• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제14권5호
• /
• pp.502-506
• /
• 2008

최근에 제안된 강화 학습 기법인 "potential-based" reinforcement learning(RL) 기법은 다수 학습들과 expert advice들을 감독 지식으로 강화 학습 알고리즘에 융합하는 것을 가능하게 했고 그 효용성은 최적 정책으로의 이론적 수렴성 보장으로 증명되었다. 본 논문에서는 potential-based RL 기법을 셀룰러 네트워크에서의 채널 할당 문제에 적용한다. Potential-based RL 기반의 동적 채널 할당 기법이 기존의 fixed channel assignment, Maxavail, Q-learning-based dynamic channel assignment 채널 할당 기법들보다 효율적으로 채널을 할당한다. 또한, potential-based RL 기법이 기존의 강화 학습 알고리즘인 Q-learning, SARSA(0)에 비하여 최적 정책에 더 빠르게 수렴함을 실험적으로 보인다.

• 한국정밀공학회지
• /
• 제15권6호
• /
• pp.107-115
• /
• 1998

A path planning using potential field method is very useful for the real-time navigation of mobile robots. However, the method needs high modeling cost to calculate the potential field because of complex preprocessing, and mobile robots may get stuck into local minima. In this paper, An efficient path planning algorithm for multiple mobile robots, based on the potential field method, was proposed. In the algorithm. the concepts of subgoals and obstacle priority were introduced. The subgoals can be used to escape local minima, or to design and change the paths of mobile robots in the work space. In obstacle priority, all the objects (obstacles and mobile robots) in the work space have their own priorities, and the object having lower priority should avoid the objects having higher priority than it has. In this paper, first, potential based path planning method was introduced, next an efficient collision-avoidance algorithm for multiple mobile robots, moving in the obstacle environment, was proposed by using subgoals and obstacle priority. Finally, the developed algorithm was demonstrated graphically to show the usefulness of the algorithm.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.554-557
• /
• 2002

This paper describes power potential field method for the collision-free path planning of stereo-vision based mobile robot. Area based stereo matching is performed for obstacle detection in uncertain environment. The repulsive potential is constructed by distributing source points discretely and evenly on the boundaries of obstacles and superposing the power potential which is defined so that the source potential will have more influence on the robot than the sink potential when the robot is near to source point. The mobile robot approaches the goal point by moving the robot directly in negative gradient direction of the main potential. We have investigated the possibility of power potential method for the collision-free path planning of mobile robot through various experiments.

• Journal of Advanced Marine Engineering and Technology
• /
• 제31권5호
• /
• pp.614-621
• /
• 2007

The fishing boat propulsion system employing the modified stern shape and the tunnel to protect a propeller is developed to increase the cruise speed and reduce he problem resulting from the open propeller accidentally catching the waste net and able on the sea. Using 3 different tunnel types, the model test was performed in the circular water channel and the panel method based on the potential theory is applied to analyze the open water performance of the propeller. In the numerical analysis using he potential-based panel method, it calculates the hydrodynamic interaction between the propeller and the tunnel and evaluates the effect of the tunnel geometry. From the numerical and experimental results differing tunnel geometries, the propulsion efficiency is increased by the larger diameter of the inlet than the outlet of the tunnel and the smaller gap between the propeller tip and the tunnel internal surface. These results provide the information of the propeller system with the tunnel and the hydrodynamic interaction between the propeller and the tunnel.

• 한국지능시스템학회논문지
• /
• 제19권5호
• /
• pp.737-742
• /
• 2009

청소 로봇, 관광 안내 로봇부터 우주 탐사로봇까지 자율이동로봇의 응용분야가 넓어짐에 따라서 자율이동로봇의 인기는 급속도로 높아지고 있다. 하지만 동적인 환경 내에서 자율이동로봇의 안전한 네비게이션을 위한 만족스러운 제어 알고리즘은 여전히 연구 과제이다. 본 논문에서는 새로운 Potential field method를 이용한 제어 방법을 제안하였고, 컴퓨터 시뮬레이션을 통해 제안한 알고리즘을 실행하고 분석하였고, 이 실험 결과들로서 Potential field method를 사용한 행동(behavior)에 기반한 제어 시스템의 유효성을 나타내었다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1996년도 추계학술대회 논문집
• /
• pp.430-433
• /
• 1996

In This paper, we design the developed path generation method which is named that CBPM(Continuous path generation method Based artificial Potential field) that is able to be used in the obstacles environment. This CBPM is designed so that it puts together two obstacle avoidance algorithm-the continuous path generation method and the artificial potential field method. Here, the continuous path generation method generate the safety path using continuous path curvature. But, this method has demerits when used in obstacles environment in which are closely located. Another method which is named the artificial potential field method generates the path with the artificial potential field in the obstacles environment. But, APFM has local minima in certain places and unnecessarily calculates the path in which obstacles are not located. So, the developed path generation method, CBPM, is suggested and performances in many different obstacles environments are shown by using computer simulation.

• Journal of Magnetics
• /
• 제18권2호
• /
• pp.95-104
• /
• 2013

This paper presents a general analytical method for predicting the magnetic fields of different Halbach magnet arrays with or without back iron mounted on slotless permanent magnet (PM) linear machines. By using Fourier decomposition, the magnetization components of four typical Halbach magnet arrays are determined. By applying special synthetic boundary conditions on the PM surfaces, the expressions of their magnetic field distributions are derived based on the magnetic scalar potential (MSP), which are simpler than those based on the magnetic vector potential (MVP). The correctness of the method is validated by finite element analysis. The harmonics of airgap flux density waveforms of these Halbach magnet arrays with or without back iron are also compared and optimized.

• 제어로봇시스템학회논문지
• /
• 제17권4호
• /
• pp.362-367
• /
• 2011

The collision-free path of a manipulator should be regenerated in the real time to achieve collision safety when obstacles or humans come into the workspace of the manipulator. A probabilistic roadmap (PRM) method, one of the popular path planning schemes for a manipulator, can find a collision-free path by connecting the start and goal poses through the roadmap constructed by drawing random nodes in the free configuration space. The path planning method based on the configuration space shows robust performance for static environments which can be converted into the off-line processing. However, since this method spends considerable time on converting dynamic obstacles into the configuration space, it is not appropriate for real-time generation of a collision-free path. On the other hand, the method based on the workspace can provide fast response even for dynamic environments because it does not need the conversion into the configuration space. In this paper, we propose an efficient real-time path planning by combining the PRM and the potential field methods to cope with static and dynamic environments. The PRM can generate a collision-free path and the potential field method can determine the configuration of the manipulator. A series of experiments show that the proposed path planning method can provide robust performance for various obstacles.

• Journal of Mechanical Science and Technology
• /
• 제17권12호
• /
• pp.1876-1885
• /
• 2003

The artificial potential field (APF) methods provide simple and efficient motion planners for practical purposes. However, these methods have a local minimum problem, which can trap an object before reaching its goal. The local minimum problem is sometimes inevitable when an object moves in unknown environments, because the object cannot predict local minima before it detects obstacles forming the local minima. The avoidance of local minima has been an active research topic in the potential field based path planing. In this study, we propose a new concept using a virtual obstacle to escape local minima that occur in local path planning. A virtual obstacle is located around local minima to repel an object from local minima. We also propose the discrete modeling method for the modeling of arbitrary shaped objects used in this approach. This modeling method is adaptable for real-time path planning because it is reliable and provides lower complexity.

• Bulletin of the Korean Chemical Society
• /
• 제18권12호
• /
• pp.1281-1285
• /
• 1997

The time-dependent tracking inversion method is developed to extract the potential of the excited state from frequency-domain measurements, such as the absorption profile. Based on the relay of the regularized inversion procedure and time-dependent wave-packet propagation, the algorithm extract the underlying potential piece by piece by tracking the time-dependent data which can be synthesized from frequency-domain measurements. We have demonstrated the algorithm to extract the potential of excited state for a model diatomic molecule. Finally, we describe the merits of the time-dependent tracking inversion method compared to the time-dependent inversion and discuss several extensions of the algorithm.