• Journal of Electrical Engineering and Technology
• /
• 제12권2호
• /
• pp.890-903
• /
• 2017

The problem of determining a smooth and collision-free path with maximum possible speed for a Mobile Robot (MR) which is chasing a moving target in a dynamic environment is addressed in this paper. Genetic Network Programming with Reinforcement Learning (GNP-RL) has several important features over other evolutionary algorithms such as it combines offline and online learning on the one hand, and it combines diversified and intensified search on the other hand, but it was used in solving the problem of MR navigation in static environment only. This paper presents GNP-RL based on predicting collision positions as a first attempt to apply it for MR navigation in dynamic environment. The combination between features of the proposed collision prediction and that of GNP-RL provides safe navigation (effective obstacle avoidance) in dynamic environment, smooth movement, and reducing the obstacle avoidance latency time. Simulation in dynamic environment is used to evaluate the performance of collision prediction based GNP-RL compared with that of two state-of-the art navigation approaches, namely, Q-Learning (QL) and Artificial Potential Field (APF). The simulation results show that the proposed GNP-RL outperforms both QL and APF in terms of smooth movement and safer navigation. In addition, it outperforms APF in terms of preserving maximum possible speed during obstacle avoidance.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.547-550
• /
• 2009

The object recognition mechanism of human being is not well understood yet. On research of animal experiment using an ape, however, neurons that respond to simple shape (e.g. circle, triangle, square and so on) were found. And Hypothesis has been set up as human being may recognize object as combination of such simple shapes. That mechanism is called Figure Alphabet Hypothesis, and those simple shapes are called Figure Alphabet. As one way to research object recognition algorithm, we focused attention to this Figure Alphabet Hypothesis. Getting idea from it, we proposed the feature extraction algorithm for object recognition. In this paper, we described recognition of binarized images of multifont alphabet characters by the recognition model which combined three-layered neural network in the feature extraction algorithm. First of all, we calculated the difference between the learning image data set and the template by the feature extraction algorithm. The computed finite difference is a feature quantity of the feature extraction algorithm. We had it input the feature quantity to the neural network model and learn by backpropagation (BP method). We had the recognition model recognize the unknown image data set and found the correct answer rate. To estimate the performance of the contriving recognition model, we had the unknown image data set recognized by a conventional neural network. As a result, the contriving recognition model showed a higher correct answer rate than a conventional neural network model. Therefore the validity of the contriving recognition model could be proved. We'll plan the research a recognition of natural image by the contriving recognition model in the future.

• 한국컴퓨터정보학회논문지
• /
• 제16권4호
• /
• pp.179-187
• /
• 2011

현재 많은 Map DB Provider들이 지도 정보를 제공하고 있으며, 자신들의 Map DB에 새로운 도로 정보를 업데이트 하는데 많은 노력을 기울이고 있다. 하지만, 아직까지 Provider들 상호간 도로 정보 공유에 대해서는 고려하지 않고 있다. 본 논문은 클라우드 컴퓨팅(Cloud Computing) 환경을 이용해 클라우드에서 이기종 카 네비게이션 시스템을 사용하는 운전자들에 의해 추출된 새로운 도로의 속성 정보를 실시간으로 모든 운전자의 네비게이션 Map DB를 업데이트하는 방법을 제안한다. 이 방법은 새로운 도로 정보를 모든 운전자들의 Map DB에 더욱 효율적으로 업데이트할 수 있으며, Map DB Provider들이 수행하는 실차 주행 테스트 비용을 줄이고 서버 자원 통합 구축을 통한 Map DB 데이터센터의 유지비용을 줄일 수 있다.

• 분석과학
• /
• 제25권2호
• /
• pp.133-145
• /
• 2012

대기 중의 총부유먼지(total suspended particulate, TSP)를 구성하는 성분들 중 organic carbon (OC), element carbon (EC), 금속성분은 양적으로 중요한 구성인자에 해당한다. 이들을 제외한 나머지 부분은 아직까지 정성 및 정량분석이 취약한 미지 물질(${\Sigma}X$)에 해당한다. 본 연구에서는 서울시 강서 지역에서 2009년 2-12월 기간동안 관측한 자료를 이용하여, TSP의 주요 성분들 간의 관계에 대한 분석을 시도하였다. 이를 통해, TSP의 거동을 다양한 각도에서 해석하기 위한 기초 자료로 활용하고자 하였다. 전체 연구기간 동안, TSP를 이루는 주요인자로서 미지의 영역이 평균적으로 48.6%를 차지할 정도로 더 지배적이란 것을 확인하였다. 그리고 TSP에 대한 그 구성 성분들간의 관계를 검토하였을 때, 미지 물질들은 이온성분들과 밀접한 연관성을 보일뿐 아니라 TSP의 함량과 정비례 관계임을 확인하였다. 반면, 양자를 TSP의 농도로 표준화(normalization)를 하였을 경우, 뚜렷한 반비례 관계에(강한 역상관성)이 두드러지게 나타났다. 이러한 현상은 ${\Sigma}X$가 이온성분과는 달리 수용성이 떨어지는 특성을 지닌 것을 반영한 것으로 사료된다. TSP의 거동을 보다 체계적으로 이해하고 이를 도시 대기질 관리에 적용하기 위해서는, ${\Sigma}X$의 조성이나 거동을 명확하게 규정하기 위한 여러 가지 연구가 필요하다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.41-41
• /
• 2000

biped robots are expected to robustly traverse terrain with various unknown surfaces. The robot will occasionally encounter the unexpected events in made-for human environments. The slipping is a very real and serious problem in the unexpected events. The robot system must respond to the unexpected slipping after it has occurred and before control is lost. This paper proposes a reflex control method for biped robots to recover from slipage. Computer simulations with the 6-DOF environment model which consists of nonlinear dampers, nonlinear springs, and linear springs, show that the proposed method is effective in preventing fall-down due to slippage.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.82.1-82
• /
• 2002

$\textbullet$ Nearest neighbor filter $\textbullet$ Probabilistic nearest neighbor filter $\textbullet$ Probabilistic nearest neighbor filter incorporating numbers of validated measurements $\textbullet$ Probability density function of the NDS $\textbullet$ Simulation results in a clutter environment to verify the performances $\textbullet$ Sensitivity analysis for the unknown spatial clutter density

• Steel and Composite Structures
• /
• 제41권6호
• /
• pp.899-910
• /
• 2021

A 4-unknown shear deformation theory is applied to investigate the vibration of functionally graded plates under thermal environment. The plate is fabricated from a functionally graded material mixed of ceramic and metal with continuously varying material properties through the plate thickness. Three types of thermal loadings, uniform, linear and nonlinear temperature rises along the plate thickness are taken into account. The present theory contains four unknown functions as against five or more in other higher order shear deformation theories. The through-the-thickness distributions of transverse shear stresses of the plate are considered to vary parabolically and vanish at upper and lower surfaces. The present model does not require any problem dependent shear correction factor. Analytical solutions for the free vibration analysis are derived based on Fourier series that satisfy the boundary conditions (Navier's method). Benchmark solutions are firstly considered to evaluate the accuracy of the proposed model. Comparisons with the solutions available in literature revealed the good capabilities of the present model for the simulations of vibration responses of FG plates. Some parametric studies are carried out for the frequency analysis by varying the volume fraction profile and the temperature distribution across the plate thickness.

• 한국ITS학회 논문지
• /
• 제10권3호
• /
• pp.85-94
• /
• 2011

스펙트럼 센싱은 인지 라디오에서 가장 핵심이 되는 기술이다. 이미 여러 논문에서 에너지 검출기를 바탕으로 하는 스펙트럼 센싱 기법들에 대해 연구하였지만, 실제 시스템에서는 노이즈의 분산을 정확히 추정하는 것이 어려우므로 에너지 검출기를 쓰면 시스템이 요구하는 오경보 확률을 유지할 수 없는 문제가 생긴다. 이에 본 논문에서는, 인지 라디오가 예측 가능하지만 알지 못하는 주사용자의 신호를 검출해야 할 때 노이즈의 분산을 몰라도 스펙트럼을 검출할 수 있는 새로운 검출기를 제안한다. 시뮬레이션을 통해 제안한 검출기는 노이즈의 분산을 몰라도 스펙트럼을 검출할 수 있으며 노이즈 분산의 변화에 강인한 특성을 지닌다는 것을 보인다.

• 한국멀티미디어학회논문지
• /
• 제12권12호
• /
• pp.1819-1826
• /
• 2009

To enhance the automatic performance of existing predicting and planning algorithms that require a predefined probability of the states' transition, this paper proposes a multiple sequence generation system. When interacting with unknown environments, a virtual agent needs to decide which action or action order can result in a good state and determine the transition probability based on the current state and the action taken. We describe a sequential behavior generation method motivated from the change in the agent's state in order to help the virtual agent learn how to adapt to unknown environments. In a sequence learning process, the sensed states are grouped by a set of proposed motivation filters in order to reduce the learning computation of the large state space. In order to accomplish a goal with a high payoff, the learning agent makes a decision based on the observation of states' transitions. The proposed multiple sequence behaviors generation system increases the complexity and heightens the automatic planning of the virtual agent for interacting with the dynamic unknown environment. This model was tested in a virtual library to elucidate the process of the system.

• 자동차안전학회지
• /
• 제13권1호
• /
• pp.14-25
• /
• 2021

This paper presents a RLS based adaptive sliding mode observer (A-SMO) for unknown fault reconstruction in longitudinal autonomous driving. Securing the functional safety of autonomous vehicles from unexpected faults of sensors is essential for avoidance of fatal accidents. Because the magnitude and type of the faults cannot be known exactly, the RLS based A-SMO for unknown acceleration fault reconstruction has been designed with relationship function in this study. It is assumed that longitudinal acceleration of preceding vehicle can be obtained by using the V2V (Vehicle to Vehicle) communication. The kinematic model that represents relative relation between subject and preceding vehicles has been used for fault reconstruction. In order to reconstruct fault signal in acceleration, the magnitude of the injection term has been adjusted by adaptation rule designed based on MIT rule. The proposed A-SMO in this study was developed in Matlab/Simulink environment. Performance evaluation has been conducted using the commercial software (CarMaker) with car-following scenario and evaluation results show that maximum reconstruction error ratios exist within range of ±10%.