• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 A
• /
• pp.259-262
• /
• 2003

In this paper, we studied the path determination algorithm of the guidance robot for the visually impaired. Using the guidance robot for the visually impaired, the visually impaired can go to the destination where they want without other's heir. The navigation path of the guidance robot for the visually impaired must be the optimal path not only the shortest but also the most safe, which is different from a shortest path for common people. GPS and electronic map are used for the location information of the visually impaired. We corrected the error by converting the coordinates of location information from GPS, which includes maximum several tens of meters error, to the coordinates of electronic map. Information such as simple path and direction to the destination is not enough because it may be different between a going path from the start to the destination and a coming path from the destination to the start as around environment. So, we added information which can be dangerous for the visually impaired such as driveway, sidewalk without braille blocks, crosswalk, stairs and overpass, each has weight value as dangerous degree, when matching the GPS information to the electronic map, enough large as 1:5,000 scale.

• 한국정보통신학회논문지
• /
• 제27권1호
• /
• pp.117-123
• /
• 2023

여름철 집중적인 태풍이나 호우로 인해 침수 및 범람으로 인명 피해가 존재한다. 이러한 피해로 인해 제일 큰 재해는 홍수이며 인명 피해를 줄이기 위해 본 논문에서는 Map API를 활용한 최단 거리 알고리즘 기반 보행자 경로 탐색 연구를 제안한다. 본 시스템은 Map API를 비교분석을 통하여 선정하고 최단 경로를 제공한다. 탐색 된 경로는 JSON 형태와 대피소의 데이터를 데이터베이스에 저장한다. 이 데이터를 기반하여 설계 및 구현한 경로 탐색 시스템은 보행자의 위치를 파악하여 돌발 홍수 발생하였을 때 대피 경로를 제공한다. 또 대피 경로로 이동 중 진입하지 못하는 경로일 경우 보행자의 현재 위치를 파악하여 경로 재탐색하여 새로운 경로를 제공한다. 이에 본 논문에서 제안하는 보행자 경로 탐색 시스템은 안전사고에 예방할 것으로 사려된다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.219-221
• /
• 2022

최근 여름철에 집중되면서 산악지역에서도 침수 및 범람으로 보행자는 대피 상황에서 인명 피해로 발생한다. 이를 보완하기 위해서는 범람 발생을 파악하여 보행자가 안전한 대피를 할 수 있는 시스템이 필요로 하다. 이에 본 논문에서는 Map API를 활용한 최단 거리 알고리즘 기반 보행자 경로 탐색 연구에 대해 제안한다. 보행자 경로 탐색 시스템은 T Map API를 사용하여 지도를 출력하고, 주변 건물을 대피소로 선정하여 데이터를 저장한다. 보행자의 현재 위치에서 가까운 대피소가 선정되어 최단 경로를 출력하고, 거리 및 시간을 제공한다. 대피 중 현재 진행 중인 경로에 문제가 생겼을 경우 현재 위치에서 다른 대피소의 경로를 제공한다. 이에 본 논문에서 제안하는 보행자 경로 탐색 대피 시스템은 대피 중 사고 예방을 할 것으로 사료한다.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.1085-1092
• /
• 2022

Travel distance is a parameter mainly used in the objective function of Construction Site Layout Planning (CSLP) automation models. To obtain travel distance, common approaches, such as linear distance, shortest-distance algorithm, visibility graph, and access road path, concentrate only on identifying the shortest path. However, humans do not necessarily follow one shortest path but can choose a safer and more comfortable path according to their situation within a reasonable range. Thus, paths generated by these approaches may be different from the actual paths of the workers, which may cause a decrease in the reliability of the optimized construction site layout. To solve this problem, this paper adopts reinforcement learning (RL) inspired by various concepts of cognitive science and behavioral psychology to generate a realistic path that mimics the decision-making and behavioral processes of wayfinding of workers on the construction site. To do so, in this paper, the collection of human wayfinding tendencies and the characteristics of the walking environment of construction sites are investigated and the importance of taking these into account in simulating the actual path of workers is emphasized. Furthermore, a simulation developed by mapping the identified tendencies to the reward design shows that the RL agent behaves like a real construction worker. Based on the research findings, some opportunities and challenges were proposed. This study contributes to simulating the potential path of workers based on deep RL, which can be utilized to calculate the travel distance of CSLP automation models, contributing to providing more reliable solutions.

• 한국정보처리학회논문지
• /
• 제6권1호
• /
• pp.42-48
• /
• 1999

최단경로를 포함한 어떤 문제를 해결하는데 필요한 정보가 네트워상의 프로세서에 분산되어 있는 상황에서 그들 정보를 교환하면서, 그 문제를 해결하는 알고리즘을 분산알고리즘(Distributed Algorithm)이라고 한다. 본 논문에서는 비동기식 네트워크에서 최단경로문제를 해결하는 분산 알고리즘을 제안한다. 일반적으로 분산 알고리즘은 메시지 복잡도와 이상시간 복잡도로 평가되는데, 본 논문에서 제안하는 분산 알고리즘이 메시지 복잡도와 이상 시간 복잡도는 각각 O(n53)와 O(nln)이다. 여기서, n은 네트상에 있는 프로세서 수를 나타낸다.

• 한국컴퓨터정보학회논문지
• /
• 제21권7호
• /
• pp.47-52
• /
• 2016

This paper introduces an algorithm to construct an Eulerian cycle for Chinese postman problem. The Eulerian cycle is formed only when all vertices in the graph have an even degree. Among available algorithms to the Eulerian cycle problem, Edmonds-Johnson's stands out as the most efficient of its kind. This algorithm constructs a complete graph composed of shortest path between odd-degree vertices and derives the Eulerian cycle through minimum-weight complete matching method, thus running in $O({\mid}V{\mid}^3)$. On the contrary, the algorithm proposed in this paper selects minimum weight edge from edges incidental to each vertex and derives the minimum spanning tree (MST) so as to finally obtain the shortest-path edge of odd-degree vertices. The algorithm not only runs in simple linear time complexity $O({\mid}V{\mid}log{\mid}V{\mid})$ but also obtains the optimal Eulerian cycle, as the implementation results on 4 different graphs concur.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 하계학술대회 논문집 D
• /
• pp.2417-2419
• /
• 2001

A path planning is one of the main subjects in a mobile robot. It is divided into two parts. One is a global path planning and another is a local path planning. This paper, using the formal two methods, presents that the mobile robot moves to multi-targets with avoiding unknown obstacles. For the shortest time and the lowest cost, the mobile robot has to find a optimal path between targets. To find a optimal global path, we used GA(Genetic Algorithm) that has advantage of optimization. After finding the global path, the mobile robot has to move toward targets without a collision. FLC(Fuzzy Logic Controller) is used for local path planning. FLC decides where and how faster the mobile robot moves. The validity of the study that searches the shortest global path using GA in multi targets and moves to targets without a collision using FLC, is verified by simulations.

• 산업공학
• /
• 제25권3호
• /
• pp.365-375
• /
• 2012

An Unmanned Aerial Vehicle (UAV) is a powered pilotless aircraft, which is controlled remotely or autonomously. UAVs are an attractive alternative for many scientific and military organizations. UAVs can perform operations that are considered to be risky or uninhabitable for humans. UAVs are currently employed in many military missions and a number of civilian applications. For accomplishing the UAV's missions, guarantee of survivability should be preceded. The main objective of this study is to suggest a mathematical programming model and a $A^*PS$_PGA (A-star with Post Smoothing_Parallel Genetic Algorithm) for Multiple UAVs's path planning to maximize survivability. A mathematical programming model is composed by using MRPP (Most Reliable Path Problem) and MTSP (Multiple Traveling Salesman Problem). After transforming MRPP into Shortest Path Problem (SPP),$A^*PS$_PGA applies a path planning for multiple UAVs.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.77-78
• /
• 2008

This paper proposes a new algorithm for path planning and obstacles avoidance using the ant colony optimization algorithm and the particle swarm optimization. The proposed algorithm is a new hybrid algorithm that composes of the ant colony algorithm method and the particle swarm optimization method. At first, we produce paths of a mobile robot in the static environment. And then, we find midpoints of each path using the Maklink graph. Finally, the hybrid algorithm is adopted to get a shortest path. We prove the performance of the proposed algorithm is better than that of the path planning algorithm using the ant colony optimization only through simulation.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.311-312
• /
• 2007

This paper proposes a new algorithm for path planning and obstacles avoidance using the ant colony optimization algorithm. The proposed algorithm is a new hybrid algorithm that composes of the ant colony algorithm method and the Maklink graph method. At first, we produce the path of a mobile robot a the static environment. And then we find midpoints of each path using the Maklink graph. Finally the ant colony optimization algorithm is adopted to get a shortest path. In this paper, we prove the performance of the proposed algorithm is better than that of the Dijkstra algorithm through simulation.