• 한국항행학회논문지
• /
• 제13권5호
• /
• pp.646-655
• /
• 2009

본 논문은 로봇 충돌회피 경로계획의 문제점을 해결하기 위해 진화된 모델에 근거한 새로운 경로탐색 전략을 소개한다. 최적화된 지능형 검색 방법으로 잘 알려진 유전자 알고리즘을 이용하여 로봇 경로계획 방법을 설계하였다. 염색체 안에 있는 유전자 인자로 경로점을 고찰해보면 주어진 맵에 대한 가능한 해법이제공된다. 생성된 염색체 간의 거리가 먼 경우 유사한 염색체에 대한 적합도로 간주할 수 있다. 경로계획에 있어 본 논문에서 제안한 유전자 알고리즘의 유효성을 증명하기위해 다양한 방법으로 시뮬레이션을 실시하였으며, 제안한 경로 검색 방법은 정지된 장애물이나 복잡한 장애물에도 사용될 수 있음을 증명하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권3호
• /
• pp.1477-1491
• /
• 2017

Inspired by the multi-scale nature of hippocampal place cells, a biologically inspired model based on a multi-scale spatial representation for goal-directed navigation is proposed in order to achieve robotic spatial cognition and autonomous navigation. First, a map of the place cells is constructed in different scales, which is used for encoding the spatial environment. Then, the firing rate of the place cells in each layer is calculated by the Gaussian function as the input of the Q-learning process. The robot decides on its next direction for movement through several candidate actions according to the rules of action selection. After several training trials, the robot can accumulate experiential knowledge and thus learn an appropriate navigation policy to find its goal. The results in simulation show that, in contrast to the other two methods(G-Q, S-Q), the multi-scale model presented in this paper is not only in line with the multi-scale nature of place cells, but also has a faster learning potential to find the optimized path to the goal. Additionally, this method also has a good ability to complete the goal-directed navigation task in large space and in the environments with obstacles.

• 한국지능시스템학회논문지
• /
• 제11권5호
• /
• pp.367-372
• /
• 2001

본 논문은 미시공간에서 다수의 로봇들의 자율 이동에 대해 계층적 구조를 가진 퍼지-뉴럴 알고리즘을 제안한다. 이 계층적 알고리즘은 그 하부에 로봇이 목표에 도달하게 하며 주는 퍼지 알고리즘과 주행 중 만날 수 있는 장애물들에 대한 회피를 수행하는 퍼지-뉴럴 알고리즘이 존재하고 상부의 가중치 퍼지 알고리즘은 위의 두 알고리즘에 의한 로봇의 회전각도 와 이동 거리를 합성하여 주위 환경에 대하여 로봇이 지능적인 주행을 수행한 누 있도록 구성되어 있으며 시뮬레이션을 통하여 만족할 만한 결과를 얻을 수 있었다.

• 전기전자학회논문지
• /
• 제17권4호
• /
• pp.434-439
• /
• 2013

인공표식은 이동로봇의 위치추정에서 불확실성을 감소시키기 위해 널리 사용되어 왔다. 또한, 사용되는 인공표식의 수가 증가함에 따라 위치추정 비용이 증가하기 때문에, 인공표식의 효율적 배치를 위한 연구는 핵심적인 이슈중 하나로서 여겨져 왔다. 따라서 본 논문은 운동모델과 센서모델의 불확실성 특성을 고려함으로써 인공표식들을 효율적으로 배치하기 위한 방법을 제안한다. 운동모델과 센서모델은 서로 다른 불확실성 분포를 가지기 때문에, 최종 불확실성은 두 가지 불확실성의 효율적 조합을 통해 크게 감소될 수 있다. 제안한 기법의 유용성은 시뮬레이션 결과에 의해 입증된다.

• 한국지능시스템학회논문지
• /
• 제8권2호
• /
• pp.50-59
• /
• 1998

This paper presents stabilization and adaptive control of flexible single link robot manipulator system by self-recurrent neural networks that is one of the neural networks and is effective in nonlinear control. The architecture of neural networks is a modified model of self-recurrent structure which has a hidden layer. The self-recurrent neural networks can be used to approximate any continuous function to any desired degree of accuracy and the weights are updated by feedback-error learning algorithm. When a flexible manipulator is rotated by a motor through the fixed end, transverse vibration may occur. The motor toroque should be controlled in such a way that the motor rotates by a specified angle, while simultaneously stabilizing vibration of the flexible manipuators so that it is arresed as soon as possible at the end of rotation. Accurate vibration control of lightweight manipulator during the large changes in configuration common to robotic tasks requires dynamic models that describe both the rigid body motions, as well as the flexural vibrations. Therefore, a dynamic models for a flexible single link robot manipulator is derived, and then a comparative analysis was made with linear controller through an simulation and experiment. The results are proesented to illustrate thd advantages and imporved performance of the proposed adaptive control ove the conventional linear controller.

• 제어로봇시스템학회논문지
• /
• 제16권4호
• /
• pp.353-360
• /
• 2010

A skid-steering method which applied to the various mobile robot platforms currently shows its effectiveness in the specified field areas and purposes. This system contains however, several problems of its intrinsic properties such as slippages occurred by different moving direction between vehicle's driving and wheel's rotary and difficulties of driving performance control and so on. This paper deals with the suggestion of suitable control algorithm for 6WD/6WS skid steering wheeled vehicle and verified its feasibility by analyzing the behavior of 6WD/6WS skid-steered wheeled vehicle model and by applying the engineering analytical method to the considered mobile platform. The Performance of vehicle model is evaluated by using slip mode control to follow the steering input and, as a future work, this control algorithm could be applied to real 6WD/6WS in-wheel drive type vehicle finally.

• 제어로봇시스템학회논문지
• /
• 제19권9호
• /
• pp.805-812
• /
• 2013

This paper describes the design, control, and localization which comprise major aspects of the development of underwater robots for the mine disposal. The developed robots are called the Mine Killer (MK-1) and MK-2. MK-1 had been developed from September 2009 and was presented at the 9-th International Symposium at NPS Monterey CA, on May 17-21, 2010[1]. The paper presents design of MK-1 and MK-2 in detail with comparison of these two versions of MKs. Then it derives hydrodynamic coefficients of MK-1. Based on the coefficients, the motion of MK-1 is simulated for straight line motion and circular motion. Also simulation results for PD control, LQ control and sliding mode control are presented. Finally, it shows a particle filter method for localization of MK-1 and MK-2 using simple range data from acoustic beacons.

• 대한전자공학회논문지
• /
• 제27권10호
• /
• pp.53-59
• /
• 1990

로보트 매니퓰레이터를 제어하는데 있어서, 토오크 계산법을 이용한 새로운 가변구조 모델 추종제어기를 설계한다. 슬라이딩 모드가 존재하기 위한 충부조건은 Lyapunov 함수에 의해 유도된다. 기준 모델은 이중 적분기를 사용하고 가속도 입력은 시스템의 안정성과 원하는 성능을 얻기 위하여 비례-미분 제어기로 구성한다. 제안된 제어기법은 매니퓰레이터 동력학 방정식 각 항들의 상한값과 추정값을 부여함으로써 정확한 매개변수의 지식과 역행렬 계산을 요구하지 않는다. 따라서 모의실험 결과 제어된 제어기가 목적궤적의 수렴성이 개선되었음을 보여준다.

• 한국기계가공학회지
• /
• 제16권3호
• /
• pp.119-124
• /
• 2017

Machining optimization using typical computer-aided manufacturing (CAM) software mainly depends on tool paths, and it is impossible to predict the behavior of material or cutting force. In this paper, cutting force analysis simulation is performed on the Unibody Case of a mobile phone with the aim of optimizing cutting-force-based machining using the Third Wave Systems' AdventEdge Production Module. Machining time after optimization was shortened by 42% for roughing compared to pre-optimization, and actual machining time was reduced by 36.8%. For finishing, machining time was reduced by 92%, and actual machining time was reduced around 90%. A surface roughness analysis found that the post-optimization surface roughness was $1.16{\mu}m$ Ra, compared to a pre-optimization value of $1.75{\mu}m$ Ra.

• 대한기계학회논문집A
• /
• 제31권1호
• /
• pp.62-69
• /
• 2007

Micromanipulator is a device that manipulates an object with high precision. Generally, a parallel-type robot has inherently higher precision than a serial-type robot. In most cases, the use of flexure hinge mechanisms is the most appropriate approach to micromanipulators. The micromanipulator is basically required that have high natural frequency and sufficient workspace. However, previous designs are hard to satisfy the required workspace and natural frequency, simultaneously, because the previous micromanipulators are coupled designs. Therefore, this paper suggests a new design parameter as displacement amplifier and new design procedure based on semi-coupled design in axiomatic design. As a consequence the spatial 3-DOF micromanipulator which is chosen as an exemplary device has natural frequency of 500Hz and workspace of $-0.5^{\circ}{\sim}0.5^{\circ}$. To investigate the effectiveness of the displacement amplifier, simulation and experiment are performed.