• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.1
• /
• pp.261-268
• /
• 2013

In this paper, we propose the algorithm that improves the linearity of the walking assistant robot on lateral slopes. The walking assistant robot goes out of the course due to the rotational moment which is caused by the weight of the robot and the slope. To compensate this, we give the weight to each driving axle after comparing the real rotational angular velocity with the target rotational angular velocity which is entered by an user. The results of applying the algorithm to the real walking assistant robot show that the yaw axis deviation of the robot without the algorithm diverges, but the yaw axis deviation of the robot with the algorithm lies within 20cm, which can be recognized as stable. In addition, the changing rate of the course deviation is stabilized and shows no more course deviation, after moving 300cm.

• Journal of Korean Society for Geospatial Information Science
• /
• v.20 no.2
• /
• pp.23-29
• /
• 2012

Existing pedestrian and evacuation models generally seek to find locally optimal solutions for the shortest or the least time paths to exits from individual locations considering pedestrian's characteristics (eg. speed, direction, sex, age, weight and size). These models are not designed to produce globally optimal solutions that reduce the total evacuation time of the entire pedestrians in a building when all of them evacuate at the same time. In this study, we suggest a globally optimal model for indoor pedestrian evacuation to minimize the total evacuation time of occupants in a building considering different distributions of them. We used the genetic algorithm, one of meta-heuristic techniques because minimizing the total evacuation time can not be easily solved by polynomial expressions. We found near-optimal evacuation path and time by expressing varying pedestrians distributions using chromosomes and repeatedly filtering solutions. In order to express and experiment our suggested algorithm, we used CA(cellular automata)-based simulator and applied to different indoor distributions and presented the results.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.1
• /
• pp.169-174
• /
• 2018

There are many CCTV cameras connected to the video surveillance and monitoring center for the safety of citizens, and it is difficult for a few monitoring agents to monitor many channels of videos. In this paper, we propose an intelligent video surveillance system utilizing a safety map to efficiently monitor many channels of CCTV camera videos. The safety map establishes the frequency of crime occurrence as a database, expresses the degree of crime risk and makes it possible for agents of the video surveillance center to pay attention when a woman enters the crime risk area. The proposed gender classification method is processed in the order of pedestrian detection, tracking and classification with deep training. The pedestrian detection and tracking uses Adaboost algorithm and probabilistic data association filter, respectively. In order to classify the gender of the pedestrian, relatively simple AlexNet is applied to determine gender. Experimental results show that the proposed gender classification method is more effective than the conventional algorithm. In addition, the results of implementation of intelligent video security system combined with safety map are introduced.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.2
• /
• pp.129-135
• /
• 2015

This study, in the operation of street lamp, suggests appropriate algorithm to extend the number of days of street lamp operation as much as possible if the number of sunless days continues and experimentally determines the value of Weather Factor necessary for this algorithm. This is conducted by reducing electricity consumption and securing battery remains through the use of standby power mode, in which maximum amount of light is maintained if there is a pedestrian, and constant brightness is maintained without utilizing maximum electric power if no pedestrians exist, with the application of WFactor value created by the algorithm considering weather forecast and amount of sunlight.

• Journal of KIISE:Software and Applications
• /
• v.36 no.6
• /
• pp.462-470
• /
• 2009

We propose a wearable system to help the visually impaired persons for walking safely to destination. If a user selects a destination, the system guides the user to destination with position data from GPS receiver and shortest path algorithm. At the same time, after acquiring complex spatial structures in front of the user with ultrasonic sensors, we categorize them into several predefined patterns, and determine an avoidance direction by estimating the patterns. As a result, visually impaired persons can arrive at destination safely and correctly without others help.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.7 no.2
• /
• pp.1-5
• /
• 2013

In this paper, we proposed how to estimate the walking state in the knee disarticulation prosthesis's knee angle control. In control of the knee disarticulation prosthesis, we can estimate walking state that measurement of knee angle using absolute encoder and measurement of load on the soles using strain gage. We suggested a method of estimating the current walking states which can be divided into four cases and showed the effectiveness of the method via a series of experiments.

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.3
• /
• pp.83-91
• /
• 2000

During static walking of a quadruped walking robot, stability of the robot depends on whether the projection of the mass center is located within the supporting area that is varying with leg motion and formed by standing legs. In this paper, force margin instead of the mass center was used to determine stability and body-tilting method was used to enhance it. On-line control of body tilting was realized with simple reaction feedback based on force margin of the static walking model of the robot instead of complicated calculation. Model reference on-line control where the model searches stable pose for predefined force margin also gave good walking performance.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.165-168
• /
• 2004

본 연구에서는 근골격계로 구성된 신체 역학계와 신경 진동자로 구성된 신경계의 상호작용에 의해서 자율적인 2족 보행운동 생성하려고 하고 있다. 이를 위해서는 역학계와 신경계의 않은 파라메트(Parameter)의 조절이 필요하다 본 연구에서는 유전적 프로그래밍(GP)을 이용하여 파라메트의 자동조절 수법을 제안하였다. GP는 문제를 해결하기 위한 계산 프로그래밍을 탐색하는 진화형 탐색 알고리즘으로, GP를 이용해서 문제해결을 행하기 위해서는 노드의 선택이 매우 중요하다. 그러나 대상문제에 대한 충분한 정보가 없는 경우에는 노드를 용장성 있게 설계하게 되어, 이로 인한 탐색공간의 확장으로 GP에 대한 탐색성능의 저하를 초래한다. 본 논문에서는 이러한 문제를 해결하기 위해서 용장성 노드 집합으로부터 유용한 노드를 획득하기 위해 제안한 수법을 2족 보행운동 생성 시스템에 적용하기 전에 사전 평가로서 기호회귀(Symbolic Regression)문제에 적용하여 실험을 통해 제안 수법의 타당성과 탐색성능 향상의 효과에 관해서 논하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.141-142
• /
• 2016

본 논문은 보행자의 이동경로 추적을 위해 PDR(Pedestrian Dead Reckoning) 알고리즘을 탑재한 임베디드 모듈과 연결 가능한 안드로이드 어플리케이션을 구현하였다. 임베디드 모듈은 IMU센서를 통해 얻은 값을 통해 보행자의 위치를 구하고 어플리케이션에 전송한다. 어플리케이션은 임베디드 모듈로부터 위치 값을 받아 스마트폰 화면에 실시간으로 사용자의 위치를 디스플레이 한다. 어플리케이션을 구현하여 필드 테스트를 진행한 결과 보행자의 이동경로를 비교적 정확하게 추적하였다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1994.10a
• /
• pp.323-329
• /
• 1994

In the systems such as walking robots or high speed operating manipulators, the effect of nonlinear terms is important and can not be neglected. Therefore the application of linear control law to such systems is inadequate. Moreover, because of the mathematical modeling errors the systems may become unstable. In this study, we designed a nonlinear controller with sliding mode scheme, which is robust to the modeling errors and applied this control algorithm to the 5 DOF biped robot system. Throught the computer simulations, we examined walking characteris and walking stability of the 5 DOF biped robot system.