• 정보처리학회 논문지
• /
• 제13권3호
• /
• pp.111-121
• /
• 2024

최근 영상 인식 등의 인공지능 기술 발전에 힘입어 무인기 자율화에 관한 연구가 활발히 이루어지고 있다. 특히 전문 조종 인력 육성에 큰 비용이 들어가는 군용 무인기 분야에서 관련 연구가 늘어나고 있으며, 그중 하나가 정찰용 무인기의 자율적인 임무 수행을 위한 지능형 프레임워크 연구이다. 해당 연구에선 서비스 로봇을 위한 지능형 프레임워크 설계의 방법론을 활용해 무인기용 지능형 프레임워크를 설계하고자 하였다. 무인기의 자율적인 임무 수행 능력을 위해선 지능형 프레임워크와 무인기 모듈의 연동이 원활하게 이루어져야 한다. 하지만 기존 서비스 로봇을 위한 지능형 프레임워크의 모델 기반 인터페이스로는 주기성 메시지 프로토콜을 사용하는 무인기에 대한 연동 제공이 어려웠다. 먼저 주기성 메시지 프로토콜에 대한 메시지 모델의 표현력이 부족했고, 다음으로 주기성 메시지 프로토콜과 지능형 프레임워크의 비동기적 데이터 교환 방식의 상호운용성이 제공되지 않는다는 문제가 있었다. 본 논문에서는 이러한 문제를 해결하기 위해 메시지 주기성 서술을 위한 메시지 모델 확장 방법을 제안하여 주기성 메시지 모델에 대한 모델의 표현력을 확보하고, 확장된 모델을 이용한 주기적 및 비동기적 데이터 교환 방법을 제안하여 서로 다른 데이터 교환 방식의 상호운용성을 제공하고자 한다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권4호
• /
• pp.262-269
• /
• 2016

In this paper, we propose a novel dynamical love model of Romeo and Juliet, which has an external force with a fuzzy membership function. The external force used in the model has the characteristics of a Gaussian function. The chaotic behavior in the model is demonstrated using time series and phase portraits.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2000년도 추계학술대회 학술발표 논문집
• /
• pp.23-27
• /
• 2000

In this paper, we propose an emotional evaluation model based on information fusion. This model can transform the physical features of a color pattern to the emotional features. Our proposed model consists of the fuzzy logic system and neural network model. The evaluation values produced by them were fused. The model shows comparable performances to the neural network and fuzzy logic system for the approximation of the nonlinear transforms. We believe the evaluated results of a color pattern can be used to the emotion-based color image retrievals.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 추계학술대회 학술발표 논문집
• /
• pp.129-132
• /
• 2001

In this paper, in order to control uncertain missile autopilot, an adaptive fuzzy control(AEC) scheme via parallel distributed compensation(PDC) is developed for the multi-input/multi-output plants represented by the Takagi-Sugeno(T-S) fuzzy model. Moreover adaptive law is designed so that the plant output tracks the stable reference model(SRM), From the simulations results, we can conclude that the suggested scheme can effectively solve the control problems of uncertain missile systems based on T-S fuzzy model.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권1호
• /
• pp.64-71
• /
• 2016

This paper proposes nonlinear behavior in a love model for Romeo and Juliet with an external force of discontinuous time. We investigated the periodic motion and chaotic behavior in the love model by using time series and phase portraits with respect to some variable and fixed parameters. The computer simulation results confirmed that the proposed love model with an external force of discontinuous time shows periodic motion and chaotic behavior with respect to parameter variation.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제5권4호
• /
• pp.302-309
• /
• 2005

We have studied a model and application that evolves the behavioral knowledge of a virtual robot. The knowledge is represented in classification rules and a neural network, and is learned by a genetic algorithm. The model consists of a virtual robot with behavior knowledge, an environment that it moves in, and an evolution performer that includes a genetic algorithm. We have also applied our model to an environment where the robots gather food into a nest. When comparing our model with the conventional method on various test cases, our model showed superior overall learning.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1995년도 추계학술대회 학술발표 논문집
• /
• pp.233-242
• /
• 1995

In this paper, we introduce the identification model of dynamic system using the neural networks, We propose two identification models. The output of the parallel identification model is a linear combination of its past values as well as those of the input. The series-parallel model is a linear combination of the past values in the input and output of the plant. To generate stable adaptive laws, we prove that the series-parallel model is found to be proferable.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2006년도 춘계학술대회 논문집
• /
• pp.333-334
• /
• 2006

A novel mathematical modeling in web transport systems for Continuous Annealing Processes (CAP) is proposed. Despite of thermal and weight effects in dynamics of web transport systems, the conventional mathematical model does not consider those effects. Disregard of these effects causes the low manufacturing quality of webs in CAP. In order to improve the manufacturing quality of webs in CAP, moreover, precise tension control is required based on the mathematical model. Therefore, an advanced mathematical model considering thermal and weight effects in CAP should be established. The effectiveness of a novel mathematical model is evaluated by comparing the performances of the PI tension control system based on the proposed mathematical model with that based on the conventional one through the computer simulation.

• Journal of Electrical Engineering and Technology
• /
• 제13권5호
• /
• pp.1821-1830
• /
• 2018

With the wide application of intelligent household appliances, the optimization of electricity behavior has become an important component of home-based intelligent electricity. In this study, a multi-objective optimization model in an intelligent electricity environment is proposed based on economy and comfort. Firstly, the domestic consumer's load characteristics are analyzed, and the operating constraints of interruptible and transferable electrical appliances are defined. Then, constraints such as household electrical load, electricity habits, the correlation minimization electricity expenditure model of household appliances, and the comfort model of electricity use are integrated into multi-objective optimization. Finally, a continuous search multi-objective particle swarm algorithm is proposed to solve the optimization problem. The analysis of the corresponding example shows that the multi-objective optimization model can effectively reduce electricity costs and improve electricity use comfort.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1278-1282
• /
• 2003

A new interacting multiple model (IMM) method using intelligent input estimation (IIE) is proposed to track a maneuvering target. In the proposed method, the acceleration level for each sub-model is determined by IIE-the estimation of the unknown acceleration input by a fuzzy system using the relation between maneuvering filter residual and non-maneuvering one. The genetic algorithm (GA) is utilized to optimize a fuzzy system for a sub-model within a fixed range of acceleration input. Then, multiple models are composed of these fuzzy systems, which are optimized for different ranges of acceleration input. In computer simulation for an incoming ballistic missile, the tracking performance of the proposed method is compared with those of the input estimation (IE) technique and the adaptive interacting multiple model (AIMM) method.