• The Transactions of the Korea Information Processing Society
• /
• v.2 no.3
• /
• pp.343-353
• /
• 1995

The path navigation of autonomous guided vehicle(AGV) or autonomous mobile robot(AMR) assumed that the environment was completely known and the obstacles were fixed. So that, in an environment only partly known or not known at all, the previous works were not successful since the path exploration techniques involved in the work were neither directly applicable nor extensible. In order to improve such problems, this paper was adopted the quadtree technique and proposed the algorithm for an optimal path planning autonomously in an environment and proved a validity through a simulation.

• Journal of the Korea Society for Simulation
• /
• v.16 no.1
• /
• pp.31-37
• /
• 2007

The importance of NPC's role in computer games is increasing. An NPC must perform its tasks by perceiving obstacles and other characters and by moving through them. It has been proposed to plan a natural-looking path against fixed obstacles by using a generalized visibility graph. In this paper we develop the execution module for an NPC to move efficiently along the path planned on the generalized visibility graph. The planned path consists of line segments and arc segments, so we define steering behaviors such as linear behaviors, circular behaviors, and an arriving behavior for NPC's movements to be realistic and utilize them during execution. The execution module also includes the collision detection capability to be able to detect dynamic obstacles and uses a decision tree to react differently according to the detected obstacles. The execution module is tested through the simulation based on the example scenario in which an NPC interferes the other moving NPC.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.3
• /
• pp.15-20
• /
• 2024

Path planning for unmanned aerial vehicles (UAV) is crucial in avoiding collisions with obstacles in complex environments that include both static and dynamic obstacles. Path planning algorithms like RRT and A^* are effectively handle static obstacle avoidance but have limitations with increasing computational complexity in high-dimensional environments. Reinforcement learning-based algorithms can accommodate complex environments, but like traditional path planning algorithms, they struggle with training complexity and convergence in higher-dimensional environment. In this paper, we proposed a reinforcement learning model utilizing a cell decomposition algorithm. The proposed model reduces the complexity of the environment by decomposing the learning environment in detail, and improves the obstacle avoidance performance by establishing the valid action of the agent. This solves the exploration problem of reinforcement learning and improves the convergence of learning. Simulation results show that the proposed model improves learning speed and efficient path planning compared to reinforcement learning models in general environments.

• 재활복지
• /
• v.17 no.4
• /
• pp.383-399
• /
• 2013

The purpose of this study was to comparison the effects of aqua-and-land based obstacle training on balance of chronic stroke patients. Subjects were randomly divided into an aqua group(n=15) and d land group(n=15). Both group received obstacle training for 40 minutes, 3 times a week during 12 weeks. Static balance was assessed by measuring the mean velocity of mediolateral, anteroposterior and sway area with the eyes open using Good Balance System. Dynamic balance was assessed by measuring Functional Reaching Test(FRT) and the Timed Up and Go test(TUG). Following the intervention, both groups showed significant changes static balance(the mean velocity of mediolateral, anteroposterior and sway area) and dynamic balance(FRT and TUG). There were significant difference in the mean velocity of mediolateral, anteroposterior, sway area, FRT and TUG between the two groups after the interventions. The results of this study suggest that the aqua group and land group were increase balance functions of chronic stroke patients. The aqua group was significantly higher than the land group for patients with chronic stroke patients. We hope that aquatic training can be useful for patients with chronic stroke patients to improve balance functions and the aqua training research for improve balance functions will be conducted continuously.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.94-96
• /
• 2021

In this paper, we develop a new navigation algorithm for industrial mobile robots to arrive at the destination in unknown environment. To achieve this, we suggest a navigation algorithm that combines Dynamic Window Approach (DWA) and Dijkstra path planning algorithm. We compare Local Dynamic Window Approach (LDWA), Global Dynamic Window Approach(GDWA), Rapidly-exploring Random Tree (RRT) Algorithm. The navigation algorithm using Dijkstra algorithm combined with LDWA and GDWA makes mobile robots to reach the destination. and obstacles faced during the path planning process of LDWA and GDWA. Then, we compare on time taken to arrive at the destination, obstacle avoidance and computation complexity of each algorithm. To overcome the limitation, we seek ways to use the optimized navigation algorithm for industrial use.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.328-332
• /
• 2007

본연구에서는 센서의 융합을 통하여 환경을 인식하며, 주변환경에 대한 지식을 갱신, 학습할수 있는 방법론을 연구하며, 동적인 장애물의 감지및 움직임 예측에 기반한 지능적 회피 알고리즘과 AHP를 이용한 Navigation Strategy수정과 이동 로봇 스스로 최적의 결과를 낼수 있게 개선 시키는 알고리즘을 구현한다. 그와 더불어 AHP를 이용하여 Navigation Performance를 최대로 높일 수 있는 방향을로 진화시키는 알고리즘을 구현한다. 또한 부여된 임무수행을 위한 목표물 추적을 위한 비전 시스템에서의 대상체 추출및 인식 알고리즘을 개발하며 인간뇌의 환경인식 체계와 유사한 방식의 Map building기법을 연구한다.

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.1809-1810
• /
• 2008

자율이동로봇의 동특성을 고려하여 실용적인 경로를 생성하는 방법을 제안한다. 목표 지점까지 장애물을 회피하고, 자율이동로봇의 속도 및 조향각 등을 고려하여, 최적에 가까운 경로를 생성하는 방법을 다룬다. 본 논문에서 골격선 그래프를 구성하여 딕스트라알고리즘으로 초기 전역 경로를 설정하고, 이를 로봇의 동특성을 고려하여 동적 프로그래밍을 통해 경로를 개선한다. 개선된 경로는 자율이동로봇이 이동하는데 걸리는 시간을 단축한다. 마지막으로 시뮬레이션을 통해 제안하는 방법의 성능을 검증한다.

• Journal of the KSME
• /
• v.57 no.7
• /
• pp.40-45
• /
• 2017

이 글에서는 지능형 로봇의 자율주행기술이 자율주행자동차를 위하여 응용된 사례에 대해서 살펴본다. 주로 로봇분야 연구자들이 자율주행자동차를 위하여 개발한 위치 추정, 경로 생성 및 운동제어, 동적 장애물 검지 및 추적 등의 다양한 주제에 관한 기술 개발 동향을 소개한다.

• Annual Conference on Human and Language Technology
• /
• 1992.10a
• /
• pp.533-542
• /
• 1992

손으로 쓴 글씨는 인쇄체와 달리 많은 변형이 있다는 점이 한글 필기 인식에서 가장 큰 장애물로 통한다. 본 논문에서는 이점을 해결하면서 필기에 대한 제한을 대폭 줄인 온라인 한글 인식 방법을 제시하고자 한다. 봉넷(BongNet)은 온라인 한글 필기를 인식하기 위한 네트워크 모델이다. 글씨 인식에 들어가는 여러가지 정보를 네트워크라는 틀 안에 표현한 것 인데, 기본적으로 네트워크 구조 자체가 표현하는 정적 글자 구조 정보와, 글꼴에 따라 달라지는 것으로써 노드간 확률적 이동을 나타내는 동적 정보를 포함한다. 본 모델에 따르면 한글 인식은 네트워크 안에서 최적 경로를 따라 초, 중, 종성 자소열을 찾는 문제로 변환된다. 동적 프로그래밍 기법을 이용하여 그 경로를 찾는 인식 알고리즘은 입력 데이타의 양에 정비례하는 효율성을 갖는다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.3
• /
• pp.355-362
• /
• 2009

In this paper, we present a framework for managing group behaviors in multi-agent swarm systems. The framework explores the benefits by dynamic associations with the proposed artificial potential functions to realize complex swarming behaviors. A key development is the introduction of a set of flocking by dynamic association (DA) algorithms that effectively deal with a host of swarming issues such as cooperation for fast migration to a target, flexible and agile formation, and inter-agent collision avoidance. In particular, the DA algorithms employ a so-called systematic singular association (SSA) rule for fast migration to a target and compact formation through inter-agent interaction. The resulting algorithms enjoy two important interrelated benefits. First, the SSA rule greatly reduces time-consuming for migration and satisfies low possibility that agents may be lost. Secondly, the SSA is advantageous for practical implementations, since it considers for agents even the case that a target is blocked by obstacles. Extensive simulation presents to illustrate the viability and effectiveness of the proposed framework.