• Journal of Mechanical Science and Technology
• /
• v.18 no.3
• /
• pp.337-346
• /
• 2004

The control scheme using fuzzy modeling and Parallel Distributed Compensation (PDC) concept is proposed to provide asymptotic tracking of a reference signal for the flexible joint manipulators with uncertain parameters. From Lyapunov stability analysis and simulation results, the developed control law and adaptive law guarantee the boundedness of all signals in the closed-loop multi-input/multi-output system. In addition, the plant state tracks the state of the reference model asymptotically with time for any bounded reference input signal.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.439-442
• /
• 2016

제한된 환경에서 로봇이 동적 장애물들에 대해 능동적으로 대처하며 목표한 지점까지 도달하기 위한 알고리즘을 제안한다. 로봇은 행동기반 시스템으로 만들어져 주변 장애물들을 자율적으로 회피한다. ex-agent는 공중에서 주변 환경들을 modeling 한 뒤 cell-map을 만들어 $A^*$알고리즘을 통해 이동 경로를 설정한다. 이동 경로와 로봇의 진행방향을 비교하여 회전 방향을 조언해준다. 로봇은 ex-agent 로부터 받은 조언과 센서값들을 조율하여 장애물들을 능동적으로 회피하며 목표 위치를 찾아갈 수 있다. 실험은 시뮬레이터를 통해 이루어졌으며 장애물들에 대해 원반한 회피율을 보였다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.315-318
• /
• 2003

A systematic output-tracking control design technique for robust control of Takagi-Sugeno (T-S) fuzzy systems with norm-bounded uncertainties is developed. The uncertain T-S fuzzy system is first represented as a set of uncertain local linear systems. The tracking problem is then converted into the stabilization problem for a set of uncertain local linear systems thereby leading to a more feasible controller design procedure. A sufficient condition for robust asymptotic output tracking is derived in terms of a set of linear matrix inequalities (LMIs). A stability condition on the traversing time-instances is also established. The output tracking control simulation for a flexible-joint robot-arm model is demonstrated, to convincingly show the effectiveness of the proposed system modeling and controller design method.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.515-515
• /
• 2000

The performance of dynamic path following of a wheeled mobile robot with nonholonomic constraints has some drawbacks such as the influence of the initial state. The drawbacks can be overcome by the temporary path generator and modified output. But with the previous input-output linearization method using them, it is difficult to tune the gains, and if there are some modeling errors, the low gain can make the system unstable. And if a high gain is used to overcome the model uncertainties, the control inputs are apt to be large so the system can be unstable. In this paper. an H$_{\infty}$ controller is designed to guarantee robustness to model parameter uncertainties and to consider the magnitude of control inputs. And the solution to Hamilton Jacobi (HJ) inequality, which is essential to H$_{\infty}$ control design, is obtained by nonlinear matrix inequality (NLMI).

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.17 no.6
• /
• pp.1372-1380
• /
• 1993

Surface trimming is an essential function in a surface modeler for representing multi-boundary surfaces, blended surfaces, and surfaces with islands or pockets. A procedure and a data structure for designing trimmed surfaces were developed. For generating a trimmed surface, edges (curves difined on a surface) are generated and trimmed first. Then the trimmed edges are selected sequentially to form a closed loop. The data of supporting surface, surface on which the trimmed surface is defined, and bounding edges are stored and used for the application such as NC programming, robot programming, graphic display, etc.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.339-342
• /
• 2011

지능형 로봇산업은 인간의 생활에 지대한 영향을 끼치는 미래 산업으로 손꼽히는 분야이다. 향후 소비자들의 욕구를 충족시키기 위해서는 다양한 플랫폼을 개발하고 사용자의 편의성을 만족시킬 필요가 있다. 이 논문에서는 사용자에게 효율적으로 정보를 전달하기 위한 작업 정보 스키마의 정의 및 이용자의 성향에 따른 차별화된 정보 전달 방법을 제안한다. 정형화된 작업 정보를 통해 다양한 플랫폼의 상호작용을 일원화 하고, 이를 전달하기 위해 사용자 모델을 이용한 차등적 정보제공을 통해 다양한 소비자의 욕구를 충족시키는 것이야 말로 미래 산업의 경쟁력을 확보하기 위한 한 방향을 제시할 것이다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1996.10a
• /
• pp.27-34
• /
• 1996

GENIE is a learning-based engine for building intelligent systems. Learning in GENIE proceeds by incrementally modeling its human or technical environment using a neural network and a genetic algorithm. The neural network is used to represent the knowledge for solving a given task and has the ability to grow its structure. The genetic algorithm provides the neural network with training examples by actively exploring the example space of the problem. Integrated into the training examples by actively exploring the example space of the problem. Integrated into the GENIE system architecture, the genetic algorithm and the neural network build a virtually self-teaching autonomous learning system. This paper describes the structure of GENIE and its learning components. The performance is demonstrated on a robot learning problem. We also discuss the lessons learned from experiments with GENIE and point out further possibilities of effectively hybridizing genetic algorithms with neural networks and other softcomputing techniques.

• Annual Conference on Human and Language Technology
• /
• 2008.10a
• /
• pp.156-161
• /
• 2008

This work presents an agenda-based approach to improve the robustness of the dialog manager by using dialog examples and n-best recognition hypotheses. This approach supports n-best hypotheses in the dialog manager and keeps track of the dialog state using a discourse interpretation algorithm with the agenda graph and focus stack. Given the agenda graph and n-best hypotheses, the system can predict the next system actions to maximize multi-level score functions. To evaluate the proposed method, a spoken dialog system for a building guidance robot was developed. Preliminary evaluation shows this approach would be effective to improve the robustness of example-based dialog modeling.

• Journal of Institute of Control, Robotics and Systems
• /
• v.1 no.1
• /
• pp.43-49
• /
• 1995

본 논문에서는 초음파 센서와 시각 센서에서 얻은 전방향 센서 데이타를 이용하여 실내 이동 로봇용 국부 유도 항법을 위한 새로운 환경 모델링 방법을 제안한다. 그리고 이 두 종류의 센서 데이타에 포함된 불확실성을 주관적 지식과 퍼지 연산법을 사용하여 정량적으로 다룰 수 있는 센서 융합법을 제안한다. 이 방법을 사용하여, 로봇의 현재 위치와 목표 위치간의 기하학적 관계를 더욱 정확하게 얻을 수 있다. 실험 결과를 통하여 제안된 모델링과 센서 융합법이 실내 이동 로봇 항법에 효과적임을 보였다.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.5
• /
• pp.626-633
• /
• 1995

It is vary hard to identify the fuzzy rules and tune the membership functions of the fuzzy inference in fuzzy systems modeling, We propose a fuzzy neural network model which can automatically identify the fuzzy rules and tune the membership functions of fuzzy inference simultaneously using artificial neural networks, and modify backpropagation algorithm for improving the convergence. The proposed method is verified by the simulation for a robot manipulator.