• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.2
• /
• pp.64-70
• /
• 2002

This paper proposes a new construction method of neural networks. The construction method consists of two fundmental ideas, which are a parallel selection-style evaluation and rules evolution. A new collision avoidance algorithm using genetic and neural network is proposed to avoid moving obstacles such as mobile robots. The input parameters of this algorithm is position of moving obstacles and target. Output is a regenerated direction of mobile robot. This algorithm is very simple and so, it is available to application of real time process. The pattern of collision avoidance is learned through test execution.

• Journal of Digital Convergence
• /
• v.11 no.11
• /
• pp.321-326
• /
• 2013

GPS reception rate in the room has less features. To overcome these shortcomings, the AP positioning using RSS technology research and development is being done. If we use positioning technology and signal strength in order to detect a obstacles, it has the advantage of no-cost in terms of utilization and efficiency when we do this applied service. In this paper, We are presented method to determine the obstacles using RSS(Received Signal Strength).

• The Journal of Korea Robotics Society
• /
• v.2 no.3
• /
• pp.212-220
• /
• 2007

This paper proposes a method of avoiding obstacles and tracking a moving object continuously and simultaneously by using new concepts of virtual tow point and fuzzy danger factor for differential wheeled mobile robots. Since differential wheeled mobile robot has smaller degree of freedom to control and are non-holonomic systems, there exist multiple solutions (trajectories) to control and reach a target position. The paper proposes 'fuzzy danger factor' for obstacles avoidance, 'virtual tow point' to solve non-holonomic object tracking control problem for unique solution and three kinds of fuzzy logic controller. The fuzzy logic controller is policy decision controller with fuzzy danger factor to decide which controller's result is more valuable when the mobile robot is tracking a moving object with obstacles to be avoided.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.3
• /
• pp.1303-1306
• /
• 2015

Studies of epidemiological and prognostic factors are very important for oncology practice. There is a rapidly increasing amount of research and resultant knowledge in the scientific literature. This means that health professionals have major challenges in accessing relevant information and they increasingly require best available evidence to make their clinical decisions. Meta-analyses of prognostic and other epidemiological factors are very practical statistical approaches to define clinically important parameters. However, they also feature many obstacles in terms of data collection, standardization of results from multiple centers, bias, and commentary for intepretation. In this paper, the obstacles of meta-analysis are briefly reviewed, and potential problems with this statistical method are discussed.

• The Korean Journal of Air & Space Law and Policy
• /
• v.21 no.1
• /
• pp.97-133
• /
• 2006

항공기사고는 약 70%가 이 착륙단계에서 일어나는 CFIT사고이다. 그러므로 비행장주위의 장애물 관리는 사고방지에 매우 중요하다. 국내에서도 비행장주위의 장애물제한을 항공법에 규정하고 있고, 최근 개정안으로 제시된 동법 시행규칙에서 ICAO의 차폐기준의 적용을 포함하였으나 이 규정만으로는 비행장 주위의 장애물의 체계적인 관리가 어려우며, 특히 국내 비행장 주위의 차폐이론적용에 필요한 세부기준이 명확하지 않다. 본 연구는 항공장애물과 관련된 ICAO의 규정 및 항공선진국들의 관련 규정을 검토 분석하고 국내 현황과 비교분석한 후 국제기준에 비추어 국내 환경에서도 적용 가능한 비행장 공역에서의 항공장애물관리규정(안)의 방향을 제시하였고 특히 논란의 여지가 많은 차폐이론의 적용의 명확한 기준방안을 제시하였다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.5
• /
• pp.377-388
• /
• 2020

In this paper, the autonomous mobile robot whit only LRF sensors proposes an algorithm for avoiding moving obstacles in an environment where a global map containing fixed obstacles. First of all, in oder to avoid moving obstacles, moving obstacles are extracted using LRF distance sensor data and a global map. An ellipse-shaped safety radius is created using the sum of relative vector components between the extracted moving obstacles and of the autonomuos mobile robot. Considering the created safety radius, the autonomous mobile robot can avoid moving obstacles and reach the destination. To verify the proposed algorithm, use quantitative analysis methods to compare and analyze with existing algorithms. The analysis method compares the length and run time of the proposed algorithm with the length of the path of the existing algorithm based on the absence of a moving obstacle. The proposed algorithm can be avoided by taking into account the relative speed and direction of the moving obstacle, so both the route and the driving time show higher performance than the existing algorithm.

• The Journal of Korean Physical Therapy
• /
• v.23 no.6
• /
• pp.15-22
• /
• 2011

Purpose: This research investigated falls due to obstacles that occur among elderly people by assessing changes in the values of plantar foot force, peak force, and plantar foot pressure in elderly subjects while they were stepping over obstacles of different heights. Methods: The subjects were 20 elderly people aged 70-80 years; Pressure was measured on flat ground(0 cm), and after installing obstacles of 8 cm and 12 cm using the F-scan system, which is a resistance-type pressure sensor. A one-way analysis of variance was performed to compare pressure on each part of the foot according to various heights after collecting data using the Tekscan program. The least significant difference test was used for the post-hoc analysis, A p-value <0.05 was considered significant. Results: The force value for the toe area (parts 1, and 2) and contact pressure increased significantly with the 12 cm obstacle (p<0.05). The peak force value and the peak contact pressure for part 1 increased significantly with the 12 cm obstacle (p<0.05). Conclusion: Larger changes appeared in the functions and structure of the foot while subjects walked over obstacles of different heights compared to flatland walking. This result suggests that people have safety strategies to prevent falls, and that there is a need for a more realistic approach through practice to overcome obstacles of various heights to prevent falls.

• Journal of Platform Technology
• /
• v.9 no.4
• /
• pp.71-78
• /
• 2021

Self-driving vehicles are increasing as new alternatives to solving problems such as human safety, environment and aging. And such technology development has a great ripple effect on other industries. However, various problems are occurring. The number of casualties caused by self-driving is increasing. Although the collision of fixed obstacles is somewhat decreasing, on the contrary, the technology by active obstacles is still insignificant. Therefore, in this study, in order to solve the core problem of self-driving vehicles, we propose a method of extracting active obstacles on the road. First, a center scene is extracted from a continuous image. In addition, it was proposed to extract activity obstacles using activity size and activity repeatability information from objects included in the center scene. The center scene is calculated using region segmentation and merging. Based on these results, the size of the frequency for each pixel in the region was calculated and the size of the activity of the obstacle was calculated using information that frequently appears in activity. Compared to the results extracted directly by humans, the extraction accuracy was somewhat lower, but satisfactory results were obtained. Therefore, it is believed that the proposed method will contribute to solving the problems of self-driving and reducing human accidents.

• Journal of the Korean Society of Physical Medicine
• /
• v.12 no.3
• /
• pp.85-91
• /
• 2017

PURPOSE: The purpose of this study was to compare muscle activation of the trunk and lower limbs of subjects wearing high-heeled or flat shoes while crossing over obstacles of different heights. METHODS: Twenty subjects participated in this study. While wearing high-heeled shoes (7 cm) or flat shoes (0 cm), the subjects were asked to cross over obstacles of different heights (10%, 20%, and 30% of their lower-limb length). Muscle activation of the trunk and lower limbs with the supported side while crossing over obstacles of different heights was measured using the electromyogram (Noraxon, DTS, Germany). Two-way repeated ANOVA was used to compare the muscle activation between high-heel shoes and flat shoes while crossing over obstacles of different heights. All statistical analyses were performed using SPSS ver. 21, and p-values less than .05 were used to identify significant differences. RESULTS: As an obstacle's height increased, muscle activation of the trunk and lower limbs with the supported side was increased while wearing either type of shoe, and it was generally higher while wearing high-heeled shoes. However, tibialis anterior muscle activity while wearing high-heeled shoes was lower than while wearing flat shoes. CONCLUSION: This study showed that muscle activation of the trunk and lower limbs was higher when subjects wore high-heeled shoes than when they wore flat shoes while crossing over obstacles of different heights. Therefore, high-heeled shoes can easily cause high muscle fatigue of the trunk and lower limbs, and the TA muscle may weaken in persons who wear high-heeled shoes.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.21 no.12
• /
• pp.1992-2007
• /
• 1997

A new algorithm for planning a collision-free path is developed based on linear prametric curve. In this paper robot is assumed to a point, and two linear parametric curve is used to construct a path connecting start and goal point, in which single intermediate connection point between start and goal point is considered. The intermediate connection point is set in polar coordinate(${\theta}{\delta}$) , and the interference between path and obstacle is mapped into CPS(connection point space), which is defined a CWS GM(circular work space geometry mapping). GM of all obstacles in workspace creates overlapping images of obstacle in CPS(Connection Point Space). The GM for all obstacles produces overlapping images of obstacle in CPS. The empty area of CPS that is not occupied by obstacle images represents collision-free paths in Euclidian Space. A GM based on connection point in elliptic coordinate(${\theta}{\delta}$) is also developed in that the total length of path is depend only on the variable .delta.. Hence in EWS GM(elliptic work space geometry mapping), increasing .delta. and finding the value of .delta. for collision-free path, the shortest path can be searched without carring out whole GM. The GM of obstacles expersses all possible collision-free path as empty spaces in CPS. If there is no empty space available in CPS, it indicates that path planning is not possible with given number of connection points, i.e. path planning is failed, and it is necessary to increase the number of connection point. A general case collision-free path planning is possible by appling GM to configuration space obstacles. Simulation of GM of obstacles in Euclidian space is carried out to measure performance of algorithm and the resulting obstacle images are reported.