult to adopt this in speaker verification application in which speakers should enroll themselves at real time. To relieve this problem, this works presents a solution that introduces speaker cohort models from speaker verification score normalization technique established before, dividing background speakers into small cohorts in advance. As a result, this enables computation burden to be reduced through classifying the enrolling speaker into one of those cohorts and going through enrollment for only that cohort.