• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.3
• /
• pp.27-38
• /
• 2000

This paper proposes how the recurrent neural network controller for a Khepera mobile robot with an obstacle avoiding ability can be determined by co-adaptation of the evolution and learning, The proposed co-adaptation scheme consists of two folds： a population of NN controllers are evolved by the genetic algorithm so that the degree of obstacle avoidance might be reduced through the global searching and each NN controller is trained by CRBP learning so that the running behavior is adapted to its outer environment through the local searching. Experimental results shows that the NN controller coadapted by evolution and learning outperforms its non-learning equivalent evolved by only genetic algorithm in both the ability of obstacle avoidance and the convergence speed reaching to the required running behavior.

• Journal of Korean Society for Geospatial Information Science
• /
• v.20 no.1
• /
• pp.3-12
• /
• 2012

It is a global trend to give attention to generating precise 3D navigation maps since eco-friendly vehicles have become a critical issue due to environmental protection and depletion of fossil fuels. To date, Mobile Mapping System (MMS) has been a efficient method to acquire the data for generating the 3D navigation maps. To achieve this goal so far in the Mobile Mapping System using the data acquisition method has been proposed to be most effective. For this study the basic RTF filter algorithm was applied to modify to fit MMS quantitative analysis derived floor 99.71%, 99.95% of the highly non-producers to maintain accuracy and high-precision 3D road could create DEM. In addition, the roads that exist within the cars, roadside tree, road cars, such as the median strips have been removed to shields it takes to get results effectively, and effective in practical applications and can be expected to improve operational efficiency is considered.

• Journal of KIISE:Software and Applications
• /
• v.29 no.1_2
• /
• pp.91-97
• /
• 2002

This paper describes a heuristic search technique carrying out collision avoidance for Autonomous Underwater Vehicles(AUVs). Fuzzy relational products are used as the mathematical implement for the analysis and synthesis of relations between obstacles that are met in the navigation environment and available candidate nodes. In this paper, we propose a more effective evaluation function that reflects the heuristic information of domain experts on obstacle clearance, and an advanced heuristic search method performing collision avoidance for AUVs. The search technique adopts fuzzy relational products to conduct path-planning of intelligent navigation system. In order to verify the performance of proposed heuristic search, it is compared with $A^*$ search method through simulation in view of the CPU time, the optimization of path and the amount of memory usage.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.01a
• /
• pp.163-164
• /
• 2015

최근 로봇 기술은 전자공학, 컴퓨터, 기계공학 등의 비약적인 발전에 힘입어 다양한 용도에 사용되고 있다. 특히 로봇은 극한 환경에서 인간이 실천하기 어려운 작업을 수행할 수가 있으며, 인간과 함께 운용되거나 인간이 로봇을 무선으로 제어하여 현장을 확인을 할 수 있으며 이를 통하여 화재진압 및 인명구조를 수행할 수 있다. 이 때 무선 제어 로봇은 탐사 시 동체가 전복되더라도 지속적인 탐사가 가능해야 한다. 따라서 로봇의 동체보다 바퀴를 크게 하여 동체가 전복해도 동작이 가능하도록 한다. 본 논문에서는 무선 조정 자동차를 사용 하여 차체의 전복에도 충분히 제어 및 탐사가 가능한지 실험하고, 초음파센서로 하여금 능동적으로 장애물 회피를 하는 것을 목적으로 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.409-411
• /
• 2018

자율주행차에서 경로계획기법은 지도, 목적지 경로와 다른 정적/동적 장애물에 대한 예측 정보를 바탕으로, 안전하고, 합법적이며 효율적으로 차량을 조종하는 목표를 가진다. 고속도로 환경에서, 차량이 차선을 유지하고, 다른 차량들과 충돌을 회피하며, 더 느리게 움직이는 트래픽을 지나쳐 효율적이면서 안전한 경로를 생성하는 기법이 요구된다. 본 연구에서는, 시스템의 행위를 모델링하는 기법 중의 하나인 유한상태기계를 적용하였다. 시뮬레이터를 통해, 급가속/감속과, 충돌 없이, 차선을 유지/변경을 힐 수 있음을 보였다. 자율주행차의 고속도로 주행의 경우, 유한상태기계를 적용하여, 효율적이고 안전한 경로계획을 수행할 수 있다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.7
• /
• pp.852-860
• /
• 2019

In this paper, we proposed a new trilateration technique based on exponential moving average (EMA) filter with adaptive signal model which enhances accuracy of positioning system even if the RSSI changes randomly due to movement of obstacles or blind node in indoor environment. In the proposed scheme, three fixed transmitters sent out the signal to blind node. The transmitter decides the location of the blind node based on RSSI and it estimates the cause of RSSI fluctuation which is interference of obstacle or movement of blind node. When the path between blind node and transmitter has become NLOS path because of obstacles, the transmitter ignores the measured RSSI in NLOS path and replace estimated RSSI in LOS environment. In the other case, the transmitter updated the new RSSI to represent of movement of blind node. The proposed scheme has been verified on a ZigBee testbed and we proved the improved positioning accuracy compared to the existing indoor position system.

• Journal of Korea Game Society
• /
• v.19 no.6
• /
• pp.5-14
• /
• 2019

In this paper, we propose a modeling and simulation of group behavioral movement of pedestrians using Agent based and Cellular Automata model in intelligent game environment. The social behaviors of the crowds are complex and important, and based on this, the prototype game-model was implemented to show the crowd interaction on AB and CA in the game environment. Our experiment revealed the promise of group behaviour as a cost-efficient, yet accurate platform for researching crowd behaviour in risk situations with real models.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.4
• /
• pp.549-557
• /
• 2021

In this research, we will use the existing OID sensor environment for smart robots, which are a type of educational robot, but we would like to propose that the problem of running be handled by a program. Maybe you have driving information We are building a driving test environment focusing on environment, position recognition, route planning, obstacle avoidance and path reset, and it is not the average final error rate, but the time when the error increases The experiment was conducted by a household that catches the moment of recalibration. Through the process, stable running results were obtained compared to the previous experiment. In this research, I think that it will be a development method that can improve the running performance of educational robots equipped with low-cost sensors currently on the market.

• Nuclear industry
• /
• v.38 no.2
• /
• pp.13-27
• /
• 2018

재생에너지의 활용 가능성이 제한적이고 인구 밀도가 높은 대한민국의 현실을 놓고 볼 때, 원자력은 온실가스 배출 및 공해를 줄이면서도 충분한 전력을 생산하여 공급해줄 수 있는 가장 신뢰할만한 발전 수단이다. 그러나 한국 정부는 원전과 석탄발전소를 단계적으로 폐쇄하고 이를 대체하기 위해서 다양한 재생에너지를 늘리겠다는 정책을 확고하게 고수하고 있다. 그렇지만 에너지 생산 수단을 전환하겠다는 이 정책의 주요 목표는 액화천연가스(LNG) 발전을 대체 수단으로 삼고 있다. 그 이유는 다른 재생에너지들의 대규모 생산 수단을 개발하는 데는 기술적이고 경제적인 난제들이 걸림돌이 되기 때문이다. 그러므로 미래의 에너지 정책을 결정하기에 앞서, 에너지 전환 정책의 구체적인 사항들을 확실한 근거에 기반해서 검토한 후 계획을 수립하는 것이 매우 중요한 일이다. 이 문제에 관해서 우리는 다음과 같은 점들을 검토하였다 (1) 한국이 처해 있는 기술적 경제적인 제약을 전제로 한 재생에너지원의 개발에 대한 정부의 역할, (2) 가스 발전으로 인해 발생할 수 있는 환경적이며 경제적인 문제점들, (3) 원전정책을 지속함으로써 얻을 수 있는 이점과 원전 유지에 대한 장애물. 위와 같은 세 가지 사항을 검토한 결과, 한국이 지니고 있는 지리적 경제적인 제약과 함께 탄소 배출로 인해 발생하는 비용까지 효과적으로 줄여야 한다는 점 등을 감안할 때 천연가스 발전으로 집중하겠다는 한국의 미래 에너지 정책은 친환경적이지 못함은 물론 경제적이지도 않기 때문에 적정한 비율의 재생에너지를 포함하는 원전 정책을 지속하는 것만이 현실적인 성공 가능성이 가장 높다고 보는 것이 우리의 결론이다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.747-754
• /
• 2023

Energy-efficient routing protocol is an important task in a wireless sensor network that is used for monitoring and control by wirelessly collecting information obtained from sensor nodes deployed in various environments. Various routing techniques have been studied for this, but it is also necessary to consider WSN environments with specific situations and conditions. In particular, due to topographical characteristics or specific obstacles, a hole where sensor nodes are not deployed may exist in most WSN environments, which may result in inefficient routing or routing failures. In this case, the geographical routing-based hall bypass routing method using GPS functions will form the most efficient path, but sensors with GPS functions have the disadvantage of being expensive and consuming energy. Therefore, we would like to find the boundary node of the hole in a WSN environment with holes through minimal sensor function and propose hole bypass routing through boundary line formation.